| 
									
										
										
										
											2018-03-20 10:42:06 +01:00
										 |  |  | // asmcheck | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | // Copyright 2018 The Go Authors. All rights reserved. | 
					
						
							|  |  |  | // Use of this source code is governed by a BSD-style | 
					
						
							|  |  |  | // license that can be found in the LICENSE file. | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | package codegen | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | import "unsafe" | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | // This file contains code generation tests related to the comparison | 
					
						
							|  |  |  | // operators. | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | // -------------- // | 
					
						
							|  |  |  | //    Equality    // | 
					
						
							|  |  |  | // -------------- // | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | // Check that compare to constant string use 2/4/8 byte compares | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | func CompareString1(s string) bool { | 
					
						
							|  |  |  | 	// amd64:`CMPW\t\(.*\), [$]` | 
					
						
							| 
									
										
											  
											
												cmd/compile: add late lower pass for last rules to run
Usually optimization rules have corresponding priorities, some need to
be run first, some run next, and some run last, which produces the best
code. But currently our optimization rules have no priority, this CL
adds a late lower pass that runs those rules that need to be run at last,
such as split unreasonable constant folding. This pass can be seen as
the second round of the lower pass.
For example:
func foo(a, b uint64) uint64 {
        d := a+0x1234568
        d1 := b+0x1234568
        return d&d1
}
The code generated by the master branch:
	0x0004 00004        ADD     $19088744, R0, R2 // movz+movk+add
	0x0010 00016        ADD     $19088744, R1, R1 // movz+movk+add
	0x001c 00028        AND     R1, R2, R0
This is because the current constant folding optimization rules do not
take into account the range of constants, causing the constant to be
loaded repeatedly. This CL splits these unreasonable constants folding
in the late lower pass. With this CL the generated code:
	0x0004 00004        MOVD    $19088744, R2 // movz+movk
	0x000c 00012        ADD     R0, R2, R3
	0x0010 00016        ADD     R1, R2, R1
	0x0014 00020        AND     R1, R3, R0
This CL also adds constant folding optimization for ADDS instruction.
In addition, in order not to introduce the codegen regression, an
optimization rule is added to change the addition of a negative number
into a subtraction of a positive number.
go1 benchmarks:
name                     old time/op    new time/op    delta
BinaryTree17-8              1.22s ± 1%     1.24s ± 0%  +1.56%  (p=0.008 n=5+5)
Fannkuch11-8                1.54s ± 0%     1.53s ± 0%  -0.69%  (p=0.016 n=4+5)
FmtFprintfEmpty-8          14.1ns ± 0%    14.1ns ± 0%    ~     (p=0.079 n=4+5)
FmtFprintfString-8         26.0ns ± 0%    26.1ns ± 0%  +0.23%  (p=0.008 n=5+5)
FmtFprintfInt-8            32.3ns ± 0%    32.9ns ± 1%  +1.72%  (p=0.008 n=5+5)
FmtFprintfIntInt-8         54.5ns ± 0%    55.5ns ± 0%  +1.83%  (p=0.008 n=5+5)
FmtFprintfPrefixedInt-8    61.5ns ± 0%    62.0ns ± 0%  +0.93%  (p=0.008 n=5+5)
FmtFprintfFloat-8          72.0ns ± 0%    73.6ns ± 0%  +2.24%  (p=0.008 n=5+5)
FmtManyArgs-8               221ns ± 0%     224ns ± 0%  +1.22%  (p=0.008 n=5+5)
GobDecode-8                1.91ms ± 0%    1.93ms ± 0%  +0.98%  (p=0.008 n=5+5)
GobEncode-8                1.40ms ± 1%    1.39ms ± 0%  -0.79%  (p=0.032 n=5+5)
Gzip-8                      115ms ± 0%     117ms ± 1%  +1.17%  (p=0.008 n=5+5)
Gunzip-8                   19.4ms ± 1%    19.3ms ± 0%  -0.71%  (p=0.016 n=5+4)
HTTPClientServer-8         27.0µs ± 0%    27.3µs ± 0%  +0.80%  (p=0.008 n=5+5)
JSONEncode-8               3.36ms ± 1%    3.33ms ± 0%    ~     (p=0.056 n=5+5)
JSONDecode-8               17.5ms ± 2%    17.8ms ± 0%  +1.71%  (p=0.016 n=5+4)
Mandelbrot200-8            2.29ms ± 0%    2.29ms ± 0%    ~     (p=0.151 n=5+5)
GoParse-8                  1.35ms ± 1%    1.36ms ± 1%    ~     (p=0.056 n=5+5)
RegexpMatchEasy0_32-8      24.5ns ± 0%    24.5ns ± 0%    ~     (p=0.444 n=4+5)
RegexpMatchEasy0_1K-8       131ns ±11%     118ns ± 6%    ~     (p=0.056 n=5+5)
RegexpMatchEasy1_32-8      22.9ns ± 0%    22.9ns ± 0%    ~     (p=0.905 n=4+5)
RegexpMatchEasy1_1K-8       126ns ± 0%     127ns ± 0%    ~     (p=0.063 n=4+5)
RegexpMatchMedium_32-8      486ns ± 5%     483ns ± 0%    ~     (p=0.381 n=5+4)
RegexpMatchMedium_1K-8     15.4µs ± 1%    15.5µs ± 0%    ~     (p=0.151 n=5+5)
RegexpMatchHard_32-8        687ns ± 0%     686ns ± 0%    ~     (p=0.103 n=5+5)
RegexpMatchHard_1K-8       20.7µs ± 0%    20.7µs ± 1%    ~     (p=0.151 n=5+5)
Revcomp-8                   175ms ± 2%     176ms ± 3%    ~     (p=1.000 n=5+5)
Template-8                 20.4ms ± 6%    20.1ms ± 2%    ~     (p=0.151 n=5+5)
TimeParse-8                 112ns ± 0%     113ns ± 0%  +0.97%  (p=0.016 n=5+4)
TimeFormat-8                156ns ± 0%     145ns ± 0%  -7.14%  (p=0.029 n=4+4)
Change-Id: I3ced26e89041f873ac989586514ccc5ee09f13da
Reviewed-on: https://go-review.googlesource.com/c/go/+/425134
Reviewed-by: Keith Randall <khr@google.com>
Reviewed-by: Cherry Mui <cherryyz@google.com>
TryBot-Result: Gopher Robot <gobot@golang.org>
Reviewed-by: Keith Randall <khr@golang.org>
Run-TryBot: Eric Fang <eric.fang@arm.com>
											
										 
											2022-08-17 10:01:17 +00:00
										 |  |  | 	// arm64:`MOVHU\t\(.*\), [R]`,`MOVD\t[$]`,`CMPW\tR` | 
					
						
							| 
									
										
										
										
											2018-03-26 21:18:27 +01:00
										 |  |  | 	// ppc64le:`MOVHZ\t\(.*\), [R]`,`CMPW\t.*, [$]` | 
					
						
							|  |  |  | 	// s390x:`MOVHBR\t\(.*\), [R]`,`CMPW\t.*, [$]` | 
					
						
							| 
									
										
										
										
											2018-03-20 10:42:06 +01:00
										 |  |  | 	return s == "xx" | 
					
						
							|  |  |  | } | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | func CompareString2(s string) bool { | 
					
						
							|  |  |  | 	// amd64:`CMPL\t\(.*\), [$]` | 
					
						
							| 
									
										
										
										
											2018-03-26 21:18:27 +01:00
										 |  |  | 	// arm64:`MOVWU\t\(.*\), [R]`,`CMPW\t.*, [R]` | 
					
						
							|  |  |  | 	// ppc64le:`MOVWZ\t\(.*\), [R]`,`CMPW\t.*, [R]` | 
					
						
							|  |  |  | 	// s390x:`MOVWBR\t\(.*\), [R]`,`CMPW\t.*, [$]` | 
					
						
							| 
									
										
										
										
											2018-03-20 10:42:06 +01:00
										 |  |  | 	return s == "xxxx" | 
					
						
							|  |  |  | } | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | func CompareString3(s string) bool { | 
					
						
							|  |  |  | 	// amd64:`CMPQ\t\(.*\), [A-Z]` | 
					
						
							| 
									
										
										
										
											2018-03-26 21:18:27 +01:00
										 |  |  | 	// arm64:-`CMPW\t` | 
					
						
							| 
									
										
										
										
											2018-10-15 12:53:07 -04:00
										 |  |  | 	// ppc64:-`CMPW\t` | 
					
						
							| 
									
										
										
										
											2018-03-26 21:18:27 +01:00
										 |  |  | 	// ppc64le:-`CMPW\t` | 
					
						
							|  |  |  | 	// s390x:-`CMPW\t` | 
					
						
							| 
									
										
										
										
											2018-03-20 10:42:06 +01:00
										 |  |  | 	return s == "xxxxxxxx" | 
					
						
							|  |  |  | } | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | // Check that arrays compare use 2/4/8 byte compares | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | func CompareArray1(a, b [2]byte) bool { | 
					
						
							| 
									
										
											  
											
												cmd/compile: set LocalPkg.Path to -p flag
Since CL 391014, cmd/compile now requires the -p flag to be set the
build system. This CL changes it to initialize LocalPkg.Path to the
provided path, rather than relying on writing out `"".` into object
files and expecting cmd/link to substitute them.
However, this actually involved a rather long tail of fixes. Many have
already been submitted, but a few notable ones that have to land
simultaneously with changing LocalPkg:
1. When compiling package runtime, there are really two "runtime"
packages: types.LocalPkg (the source package itself) and
ir.Pkgs.Runtime (the compiler's internal representation, for synthetic
references). Previously, these ended up creating separate link
symbols (`"".xxx` and `runtime.xxx`, respectively), but now they both
end up as `runtime.xxx`, which causes lsym collisions (notably
inittask and funcsyms).
2. test/codegen tests need to be updated to expect symbols to be named
`command-line-arguments.xxx` rather than `"".foo`.
3. The issue20014 test case is sensitive to the sort order of field
tracking symbols. In particular, the local package now sorts to its
natural place in the list, rather than to the front.
Thanks to David Chase for helping track down all of the fixes needed
for this CL.
Updates #51734.
Change-Id: Iba3041cf7ad967d18c6e17922fa06ba11798b565
Reviewed-on: https://go-review.googlesource.com/c/go/+/393715
Reviewed-by: David Chase <drchase@google.com>
Run-TryBot: Matthew Dempsky <mdempsky@google.com>
TryBot-Result: Gopher Robot <gobot@golang.org>
Reviewed-by: Cuong Manh Le <cuong.manhle.vn@gmail.com>
											
										 
											2022-03-17 13:27:40 -07:00
										 |  |  | 	// amd64:`CMPW\tcommand-line-arguments[.+_a-z0-9]+\(SP\), [A-Z]` | 
					
						
							| 
									
										
										
										
											2018-03-26 21:18:27 +01:00
										 |  |  | 	// arm64:-`MOVBU\t` | 
					
						
							|  |  |  | 	// ppc64le:-`MOVBZ\t` | 
					
						
							|  |  |  | 	// s390x:-`MOVBZ\t` | 
					
						
							| 
									
										
										
										
											2018-03-20 10:42:06 +01:00
										 |  |  | 	return a == b | 
					
						
							|  |  |  | } | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | func CompareArray2(a, b [3]uint16) bool { | 
					
						
							| 
									
										
											  
											
												cmd/compile: set LocalPkg.Path to -p flag
Since CL 391014, cmd/compile now requires the -p flag to be set the
build system. This CL changes it to initialize LocalPkg.Path to the
provided path, rather than relying on writing out `"".` into object
files and expecting cmd/link to substitute them.
However, this actually involved a rather long tail of fixes. Many have
already been submitted, but a few notable ones that have to land
simultaneously with changing LocalPkg:
1. When compiling package runtime, there are really two "runtime"
packages: types.LocalPkg (the source package itself) and
ir.Pkgs.Runtime (the compiler's internal representation, for synthetic
references). Previously, these ended up creating separate link
symbols (`"".xxx` and `runtime.xxx`, respectively), but now they both
end up as `runtime.xxx`, which causes lsym collisions (notably
inittask and funcsyms).
2. test/codegen tests need to be updated to expect symbols to be named
`command-line-arguments.xxx` rather than `"".foo`.
3. The issue20014 test case is sensitive to the sort order of field
tracking symbols. In particular, the local package now sorts to its
natural place in the list, rather than to the front.
Thanks to David Chase for helping track down all of the fixes needed
for this CL.
Updates #51734.
Change-Id: Iba3041cf7ad967d18c6e17922fa06ba11798b565
Reviewed-on: https://go-review.googlesource.com/c/go/+/393715
Reviewed-by: David Chase <drchase@google.com>
Run-TryBot: Matthew Dempsky <mdempsky@google.com>
TryBot-Result: Gopher Robot <gobot@golang.org>
Reviewed-by: Cuong Manh Le <cuong.manhle.vn@gmail.com>
											
										 
											2022-03-17 13:27:40 -07:00
										 |  |  | 	// amd64:`CMPL\tcommand-line-arguments[.+_a-z0-9]+\(SP\), [A-Z]` | 
					
						
							|  |  |  | 	// amd64:`CMPW\tcommand-line-arguments[.+_a-z0-9]+\(SP\), [A-Z]` | 
					
						
							| 
									
										
										
										
											2018-03-20 10:42:06 +01:00
										 |  |  | 	return a == b | 
					
						
							|  |  |  | } | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | func CompareArray3(a, b [3]int16) bool { | 
					
						
							| 
									
										
											  
											
												cmd/compile: set LocalPkg.Path to -p flag
Since CL 391014, cmd/compile now requires the -p flag to be set the
build system. This CL changes it to initialize LocalPkg.Path to the
provided path, rather than relying on writing out `"".` into object
files and expecting cmd/link to substitute them.
However, this actually involved a rather long tail of fixes. Many have
already been submitted, but a few notable ones that have to land
simultaneously with changing LocalPkg:
1. When compiling package runtime, there are really two "runtime"
packages: types.LocalPkg (the source package itself) and
ir.Pkgs.Runtime (the compiler's internal representation, for synthetic
references). Previously, these ended up creating separate link
symbols (`"".xxx` and `runtime.xxx`, respectively), but now they both
end up as `runtime.xxx`, which causes lsym collisions (notably
inittask and funcsyms).
2. test/codegen tests need to be updated to expect symbols to be named
`command-line-arguments.xxx` rather than `"".foo`.
3. The issue20014 test case is sensitive to the sort order of field
tracking symbols. In particular, the local package now sorts to its
natural place in the list, rather than to the front.
Thanks to David Chase for helping track down all of the fixes needed
for this CL.
Updates #51734.
Change-Id: Iba3041cf7ad967d18c6e17922fa06ba11798b565
Reviewed-on: https://go-review.googlesource.com/c/go/+/393715
Reviewed-by: David Chase <drchase@google.com>
Run-TryBot: Matthew Dempsky <mdempsky@google.com>
TryBot-Result: Gopher Robot <gobot@golang.org>
Reviewed-by: Cuong Manh Le <cuong.manhle.vn@gmail.com>
											
										 
											2022-03-17 13:27:40 -07:00
										 |  |  | 	// amd64:`CMPL\tcommand-line-arguments[.+_a-z0-9]+\(SP\), [A-Z]` | 
					
						
							|  |  |  | 	// amd64:`CMPW\tcommand-line-arguments[.+_a-z0-9]+\(SP\), [A-Z]` | 
					
						
							| 
									
										
										
										
											2018-03-20 10:42:06 +01:00
										 |  |  | 	return a == b | 
					
						
							|  |  |  | } | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | func CompareArray4(a, b [12]int8) bool { | 
					
						
							| 
									
										
											  
											
												cmd/compile: set LocalPkg.Path to -p flag
Since CL 391014, cmd/compile now requires the -p flag to be set the
build system. This CL changes it to initialize LocalPkg.Path to the
provided path, rather than relying on writing out `"".` into object
files and expecting cmd/link to substitute them.
However, this actually involved a rather long tail of fixes. Many have
already been submitted, but a few notable ones that have to land
simultaneously with changing LocalPkg:
1. When compiling package runtime, there are really two "runtime"
packages: types.LocalPkg (the source package itself) and
ir.Pkgs.Runtime (the compiler's internal representation, for synthetic
references). Previously, these ended up creating separate link
symbols (`"".xxx` and `runtime.xxx`, respectively), but now they both
end up as `runtime.xxx`, which causes lsym collisions (notably
inittask and funcsyms).
2. test/codegen tests need to be updated to expect symbols to be named
`command-line-arguments.xxx` rather than `"".foo`.
3. The issue20014 test case is sensitive to the sort order of field
tracking symbols. In particular, the local package now sorts to its
natural place in the list, rather than to the front.
Thanks to David Chase for helping track down all of the fixes needed
for this CL.
Updates #51734.
Change-Id: Iba3041cf7ad967d18c6e17922fa06ba11798b565
Reviewed-on: https://go-review.googlesource.com/c/go/+/393715
Reviewed-by: David Chase <drchase@google.com>
Run-TryBot: Matthew Dempsky <mdempsky@google.com>
TryBot-Result: Gopher Robot <gobot@golang.org>
Reviewed-by: Cuong Manh Le <cuong.manhle.vn@gmail.com>
											
										 
											2022-03-17 13:27:40 -07:00
										 |  |  | 	// amd64:`CMPQ\tcommand-line-arguments[.+_a-z0-9]+\(SP\), [A-Z]` | 
					
						
							|  |  |  | 	// amd64:`CMPL\tcommand-line-arguments[.+_a-z0-9]+\(SP\), [A-Z]` | 
					
						
							| 
									
										
										
										
											2018-03-20 10:42:06 +01:00
										 |  |  | 	return a == b | 
					
						
							|  |  |  | } | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | func CompareArray5(a, b [15]byte) bool { | 
					
						
							| 
									
										
											  
											
												cmd/compile: set LocalPkg.Path to -p flag
Since CL 391014, cmd/compile now requires the -p flag to be set the
build system. This CL changes it to initialize LocalPkg.Path to the
provided path, rather than relying on writing out `"".` into object
files and expecting cmd/link to substitute them.
However, this actually involved a rather long tail of fixes. Many have
already been submitted, but a few notable ones that have to land
simultaneously with changing LocalPkg:
1. When compiling package runtime, there are really two "runtime"
packages: types.LocalPkg (the source package itself) and
ir.Pkgs.Runtime (the compiler's internal representation, for synthetic
references). Previously, these ended up creating separate link
symbols (`"".xxx` and `runtime.xxx`, respectively), but now they both
end up as `runtime.xxx`, which causes lsym collisions (notably
inittask and funcsyms).
2. test/codegen tests need to be updated to expect symbols to be named
`command-line-arguments.xxx` rather than `"".foo`.
3. The issue20014 test case is sensitive to the sort order of field
tracking symbols. In particular, the local package now sorts to its
natural place in the list, rather than to the front.
Thanks to David Chase for helping track down all of the fixes needed
for this CL.
Updates #51734.
Change-Id: Iba3041cf7ad967d18c6e17922fa06ba11798b565
Reviewed-on: https://go-review.googlesource.com/c/go/+/393715
Reviewed-by: David Chase <drchase@google.com>
Run-TryBot: Matthew Dempsky <mdempsky@google.com>
TryBot-Result: Gopher Robot <gobot@golang.org>
Reviewed-by: Cuong Manh Le <cuong.manhle.vn@gmail.com>
											
										 
											2022-03-17 13:27:40 -07:00
										 |  |  | 	// amd64:`CMPQ\tcommand-line-arguments[.+_a-z0-9]+\(SP\), [A-Z]` | 
					
						
							| 
									
										
										
										
											2018-03-20 10:42:06 +01:00
										 |  |  | 	return a == b | 
					
						
							|  |  |  | } | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | // This was a TODO in mapaccess1_faststr | 
					
						
							|  |  |  | func CompareArray6(a, b unsafe.Pointer) bool { | 
					
						
							|  |  |  | 	// amd64:`CMPL\t\(.*\), [A-Z]` | 
					
						
							| 
									
										
										
										
											2018-03-26 21:18:27 +01:00
										 |  |  | 	// arm64:`MOVWU\t\(.*\), [R]`,`CMPW\t.*, [R]` | 
					
						
							|  |  |  | 	// ppc64le:`MOVWZ\t\(.*\), [R]`,`CMPW\t.*, [R]` | 
					
						
							|  |  |  | 	// s390x:`MOVWBR\t\(.*\), [R]`,`CMPW\t.*, [R]` | 
					
						
							| 
									
										
										
										
											2018-03-20 10:42:06 +01:00
										 |  |  | 	return *((*[4]byte)(a)) != *((*[4]byte)(b)) | 
					
						
							|  |  |  | } | 
					
						
							| 
									
										
										
										
											2018-03-22 15:00:12 +01:00
										 |  |  | 
 | 
					
						
							| 
									
										
										
										
											2022-08-30 21:48:17 +00:00
										 |  |  | // Check that some structs generate 2/4/8 byte compares. | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | type T1 struct { | 
					
						
							|  |  |  | 	a [8]byte | 
					
						
							|  |  |  | } | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | func CompareStruct1(s1, s2 T1) bool { | 
					
						
							|  |  |  | 	// amd64:`CMPQ\tcommand-line-arguments[.+_a-z0-9]+\(SP\), [A-Z]` | 
					
						
							|  |  |  | 	// amd64:-`CALL` | 
					
						
							|  |  |  | 	return s1 == s2 | 
					
						
							|  |  |  | } | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | type T2 struct { | 
					
						
							|  |  |  | 	a [16]byte | 
					
						
							|  |  |  | } | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | func CompareStruct2(s1, s2 T2) bool { | 
					
						
							|  |  |  | 	// amd64:`CMPQ\tcommand-line-arguments[.+_a-z0-9]+\(SP\), [A-Z]` | 
					
						
							|  |  |  | 	// amd64:-`CALL` | 
					
						
							|  |  |  | 	return s1 == s2 | 
					
						
							|  |  |  | } | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | // Assert that a memequal call is still generated when | 
					
						
							|  |  |  | // inlining would increase binary size too much. | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | type T3 struct { | 
					
						
							|  |  |  | 	a [24]byte | 
					
						
							|  |  |  | } | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | func CompareStruct3(s1, s2 T3) bool { | 
					
						
							|  |  |  | 	// amd64:-`CMPQ\tcommand-line-arguments[.+_a-z0-9]+\(SP\), [A-Z]` | 
					
						
							|  |  |  | 	// amd64:`CALL` | 
					
						
							|  |  |  | 	return s1 == s2 | 
					
						
							|  |  |  | } | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | type T4 struct { | 
					
						
							|  |  |  | 	a [32]byte | 
					
						
							|  |  |  | } | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | func CompareStruct4(s1, s2 T4) bool { | 
					
						
							|  |  |  | 	// amd64:-`CMPQ\tcommand-line-arguments[.+_a-z0-9]+\(SP\), [A-Z]` | 
					
						
							|  |  |  | 	// amd64:`CALL` | 
					
						
							|  |  |  | 	return s1 == s2 | 
					
						
							|  |  |  | } | 
					
						
							|  |  |  | 
 | 
					
						
							| 
									
										
										
										
											2018-03-22 15:00:12 +01:00
										 |  |  | // -------------- // | 
					
						
							|  |  |  | //    Ordering    // | 
					
						
							|  |  |  | // -------------- // | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | // Test that LEAQ/ADDQconst are folded into SETx ops | 
					
						
							|  |  |  | 
 | 
					
						
							| 
									
										
										
										
											2021-04-12 14:00:49 -04:00
										 |  |  | var r bool | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | func CmpFold(x uint32) { | 
					
						
							|  |  |  | 	// amd64:`SETHI\t.*\(SB\)` | 
					
						
							|  |  |  | 	r = x > 4 | 
					
						
							| 
									
										
										
										
											2018-03-22 15:00:12 +01:00
										 |  |  | } | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | // Test that direct comparisons with memory are generated when | 
					
						
							|  |  |  | // possible | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | func CmpMem1(p int, q *int) bool { | 
					
						
							|  |  |  | 	// amd64:`CMPQ\t\(.*\), [A-Z]` | 
					
						
							|  |  |  | 	return p < *q | 
					
						
							|  |  |  | } | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | func CmpMem2(p *int, q int) bool { | 
					
						
							|  |  |  | 	// amd64:`CMPQ\t\(.*\), [A-Z]` | 
					
						
							|  |  |  | 	return *p < q | 
					
						
							|  |  |  | } | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | func CmpMem3(p *int) bool { | 
					
						
							|  |  |  | 	// amd64:`CMPQ\t\(.*\), [$]7` | 
					
						
							|  |  |  | 	return *p < 7 | 
					
						
							|  |  |  | } | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | func CmpMem4(p *int) bool { | 
					
						
							|  |  |  | 	// amd64:`CMPQ\t\(.*\), [$]7` | 
					
						
							|  |  |  | 	return 7 < *p | 
					
						
							|  |  |  | } | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | func CmpMem5(p **int) { | 
					
						
							|  |  |  | 	// amd64:`CMPL\truntime.writeBarrier\(SB\), [$]0` | 
					
						
							|  |  |  | 	*p = nil | 
					
						
							|  |  |  | } | 
					
						
							| 
									
										
										
										
											2018-03-23 18:50:39 +01:00
										 |  |  | 
 | 
					
						
							| 
									
										
										
										
											2018-07-29 12:50:50 +00:00
										 |  |  | func CmpMem6(a []int) int { | 
					
						
							|  |  |  | 	// 386:`CMPL\s8\([A-Z]+\),` | 
					
						
							|  |  |  | 	// amd64:`CMPQ\s16\([A-Z]+\),` | 
					
						
							|  |  |  | 	if a[1] > a[2] { | 
					
						
							|  |  |  | 		return 1 | 
					
						
							|  |  |  | 	} else { | 
					
						
							|  |  |  | 		return 2 | 
					
						
							|  |  |  | 	} | 
					
						
							|  |  |  | } | 
					
						
							|  |  |  | 
 | 
					
						
							| 
									
										
										
										
											2018-03-23 18:50:39 +01:00
										 |  |  | // Check tbz/tbnz are generated when comparing against zero on arm64 | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | func CmpZero1(a int32, ptr *int) { | 
					
						
							|  |  |  | 	if a < 0 { // arm64:"TBZ" | 
					
						
							|  |  |  | 		*ptr = 0 | 
					
						
							|  |  |  | 	} | 
					
						
							|  |  |  | } | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | func CmpZero2(a int64, ptr *int) { | 
					
						
							|  |  |  | 	if a < 0 { // arm64:"TBZ" | 
					
						
							|  |  |  | 		*ptr = 0 | 
					
						
							|  |  |  | 	} | 
					
						
							|  |  |  | } | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | func CmpZero3(a int32, ptr *int) { | 
					
						
							|  |  |  | 	if a >= 0 { // arm64:"TBNZ" | 
					
						
							|  |  |  | 		*ptr = 0 | 
					
						
							|  |  |  | 	} | 
					
						
							|  |  |  | } | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | func CmpZero4(a int64, ptr *int) { | 
					
						
							|  |  |  | 	if a >= 0 { // arm64:"TBNZ" | 
					
						
							|  |  |  | 		*ptr = 0 | 
					
						
							|  |  |  | 	} | 
					
						
							|  |  |  | } | 
					
						
							| 
									
										
										
										
											2018-07-10 01:48:55 +00:00
										 |  |  | 
 | 
					
						
							| 
									
										
										
										
											2022-05-04 17:03:13 +00:00
										 |  |  | func CmpToZero(a, b, d int32, e, f int64, deOptC0, deOptC1 bool) int32 { | 
					
						
							| 
									
										
										
										
											2018-07-19 08:09:13 +00:00
										 |  |  | 	// arm:`TST`,-`AND` | 
					
						
							|  |  |  | 	// arm64:`TSTW`,-`AND` | 
					
						
							| 
									
										
										
										
											2018-08-30 01:19:58 +00:00
										 |  |  | 	// 386:`TESTL`,-`ANDL` | 
					
						
							|  |  |  | 	// amd64:`TESTL`,-`ANDL` | 
					
						
							| 
									
										
										
										
											2018-07-19 08:09:13 +00:00
										 |  |  | 	c0 := a&b < 0 | 
					
						
							|  |  |  | 	// arm:`CMN`,-`ADD` | 
					
						
							|  |  |  | 	// arm64:`CMNW`,-`ADD` | 
					
						
							|  |  |  | 	c1 := a+b < 0 | 
					
						
							|  |  |  | 	// arm:`TEQ`,-`XOR` | 
					
						
							|  |  |  | 	c2 := a^b < 0 | 
					
						
							|  |  |  | 	// arm64:`TST`,-`AND` | 
					
						
							| 
									
										
										
										
											2018-08-30 01:19:58 +00:00
										 |  |  | 	// amd64:`TESTQ`,-`ANDQ` | 
					
						
							|  |  |  | 	c3 := e&f < 0 | 
					
						
							| 
									
										
										
										
											2018-07-19 08:09:13 +00:00
										 |  |  | 	// arm64:`CMN`,-`ADD` | 
					
						
							| 
									
										
										
										
											2018-08-30 01:19:58 +00:00
										 |  |  | 	c4 := e+f < 0 | 
					
						
							|  |  |  | 	// not optimized to single CMNW/CMN due to further use of b+d | 
					
						
							| 
									
										
										
										
											2018-07-19 08:09:13 +00:00
										 |  |  | 	// arm64:`ADD`,-`CMNW` | 
					
						
							| 
									
										
										
										
											2018-08-30 01:19:58 +00:00
										 |  |  | 	// arm:`ADD`,-`CMN` | 
					
						
							| 
									
										
										
										
											2018-07-19 08:09:13 +00:00
										 |  |  | 	c5 := b+d == 0 | 
					
						
							| 
									
										
										
										
											2018-08-30 01:19:58 +00:00
										 |  |  | 	// not optimized to single TSTW/TST due to further use of a&d | 
					
						
							| 
									
										
										
										
											2018-07-19 08:09:13 +00:00
										 |  |  | 	// arm64:`AND`,-`TSTW` | 
					
						
							| 
									
										
										
										
											2018-08-30 01:19:58 +00:00
										 |  |  | 	// arm:`AND`,-`TST` | 
					
						
							| 
									
										
										
										
											2018-09-06 01:13:14 +00:00
										 |  |  | 	// 386:`ANDL` | 
					
						
							| 
									
										
										
										
											2018-07-19 08:09:13 +00:00
										 |  |  | 	c6 := a&d >= 0 | 
					
						
							| 
									
										
										
										
											2018-09-27 06:21:14 +00:00
										 |  |  | 	// arm64:`TST\sR[0-9]+<<3,\sR[0-9]+` | 
					
						
							|  |  |  | 	c7 := e&(f<<3) < 0 | 
					
						
							|  |  |  | 	// arm64:`CMN\sR[0-9]+<<3,\sR[0-9]+` | 
					
						
							|  |  |  | 	c8 := e+(f<<3) < 0 | 
					
						
							| 
									
										
										
										
											2018-07-19 08:09:13 +00:00
										 |  |  | 	if c0 { | 
					
						
							| 
									
										
										
										
											2018-07-10 01:48:55 +00:00
										 |  |  | 		return 1 | 
					
						
							| 
									
										
										
										
											2018-07-19 08:09:13 +00:00
										 |  |  | 	} else if c1 { | 
					
						
							| 
									
										
										
										
											2018-07-10 01:48:55 +00:00
										 |  |  | 		return 2 | 
					
						
							| 
									
										
										
										
											2018-07-19 08:09:13 +00:00
										 |  |  | 	} else if c2 { | 
					
						
							| 
									
										
										
										
											2018-07-10 01:48:55 +00:00
										 |  |  | 		return 3 | 
					
						
							| 
									
										
										
										
											2018-07-19 08:09:13 +00:00
										 |  |  | 	} else if c3 { | 
					
						
							|  |  |  | 		return 4 | 
					
						
							|  |  |  | 	} else if c4 { | 
					
						
							|  |  |  | 		return 5 | 
					
						
							|  |  |  | 	} else if c5 { | 
					
						
							| 
									
										
										
										
											2022-05-04 17:03:13 +00:00
										 |  |  | 		return 6 | 
					
						
							| 
									
										
										
										
											2018-07-19 08:09:13 +00:00
										 |  |  | 	} else if c6 { | 
					
						
							| 
									
										
										
										
											2018-09-27 06:21:14 +00:00
										 |  |  | 		return 7 | 
					
						
							| 
									
										
										
										
											2022-05-04 17:03:13 +00:00
										 |  |  | 	} else if c7 { | 
					
						
							|  |  |  | 		return 9 | 
					
						
							| 
									
										
										
										
											2018-09-27 06:21:14 +00:00
										 |  |  | 	} else if c8 { | 
					
						
							| 
									
										
										
										
											2022-05-04 17:03:13 +00:00
										 |  |  | 		return 10 | 
					
						
							|  |  |  | 	} else if deOptC0 { | 
					
						
							|  |  |  | 		return b + d | 
					
						
							|  |  |  | 	} else if deOptC1 { | 
					
						
							|  |  |  | 		return a & d | 
					
						
							| 
									
										
										
										
											2018-07-10 01:48:55 +00:00
										 |  |  | 	} else { | 
					
						
							|  |  |  | 		return 0 | 
					
						
							|  |  |  | 	} | 
					
						
							|  |  |  | } | 
					
						
							| 
									
										
										
										
											2018-10-10 13:47:18 -04:00
										 |  |  | 
 | 
					
						
							|  |  |  | func CmpLogicalToZero(a, b, c uint32, d, e uint64) uint64 { | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | 	// ppc64:"ANDCC",-"CMPW" | 
					
						
							|  |  |  | 	// ppc64le:"ANDCC",-"CMPW" | 
					
						
							| 
									
										
										
										
											2019-09-21 16:22:50 +05:30
										 |  |  | 	// wasm:"I64Eqz",-"I32Eqz",-"I64ExtendI32U",-"I32WrapI64" | 
					
						
							| 
									
										
										
										
											2019-03-13 13:52:17 -07:00
										 |  |  | 	if a&63 == 0 { | 
					
						
							| 
									
										
										
										
											2018-10-10 13:47:18 -04:00
										 |  |  | 		return 1 | 
					
						
							|  |  |  | 	} | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | 	// ppc64:"ANDCC",-"CMP" | 
					
						
							|  |  |  | 	// ppc64le:"ANDCC",-"CMP" | 
					
						
							| 
									
										
										
										
											2019-09-21 16:22:50 +05:30
										 |  |  | 	// wasm:"I64Eqz",-"I32Eqz",-"I64ExtendI32U",-"I32WrapI64" | 
					
						
							| 
									
										
										
										
											2019-03-13 13:52:17 -07:00
										 |  |  | 	if d&255 == 0 { | 
					
						
							| 
									
										
										
										
											2018-10-10 13:47:18 -04:00
										 |  |  | 		return 1 | 
					
						
							|  |  |  | 	} | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | 	// ppc64:"ANDCC",-"CMP" | 
					
						
							|  |  |  | 	// ppc64le:"ANDCC",-"CMP" | 
					
						
							| 
									
										
										
										
											2019-09-21 16:22:50 +05:30
										 |  |  | 	// wasm:"I64Eqz",-"I32Eqz",-"I64ExtendI32U",-"I32WrapI64" | 
					
						
							| 
									
										
										
										
											2019-03-13 13:52:17 -07:00
										 |  |  | 	if d&e == 0 { | 
					
						
							| 
									
										
										
										
											2018-10-10 13:47:18 -04:00
										 |  |  | 		return 1 | 
					
						
							|  |  |  | 	} | 
					
						
							|  |  |  | 	// ppc64:"ORCC",-"CMP" | 
					
						
							|  |  |  | 	// ppc64le:"ORCC",-"CMP" | 
					
						
							| 
									
										
										
										
											2019-09-21 16:22:50 +05:30
										 |  |  | 	// wasm:"I64Eqz",-"I32Eqz",-"I64ExtendI32U",-"I32WrapI64" | 
					
						
							| 
									
										
										
										
											2019-03-13 13:52:17 -07:00
										 |  |  | 	if d|e == 0 { | 
					
						
							| 
									
										
										
										
											2018-10-10 13:47:18 -04:00
										 |  |  | 		return 1 | 
					
						
							|  |  |  | 	} | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | 	// ppc64:"XORCC",-"CMP" | 
					
						
							|  |  |  | 	// ppc64le:"XORCC",-"CMP" | 
					
						
							| 
									
										
										
										
											2019-09-21 16:22:50 +05:30
										 |  |  | 	// wasm:"I64Eqz","I32Eqz",-"I64ExtendI32U",-"I32WrapI64" | 
					
						
							| 
									
										
										
										
											2019-03-13 13:52:17 -07:00
										 |  |  | 	if e^d == 0 { | 
					
						
							| 
									
										
										
										
											2018-10-10 13:47:18 -04:00
										 |  |  | 		return 1 | 
					
						
							|  |  |  | 	} | 
					
						
							|  |  |  | 	return 0 | 
					
						
							|  |  |  | } | 
					
						
							| 
									
										
											  
											
												cmd/compile: fix incorrect rewriting to if condition
Some ARM64 rewriting rules convert 'comparing to zero' conditions of if
statements to a simplified version utilizing CMN and CMP instructions to
branch over condition flags, in order to save one Add or Sub caculation.
Such optimizations lead to wrong branching in case an overflow/underflow
occurs when executing CMN or CMP.
Fix the issue by introducing new block opcodes that don't honor the
overflow/underflow flag, in the following categories:
  Block-Op        Meaning                   ARM condition codes
  1. LTnoov        less than                 MI
  2. GEnoov        greater than or equal     PL
  3. LEnoov        less than or equal        MI || EQ
  4. GTnoov        greater than              NEQ & PL
The backend generates two consecutive branch instructions for 'LEnoov'
and 'GTnoov' to model their expected behavior. A slight change to 'gc'
and amd64/386 backends is made to unify the code generation.
Add a test 'TestCondRewrite' as justification, it covers 32 incorrect rules
identified on arm64, more might be needed on other arches, like 32-bit arm.
Add two benchmarks profiling the aforementioned category 1&2 and category
3&4 separetely, we expect the first two categories will show performance
improvement and the second will not result in visible regression compared with
the non-optimized version.
This change also updates TestFormats to support using %#x.
Examples exhibiting where does the issue come from:
  1: 'if x + 3 < 0' might be converted to:
  before:
    CMN $3, R0
    BGE <else branch> // wrong branch is taken if 'x+3' overflows
  after:
    CMN $3, R0
    BPL <else branch>
  2: 'if y - 3 > 0' might be converted to:
  before:
    CMP $3, R0
    BLE <else branch> // wrong branch is taken if 'y-3' underflows
  after:
    CMP $3, R0
    BMI <else branch>
    BEQ <else branch>
Benchmark data from different kinds of arm64 servers, 'old' is the non-optimized
version (not the parent commit), generally the optimization version outperforms.
S1:
name                    old time/op  new time/op  delta
CondRewrite/SoloJump  13.6ns ± 0%  12.9ns ± 0%  -5.15%  (p=0.000 n=10+10)
CondRewrite/CombJump  13.8ns ± 1%  12.9ns ± 0%  -6.32%  (p=0.000 n=10+10)
S2:
name                     old time/op  new time/op  delta
CondRewrite/SoloJump  11.6ns ± 0%  10.9ns ± 0%  -6.03%  (p=0.000 n=10+10)
CondRewrite/CombJump  11.4ns ± 0%  10.8ns ± 1%  -5.53%  (p=0.000 n=10+10)
S3:
name                     old time/op  new time/op  delta
CondRewrite/SoloJump  7.36ns ± 0%  7.50ns ± 0%  +1.79%  (p=0.000 n=9+10)
CondRewrite/CombJump  7.35ns ± 0%  7.75ns ± 0%  +5.51%  (p=0.000 n=8+9)
S4:
name                      old time/op  new time/op  delta
CondRewrite/SoloJump-224  11.5ns ± 1%  10.9ns ± 0%  -4.97%  (p=0.000 n=10+10)
CondRewrite/CombJump-224  11.9ns ± 0%  11.5ns ± 0%  -2.95%  (p=0.000 n=10+10)
S5:
name                     old time/op  new time/op  delta
CondRewrite/SoloJump  10.0ns ± 0%  10.0ns ± 0%  -0.45%  (p=0.000 n=9+10)
CondRewrite/CombJump  9.93ns ± 0%  9.77ns ± 0%  -1.53%  (p=0.000 n=10+9)
Go1 perf. data:
name                     old time/op    new time/op    delta
BinaryTree17              6.29s ± 1%     6.30s ± 1%    ~     (p=1.000 n=5+5)
Fannkuch11                5.40s ± 0%     5.40s ± 0%    ~     (p=0.841 n=5+5)
FmtFprintfEmpty          97.9ns ± 0%    98.9ns ± 3%    ~     (p=0.937 n=4+5)
FmtFprintfString          171ns ± 3%     171ns ± 2%    ~     (p=0.754 n=5+5)
FmtFprintfInt             212ns ± 0%     217ns ± 6%  +2.55%  (p=0.008 n=5+5)
FmtFprintfIntInt          296ns ± 1%     297ns ± 2%    ~     (p=0.516 n=5+5)
FmtFprintfPrefixedInt     371ns ± 2%     374ns ± 7%    ~     (p=1.000 n=5+5)
FmtFprintfFloat           435ns ± 1%     439ns ± 2%    ~     (p=0.056 n=5+5)
FmtManyArgs              1.37µs ± 1%    1.36µs ± 1%    ~     (p=0.730 n=5+5)
GobDecode                14.6ms ± 4%    14.4ms ± 4%    ~     (p=0.690 n=5+5)
GobEncode                11.8ms ±20%    11.6ms ±15%    ~     (p=1.000 n=5+5)
Gzip                      507ms ± 0%     491ms ± 0%  -3.22%  (p=0.008 n=5+5)
Gunzip                   73.8ms ± 0%    73.9ms ± 0%    ~     (p=0.690 n=5+5)
HTTPClientServer          116µs ± 0%     116µs ± 0%    ~     (p=0.686 n=4+4)
JSONEncode               21.8ms ± 1%    21.6ms ± 2%    ~     (p=0.151 n=5+5)
JSONDecode                104ms ± 1%     103ms ± 1%  -1.08%  (p=0.016 n=5+5)
Mandelbrot200            9.53ms ± 0%    9.53ms ± 0%    ~     (p=0.421 n=5+5)
GoParse                  7.55ms ± 1%    7.51ms ± 1%    ~     (p=0.151 n=5+5)
RegexpMatchEasy0_32       158ns ± 0%     158ns ± 0%    ~     (all equal)
RegexpMatchEasy0_1K       606ns ± 1%     608ns ± 3%    ~     (p=0.937 n=5+5)
RegexpMatchEasy1_32       143ns ± 0%     144ns ± 1%    ~     (p=0.095 n=5+4)
RegexpMatchEasy1_1K       927ns ± 2%     944ns ± 2%    ~     (p=0.056 n=5+5)
RegexpMatchMedium_32     16.0ns ± 0%    16.0ns ± 0%    ~     (all equal)
RegexpMatchMedium_1K     69.3µs ± 2%    69.7µs ± 0%    ~     (p=0.690 n=5+5)
RegexpMatchHard_32       3.73µs ± 0%    3.73µs ± 1%    ~     (p=0.984 n=5+5)
RegexpMatchHard_1K        111µs ± 1%     110µs ± 0%    ~     (p=0.151 n=5+5)
Revcomp                   1.91s ±47%     1.77s ±68%    ~     (p=1.000 n=5+5)
Template                  138ms ± 1%     138ms ± 1%    ~     (p=1.000 n=5+5)
TimeParse                 787ns ± 2%     785ns ± 1%    ~     (p=0.540 n=5+5)
TimeFormat                729ns ± 1%     726ns ± 1%    ~     (p=0.151 n=5+5)
Updates #38740
Change-Id: I06c604874acdc1e63e66452dadee5df053045222
Reviewed-on: https://go-review.googlesource.com/c/go/+/233097
Reviewed-by: Keith Randall <khr@golang.org>
Run-TryBot: Keith Randall <khr@golang.org>
											
										 
											2020-05-06 09:54:40 +00:00
										 |  |  | 
 | 
					
						
							|  |  |  | // The following CmpToZero_ex* check that cmp|cmn with bmi|bpl are generated for | 
					
						
							|  |  |  | // 'comparing to zero' expressions | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | // var + const | 
					
						
							| 
									
										
										
										
											2020-06-01 11:01:14 +00:00
										 |  |  | // 'x-const' might be canonicalized to 'x+(-const)', so we check both | 
					
						
							|  |  |  | // CMN and CMP for subtraction expressions to make the pattern robust. | 
					
						
							| 
									
										
											  
											
												cmd/compile: fix incorrect rewriting to if condition
Some ARM64 rewriting rules convert 'comparing to zero' conditions of if
statements to a simplified version utilizing CMN and CMP instructions to
branch over condition flags, in order to save one Add or Sub caculation.
Such optimizations lead to wrong branching in case an overflow/underflow
occurs when executing CMN or CMP.
Fix the issue by introducing new block opcodes that don't honor the
overflow/underflow flag, in the following categories:
  Block-Op        Meaning                   ARM condition codes
  1. LTnoov        less than                 MI
  2. GEnoov        greater than or equal     PL
  3. LEnoov        less than or equal        MI || EQ
  4. GTnoov        greater than              NEQ & PL
The backend generates two consecutive branch instructions for 'LEnoov'
and 'GTnoov' to model their expected behavior. A slight change to 'gc'
and amd64/386 backends is made to unify the code generation.
Add a test 'TestCondRewrite' as justification, it covers 32 incorrect rules
identified on arm64, more might be needed on other arches, like 32-bit arm.
Add two benchmarks profiling the aforementioned category 1&2 and category
3&4 separetely, we expect the first two categories will show performance
improvement and the second will not result in visible regression compared with
the non-optimized version.
This change also updates TestFormats to support using %#x.
Examples exhibiting where does the issue come from:
  1: 'if x + 3 < 0' might be converted to:
  before:
    CMN $3, R0
    BGE <else branch> // wrong branch is taken if 'x+3' overflows
  after:
    CMN $3, R0
    BPL <else branch>
  2: 'if y - 3 > 0' might be converted to:
  before:
    CMP $3, R0
    BLE <else branch> // wrong branch is taken if 'y-3' underflows
  after:
    CMP $3, R0
    BMI <else branch>
    BEQ <else branch>
Benchmark data from different kinds of arm64 servers, 'old' is the non-optimized
version (not the parent commit), generally the optimization version outperforms.
S1:
name                    old time/op  new time/op  delta
CondRewrite/SoloJump  13.6ns ± 0%  12.9ns ± 0%  -5.15%  (p=0.000 n=10+10)
CondRewrite/CombJump  13.8ns ± 1%  12.9ns ± 0%  -6.32%  (p=0.000 n=10+10)
S2:
name                     old time/op  new time/op  delta
CondRewrite/SoloJump  11.6ns ± 0%  10.9ns ± 0%  -6.03%  (p=0.000 n=10+10)
CondRewrite/CombJump  11.4ns ± 0%  10.8ns ± 1%  -5.53%  (p=0.000 n=10+10)
S3:
name                     old time/op  new time/op  delta
CondRewrite/SoloJump  7.36ns ± 0%  7.50ns ± 0%  +1.79%  (p=0.000 n=9+10)
CondRewrite/CombJump  7.35ns ± 0%  7.75ns ± 0%  +5.51%  (p=0.000 n=8+9)
S4:
name                      old time/op  new time/op  delta
CondRewrite/SoloJump-224  11.5ns ± 1%  10.9ns ± 0%  -4.97%  (p=0.000 n=10+10)
CondRewrite/CombJump-224  11.9ns ± 0%  11.5ns ± 0%  -2.95%  (p=0.000 n=10+10)
S5:
name                     old time/op  new time/op  delta
CondRewrite/SoloJump  10.0ns ± 0%  10.0ns ± 0%  -0.45%  (p=0.000 n=9+10)
CondRewrite/CombJump  9.93ns ± 0%  9.77ns ± 0%  -1.53%  (p=0.000 n=10+9)
Go1 perf. data:
name                     old time/op    new time/op    delta
BinaryTree17              6.29s ± 1%     6.30s ± 1%    ~     (p=1.000 n=5+5)
Fannkuch11                5.40s ± 0%     5.40s ± 0%    ~     (p=0.841 n=5+5)
FmtFprintfEmpty          97.9ns ± 0%    98.9ns ± 3%    ~     (p=0.937 n=4+5)
FmtFprintfString          171ns ± 3%     171ns ± 2%    ~     (p=0.754 n=5+5)
FmtFprintfInt             212ns ± 0%     217ns ± 6%  +2.55%  (p=0.008 n=5+5)
FmtFprintfIntInt          296ns ± 1%     297ns ± 2%    ~     (p=0.516 n=5+5)
FmtFprintfPrefixedInt     371ns ± 2%     374ns ± 7%    ~     (p=1.000 n=5+5)
FmtFprintfFloat           435ns ± 1%     439ns ± 2%    ~     (p=0.056 n=5+5)
FmtManyArgs              1.37µs ± 1%    1.36µs ± 1%    ~     (p=0.730 n=5+5)
GobDecode                14.6ms ± 4%    14.4ms ± 4%    ~     (p=0.690 n=5+5)
GobEncode                11.8ms ±20%    11.6ms ±15%    ~     (p=1.000 n=5+5)
Gzip                      507ms ± 0%     491ms ± 0%  -3.22%  (p=0.008 n=5+5)
Gunzip                   73.8ms ± 0%    73.9ms ± 0%    ~     (p=0.690 n=5+5)
HTTPClientServer          116µs ± 0%     116µs ± 0%    ~     (p=0.686 n=4+4)
JSONEncode               21.8ms ± 1%    21.6ms ± 2%    ~     (p=0.151 n=5+5)
JSONDecode                104ms ± 1%     103ms ± 1%  -1.08%  (p=0.016 n=5+5)
Mandelbrot200            9.53ms ± 0%    9.53ms ± 0%    ~     (p=0.421 n=5+5)
GoParse                  7.55ms ± 1%    7.51ms ± 1%    ~     (p=0.151 n=5+5)
RegexpMatchEasy0_32       158ns ± 0%     158ns ± 0%    ~     (all equal)
RegexpMatchEasy0_1K       606ns ± 1%     608ns ± 3%    ~     (p=0.937 n=5+5)
RegexpMatchEasy1_32       143ns ± 0%     144ns ± 1%    ~     (p=0.095 n=5+4)
RegexpMatchEasy1_1K       927ns ± 2%     944ns ± 2%    ~     (p=0.056 n=5+5)
RegexpMatchMedium_32     16.0ns ± 0%    16.0ns ± 0%    ~     (all equal)
RegexpMatchMedium_1K     69.3µs ± 2%    69.7µs ± 0%    ~     (p=0.690 n=5+5)
RegexpMatchHard_32       3.73µs ± 0%    3.73µs ± 1%    ~     (p=0.984 n=5+5)
RegexpMatchHard_1K        111µs ± 1%     110µs ± 0%    ~     (p=0.151 n=5+5)
Revcomp                   1.91s ±47%     1.77s ±68%    ~     (p=1.000 n=5+5)
Template                  138ms ± 1%     138ms ± 1%    ~     (p=1.000 n=5+5)
TimeParse                 787ns ± 2%     785ns ± 1%    ~     (p=0.540 n=5+5)
TimeFormat                729ns ± 1%     726ns ± 1%    ~     (p=0.151 n=5+5)
Updates #38740
Change-Id: I06c604874acdc1e63e66452dadee5df053045222
Reviewed-on: https://go-review.googlesource.com/c/go/+/233097
Reviewed-by: Keith Randall <khr@golang.org>
Run-TryBot: Keith Randall <khr@golang.org>
											
										 
											2020-05-06 09:54:40 +00:00
										 |  |  | func CmpToZero_ex1(a int64, e int32) int { | 
					
						
							|  |  |  | 	// arm64:`CMN`,-`ADD`,`(BMI|BPL)` | 
					
						
							|  |  |  | 	if a+3 < 0 { | 
					
						
							|  |  |  | 		return 1 | 
					
						
							|  |  |  | 	} | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | 	// arm64:`CMN`,-`ADD`,`BEQ`,`(BMI|BPL)` | 
					
						
							|  |  |  | 	if a+5 <= 0 { | 
					
						
							|  |  |  | 		return 1 | 
					
						
							|  |  |  | 	} | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | 	// arm64:`CMN`,-`ADD`,`(BMI|BPL)` | 
					
						
							|  |  |  | 	if a+13 >= 0 { | 
					
						
							|  |  |  | 		return 2 | 
					
						
							|  |  |  | 	} | 
					
						
							|  |  |  | 
 | 
					
						
							| 
									
										
										
										
											2020-06-01 11:01:14 +00:00
										 |  |  | 	// arm64:`CMP|CMN`,-`(ADD|SUB)`,`(BMI|BPL)` | 
					
						
							| 
									
										
											  
											
												cmd/compile: fix incorrect rewriting to if condition
Some ARM64 rewriting rules convert 'comparing to zero' conditions of if
statements to a simplified version utilizing CMN and CMP instructions to
branch over condition flags, in order to save one Add or Sub caculation.
Such optimizations lead to wrong branching in case an overflow/underflow
occurs when executing CMN or CMP.
Fix the issue by introducing new block opcodes that don't honor the
overflow/underflow flag, in the following categories:
  Block-Op        Meaning                   ARM condition codes
  1. LTnoov        less than                 MI
  2. GEnoov        greater than or equal     PL
  3. LEnoov        less than or equal        MI || EQ
  4. GTnoov        greater than              NEQ & PL
The backend generates two consecutive branch instructions for 'LEnoov'
and 'GTnoov' to model their expected behavior. A slight change to 'gc'
and amd64/386 backends is made to unify the code generation.
Add a test 'TestCondRewrite' as justification, it covers 32 incorrect rules
identified on arm64, more might be needed on other arches, like 32-bit arm.
Add two benchmarks profiling the aforementioned category 1&2 and category
3&4 separetely, we expect the first two categories will show performance
improvement and the second will not result in visible regression compared with
the non-optimized version.
This change also updates TestFormats to support using %#x.
Examples exhibiting where does the issue come from:
  1: 'if x + 3 < 0' might be converted to:
  before:
    CMN $3, R0
    BGE <else branch> // wrong branch is taken if 'x+3' overflows
  after:
    CMN $3, R0
    BPL <else branch>
  2: 'if y - 3 > 0' might be converted to:
  before:
    CMP $3, R0
    BLE <else branch> // wrong branch is taken if 'y-3' underflows
  after:
    CMP $3, R0
    BMI <else branch>
    BEQ <else branch>
Benchmark data from different kinds of arm64 servers, 'old' is the non-optimized
version (not the parent commit), generally the optimization version outperforms.
S1:
name                    old time/op  new time/op  delta
CondRewrite/SoloJump  13.6ns ± 0%  12.9ns ± 0%  -5.15%  (p=0.000 n=10+10)
CondRewrite/CombJump  13.8ns ± 1%  12.9ns ± 0%  -6.32%  (p=0.000 n=10+10)
S2:
name                     old time/op  new time/op  delta
CondRewrite/SoloJump  11.6ns ± 0%  10.9ns ± 0%  -6.03%  (p=0.000 n=10+10)
CondRewrite/CombJump  11.4ns ± 0%  10.8ns ± 1%  -5.53%  (p=0.000 n=10+10)
S3:
name                     old time/op  new time/op  delta
CondRewrite/SoloJump  7.36ns ± 0%  7.50ns ± 0%  +1.79%  (p=0.000 n=9+10)
CondRewrite/CombJump  7.35ns ± 0%  7.75ns ± 0%  +5.51%  (p=0.000 n=8+9)
S4:
name                      old time/op  new time/op  delta
CondRewrite/SoloJump-224  11.5ns ± 1%  10.9ns ± 0%  -4.97%  (p=0.000 n=10+10)
CondRewrite/CombJump-224  11.9ns ± 0%  11.5ns ± 0%  -2.95%  (p=0.000 n=10+10)
S5:
name                     old time/op  new time/op  delta
CondRewrite/SoloJump  10.0ns ± 0%  10.0ns ± 0%  -0.45%  (p=0.000 n=9+10)
CondRewrite/CombJump  9.93ns ± 0%  9.77ns ± 0%  -1.53%  (p=0.000 n=10+9)
Go1 perf. data:
name                     old time/op    new time/op    delta
BinaryTree17              6.29s ± 1%     6.30s ± 1%    ~     (p=1.000 n=5+5)
Fannkuch11                5.40s ± 0%     5.40s ± 0%    ~     (p=0.841 n=5+5)
FmtFprintfEmpty          97.9ns ± 0%    98.9ns ± 3%    ~     (p=0.937 n=4+5)
FmtFprintfString          171ns ± 3%     171ns ± 2%    ~     (p=0.754 n=5+5)
FmtFprintfInt             212ns ± 0%     217ns ± 6%  +2.55%  (p=0.008 n=5+5)
FmtFprintfIntInt          296ns ± 1%     297ns ± 2%    ~     (p=0.516 n=5+5)
FmtFprintfPrefixedInt     371ns ± 2%     374ns ± 7%    ~     (p=1.000 n=5+5)
FmtFprintfFloat           435ns ± 1%     439ns ± 2%    ~     (p=0.056 n=5+5)
FmtManyArgs              1.37µs ± 1%    1.36µs ± 1%    ~     (p=0.730 n=5+5)
GobDecode                14.6ms ± 4%    14.4ms ± 4%    ~     (p=0.690 n=5+5)
GobEncode                11.8ms ±20%    11.6ms ±15%    ~     (p=1.000 n=5+5)
Gzip                      507ms ± 0%     491ms ± 0%  -3.22%  (p=0.008 n=5+5)
Gunzip                   73.8ms ± 0%    73.9ms ± 0%    ~     (p=0.690 n=5+5)
HTTPClientServer          116µs ± 0%     116µs ± 0%    ~     (p=0.686 n=4+4)
JSONEncode               21.8ms ± 1%    21.6ms ± 2%    ~     (p=0.151 n=5+5)
JSONDecode                104ms ± 1%     103ms ± 1%  -1.08%  (p=0.016 n=5+5)
Mandelbrot200            9.53ms ± 0%    9.53ms ± 0%    ~     (p=0.421 n=5+5)
GoParse                  7.55ms ± 1%    7.51ms ± 1%    ~     (p=0.151 n=5+5)
RegexpMatchEasy0_32       158ns ± 0%     158ns ± 0%    ~     (all equal)
RegexpMatchEasy0_1K       606ns ± 1%     608ns ± 3%    ~     (p=0.937 n=5+5)
RegexpMatchEasy1_32       143ns ± 0%     144ns ± 1%    ~     (p=0.095 n=5+4)
RegexpMatchEasy1_1K       927ns ± 2%     944ns ± 2%    ~     (p=0.056 n=5+5)
RegexpMatchMedium_32     16.0ns ± 0%    16.0ns ± 0%    ~     (all equal)
RegexpMatchMedium_1K     69.3µs ± 2%    69.7µs ± 0%    ~     (p=0.690 n=5+5)
RegexpMatchHard_32       3.73µs ± 0%    3.73µs ± 1%    ~     (p=0.984 n=5+5)
RegexpMatchHard_1K        111µs ± 1%     110µs ± 0%    ~     (p=0.151 n=5+5)
Revcomp                   1.91s ±47%     1.77s ±68%    ~     (p=1.000 n=5+5)
Template                  138ms ± 1%     138ms ± 1%    ~     (p=1.000 n=5+5)
TimeParse                 787ns ± 2%     785ns ± 1%    ~     (p=0.540 n=5+5)
TimeFormat                729ns ± 1%     726ns ± 1%    ~     (p=0.151 n=5+5)
Updates #38740
Change-Id: I06c604874acdc1e63e66452dadee5df053045222
Reviewed-on: https://go-review.googlesource.com/c/go/+/233097
Reviewed-by: Keith Randall <khr@golang.org>
Run-TryBot: Keith Randall <khr@golang.org>
											
										 
											2020-05-06 09:54:40 +00:00
										 |  |  | 	if a-7 < 0 { | 
					
						
							|  |  |  | 		return 3 | 
					
						
							|  |  |  | 	} | 
					
						
							|  |  |  | 
 | 
					
						
							| 
									
										
											  
											
												cmd/compile: add late lower pass for last rules to run
Usually optimization rules have corresponding priorities, some need to
be run first, some run next, and some run last, which produces the best
code. But currently our optimization rules have no priority, this CL
adds a late lower pass that runs those rules that need to be run at last,
such as split unreasonable constant folding. This pass can be seen as
the second round of the lower pass.
For example:
func foo(a, b uint64) uint64 {
        d := a+0x1234568
        d1 := b+0x1234568
        return d&d1
}
The code generated by the master branch:
	0x0004 00004        ADD     $19088744, R0, R2 // movz+movk+add
	0x0010 00016        ADD     $19088744, R1, R1 // movz+movk+add
	0x001c 00028        AND     R1, R2, R0
This is because the current constant folding optimization rules do not
take into account the range of constants, causing the constant to be
loaded repeatedly. This CL splits these unreasonable constants folding
in the late lower pass. With this CL the generated code:
	0x0004 00004        MOVD    $19088744, R2 // movz+movk
	0x000c 00012        ADD     R0, R2, R3
	0x0010 00016        ADD     R1, R2, R1
	0x0014 00020        AND     R1, R3, R0
This CL also adds constant folding optimization for ADDS instruction.
In addition, in order not to introduce the codegen regression, an
optimization rule is added to change the addition of a negative number
into a subtraction of a positive number.
go1 benchmarks:
name                     old time/op    new time/op    delta
BinaryTree17-8              1.22s ± 1%     1.24s ± 0%  +1.56%  (p=0.008 n=5+5)
Fannkuch11-8                1.54s ± 0%     1.53s ± 0%  -0.69%  (p=0.016 n=4+5)
FmtFprintfEmpty-8          14.1ns ± 0%    14.1ns ± 0%    ~     (p=0.079 n=4+5)
FmtFprintfString-8         26.0ns ± 0%    26.1ns ± 0%  +0.23%  (p=0.008 n=5+5)
FmtFprintfInt-8            32.3ns ± 0%    32.9ns ± 1%  +1.72%  (p=0.008 n=5+5)
FmtFprintfIntInt-8         54.5ns ± 0%    55.5ns ± 0%  +1.83%  (p=0.008 n=5+5)
FmtFprintfPrefixedInt-8    61.5ns ± 0%    62.0ns ± 0%  +0.93%  (p=0.008 n=5+5)
FmtFprintfFloat-8          72.0ns ± 0%    73.6ns ± 0%  +2.24%  (p=0.008 n=5+5)
FmtManyArgs-8               221ns ± 0%     224ns ± 0%  +1.22%  (p=0.008 n=5+5)
GobDecode-8                1.91ms ± 0%    1.93ms ± 0%  +0.98%  (p=0.008 n=5+5)
GobEncode-8                1.40ms ± 1%    1.39ms ± 0%  -0.79%  (p=0.032 n=5+5)
Gzip-8                      115ms ± 0%     117ms ± 1%  +1.17%  (p=0.008 n=5+5)
Gunzip-8                   19.4ms ± 1%    19.3ms ± 0%  -0.71%  (p=0.016 n=5+4)
HTTPClientServer-8         27.0µs ± 0%    27.3µs ± 0%  +0.80%  (p=0.008 n=5+5)
JSONEncode-8               3.36ms ± 1%    3.33ms ± 0%    ~     (p=0.056 n=5+5)
JSONDecode-8               17.5ms ± 2%    17.8ms ± 0%  +1.71%  (p=0.016 n=5+4)
Mandelbrot200-8            2.29ms ± 0%    2.29ms ± 0%    ~     (p=0.151 n=5+5)
GoParse-8                  1.35ms ± 1%    1.36ms ± 1%    ~     (p=0.056 n=5+5)
RegexpMatchEasy0_32-8      24.5ns ± 0%    24.5ns ± 0%    ~     (p=0.444 n=4+5)
RegexpMatchEasy0_1K-8       131ns ±11%     118ns ± 6%    ~     (p=0.056 n=5+5)
RegexpMatchEasy1_32-8      22.9ns ± 0%    22.9ns ± 0%    ~     (p=0.905 n=4+5)
RegexpMatchEasy1_1K-8       126ns ± 0%     127ns ± 0%    ~     (p=0.063 n=4+5)
RegexpMatchMedium_32-8      486ns ± 5%     483ns ± 0%    ~     (p=0.381 n=5+4)
RegexpMatchMedium_1K-8     15.4µs ± 1%    15.5µs ± 0%    ~     (p=0.151 n=5+5)
RegexpMatchHard_32-8        687ns ± 0%     686ns ± 0%    ~     (p=0.103 n=5+5)
RegexpMatchHard_1K-8       20.7µs ± 0%    20.7µs ± 1%    ~     (p=0.151 n=5+5)
Revcomp-8                   175ms ± 2%     176ms ± 3%    ~     (p=1.000 n=5+5)
Template-8                 20.4ms ± 6%    20.1ms ± 2%    ~     (p=0.151 n=5+5)
TimeParse-8                 112ns ± 0%     113ns ± 0%  +0.97%  (p=0.016 n=5+4)
TimeFormat-8                156ns ± 0%     145ns ± 0%  -7.14%  (p=0.029 n=4+4)
Change-Id: I3ced26e89041f873ac989586514ccc5ee09f13da
Reviewed-on: https://go-review.googlesource.com/c/go/+/425134
Reviewed-by: Keith Randall <khr@google.com>
Reviewed-by: Cherry Mui <cherryyz@google.com>
TryBot-Result: Gopher Robot <gobot@golang.org>
Reviewed-by: Keith Randall <khr@golang.org>
Run-TryBot: Eric Fang <eric.fang@arm.com>
											
										 
											2022-08-17 10:01:17 +00:00
										 |  |  | 	// arm64:`SUB`,`TBZ` | 
					
						
							| 
									
										
											  
											
												cmd/compile: fix incorrect rewriting to if condition
Some ARM64 rewriting rules convert 'comparing to zero' conditions of if
statements to a simplified version utilizing CMN and CMP instructions to
branch over condition flags, in order to save one Add or Sub caculation.
Such optimizations lead to wrong branching in case an overflow/underflow
occurs when executing CMN or CMP.
Fix the issue by introducing new block opcodes that don't honor the
overflow/underflow flag, in the following categories:
  Block-Op        Meaning                   ARM condition codes
  1. LTnoov        less than                 MI
  2. GEnoov        greater than or equal     PL
  3. LEnoov        less than or equal        MI || EQ
  4. GTnoov        greater than              NEQ & PL
The backend generates two consecutive branch instructions for 'LEnoov'
and 'GTnoov' to model their expected behavior. A slight change to 'gc'
and amd64/386 backends is made to unify the code generation.
Add a test 'TestCondRewrite' as justification, it covers 32 incorrect rules
identified on arm64, more might be needed on other arches, like 32-bit arm.
Add two benchmarks profiling the aforementioned category 1&2 and category
3&4 separetely, we expect the first two categories will show performance
improvement and the second will not result in visible regression compared with
the non-optimized version.
This change also updates TestFormats to support using %#x.
Examples exhibiting where does the issue come from:
  1: 'if x + 3 < 0' might be converted to:
  before:
    CMN $3, R0
    BGE <else branch> // wrong branch is taken if 'x+3' overflows
  after:
    CMN $3, R0
    BPL <else branch>
  2: 'if y - 3 > 0' might be converted to:
  before:
    CMP $3, R0
    BLE <else branch> // wrong branch is taken if 'y-3' underflows
  after:
    CMP $3, R0
    BMI <else branch>
    BEQ <else branch>
Benchmark data from different kinds of arm64 servers, 'old' is the non-optimized
version (not the parent commit), generally the optimization version outperforms.
S1:
name                    old time/op  new time/op  delta
CondRewrite/SoloJump  13.6ns ± 0%  12.9ns ± 0%  -5.15%  (p=0.000 n=10+10)
CondRewrite/CombJump  13.8ns ± 1%  12.9ns ± 0%  -6.32%  (p=0.000 n=10+10)
S2:
name                     old time/op  new time/op  delta
CondRewrite/SoloJump  11.6ns ± 0%  10.9ns ± 0%  -6.03%  (p=0.000 n=10+10)
CondRewrite/CombJump  11.4ns ± 0%  10.8ns ± 1%  -5.53%  (p=0.000 n=10+10)
S3:
name                     old time/op  new time/op  delta
CondRewrite/SoloJump  7.36ns ± 0%  7.50ns ± 0%  +1.79%  (p=0.000 n=9+10)
CondRewrite/CombJump  7.35ns ± 0%  7.75ns ± 0%  +5.51%  (p=0.000 n=8+9)
S4:
name                      old time/op  new time/op  delta
CondRewrite/SoloJump-224  11.5ns ± 1%  10.9ns ± 0%  -4.97%  (p=0.000 n=10+10)
CondRewrite/CombJump-224  11.9ns ± 0%  11.5ns ± 0%  -2.95%  (p=0.000 n=10+10)
S5:
name                     old time/op  new time/op  delta
CondRewrite/SoloJump  10.0ns ± 0%  10.0ns ± 0%  -0.45%  (p=0.000 n=9+10)
CondRewrite/CombJump  9.93ns ± 0%  9.77ns ± 0%  -1.53%  (p=0.000 n=10+9)
Go1 perf. data:
name                     old time/op    new time/op    delta
BinaryTree17              6.29s ± 1%     6.30s ± 1%    ~     (p=1.000 n=5+5)
Fannkuch11                5.40s ± 0%     5.40s ± 0%    ~     (p=0.841 n=5+5)
FmtFprintfEmpty          97.9ns ± 0%    98.9ns ± 3%    ~     (p=0.937 n=4+5)
FmtFprintfString          171ns ± 3%     171ns ± 2%    ~     (p=0.754 n=5+5)
FmtFprintfInt             212ns ± 0%     217ns ± 6%  +2.55%  (p=0.008 n=5+5)
FmtFprintfIntInt          296ns ± 1%     297ns ± 2%    ~     (p=0.516 n=5+5)
FmtFprintfPrefixedInt     371ns ± 2%     374ns ± 7%    ~     (p=1.000 n=5+5)
FmtFprintfFloat           435ns ± 1%     439ns ± 2%    ~     (p=0.056 n=5+5)
FmtManyArgs              1.37µs ± 1%    1.36µs ± 1%    ~     (p=0.730 n=5+5)
GobDecode                14.6ms ± 4%    14.4ms ± 4%    ~     (p=0.690 n=5+5)
GobEncode                11.8ms ±20%    11.6ms ±15%    ~     (p=1.000 n=5+5)
Gzip                      507ms ± 0%     491ms ± 0%  -3.22%  (p=0.008 n=5+5)
Gunzip                   73.8ms ± 0%    73.9ms ± 0%    ~     (p=0.690 n=5+5)
HTTPClientServer          116µs ± 0%     116µs ± 0%    ~     (p=0.686 n=4+4)
JSONEncode               21.8ms ± 1%    21.6ms ± 2%    ~     (p=0.151 n=5+5)
JSONDecode                104ms ± 1%     103ms ± 1%  -1.08%  (p=0.016 n=5+5)
Mandelbrot200            9.53ms ± 0%    9.53ms ± 0%    ~     (p=0.421 n=5+5)
GoParse                  7.55ms ± 1%    7.51ms ± 1%    ~     (p=0.151 n=5+5)
RegexpMatchEasy0_32       158ns ± 0%     158ns ± 0%    ~     (all equal)
RegexpMatchEasy0_1K       606ns ± 1%     608ns ± 3%    ~     (p=0.937 n=5+5)
RegexpMatchEasy1_32       143ns ± 0%     144ns ± 1%    ~     (p=0.095 n=5+4)
RegexpMatchEasy1_1K       927ns ± 2%     944ns ± 2%    ~     (p=0.056 n=5+5)
RegexpMatchMedium_32     16.0ns ± 0%    16.0ns ± 0%    ~     (all equal)
RegexpMatchMedium_1K     69.3µs ± 2%    69.7µs ± 0%    ~     (p=0.690 n=5+5)
RegexpMatchHard_32       3.73µs ± 0%    3.73µs ± 1%    ~     (p=0.984 n=5+5)
RegexpMatchHard_1K        111µs ± 1%     110µs ± 0%    ~     (p=0.151 n=5+5)
Revcomp                   1.91s ±47%     1.77s ±68%    ~     (p=1.000 n=5+5)
Template                  138ms ± 1%     138ms ± 1%    ~     (p=1.000 n=5+5)
TimeParse                 787ns ± 2%     785ns ± 1%    ~     (p=0.540 n=5+5)
TimeFormat                729ns ± 1%     726ns ± 1%    ~     (p=0.151 n=5+5)
Updates #38740
Change-Id: I06c604874acdc1e63e66452dadee5df053045222
Reviewed-on: https://go-review.googlesource.com/c/go/+/233097
Reviewed-by: Keith Randall <khr@golang.org>
Run-TryBot: Keith Randall <khr@golang.org>
											
										 
											2020-05-06 09:54:40 +00:00
										 |  |  | 	if a-11 >= 0 { | 
					
						
							|  |  |  | 		return 4 | 
					
						
							|  |  |  | 	} | 
					
						
							|  |  |  | 
 | 
					
						
							| 
									
										
											  
											
												cmd/compile: add late lower pass for last rules to run
Usually optimization rules have corresponding priorities, some need to
be run first, some run next, and some run last, which produces the best
code. But currently our optimization rules have no priority, this CL
adds a late lower pass that runs those rules that need to be run at last,
such as split unreasonable constant folding. This pass can be seen as
the second round of the lower pass.
For example:
func foo(a, b uint64) uint64 {
        d := a+0x1234568
        d1 := b+0x1234568
        return d&d1
}
The code generated by the master branch:
	0x0004 00004        ADD     $19088744, R0, R2 // movz+movk+add
	0x0010 00016        ADD     $19088744, R1, R1 // movz+movk+add
	0x001c 00028        AND     R1, R2, R0
This is because the current constant folding optimization rules do not
take into account the range of constants, causing the constant to be
loaded repeatedly. This CL splits these unreasonable constants folding
in the late lower pass. With this CL the generated code:
	0x0004 00004        MOVD    $19088744, R2 // movz+movk
	0x000c 00012        ADD     R0, R2, R3
	0x0010 00016        ADD     R1, R2, R1
	0x0014 00020        AND     R1, R3, R0
This CL also adds constant folding optimization for ADDS instruction.
In addition, in order not to introduce the codegen regression, an
optimization rule is added to change the addition of a negative number
into a subtraction of a positive number.
go1 benchmarks:
name                     old time/op    new time/op    delta
BinaryTree17-8              1.22s ± 1%     1.24s ± 0%  +1.56%  (p=0.008 n=5+5)
Fannkuch11-8                1.54s ± 0%     1.53s ± 0%  -0.69%  (p=0.016 n=4+5)
FmtFprintfEmpty-8          14.1ns ± 0%    14.1ns ± 0%    ~     (p=0.079 n=4+5)
FmtFprintfString-8         26.0ns ± 0%    26.1ns ± 0%  +0.23%  (p=0.008 n=5+5)
FmtFprintfInt-8            32.3ns ± 0%    32.9ns ± 1%  +1.72%  (p=0.008 n=5+5)
FmtFprintfIntInt-8         54.5ns ± 0%    55.5ns ± 0%  +1.83%  (p=0.008 n=5+5)
FmtFprintfPrefixedInt-8    61.5ns ± 0%    62.0ns ± 0%  +0.93%  (p=0.008 n=5+5)
FmtFprintfFloat-8          72.0ns ± 0%    73.6ns ± 0%  +2.24%  (p=0.008 n=5+5)
FmtManyArgs-8               221ns ± 0%     224ns ± 0%  +1.22%  (p=0.008 n=5+5)
GobDecode-8                1.91ms ± 0%    1.93ms ± 0%  +0.98%  (p=0.008 n=5+5)
GobEncode-8                1.40ms ± 1%    1.39ms ± 0%  -0.79%  (p=0.032 n=5+5)
Gzip-8                      115ms ± 0%     117ms ± 1%  +1.17%  (p=0.008 n=5+5)
Gunzip-8                   19.4ms ± 1%    19.3ms ± 0%  -0.71%  (p=0.016 n=5+4)
HTTPClientServer-8         27.0µs ± 0%    27.3µs ± 0%  +0.80%  (p=0.008 n=5+5)
JSONEncode-8               3.36ms ± 1%    3.33ms ± 0%    ~     (p=0.056 n=5+5)
JSONDecode-8               17.5ms ± 2%    17.8ms ± 0%  +1.71%  (p=0.016 n=5+4)
Mandelbrot200-8            2.29ms ± 0%    2.29ms ± 0%    ~     (p=0.151 n=5+5)
GoParse-8                  1.35ms ± 1%    1.36ms ± 1%    ~     (p=0.056 n=5+5)
RegexpMatchEasy0_32-8      24.5ns ± 0%    24.5ns ± 0%    ~     (p=0.444 n=4+5)
RegexpMatchEasy0_1K-8       131ns ±11%     118ns ± 6%    ~     (p=0.056 n=5+5)
RegexpMatchEasy1_32-8      22.9ns ± 0%    22.9ns ± 0%    ~     (p=0.905 n=4+5)
RegexpMatchEasy1_1K-8       126ns ± 0%     127ns ± 0%    ~     (p=0.063 n=4+5)
RegexpMatchMedium_32-8      486ns ± 5%     483ns ± 0%    ~     (p=0.381 n=5+4)
RegexpMatchMedium_1K-8     15.4µs ± 1%    15.5µs ± 0%    ~     (p=0.151 n=5+5)
RegexpMatchHard_32-8        687ns ± 0%     686ns ± 0%    ~     (p=0.103 n=5+5)
RegexpMatchHard_1K-8       20.7µs ± 0%    20.7µs ± 1%    ~     (p=0.151 n=5+5)
Revcomp-8                   175ms ± 2%     176ms ± 3%    ~     (p=1.000 n=5+5)
Template-8                 20.4ms ± 6%    20.1ms ± 2%    ~     (p=0.151 n=5+5)
TimeParse-8                 112ns ± 0%     113ns ± 0%  +0.97%  (p=0.016 n=5+4)
TimeFormat-8                156ns ± 0%     145ns ± 0%  -7.14%  (p=0.029 n=4+4)
Change-Id: I3ced26e89041f873ac989586514ccc5ee09f13da
Reviewed-on: https://go-review.googlesource.com/c/go/+/425134
Reviewed-by: Keith Randall <khr@google.com>
Reviewed-by: Cherry Mui <cherryyz@google.com>
TryBot-Result: Gopher Robot <gobot@golang.org>
Reviewed-by: Keith Randall <khr@golang.org>
Run-TryBot: Eric Fang <eric.fang@arm.com>
											
										 
											2022-08-17 10:01:17 +00:00
										 |  |  | 	// arm64:`SUB`,`CMP`,`BGT` | 
					
						
							| 
									
										
											  
											
												cmd/compile: fix incorrect rewriting to if condition
Some ARM64 rewriting rules convert 'comparing to zero' conditions of if
statements to a simplified version utilizing CMN and CMP instructions to
branch over condition flags, in order to save one Add or Sub caculation.
Such optimizations lead to wrong branching in case an overflow/underflow
occurs when executing CMN or CMP.
Fix the issue by introducing new block opcodes that don't honor the
overflow/underflow flag, in the following categories:
  Block-Op        Meaning                   ARM condition codes
  1. LTnoov        less than                 MI
  2. GEnoov        greater than or equal     PL
  3. LEnoov        less than or equal        MI || EQ
  4. GTnoov        greater than              NEQ & PL
The backend generates two consecutive branch instructions for 'LEnoov'
and 'GTnoov' to model their expected behavior. A slight change to 'gc'
and amd64/386 backends is made to unify the code generation.
Add a test 'TestCondRewrite' as justification, it covers 32 incorrect rules
identified on arm64, more might be needed on other arches, like 32-bit arm.
Add two benchmarks profiling the aforementioned category 1&2 and category
3&4 separetely, we expect the first two categories will show performance
improvement and the second will not result in visible regression compared with
the non-optimized version.
This change also updates TestFormats to support using %#x.
Examples exhibiting where does the issue come from:
  1: 'if x + 3 < 0' might be converted to:
  before:
    CMN $3, R0
    BGE <else branch> // wrong branch is taken if 'x+3' overflows
  after:
    CMN $3, R0
    BPL <else branch>
  2: 'if y - 3 > 0' might be converted to:
  before:
    CMP $3, R0
    BLE <else branch> // wrong branch is taken if 'y-3' underflows
  after:
    CMP $3, R0
    BMI <else branch>
    BEQ <else branch>
Benchmark data from different kinds of arm64 servers, 'old' is the non-optimized
version (not the parent commit), generally the optimization version outperforms.
S1:
name                    old time/op  new time/op  delta
CondRewrite/SoloJump  13.6ns ± 0%  12.9ns ± 0%  -5.15%  (p=0.000 n=10+10)
CondRewrite/CombJump  13.8ns ± 1%  12.9ns ± 0%  -6.32%  (p=0.000 n=10+10)
S2:
name                     old time/op  new time/op  delta
CondRewrite/SoloJump  11.6ns ± 0%  10.9ns ± 0%  -6.03%  (p=0.000 n=10+10)
CondRewrite/CombJump  11.4ns ± 0%  10.8ns ± 1%  -5.53%  (p=0.000 n=10+10)
S3:
name                     old time/op  new time/op  delta
CondRewrite/SoloJump  7.36ns ± 0%  7.50ns ± 0%  +1.79%  (p=0.000 n=9+10)
CondRewrite/CombJump  7.35ns ± 0%  7.75ns ± 0%  +5.51%  (p=0.000 n=8+9)
S4:
name                      old time/op  new time/op  delta
CondRewrite/SoloJump-224  11.5ns ± 1%  10.9ns ± 0%  -4.97%  (p=0.000 n=10+10)
CondRewrite/CombJump-224  11.9ns ± 0%  11.5ns ± 0%  -2.95%  (p=0.000 n=10+10)
S5:
name                     old time/op  new time/op  delta
CondRewrite/SoloJump  10.0ns ± 0%  10.0ns ± 0%  -0.45%  (p=0.000 n=9+10)
CondRewrite/CombJump  9.93ns ± 0%  9.77ns ± 0%  -1.53%  (p=0.000 n=10+9)
Go1 perf. data:
name                     old time/op    new time/op    delta
BinaryTree17              6.29s ± 1%     6.30s ± 1%    ~     (p=1.000 n=5+5)
Fannkuch11                5.40s ± 0%     5.40s ± 0%    ~     (p=0.841 n=5+5)
FmtFprintfEmpty          97.9ns ± 0%    98.9ns ± 3%    ~     (p=0.937 n=4+5)
FmtFprintfString          171ns ± 3%     171ns ± 2%    ~     (p=0.754 n=5+5)
FmtFprintfInt             212ns ± 0%     217ns ± 6%  +2.55%  (p=0.008 n=5+5)
FmtFprintfIntInt          296ns ± 1%     297ns ± 2%    ~     (p=0.516 n=5+5)
FmtFprintfPrefixedInt     371ns ± 2%     374ns ± 7%    ~     (p=1.000 n=5+5)
FmtFprintfFloat           435ns ± 1%     439ns ± 2%    ~     (p=0.056 n=5+5)
FmtManyArgs              1.37µs ± 1%    1.36µs ± 1%    ~     (p=0.730 n=5+5)
GobDecode                14.6ms ± 4%    14.4ms ± 4%    ~     (p=0.690 n=5+5)
GobEncode                11.8ms ±20%    11.6ms ±15%    ~     (p=1.000 n=5+5)
Gzip                      507ms ± 0%     491ms ± 0%  -3.22%  (p=0.008 n=5+5)
Gunzip                   73.8ms ± 0%    73.9ms ± 0%    ~     (p=0.690 n=5+5)
HTTPClientServer          116µs ± 0%     116µs ± 0%    ~     (p=0.686 n=4+4)
JSONEncode               21.8ms ± 1%    21.6ms ± 2%    ~     (p=0.151 n=5+5)
JSONDecode                104ms ± 1%     103ms ± 1%  -1.08%  (p=0.016 n=5+5)
Mandelbrot200            9.53ms ± 0%    9.53ms ± 0%    ~     (p=0.421 n=5+5)
GoParse                  7.55ms ± 1%    7.51ms ± 1%    ~     (p=0.151 n=5+5)
RegexpMatchEasy0_32       158ns ± 0%     158ns ± 0%    ~     (all equal)
RegexpMatchEasy0_1K       606ns ± 1%     608ns ± 3%    ~     (p=0.937 n=5+5)
RegexpMatchEasy1_32       143ns ± 0%     144ns ± 1%    ~     (p=0.095 n=5+4)
RegexpMatchEasy1_1K       927ns ± 2%     944ns ± 2%    ~     (p=0.056 n=5+5)
RegexpMatchMedium_32     16.0ns ± 0%    16.0ns ± 0%    ~     (all equal)
RegexpMatchMedium_1K     69.3µs ± 2%    69.7µs ± 0%    ~     (p=0.690 n=5+5)
RegexpMatchHard_32       3.73µs ± 0%    3.73µs ± 1%    ~     (p=0.984 n=5+5)
RegexpMatchHard_1K        111µs ± 1%     110µs ± 0%    ~     (p=0.151 n=5+5)
Revcomp                   1.91s ±47%     1.77s ±68%    ~     (p=1.000 n=5+5)
Template                  138ms ± 1%     138ms ± 1%    ~     (p=1.000 n=5+5)
TimeParse                 787ns ± 2%     785ns ± 1%    ~     (p=0.540 n=5+5)
TimeFormat                729ns ± 1%     726ns ± 1%    ~     (p=0.151 n=5+5)
Updates #38740
Change-Id: I06c604874acdc1e63e66452dadee5df053045222
Reviewed-on: https://go-review.googlesource.com/c/go/+/233097
Reviewed-by: Keith Randall <khr@golang.org>
Run-TryBot: Keith Randall <khr@golang.org>
											
										 
											2020-05-06 09:54:40 +00:00
										 |  |  | 	if a-19 > 0 { | 
					
						
							|  |  |  | 		return 4 | 
					
						
							|  |  |  | 	} | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | 	// arm64:`CMNW`,-`ADDW`,`(BMI|BPL)` | 
					
						
							| 
									
										
										
										
											2020-06-01 11:01:14 +00:00
										 |  |  | 	// arm:`CMN`,-`ADD`,`(BMI|BPL)` | 
					
						
							| 
									
										
											  
											
												cmd/compile: fix incorrect rewriting to if condition
Some ARM64 rewriting rules convert 'comparing to zero' conditions of if
statements to a simplified version utilizing CMN and CMP instructions to
branch over condition flags, in order to save one Add or Sub caculation.
Such optimizations lead to wrong branching in case an overflow/underflow
occurs when executing CMN or CMP.
Fix the issue by introducing new block opcodes that don't honor the
overflow/underflow flag, in the following categories:
  Block-Op        Meaning                   ARM condition codes
  1. LTnoov        less than                 MI
  2. GEnoov        greater than or equal     PL
  3. LEnoov        less than or equal        MI || EQ
  4. GTnoov        greater than              NEQ & PL
The backend generates two consecutive branch instructions for 'LEnoov'
and 'GTnoov' to model their expected behavior. A slight change to 'gc'
and amd64/386 backends is made to unify the code generation.
Add a test 'TestCondRewrite' as justification, it covers 32 incorrect rules
identified on arm64, more might be needed on other arches, like 32-bit arm.
Add two benchmarks profiling the aforementioned category 1&2 and category
3&4 separetely, we expect the first two categories will show performance
improvement and the second will not result in visible regression compared with
the non-optimized version.
This change also updates TestFormats to support using %#x.
Examples exhibiting where does the issue come from:
  1: 'if x + 3 < 0' might be converted to:
  before:
    CMN $3, R0
    BGE <else branch> // wrong branch is taken if 'x+3' overflows
  after:
    CMN $3, R0
    BPL <else branch>
  2: 'if y - 3 > 0' might be converted to:
  before:
    CMP $3, R0
    BLE <else branch> // wrong branch is taken if 'y-3' underflows
  after:
    CMP $3, R0
    BMI <else branch>
    BEQ <else branch>
Benchmark data from different kinds of arm64 servers, 'old' is the non-optimized
version (not the parent commit), generally the optimization version outperforms.
S1:
name                    old time/op  new time/op  delta
CondRewrite/SoloJump  13.6ns ± 0%  12.9ns ± 0%  -5.15%  (p=0.000 n=10+10)
CondRewrite/CombJump  13.8ns ± 1%  12.9ns ± 0%  -6.32%  (p=0.000 n=10+10)
S2:
name                     old time/op  new time/op  delta
CondRewrite/SoloJump  11.6ns ± 0%  10.9ns ± 0%  -6.03%  (p=0.000 n=10+10)
CondRewrite/CombJump  11.4ns ± 0%  10.8ns ± 1%  -5.53%  (p=0.000 n=10+10)
S3:
name                     old time/op  new time/op  delta
CondRewrite/SoloJump  7.36ns ± 0%  7.50ns ± 0%  +1.79%  (p=0.000 n=9+10)
CondRewrite/CombJump  7.35ns ± 0%  7.75ns ± 0%  +5.51%  (p=0.000 n=8+9)
S4:
name                      old time/op  new time/op  delta
CondRewrite/SoloJump-224  11.5ns ± 1%  10.9ns ± 0%  -4.97%  (p=0.000 n=10+10)
CondRewrite/CombJump-224  11.9ns ± 0%  11.5ns ± 0%  -2.95%  (p=0.000 n=10+10)
S5:
name                     old time/op  new time/op  delta
CondRewrite/SoloJump  10.0ns ± 0%  10.0ns ± 0%  -0.45%  (p=0.000 n=9+10)
CondRewrite/CombJump  9.93ns ± 0%  9.77ns ± 0%  -1.53%  (p=0.000 n=10+9)
Go1 perf. data:
name                     old time/op    new time/op    delta
BinaryTree17              6.29s ± 1%     6.30s ± 1%    ~     (p=1.000 n=5+5)
Fannkuch11                5.40s ± 0%     5.40s ± 0%    ~     (p=0.841 n=5+5)
FmtFprintfEmpty          97.9ns ± 0%    98.9ns ± 3%    ~     (p=0.937 n=4+5)
FmtFprintfString          171ns ± 3%     171ns ± 2%    ~     (p=0.754 n=5+5)
FmtFprintfInt             212ns ± 0%     217ns ± 6%  +2.55%  (p=0.008 n=5+5)
FmtFprintfIntInt          296ns ± 1%     297ns ± 2%    ~     (p=0.516 n=5+5)
FmtFprintfPrefixedInt     371ns ± 2%     374ns ± 7%    ~     (p=1.000 n=5+5)
FmtFprintfFloat           435ns ± 1%     439ns ± 2%    ~     (p=0.056 n=5+5)
FmtManyArgs              1.37µs ± 1%    1.36µs ± 1%    ~     (p=0.730 n=5+5)
GobDecode                14.6ms ± 4%    14.4ms ± 4%    ~     (p=0.690 n=5+5)
GobEncode                11.8ms ±20%    11.6ms ±15%    ~     (p=1.000 n=5+5)
Gzip                      507ms ± 0%     491ms ± 0%  -3.22%  (p=0.008 n=5+5)
Gunzip                   73.8ms ± 0%    73.9ms ± 0%    ~     (p=0.690 n=5+5)
HTTPClientServer          116µs ± 0%     116µs ± 0%    ~     (p=0.686 n=4+4)
JSONEncode               21.8ms ± 1%    21.6ms ± 2%    ~     (p=0.151 n=5+5)
JSONDecode                104ms ± 1%     103ms ± 1%  -1.08%  (p=0.016 n=5+5)
Mandelbrot200            9.53ms ± 0%    9.53ms ± 0%    ~     (p=0.421 n=5+5)
GoParse                  7.55ms ± 1%    7.51ms ± 1%    ~     (p=0.151 n=5+5)
RegexpMatchEasy0_32       158ns ± 0%     158ns ± 0%    ~     (all equal)
RegexpMatchEasy0_1K       606ns ± 1%     608ns ± 3%    ~     (p=0.937 n=5+5)
RegexpMatchEasy1_32       143ns ± 0%     144ns ± 1%    ~     (p=0.095 n=5+4)
RegexpMatchEasy1_1K       927ns ± 2%     944ns ± 2%    ~     (p=0.056 n=5+5)
RegexpMatchMedium_32     16.0ns ± 0%    16.0ns ± 0%    ~     (all equal)
RegexpMatchMedium_1K     69.3µs ± 2%    69.7µs ± 0%    ~     (p=0.690 n=5+5)
RegexpMatchHard_32       3.73µs ± 0%    3.73µs ± 1%    ~     (p=0.984 n=5+5)
RegexpMatchHard_1K        111µs ± 1%     110µs ± 0%    ~     (p=0.151 n=5+5)
Revcomp                   1.91s ±47%     1.77s ±68%    ~     (p=1.000 n=5+5)
Template                  138ms ± 1%     138ms ± 1%    ~     (p=1.000 n=5+5)
TimeParse                 787ns ± 2%     785ns ± 1%    ~     (p=0.540 n=5+5)
TimeFormat                729ns ± 1%     726ns ± 1%    ~     (p=0.151 n=5+5)
Updates #38740
Change-Id: I06c604874acdc1e63e66452dadee5df053045222
Reviewed-on: https://go-review.googlesource.com/c/go/+/233097
Reviewed-by: Keith Randall <khr@golang.org>
Run-TryBot: Keith Randall <khr@golang.org>
											
										 
											2020-05-06 09:54:40 +00:00
										 |  |  | 	if e+3 < 0 { | 
					
						
							|  |  |  | 		return 5 | 
					
						
							|  |  |  | 	} | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | 	// arm64:`CMNW`,-`ADDW`,`(BMI|BPL)` | 
					
						
							| 
									
										
										
										
											2020-06-01 11:01:14 +00:00
										 |  |  | 	// arm:`CMN`,-`ADD`,`(BMI|BPL)` | 
					
						
							| 
									
										
											  
											
												cmd/compile: fix incorrect rewriting to if condition
Some ARM64 rewriting rules convert 'comparing to zero' conditions of if
statements to a simplified version utilizing CMN and CMP instructions to
branch over condition flags, in order to save one Add or Sub caculation.
Such optimizations lead to wrong branching in case an overflow/underflow
occurs when executing CMN or CMP.
Fix the issue by introducing new block opcodes that don't honor the
overflow/underflow flag, in the following categories:
  Block-Op        Meaning                   ARM condition codes
  1. LTnoov        less than                 MI
  2. GEnoov        greater than or equal     PL
  3. LEnoov        less than or equal        MI || EQ
  4. GTnoov        greater than              NEQ & PL
The backend generates two consecutive branch instructions for 'LEnoov'
and 'GTnoov' to model their expected behavior. A slight change to 'gc'
and amd64/386 backends is made to unify the code generation.
Add a test 'TestCondRewrite' as justification, it covers 32 incorrect rules
identified on arm64, more might be needed on other arches, like 32-bit arm.
Add two benchmarks profiling the aforementioned category 1&2 and category
3&4 separetely, we expect the first two categories will show performance
improvement and the second will not result in visible regression compared with
the non-optimized version.
This change also updates TestFormats to support using %#x.
Examples exhibiting where does the issue come from:
  1: 'if x + 3 < 0' might be converted to:
  before:
    CMN $3, R0
    BGE <else branch> // wrong branch is taken if 'x+3' overflows
  after:
    CMN $3, R0
    BPL <else branch>
  2: 'if y - 3 > 0' might be converted to:
  before:
    CMP $3, R0
    BLE <else branch> // wrong branch is taken if 'y-3' underflows
  after:
    CMP $3, R0
    BMI <else branch>
    BEQ <else branch>
Benchmark data from different kinds of arm64 servers, 'old' is the non-optimized
version (not the parent commit), generally the optimization version outperforms.
S1:
name                    old time/op  new time/op  delta
CondRewrite/SoloJump  13.6ns ± 0%  12.9ns ± 0%  -5.15%  (p=0.000 n=10+10)
CondRewrite/CombJump  13.8ns ± 1%  12.9ns ± 0%  -6.32%  (p=0.000 n=10+10)
S2:
name                     old time/op  new time/op  delta
CondRewrite/SoloJump  11.6ns ± 0%  10.9ns ± 0%  -6.03%  (p=0.000 n=10+10)
CondRewrite/CombJump  11.4ns ± 0%  10.8ns ± 1%  -5.53%  (p=0.000 n=10+10)
S3:
name                     old time/op  new time/op  delta
CondRewrite/SoloJump  7.36ns ± 0%  7.50ns ± 0%  +1.79%  (p=0.000 n=9+10)
CondRewrite/CombJump  7.35ns ± 0%  7.75ns ± 0%  +5.51%  (p=0.000 n=8+9)
S4:
name                      old time/op  new time/op  delta
CondRewrite/SoloJump-224  11.5ns ± 1%  10.9ns ± 0%  -4.97%  (p=0.000 n=10+10)
CondRewrite/CombJump-224  11.9ns ± 0%  11.5ns ± 0%  -2.95%  (p=0.000 n=10+10)
S5:
name                     old time/op  new time/op  delta
CondRewrite/SoloJump  10.0ns ± 0%  10.0ns ± 0%  -0.45%  (p=0.000 n=9+10)
CondRewrite/CombJump  9.93ns ± 0%  9.77ns ± 0%  -1.53%  (p=0.000 n=10+9)
Go1 perf. data:
name                     old time/op    new time/op    delta
BinaryTree17              6.29s ± 1%     6.30s ± 1%    ~     (p=1.000 n=5+5)
Fannkuch11                5.40s ± 0%     5.40s ± 0%    ~     (p=0.841 n=5+5)
FmtFprintfEmpty          97.9ns ± 0%    98.9ns ± 3%    ~     (p=0.937 n=4+5)
FmtFprintfString          171ns ± 3%     171ns ± 2%    ~     (p=0.754 n=5+5)
FmtFprintfInt             212ns ± 0%     217ns ± 6%  +2.55%  (p=0.008 n=5+5)
FmtFprintfIntInt          296ns ± 1%     297ns ± 2%    ~     (p=0.516 n=5+5)
FmtFprintfPrefixedInt     371ns ± 2%     374ns ± 7%    ~     (p=1.000 n=5+5)
FmtFprintfFloat           435ns ± 1%     439ns ± 2%    ~     (p=0.056 n=5+5)
FmtManyArgs              1.37µs ± 1%    1.36µs ± 1%    ~     (p=0.730 n=5+5)
GobDecode                14.6ms ± 4%    14.4ms ± 4%    ~     (p=0.690 n=5+5)
GobEncode                11.8ms ±20%    11.6ms ±15%    ~     (p=1.000 n=5+5)
Gzip                      507ms ± 0%     491ms ± 0%  -3.22%  (p=0.008 n=5+5)
Gunzip                   73.8ms ± 0%    73.9ms ± 0%    ~     (p=0.690 n=5+5)
HTTPClientServer          116µs ± 0%     116µs ± 0%    ~     (p=0.686 n=4+4)
JSONEncode               21.8ms ± 1%    21.6ms ± 2%    ~     (p=0.151 n=5+5)
JSONDecode                104ms ± 1%     103ms ± 1%  -1.08%  (p=0.016 n=5+5)
Mandelbrot200            9.53ms ± 0%    9.53ms ± 0%    ~     (p=0.421 n=5+5)
GoParse                  7.55ms ± 1%    7.51ms ± 1%    ~     (p=0.151 n=5+5)
RegexpMatchEasy0_32       158ns ± 0%     158ns ± 0%    ~     (all equal)
RegexpMatchEasy0_1K       606ns ± 1%     608ns ± 3%    ~     (p=0.937 n=5+5)
RegexpMatchEasy1_32       143ns ± 0%     144ns ± 1%    ~     (p=0.095 n=5+4)
RegexpMatchEasy1_1K       927ns ± 2%     944ns ± 2%    ~     (p=0.056 n=5+5)
RegexpMatchMedium_32     16.0ns ± 0%    16.0ns ± 0%    ~     (all equal)
RegexpMatchMedium_1K     69.3µs ± 2%    69.7µs ± 0%    ~     (p=0.690 n=5+5)
RegexpMatchHard_32       3.73µs ± 0%    3.73µs ± 1%    ~     (p=0.984 n=5+5)
RegexpMatchHard_1K        111µs ± 1%     110µs ± 0%    ~     (p=0.151 n=5+5)
Revcomp                   1.91s ±47%     1.77s ±68%    ~     (p=1.000 n=5+5)
Template                  138ms ± 1%     138ms ± 1%    ~     (p=1.000 n=5+5)
TimeParse                 787ns ± 2%     785ns ± 1%    ~     (p=0.540 n=5+5)
TimeFormat                729ns ± 1%     726ns ± 1%    ~     (p=0.151 n=5+5)
Updates #38740
Change-Id: I06c604874acdc1e63e66452dadee5df053045222
Reviewed-on: https://go-review.googlesource.com/c/go/+/233097
Reviewed-by: Keith Randall <khr@golang.org>
Run-TryBot: Keith Randall <khr@golang.org>
											
										 
											2020-05-06 09:54:40 +00:00
										 |  |  | 	if e+13 >= 0 { | 
					
						
							|  |  |  | 		return 6 | 
					
						
							|  |  |  | 	} | 
					
						
							|  |  |  | 
 | 
					
						
							| 
									
										
										
										
											2020-06-01 11:01:14 +00:00
										 |  |  | 	// arm64:`CMPW|CMNW`,`(BMI|BPL)` | 
					
						
							|  |  |  | 	// arm:`CMP|CMN`, -`(ADD|SUB)`, `(BMI|BPL)` | 
					
						
							| 
									
										
											  
											
												cmd/compile: fix incorrect rewriting to if condition
Some ARM64 rewriting rules convert 'comparing to zero' conditions of if
statements to a simplified version utilizing CMN and CMP instructions to
branch over condition flags, in order to save one Add or Sub caculation.
Such optimizations lead to wrong branching in case an overflow/underflow
occurs when executing CMN or CMP.
Fix the issue by introducing new block opcodes that don't honor the
overflow/underflow flag, in the following categories:
  Block-Op        Meaning                   ARM condition codes
  1. LTnoov        less than                 MI
  2. GEnoov        greater than or equal     PL
  3. LEnoov        less than or equal        MI || EQ
  4. GTnoov        greater than              NEQ & PL
The backend generates two consecutive branch instructions for 'LEnoov'
and 'GTnoov' to model their expected behavior. A slight change to 'gc'
and amd64/386 backends is made to unify the code generation.
Add a test 'TestCondRewrite' as justification, it covers 32 incorrect rules
identified on arm64, more might be needed on other arches, like 32-bit arm.
Add two benchmarks profiling the aforementioned category 1&2 and category
3&4 separetely, we expect the first two categories will show performance
improvement and the second will not result in visible regression compared with
the non-optimized version.
This change also updates TestFormats to support using %#x.
Examples exhibiting where does the issue come from:
  1: 'if x + 3 < 0' might be converted to:
  before:
    CMN $3, R0
    BGE <else branch> // wrong branch is taken if 'x+3' overflows
  after:
    CMN $3, R0
    BPL <else branch>
  2: 'if y - 3 > 0' might be converted to:
  before:
    CMP $3, R0
    BLE <else branch> // wrong branch is taken if 'y-3' underflows
  after:
    CMP $3, R0
    BMI <else branch>
    BEQ <else branch>
Benchmark data from different kinds of arm64 servers, 'old' is the non-optimized
version (not the parent commit), generally the optimization version outperforms.
S1:
name                    old time/op  new time/op  delta
CondRewrite/SoloJump  13.6ns ± 0%  12.9ns ± 0%  -5.15%  (p=0.000 n=10+10)
CondRewrite/CombJump  13.8ns ± 1%  12.9ns ± 0%  -6.32%  (p=0.000 n=10+10)
S2:
name                     old time/op  new time/op  delta
CondRewrite/SoloJump  11.6ns ± 0%  10.9ns ± 0%  -6.03%  (p=0.000 n=10+10)
CondRewrite/CombJump  11.4ns ± 0%  10.8ns ± 1%  -5.53%  (p=0.000 n=10+10)
S3:
name                     old time/op  new time/op  delta
CondRewrite/SoloJump  7.36ns ± 0%  7.50ns ± 0%  +1.79%  (p=0.000 n=9+10)
CondRewrite/CombJump  7.35ns ± 0%  7.75ns ± 0%  +5.51%  (p=0.000 n=8+9)
S4:
name                      old time/op  new time/op  delta
CondRewrite/SoloJump-224  11.5ns ± 1%  10.9ns ± 0%  -4.97%  (p=0.000 n=10+10)
CondRewrite/CombJump-224  11.9ns ± 0%  11.5ns ± 0%  -2.95%  (p=0.000 n=10+10)
S5:
name                     old time/op  new time/op  delta
CondRewrite/SoloJump  10.0ns ± 0%  10.0ns ± 0%  -0.45%  (p=0.000 n=9+10)
CondRewrite/CombJump  9.93ns ± 0%  9.77ns ± 0%  -1.53%  (p=0.000 n=10+9)
Go1 perf. data:
name                     old time/op    new time/op    delta
BinaryTree17              6.29s ± 1%     6.30s ± 1%    ~     (p=1.000 n=5+5)
Fannkuch11                5.40s ± 0%     5.40s ± 0%    ~     (p=0.841 n=5+5)
FmtFprintfEmpty          97.9ns ± 0%    98.9ns ± 3%    ~     (p=0.937 n=4+5)
FmtFprintfString          171ns ± 3%     171ns ± 2%    ~     (p=0.754 n=5+5)
FmtFprintfInt             212ns ± 0%     217ns ± 6%  +2.55%  (p=0.008 n=5+5)
FmtFprintfIntInt          296ns ± 1%     297ns ± 2%    ~     (p=0.516 n=5+5)
FmtFprintfPrefixedInt     371ns ± 2%     374ns ± 7%    ~     (p=1.000 n=5+5)
FmtFprintfFloat           435ns ± 1%     439ns ± 2%    ~     (p=0.056 n=5+5)
FmtManyArgs              1.37µs ± 1%    1.36µs ± 1%    ~     (p=0.730 n=5+5)
GobDecode                14.6ms ± 4%    14.4ms ± 4%    ~     (p=0.690 n=5+5)
GobEncode                11.8ms ±20%    11.6ms ±15%    ~     (p=1.000 n=5+5)
Gzip                      507ms ± 0%     491ms ± 0%  -3.22%  (p=0.008 n=5+5)
Gunzip                   73.8ms ± 0%    73.9ms ± 0%    ~     (p=0.690 n=5+5)
HTTPClientServer          116µs ± 0%     116µs ± 0%    ~     (p=0.686 n=4+4)
JSONEncode               21.8ms ± 1%    21.6ms ± 2%    ~     (p=0.151 n=5+5)
JSONDecode                104ms ± 1%     103ms ± 1%  -1.08%  (p=0.016 n=5+5)
Mandelbrot200            9.53ms ± 0%    9.53ms ± 0%    ~     (p=0.421 n=5+5)
GoParse                  7.55ms ± 1%    7.51ms ± 1%    ~     (p=0.151 n=5+5)
RegexpMatchEasy0_32       158ns ± 0%     158ns ± 0%    ~     (all equal)
RegexpMatchEasy0_1K       606ns ± 1%     608ns ± 3%    ~     (p=0.937 n=5+5)
RegexpMatchEasy1_32       143ns ± 0%     144ns ± 1%    ~     (p=0.095 n=5+4)
RegexpMatchEasy1_1K       927ns ± 2%     944ns ± 2%    ~     (p=0.056 n=5+5)
RegexpMatchMedium_32     16.0ns ± 0%    16.0ns ± 0%    ~     (all equal)
RegexpMatchMedium_1K     69.3µs ± 2%    69.7µs ± 0%    ~     (p=0.690 n=5+5)
RegexpMatchHard_32       3.73µs ± 0%    3.73µs ± 1%    ~     (p=0.984 n=5+5)
RegexpMatchHard_1K        111µs ± 1%     110µs ± 0%    ~     (p=0.151 n=5+5)
Revcomp                   1.91s ±47%     1.77s ±68%    ~     (p=1.000 n=5+5)
Template                  138ms ± 1%     138ms ± 1%    ~     (p=1.000 n=5+5)
TimeParse                 787ns ± 2%     785ns ± 1%    ~     (p=0.540 n=5+5)
TimeFormat                729ns ± 1%     726ns ± 1%    ~     (p=0.151 n=5+5)
Updates #38740
Change-Id: I06c604874acdc1e63e66452dadee5df053045222
Reviewed-on: https://go-review.googlesource.com/c/go/+/233097
Reviewed-by: Keith Randall <khr@golang.org>
Run-TryBot: Keith Randall <khr@golang.org>
											
										 
											2020-05-06 09:54:40 +00:00
										 |  |  | 	if e-7 < 0 { | 
					
						
							|  |  |  | 		return 7 | 
					
						
							|  |  |  | 	} | 
					
						
							|  |  |  | 
 | 
					
						
							| 
									
										
											  
											
												cmd/compile: add late lower pass for last rules to run
Usually optimization rules have corresponding priorities, some need to
be run first, some run next, and some run last, which produces the best
code. But currently our optimization rules have no priority, this CL
adds a late lower pass that runs those rules that need to be run at last,
such as split unreasonable constant folding. This pass can be seen as
the second round of the lower pass.
For example:
func foo(a, b uint64) uint64 {
        d := a+0x1234568
        d1 := b+0x1234568
        return d&d1
}
The code generated by the master branch:
	0x0004 00004        ADD     $19088744, R0, R2 // movz+movk+add
	0x0010 00016        ADD     $19088744, R1, R1 // movz+movk+add
	0x001c 00028        AND     R1, R2, R0
This is because the current constant folding optimization rules do not
take into account the range of constants, causing the constant to be
loaded repeatedly. This CL splits these unreasonable constants folding
in the late lower pass. With this CL the generated code:
	0x0004 00004        MOVD    $19088744, R2 // movz+movk
	0x000c 00012        ADD     R0, R2, R3
	0x0010 00016        ADD     R1, R2, R1
	0x0014 00020        AND     R1, R3, R0
This CL also adds constant folding optimization for ADDS instruction.
In addition, in order not to introduce the codegen regression, an
optimization rule is added to change the addition of a negative number
into a subtraction of a positive number.
go1 benchmarks:
name                     old time/op    new time/op    delta
BinaryTree17-8              1.22s ± 1%     1.24s ± 0%  +1.56%  (p=0.008 n=5+5)
Fannkuch11-8                1.54s ± 0%     1.53s ± 0%  -0.69%  (p=0.016 n=4+5)
FmtFprintfEmpty-8          14.1ns ± 0%    14.1ns ± 0%    ~     (p=0.079 n=4+5)
FmtFprintfString-8         26.0ns ± 0%    26.1ns ± 0%  +0.23%  (p=0.008 n=5+5)
FmtFprintfInt-8            32.3ns ± 0%    32.9ns ± 1%  +1.72%  (p=0.008 n=5+5)
FmtFprintfIntInt-8         54.5ns ± 0%    55.5ns ± 0%  +1.83%  (p=0.008 n=5+5)
FmtFprintfPrefixedInt-8    61.5ns ± 0%    62.0ns ± 0%  +0.93%  (p=0.008 n=5+5)
FmtFprintfFloat-8          72.0ns ± 0%    73.6ns ± 0%  +2.24%  (p=0.008 n=5+5)
FmtManyArgs-8               221ns ± 0%     224ns ± 0%  +1.22%  (p=0.008 n=5+5)
GobDecode-8                1.91ms ± 0%    1.93ms ± 0%  +0.98%  (p=0.008 n=5+5)
GobEncode-8                1.40ms ± 1%    1.39ms ± 0%  -0.79%  (p=0.032 n=5+5)
Gzip-8                      115ms ± 0%     117ms ± 1%  +1.17%  (p=0.008 n=5+5)
Gunzip-8                   19.4ms ± 1%    19.3ms ± 0%  -0.71%  (p=0.016 n=5+4)
HTTPClientServer-8         27.0µs ± 0%    27.3µs ± 0%  +0.80%  (p=0.008 n=5+5)
JSONEncode-8               3.36ms ± 1%    3.33ms ± 0%    ~     (p=0.056 n=5+5)
JSONDecode-8               17.5ms ± 2%    17.8ms ± 0%  +1.71%  (p=0.016 n=5+4)
Mandelbrot200-8            2.29ms ± 0%    2.29ms ± 0%    ~     (p=0.151 n=5+5)
GoParse-8                  1.35ms ± 1%    1.36ms ± 1%    ~     (p=0.056 n=5+5)
RegexpMatchEasy0_32-8      24.5ns ± 0%    24.5ns ± 0%    ~     (p=0.444 n=4+5)
RegexpMatchEasy0_1K-8       131ns ±11%     118ns ± 6%    ~     (p=0.056 n=5+5)
RegexpMatchEasy1_32-8      22.9ns ± 0%    22.9ns ± 0%    ~     (p=0.905 n=4+5)
RegexpMatchEasy1_1K-8       126ns ± 0%     127ns ± 0%    ~     (p=0.063 n=4+5)
RegexpMatchMedium_32-8      486ns ± 5%     483ns ± 0%    ~     (p=0.381 n=5+4)
RegexpMatchMedium_1K-8     15.4µs ± 1%    15.5µs ± 0%    ~     (p=0.151 n=5+5)
RegexpMatchHard_32-8        687ns ± 0%     686ns ± 0%    ~     (p=0.103 n=5+5)
RegexpMatchHard_1K-8       20.7µs ± 0%    20.7µs ± 1%    ~     (p=0.151 n=5+5)
Revcomp-8                   175ms ± 2%     176ms ± 3%    ~     (p=1.000 n=5+5)
Template-8                 20.4ms ± 6%    20.1ms ± 2%    ~     (p=0.151 n=5+5)
TimeParse-8                 112ns ± 0%     113ns ± 0%  +0.97%  (p=0.016 n=5+4)
TimeFormat-8                156ns ± 0%     145ns ± 0%  -7.14%  (p=0.029 n=4+4)
Change-Id: I3ced26e89041f873ac989586514ccc5ee09f13da
Reviewed-on: https://go-review.googlesource.com/c/go/+/425134
Reviewed-by: Keith Randall <khr@google.com>
Reviewed-by: Cherry Mui <cherryyz@google.com>
TryBot-Result: Gopher Robot <gobot@golang.org>
Reviewed-by: Keith Randall <khr@golang.org>
Run-TryBot: Eric Fang <eric.fang@arm.com>
											
										 
											2022-08-17 10:01:17 +00:00
										 |  |  | 	// arm64:`SUB`,`TBNZ` | 
					
						
							| 
									
										
										
										
											2020-06-01 11:01:14 +00:00
										 |  |  | 	// arm:`CMP|CMN`, -`(ADD|SUB)`, `(BMI|BPL)` | 
					
						
							| 
									
										
											  
											
												cmd/compile: fix incorrect rewriting to if condition
Some ARM64 rewriting rules convert 'comparing to zero' conditions of if
statements to a simplified version utilizing CMN and CMP instructions to
branch over condition flags, in order to save one Add or Sub caculation.
Such optimizations lead to wrong branching in case an overflow/underflow
occurs when executing CMN or CMP.
Fix the issue by introducing new block opcodes that don't honor the
overflow/underflow flag, in the following categories:
  Block-Op        Meaning                   ARM condition codes
  1. LTnoov        less than                 MI
  2. GEnoov        greater than or equal     PL
  3. LEnoov        less than or equal        MI || EQ
  4. GTnoov        greater than              NEQ & PL
The backend generates two consecutive branch instructions for 'LEnoov'
and 'GTnoov' to model their expected behavior. A slight change to 'gc'
and amd64/386 backends is made to unify the code generation.
Add a test 'TestCondRewrite' as justification, it covers 32 incorrect rules
identified on arm64, more might be needed on other arches, like 32-bit arm.
Add two benchmarks profiling the aforementioned category 1&2 and category
3&4 separetely, we expect the first two categories will show performance
improvement and the second will not result in visible regression compared with
the non-optimized version.
This change also updates TestFormats to support using %#x.
Examples exhibiting where does the issue come from:
  1: 'if x + 3 < 0' might be converted to:
  before:
    CMN $3, R0
    BGE <else branch> // wrong branch is taken if 'x+3' overflows
  after:
    CMN $3, R0
    BPL <else branch>
  2: 'if y - 3 > 0' might be converted to:
  before:
    CMP $3, R0
    BLE <else branch> // wrong branch is taken if 'y-3' underflows
  after:
    CMP $3, R0
    BMI <else branch>
    BEQ <else branch>
Benchmark data from different kinds of arm64 servers, 'old' is the non-optimized
version (not the parent commit), generally the optimization version outperforms.
S1:
name                    old time/op  new time/op  delta
CondRewrite/SoloJump  13.6ns ± 0%  12.9ns ± 0%  -5.15%  (p=0.000 n=10+10)
CondRewrite/CombJump  13.8ns ± 1%  12.9ns ± 0%  -6.32%  (p=0.000 n=10+10)
S2:
name                     old time/op  new time/op  delta
CondRewrite/SoloJump  11.6ns ± 0%  10.9ns ± 0%  -6.03%  (p=0.000 n=10+10)
CondRewrite/CombJump  11.4ns ± 0%  10.8ns ± 1%  -5.53%  (p=0.000 n=10+10)
S3:
name                     old time/op  new time/op  delta
CondRewrite/SoloJump  7.36ns ± 0%  7.50ns ± 0%  +1.79%  (p=0.000 n=9+10)
CondRewrite/CombJump  7.35ns ± 0%  7.75ns ± 0%  +5.51%  (p=0.000 n=8+9)
S4:
name                      old time/op  new time/op  delta
CondRewrite/SoloJump-224  11.5ns ± 1%  10.9ns ± 0%  -4.97%  (p=0.000 n=10+10)
CondRewrite/CombJump-224  11.9ns ± 0%  11.5ns ± 0%  -2.95%  (p=0.000 n=10+10)
S5:
name                     old time/op  new time/op  delta
CondRewrite/SoloJump  10.0ns ± 0%  10.0ns ± 0%  -0.45%  (p=0.000 n=9+10)
CondRewrite/CombJump  9.93ns ± 0%  9.77ns ± 0%  -1.53%  (p=0.000 n=10+9)
Go1 perf. data:
name                     old time/op    new time/op    delta
BinaryTree17              6.29s ± 1%     6.30s ± 1%    ~     (p=1.000 n=5+5)
Fannkuch11                5.40s ± 0%     5.40s ± 0%    ~     (p=0.841 n=5+5)
FmtFprintfEmpty          97.9ns ± 0%    98.9ns ± 3%    ~     (p=0.937 n=4+5)
FmtFprintfString          171ns ± 3%     171ns ± 2%    ~     (p=0.754 n=5+5)
FmtFprintfInt             212ns ± 0%     217ns ± 6%  +2.55%  (p=0.008 n=5+5)
FmtFprintfIntInt          296ns ± 1%     297ns ± 2%    ~     (p=0.516 n=5+5)
FmtFprintfPrefixedInt     371ns ± 2%     374ns ± 7%    ~     (p=1.000 n=5+5)
FmtFprintfFloat           435ns ± 1%     439ns ± 2%    ~     (p=0.056 n=5+5)
FmtManyArgs              1.37µs ± 1%    1.36µs ± 1%    ~     (p=0.730 n=5+5)
GobDecode                14.6ms ± 4%    14.4ms ± 4%    ~     (p=0.690 n=5+5)
GobEncode                11.8ms ±20%    11.6ms ±15%    ~     (p=1.000 n=5+5)
Gzip                      507ms ± 0%     491ms ± 0%  -3.22%  (p=0.008 n=5+5)
Gunzip                   73.8ms ± 0%    73.9ms ± 0%    ~     (p=0.690 n=5+5)
HTTPClientServer          116µs ± 0%     116µs ± 0%    ~     (p=0.686 n=4+4)
JSONEncode               21.8ms ± 1%    21.6ms ± 2%    ~     (p=0.151 n=5+5)
JSONDecode                104ms ± 1%     103ms ± 1%  -1.08%  (p=0.016 n=5+5)
Mandelbrot200            9.53ms ± 0%    9.53ms ± 0%    ~     (p=0.421 n=5+5)
GoParse                  7.55ms ± 1%    7.51ms ± 1%    ~     (p=0.151 n=5+5)
RegexpMatchEasy0_32       158ns ± 0%     158ns ± 0%    ~     (all equal)
RegexpMatchEasy0_1K       606ns ± 1%     608ns ± 3%    ~     (p=0.937 n=5+5)
RegexpMatchEasy1_32       143ns ± 0%     144ns ± 1%    ~     (p=0.095 n=5+4)
RegexpMatchEasy1_1K       927ns ± 2%     944ns ± 2%    ~     (p=0.056 n=5+5)
RegexpMatchMedium_32     16.0ns ± 0%    16.0ns ± 0%    ~     (all equal)
RegexpMatchMedium_1K     69.3µs ± 2%    69.7µs ± 0%    ~     (p=0.690 n=5+5)
RegexpMatchHard_32       3.73µs ± 0%    3.73µs ± 1%    ~     (p=0.984 n=5+5)
RegexpMatchHard_1K        111µs ± 1%     110µs ± 0%    ~     (p=0.151 n=5+5)
Revcomp                   1.91s ±47%     1.77s ±68%    ~     (p=1.000 n=5+5)
Template                  138ms ± 1%     138ms ± 1%    ~     (p=1.000 n=5+5)
TimeParse                 787ns ± 2%     785ns ± 1%    ~     (p=0.540 n=5+5)
TimeFormat                729ns ± 1%     726ns ± 1%    ~     (p=0.151 n=5+5)
Updates #38740
Change-Id: I06c604874acdc1e63e66452dadee5df053045222
Reviewed-on: https://go-review.googlesource.com/c/go/+/233097
Reviewed-by: Keith Randall <khr@golang.org>
Run-TryBot: Keith Randall <khr@golang.org>
											
										 
											2020-05-06 09:54:40 +00:00
										 |  |  | 	if e-11 >= 0 { | 
					
						
							|  |  |  | 		return 8 | 
					
						
							|  |  |  | 	} | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | 	return 0 | 
					
						
							|  |  |  | } | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | // var + var | 
					
						
							|  |  |  | // TODO: optimize 'var - var' | 
					
						
							|  |  |  | func CmpToZero_ex2(a, b, c int64, e, f, g int32) int { | 
					
						
							|  |  |  | 	// arm64:`CMN`,-`ADD`,`(BMI|BPL)` | 
					
						
							|  |  |  | 	if a+b < 0 { | 
					
						
							|  |  |  | 		return 1 | 
					
						
							|  |  |  | 	} | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | 	// arm64:`CMN`,-`ADD`,`BEQ`,`(BMI|BPL)` | 
					
						
							|  |  |  | 	if a+c <= 0 { | 
					
						
							|  |  |  | 		return 1 | 
					
						
							|  |  |  | 	} | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | 	// arm64:`CMN`,-`ADD`,`(BMI|BPL)` | 
					
						
							|  |  |  | 	if b+c >= 0 { | 
					
						
							|  |  |  | 		return 2 | 
					
						
							|  |  |  | 	} | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | 	// arm64:`CMNW`,-`ADDW`,`(BMI|BPL)` | 
					
						
							| 
									
										
										
										
											2020-06-01 11:01:14 +00:00
										 |  |  | 	// arm:`CMN`,-`ADD`,`(BMI|BPL)` | 
					
						
							| 
									
										
											  
											
												cmd/compile: fix incorrect rewriting to if condition
Some ARM64 rewriting rules convert 'comparing to zero' conditions of if
statements to a simplified version utilizing CMN and CMP instructions to
branch over condition flags, in order to save one Add or Sub caculation.
Such optimizations lead to wrong branching in case an overflow/underflow
occurs when executing CMN or CMP.
Fix the issue by introducing new block opcodes that don't honor the
overflow/underflow flag, in the following categories:
  Block-Op        Meaning                   ARM condition codes
  1. LTnoov        less than                 MI
  2. GEnoov        greater than or equal     PL
  3. LEnoov        less than or equal        MI || EQ
  4. GTnoov        greater than              NEQ & PL
The backend generates two consecutive branch instructions for 'LEnoov'
and 'GTnoov' to model their expected behavior. A slight change to 'gc'
and amd64/386 backends is made to unify the code generation.
Add a test 'TestCondRewrite' as justification, it covers 32 incorrect rules
identified on arm64, more might be needed on other arches, like 32-bit arm.
Add two benchmarks profiling the aforementioned category 1&2 and category
3&4 separetely, we expect the first two categories will show performance
improvement and the second will not result in visible regression compared with
the non-optimized version.
This change also updates TestFormats to support using %#x.
Examples exhibiting where does the issue come from:
  1: 'if x + 3 < 0' might be converted to:
  before:
    CMN $3, R0
    BGE <else branch> // wrong branch is taken if 'x+3' overflows
  after:
    CMN $3, R0
    BPL <else branch>
  2: 'if y - 3 > 0' might be converted to:
  before:
    CMP $3, R0
    BLE <else branch> // wrong branch is taken if 'y-3' underflows
  after:
    CMP $3, R0
    BMI <else branch>
    BEQ <else branch>
Benchmark data from different kinds of arm64 servers, 'old' is the non-optimized
version (not the parent commit), generally the optimization version outperforms.
S1:
name                    old time/op  new time/op  delta
CondRewrite/SoloJump  13.6ns ± 0%  12.9ns ± 0%  -5.15%  (p=0.000 n=10+10)
CondRewrite/CombJump  13.8ns ± 1%  12.9ns ± 0%  -6.32%  (p=0.000 n=10+10)
S2:
name                     old time/op  new time/op  delta
CondRewrite/SoloJump  11.6ns ± 0%  10.9ns ± 0%  -6.03%  (p=0.000 n=10+10)
CondRewrite/CombJump  11.4ns ± 0%  10.8ns ± 1%  -5.53%  (p=0.000 n=10+10)
S3:
name                     old time/op  new time/op  delta
CondRewrite/SoloJump  7.36ns ± 0%  7.50ns ± 0%  +1.79%  (p=0.000 n=9+10)
CondRewrite/CombJump  7.35ns ± 0%  7.75ns ± 0%  +5.51%  (p=0.000 n=8+9)
S4:
name                      old time/op  new time/op  delta
CondRewrite/SoloJump-224  11.5ns ± 1%  10.9ns ± 0%  -4.97%  (p=0.000 n=10+10)
CondRewrite/CombJump-224  11.9ns ± 0%  11.5ns ± 0%  -2.95%  (p=0.000 n=10+10)
S5:
name                     old time/op  new time/op  delta
CondRewrite/SoloJump  10.0ns ± 0%  10.0ns ± 0%  -0.45%  (p=0.000 n=9+10)
CondRewrite/CombJump  9.93ns ± 0%  9.77ns ± 0%  -1.53%  (p=0.000 n=10+9)
Go1 perf. data:
name                     old time/op    new time/op    delta
BinaryTree17              6.29s ± 1%     6.30s ± 1%    ~     (p=1.000 n=5+5)
Fannkuch11                5.40s ± 0%     5.40s ± 0%    ~     (p=0.841 n=5+5)
FmtFprintfEmpty          97.9ns ± 0%    98.9ns ± 3%    ~     (p=0.937 n=4+5)
FmtFprintfString          171ns ± 3%     171ns ± 2%    ~     (p=0.754 n=5+5)
FmtFprintfInt             212ns ± 0%     217ns ± 6%  +2.55%  (p=0.008 n=5+5)
FmtFprintfIntInt          296ns ± 1%     297ns ± 2%    ~     (p=0.516 n=5+5)
FmtFprintfPrefixedInt     371ns ± 2%     374ns ± 7%    ~     (p=1.000 n=5+5)
FmtFprintfFloat           435ns ± 1%     439ns ± 2%    ~     (p=0.056 n=5+5)
FmtManyArgs              1.37µs ± 1%    1.36µs ± 1%    ~     (p=0.730 n=5+5)
GobDecode                14.6ms ± 4%    14.4ms ± 4%    ~     (p=0.690 n=5+5)
GobEncode                11.8ms ±20%    11.6ms ±15%    ~     (p=1.000 n=5+5)
Gzip                      507ms ± 0%     491ms ± 0%  -3.22%  (p=0.008 n=5+5)
Gunzip                   73.8ms ± 0%    73.9ms ± 0%    ~     (p=0.690 n=5+5)
HTTPClientServer          116µs ± 0%     116µs ± 0%    ~     (p=0.686 n=4+4)
JSONEncode               21.8ms ± 1%    21.6ms ± 2%    ~     (p=0.151 n=5+5)
JSONDecode                104ms ± 1%     103ms ± 1%  -1.08%  (p=0.016 n=5+5)
Mandelbrot200            9.53ms ± 0%    9.53ms ± 0%    ~     (p=0.421 n=5+5)
GoParse                  7.55ms ± 1%    7.51ms ± 1%    ~     (p=0.151 n=5+5)
RegexpMatchEasy0_32       158ns ± 0%     158ns ± 0%    ~     (all equal)
RegexpMatchEasy0_1K       606ns ± 1%     608ns ± 3%    ~     (p=0.937 n=5+5)
RegexpMatchEasy1_32       143ns ± 0%     144ns ± 1%    ~     (p=0.095 n=5+4)
RegexpMatchEasy1_1K       927ns ± 2%     944ns ± 2%    ~     (p=0.056 n=5+5)
RegexpMatchMedium_32     16.0ns ± 0%    16.0ns ± 0%    ~     (all equal)
RegexpMatchMedium_1K     69.3µs ± 2%    69.7µs ± 0%    ~     (p=0.690 n=5+5)
RegexpMatchHard_32       3.73µs ± 0%    3.73µs ± 1%    ~     (p=0.984 n=5+5)
RegexpMatchHard_1K        111µs ± 1%     110µs ± 0%    ~     (p=0.151 n=5+5)
Revcomp                   1.91s ±47%     1.77s ±68%    ~     (p=1.000 n=5+5)
Template                  138ms ± 1%     138ms ± 1%    ~     (p=1.000 n=5+5)
TimeParse                 787ns ± 2%     785ns ± 1%    ~     (p=0.540 n=5+5)
TimeFormat                729ns ± 1%     726ns ± 1%    ~     (p=0.151 n=5+5)
Updates #38740
Change-Id: I06c604874acdc1e63e66452dadee5df053045222
Reviewed-on: https://go-review.googlesource.com/c/go/+/233097
Reviewed-by: Keith Randall <khr@golang.org>
Run-TryBot: Keith Randall <khr@golang.org>
											
										 
											2020-05-06 09:54:40 +00:00
										 |  |  | 	if e+f < 0 { | 
					
						
							|  |  |  | 		return 5 | 
					
						
							|  |  |  | 	} | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | 	// arm64:`CMNW`,-`ADDW`,`(BMI|BPL)` | 
					
						
							| 
									
										
										
										
											2020-06-01 11:01:14 +00:00
										 |  |  | 	// arm:`CMN`,-`ADD`,`(BMI|BPL)` | 
					
						
							| 
									
										
											  
											
												cmd/compile: fix incorrect rewriting to if condition
Some ARM64 rewriting rules convert 'comparing to zero' conditions of if
statements to a simplified version utilizing CMN and CMP instructions to
branch over condition flags, in order to save one Add or Sub caculation.
Such optimizations lead to wrong branching in case an overflow/underflow
occurs when executing CMN or CMP.
Fix the issue by introducing new block opcodes that don't honor the
overflow/underflow flag, in the following categories:
  Block-Op        Meaning                   ARM condition codes
  1. LTnoov        less than                 MI
  2. GEnoov        greater than or equal     PL
  3. LEnoov        less than or equal        MI || EQ
  4. GTnoov        greater than              NEQ & PL
The backend generates two consecutive branch instructions for 'LEnoov'
and 'GTnoov' to model their expected behavior. A slight change to 'gc'
and amd64/386 backends is made to unify the code generation.
Add a test 'TestCondRewrite' as justification, it covers 32 incorrect rules
identified on arm64, more might be needed on other arches, like 32-bit arm.
Add two benchmarks profiling the aforementioned category 1&2 and category
3&4 separetely, we expect the first two categories will show performance
improvement and the second will not result in visible regression compared with
the non-optimized version.
This change also updates TestFormats to support using %#x.
Examples exhibiting where does the issue come from:
  1: 'if x + 3 < 0' might be converted to:
  before:
    CMN $3, R0
    BGE <else branch> // wrong branch is taken if 'x+3' overflows
  after:
    CMN $3, R0
    BPL <else branch>
  2: 'if y - 3 > 0' might be converted to:
  before:
    CMP $3, R0
    BLE <else branch> // wrong branch is taken if 'y-3' underflows
  after:
    CMP $3, R0
    BMI <else branch>
    BEQ <else branch>
Benchmark data from different kinds of arm64 servers, 'old' is the non-optimized
version (not the parent commit), generally the optimization version outperforms.
S1:
name                    old time/op  new time/op  delta
CondRewrite/SoloJump  13.6ns ± 0%  12.9ns ± 0%  -5.15%  (p=0.000 n=10+10)
CondRewrite/CombJump  13.8ns ± 1%  12.9ns ± 0%  -6.32%  (p=0.000 n=10+10)
S2:
name                     old time/op  new time/op  delta
CondRewrite/SoloJump  11.6ns ± 0%  10.9ns ± 0%  -6.03%  (p=0.000 n=10+10)
CondRewrite/CombJump  11.4ns ± 0%  10.8ns ± 1%  -5.53%  (p=0.000 n=10+10)
S3:
name                     old time/op  new time/op  delta
CondRewrite/SoloJump  7.36ns ± 0%  7.50ns ± 0%  +1.79%  (p=0.000 n=9+10)
CondRewrite/CombJump  7.35ns ± 0%  7.75ns ± 0%  +5.51%  (p=0.000 n=8+9)
S4:
name                      old time/op  new time/op  delta
CondRewrite/SoloJump-224  11.5ns ± 1%  10.9ns ± 0%  -4.97%  (p=0.000 n=10+10)
CondRewrite/CombJump-224  11.9ns ± 0%  11.5ns ± 0%  -2.95%  (p=0.000 n=10+10)
S5:
name                     old time/op  new time/op  delta
CondRewrite/SoloJump  10.0ns ± 0%  10.0ns ± 0%  -0.45%  (p=0.000 n=9+10)
CondRewrite/CombJump  9.93ns ± 0%  9.77ns ± 0%  -1.53%  (p=0.000 n=10+9)
Go1 perf. data:
name                     old time/op    new time/op    delta
BinaryTree17              6.29s ± 1%     6.30s ± 1%    ~     (p=1.000 n=5+5)
Fannkuch11                5.40s ± 0%     5.40s ± 0%    ~     (p=0.841 n=5+5)
FmtFprintfEmpty          97.9ns ± 0%    98.9ns ± 3%    ~     (p=0.937 n=4+5)
FmtFprintfString          171ns ± 3%     171ns ± 2%    ~     (p=0.754 n=5+5)
FmtFprintfInt             212ns ± 0%     217ns ± 6%  +2.55%  (p=0.008 n=5+5)
FmtFprintfIntInt          296ns ± 1%     297ns ± 2%    ~     (p=0.516 n=5+5)
FmtFprintfPrefixedInt     371ns ± 2%     374ns ± 7%    ~     (p=1.000 n=5+5)
FmtFprintfFloat           435ns ± 1%     439ns ± 2%    ~     (p=0.056 n=5+5)
FmtManyArgs              1.37µs ± 1%    1.36µs ± 1%    ~     (p=0.730 n=5+5)
GobDecode                14.6ms ± 4%    14.4ms ± 4%    ~     (p=0.690 n=5+5)
GobEncode                11.8ms ±20%    11.6ms ±15%    ~     (p=1.000 n=5+5)
Gzip                      507ms ± 0%     491ms ± 0%  -3.22%  (p=0.008 n=5+5)
Gunzip                   73.8ms ± 0%    73.9ms ± 0%    ~     (p=0.690 n=5+5)
HTTPClientServer          116µs ± 0%     116µs ± 0%    ~     (p=0.686 n=4+4)
JSONEncode               21.8ms ± 1%    21.6ms ± 2%    ~     (p=0.151 n=5+5)
JSONDecode                104ms ± 1%     103ms ± 1%  -1.08%  (p=0.016 n=5+5)
Mandelbrot200            9.53ms ± 0%    9.53ms ± 0%    ~     (p=0.421 n=5+5)
GoParse                  7.55ms ± 1%    7.51ms ± 1%    ~     (p=0.151 n=5+5)
RegexpMatchEasy0_32       158ns ± 0%     158ns ± 0%    ~     (all equal)
RegexpMatchEasy0_1K       606ns ± 1%     608ns ± 3%    ~     (p=0.937 n=5+5)
RegexpMatchEasy1_32       143ns ± 0%     144ns ± 1%    ~     (p=0.095 n=5+4)
RegexpMatchEasy1_1K       927ns ± 2%     944ns ± 2%    ~     (p=0.056 n=5+5)
RegexpMatchMedium_32     16.0ns ± 0%    16.0ns ± 0%    ~     (all equal)
RegexpMatchMedium_1K     69.3µs ± 2%    69.7µs ± 0%    ~     (p=0.690 n=5+5)
RegexpMatchHard_32       3.73µs ± 0%    3.73µs ± 1%    ~     (p=0.984 n=5+5)
RegexpMatchHard_1K        111µs ± 1%     110µs ± 0%    ~     (p=0.151 n=5+5)
Revcomp                   1.91s ±47%     1.77s ±68%    ~     (p=1.000 n=5+5)
Template                  138ms ± 1%     138ms ± 1%    ~     (p=1.000 n=5+5)
TimeParse                 787ns ± 2%     785ns ± 1%    ~     (p=0.540 n=5+5)
TimeFormat                729ns ± 1%     726ns ± 1%    ~     (p=0.151 n=5+5)
Updates #38740
Change-Id: I06c604874acdc1e63e66452dadee5df053045222
Reviewed-on: https://go-review.googlesource.com/c/go/+/233097
Reviewed-by: Keith Randall <khr@golang.org>
Run-TryBot: Keith Randall <khr@golang.org>
											
										 
											2020-05-06 09:54:40 +00:00
										 |  |  | 	if f+g >= 0 { | 
					
						
							|  |  |  | 		return 6 | 
					
						
							|  |  |  | 	} | 
					
						
							|  |  |  | 	return 0 | 
					
						
							|  |  |  | } | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | // var + var*var | 
					
						
							|  |  |  | func CmpToZero_ex3(a, b, c, d int64, e, f, g, h int32) int { | 
					
						
							|  |  |  | 	// arm64:`CMN`,-`MADD`,`MUL`,`(BMI|BPL)` | 
					
						
							|  |  |  | 	if a+b*c < 0 { | 
					
						
							|  |  |  | 		return 1 | 
					
						
							|  |  |  | 	} | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | 	// arm64:`CMN`,-`MADD`,`MUL`,`(BMI|BPL)` | 
					
						
							|  |  |  | 	if b+c*d >= 0 { | 
					
						
							|  |  |  | 		return 2 | 
					
						
							|  |  |  | 	} | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | 	// arm64:`CMNW`,-`MADDW`,`MULW`,`BEQ`,`(BMI|BPL)` | 
					
						
							| 
									
										
										
										
											2020-06-01 11:01:14 +00:00
										 |  |  | 	// arm:`CMN`,-`MULA`,`MUL`,`BEQ`,`(BMI|BPL)` | 
					
						
							| 
									
										
											  
											
												cmd/compile: fix incorrect rewriting to if condition
Some ARM64 rewriting rules convert 'comparing to zero' conditions of if
statements to a simplified version utilizing CMN and CMP instructions to
branch over condition flags, in order to save one Add or Sub caculation.
Such optimizations lead to wrong branching in case an overflow/underflow
occurs when executing CMN or CMP.
Fix the issue by introducing new block opcodes that don't honor the
overflow/underflow flag, in the following categories:
  Block-Op        Meaning                   ARM condition codes
  1. LTnoov        less than                 MI
  2. GEnoov        greater than or equal     PL
  3. LEnoov        less than or equal        MI || EQ
  4. GTnoov        greater than              NEQ & PL
The backend generates two consecutive branch instructions for 'LEnoov'
and 'GTnoov' to model their expected behavior. A slight change to 'gc'
and amd64/386 backends is made to unify the code generation.
Add a test 'TestCondRewrite' as justification, it covers 32 incorrect rules
identified on arm64, more might be needed on other arches, like 32-bit arm.
Add two benchmarks profiling the aforementioned category 1&2 and category
3&4 separetely, we expect the first two categories will show performance
improvement and the second will not result in visible regression compared with
the non-optimized version.
This change also updates TestFormats to support using %#x.
Examples exhibiting where does the issue come from:
  1: 'if x + 3 < 0' might be converted to:
  before:
    CMN $3, R0
    BGE <else branch> // wrong branch is taken if 'x+3' overflows
  after:
    CMN $3, R0
    BPL <else branch>
  2: 'if y - 3 > 0' might be converted to:
  before:
    CMP $3, R0
    BLE <else branch> // wrong branch is taken if 'y-3' underflows
  after:
    CMP $3, R0
    BMI <else branch>
    BEQ <else branch>
Benchmark data from different kinds of arm64 servers, 'old' is the non-optimized
version (not the parent commit), generally the optimization version outperforms.
S1:
name                    old time/op  new time/op  delta
CondRewrite/SoloJump  13.6ns ± 0%  12.9ns ± 0%  -5.15%  (p=0.000 n=10+10)
CondRewrite/CombJump  13.8ns ± 1%  12.9ns ± 0%  -6.32%  (p=0.000 n=10+10)
S2:
name                     old time/op  new time/op  delta
CondRewrite/SoloJump  11.6ns ± 0%  10.9ns ± 0%  -6.03%  (p=0.000 n=10+10)
CondRewrite/CombJump  11.4ns ± 0%  10.8ns ± 1%  -5.53%  (p=0.000 n=10+10)
S3:
name                     old time/op  new time/op  delta
CondRewrite/SoloJump  7.36ns ± 0%  7.50ns ± 0%  +1.79%  (p=0.000 n=9+10)
CondRewrite/CombJump  7.35ns ± 0%  7.75ns ± 0%  +5.51%  (p=0.000 n=8+9)
S4:
name                      old time/op  new time/op  delta
CondRewrite/SoloJump-224  11.5ns ± 1%  10.9ns ± 0%  -4.97%  (p=0.000 n=10+10)
CondRewrite/CombJump-224  11.9ns ± 0%  11.5ns ± 0%  -2.95%  (p=0.000 n=10+10)
S5:
name                     old time/op  new time/op  delta
CondRewrite/SoloJump  10.0ns ± 0%  10.0ns ± 0%  -0.45%  (p=0.000 n=9+10)
CondRewrite/CombJump  9.93ns ± 0%  9.77ns ± 0%  -1.53%  (p=0.000 n=10+9)
Go1 perf. data:
name                     old time/op    new time/op    delta
BinaryTree17              6.29s ± 1%     6.30s ± 1%    ~     (p=1.000 n=5+5)
Fannkuch11                5.40s ± 0%     5.40s ± 0%    ~     (p=0.841 n=5+5)
FmtFprintfEmpty          97.9ns ± 0%    98.9ns ± 3%    ~     (p=0.937 n=4+5)
FmtFprintfString          171ns ± 3%     171ns ± 2%    ~     (p=0.754 n=5+5)
FmtFprintfInt             212ns ± 0%     217ns ± 6%  +2.55%  (p=0.008 n=5+5)
FmtFprintfIntInt          296ns ± 1%     297ns ± 2%    ~     (p=0.516 n=5+5)
FmtFprintfPrefixedInt     371ns ± 2%     374ns ± 7%    ~     (p=1.000 n=5+5)
FmtFprintfFloat           435ns ± 1%     439ns ± 2%    ~     (p=0.056 n=5+5)
FmtManyArgs              1.37µs ± 1%    1.36µs ± 1%    ~     (p=0.730 n=5+5)
GobDecode                14.6ms ± 4%    14.4ms ± 4%    ~     (p=0.690 n=5+5)
GobEncode                11.8ms ±20%    11.6ms ±15%    ~     (p=1.000 n=5+5)
Gzip                      507ms ± 0%     491ms ± 0%  -3.22%  (p=0.008 n=5+5)
Gunzip                   73.8ms ± 0%    73.9ms ± 0%    ~     (p=0.690 n=5+5)
HTTPClientServer          116µs ± 0%     116µs ± 0%    ~     (p=0.686 n=4+4)
JSONEncode               21.8ms ± 1%    21.6ms ± 2%    ~     (p=0.151 n=5+5)
JSONDecode                104ms ± 1%     103ms ± 1%  -1.08%  (p=0.016 n=5+5)
Mandelbrot200            9.53ms ± 0%    9.53ms ± 0%    ~     (p=0.421 n=5+5)
GoParse                  7.55ms ± 1%    7.51ms ± 1%    ~     (p=0.151 n=5+5)
RegexpMatchEasy0_32       158ns ± 0%     158ns ± 0%    ~     (all equal)
RegexpMatchEasy0_1K       606ns ± 1%     608ns ± 3%    ~     (p=0.937 n=5+5)
RegexpMatchEasy1_32       143ns ± 0%     144ns ± 1%    ~     (p=0.095 n=5+4)
RegexpMatchEasy1_1K       927ns ± 2%     944ns ± 2%    ~     (p=0.056 n=5+5)
RegexpMatchMedium_32     16.0ns ± 0%    16.0ns ± 0%    ~     (all equal)
RegexpMatchMedium_1K     69.3µs ± 2%    69.7µs ± 0%    ~     (p=0.690 n=5+5)
RegexpMatchHard_32       3.73µs ± 0%    3.73µs ± 1%    ~     (p=0.984 n=5+5)
RegexpMatchHard_1K        111µs ± 1%     110µs ± 0%    ~     (p=0.151 n=5+5)
Revcomp                   1.91s ±47%     1.77s ±68%    ~     (p=1.000 n=5+5)
Template                  138ms ± 1%     138ms ± 1%    ~     (p=1.000 n=5+5)
TimeParse                 787ns ± 2%     785ns ± 1%    ~     (p=0.540 n=5+5)
TimeFormat                729ns ± 1%     726ns ± 1%    ~     (p=0.151 n=5+5)
Updates #38740
Change-Id: I06c604874acdc1e63e66452dadee5df053045222
Reviewed-on: https://go-review.googlesource.com/c/go/+/233097
Reviewed-by: Keith Randall <khr@golang.org>
Run-TryBot: Keith Randall <khr@golang.org>
											
										 
											2020-05-06 09:54:40 +00:00
										 |  |  | 	if e+f*g > 0 { | 
					
						
							|  |  |  | 		return 5 | 
					
						
							|  |  |  | 	} | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | 	// arm64:`CMNW`,-`MADDW`,`MULW`,`BEQ`,`(BMI|BPL)` | 
					
						
							| 
									
										
										
										
											2020-06-01 11:01:14 +00:00
										 |  |  | 	// arm:`CMN`,-`MULA`,`MUL`,`BEQ`,`(BMI|BPL)` | 
					
						
							| 
									
										
											  
											
												cmd/compile: fix incorrect rewriting to if condition
Some ARM64 rewriting rules convert 'comparing to zero' conditions of if
statements to a simplified version utilizing CMN and CMP instructions to
branch over condition flags, in order to save one Add or Sub caculation.
Such optimizations lead to wrong branching in case an overflow/underflow
occurs when executing CMN or CMP.
Fix the issue by introducing new block opcodes that don't honor the
overflow/underflow flag, in the following categories:
  Block-Op        Meaning                   ARM condition codes
  1. LTnoov        less than                 MI
  2. GEnoov        greater than or equal     PL
  3. LEnoov        less than or equal        MI || EQ
  4. GTnoov        greater than              NEQ & PL
The backend generates two consecutive branch instructions for 'LEnoov'
and 'GTnoov' to model their expected behavior. A slight change to 'gc'
and amd64/386 backends is made to unify the code generation.
Add a test 'TestCondRewrite' as justification, it covers 32 incorrect rules
identified on arm64, more might be needed on other arches, like 32-bit arm.
Add two benchmarks profiling the aforementioned category 1&2 and category
3&4 separetely, we expect the first two categories will show performance
improvement and the second will not result in visible regression compared with
the non-optimized version.
This change also updates TestFormats to support using %#x.
Examples exhibiting where does the issue come from:
  1: 'if x + 3 < 0' might be converted to:
  before:
    CMN $3, R0
    BGE <else branch> // wrong branch is taken if 'x+3' overflows
  after:
    CMN $3, R0
    BPL <else branch>
  2: 'if y - 3 > 0' might be converted to:
  before:
    CMP $3, R0
    BLE <else branch> // wrong branch is taken if 'y-3' underflows
  after:
    CMP $3, R0
    BMI <else branch>
    BEQ <else branch>
Benchmark data from different kinds of arm64 servers, 'old' is the non-optimized
version (not the parent commit), generally the optimization version outperforms.
S1:
name                    old time/op  new time/op  delta
CondRewrite/SoloJump  13.6ns ± 0%  12.9ns ± 0%  -5.15%  (p=0.000 n=10+10)
CondRewrite/CombJump  13.8ns ± 1%  12.9ns ± 0%  -6.32%  (p=0.000 n=10+10)
S2:
name                     old time/op  new time/op  delta
CondRewrite/SoloJump  11.6ns ± 0%  10.9ns ± 0%  -6.03%  (p=0.000 n=10+10)
CondRewrite/CombJump  11.4ns ± 0%  10.8ns ± 1%  -5.53%  (p=0.000 n=10+10)
S3:
name                     old time/op  new time/op  delta
CondRewrite/SoloJump  7.36ns ± 0%  7.50ns ± 0%  +1.79%  (p=0.000 n=9+10)
CondRewrite/CombJump  7.35ns ± 0%  7.75ns ± 0%  +5.51%  (p=0.000 n=8+9)
S4:
name                      old time/op  new time/op  delta
CondRewrite/SoloJump-224  11.5ns ± 1%  10.9ns ± 0%  -4.97%  (p=0.000 n=10+10)
CondRewrite/CombJump-224  11.9ns ± 0%  11.5ns ± 0%  -2.95%  (p=0.000 n=10+10)
S5:
name                     old time/op  new time/op  delta
CondRewrite/SoloJump  10.0ns ± 0%  10.0ns ± 0%  -0.45%  (p=0.000 n=9+10)
CondRewrite/CombJump  9.93ns ± 0%  9.77ns ± 0%  -1.53%  (p=0.000 n=10+9)
Go1 perf. data:
name                     old time/op    new time/op    delta
BinaryTree17              6.29s ± 1%     6.30s ± 1%    ~     (p=1.000 n=5+5)
Fannkuch11                5.40s ± 0%     5.40s ± 0%    ~     (p=0.841 n=5+5)
FmtFprintfEmpty          97.9ns ± 0%    98.9ns ± 3%    ~     (p=0.937 n=4+5)
FmtFprintfString          171ns ± 3%     171ns ± 2%    ~     (p=0.754 n=5+5)
FmtFprintfInt             212ns ± 0%     217ns ± 6%  +2.55%  (p=0.008 n=5+5)
FmtFprintfIntInt          296ns ± 1%     297ns ± 2%    ~     (p=0.516 n=5+5)
FmtFprintfPrefixedInt     371ns ± 2%     374ns ± 7%    ~     (p=1.000 n=5+5)
FmtFprintfFloat           435ns ± 1%     439ns ± 2%    ~     (p=0.056 n=5+5)
FmtManyArgs              1.37µs ± 1%    1.36µs ± 1%    ~     (p=0.730 n=5+5)
GobDecode                14.6ms ± 4%    14.4ms ± 4%    ~     (p=0.690 n=5+5)
GobEncode                11.8ms ±20%    11.6ms ±15%    ~     (p=1.000 n=5+5)
Gzip                      507ms ± 0%     491ms ± 0%  -3.22%  (p=0.008 n=5+5)
Gunzip                   73.8ms ± 0%    73.9ms ± 0%    ~     (p=0.690 n=5+5)
HTTPClientServer          116µs ± 0%     116µs ± 0%    ~     (p=0.686 n=4+4)
JSONEncode               21.8ms ± 1%    21.6ms ± 2%    ~     (p=0.151 n=5+5)
JSONDecode                104ms ± 1%     103ms ± 1%  -1.08%  (p=0.016 n=5+5)
Mandelbrot200            9.53ms ± 0%    9.53ms ± 0%    ~     (p=0.421 n=5+5)
GoParse                  7.55ms ± 1%    7.51ms ± 1%    ~     (p=0.151 n=5+5)
RegexpMatchEasy0_32       158ns ± 0%     158ns ± 0%    ~     (all equal)
RegexpMatchEasy0_1K       606ns ± 1%     608ns ± 3%    ~     (p=0.937 n=5+5)
RegexpMatchEasy1_32       143ns ± 0%     144ns ± 1%    ~     (p=0.095 n=5+4)
RegexpMatchEasy1_1K       927ns ± 2%     944ns ± 2%    ~     (p=0.056 n=5+5)
RegexpMatchMedium_32     16.0ns ± 0%    16.0ns ± 0%    ~     (all equal)
RegexpMatchMedium_1K     69.3µs ± 2%    69.7µs ± 0%    ~     (p=0.690 n=5+5)
RegexpMatchHard_32       3.73µs ± 0%    3.73µs ± 1%    ~     (p=0.984 n=5+5)
RegexpMatchHard_1K        111µs ± 1%     110µs ± 0%    ~     (p=0.151 n=5+5)
Revcomp                   1.91s ±47%     1.77s ±68%    ~     (p=1.000 n=5+5)
Template                  138ms ± 1%     138ms ± 1%    ~     (p=1.000 n=5+5)
TimeParse                 787ns ± 2%     785ns ± 1%    ~     (p=0.540 n=5+5)
TimeFormat                729ns ± 1%     726ns ± 1%    ~     (p=0.151 n=5+5)
Updates #38740
Change-Id: I06c604874acdc1e63e66452dadee5df053045222
Reviewed-on: https://go-review.googlesource.com/c/go/+/233097
Reviewed-by: Keith Randall <khr@golang.org>
Run-TryBot: Keith Randall <khr@golang.org>
											
										 
											2020-05-06 09:54:40 +00:00
										 |  |  | 	if f+g*h <= 0 { | 
					
						
							|  |  |  | 		return 6 | 
					
						
							|  |  |  | 	} | 
					
						
							|  |  |  | 	return 0 | 
					
						
							|  |  |  | } | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | // var - var*var | 
					
						
							|  |  |  | func CmpToZero_ex4(a, b, c, d int64, e, f, g, h int32) int { | 
					
						
							|  |  |  | 	// arm64:`CMP`,-`MSUB`,`MUL`,`BEQ`,`(BMI|BPL)` | 
					
						
							|  |  |  | 	if a-b*c > 0 { | 
					
						
							|  |  |  | 		return 1 | 
					
						
							|  |  |  | 	} | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | 	// arm64:`CMP`,-`MSUB`,`MUL`,`(BMI|BPL)` | 
					
						
							|  |  |  | 	if b-c*d >= 0 { | 
					
						
							|  |  |  | 		return 2 | 
					
						
							|  |  |  | 	} | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | 	// arm64:`CMPW`,-`MSUBW`,`MULW`,`(BMI|BPL)` | 
					
						
							|  |  |  | 	if e-f*g < 0 { | 
					
						
							|  |  |  | 		return 5 | 
					
						
							|  |  |  | 	} | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | 	// arm64:`CMPW`,-`MSUBW`,`MULW`,`(BMI|BPL)` | 
					
						
							|  |  |  | 	if f-g*h >= 0 { | 
					
						
							|  |  |  | 		return 6 | 
					
						
							|  |  |  | 	} | 
					
						
							|  |  |  | 	return 0 | 
					
						
							|  |  |  | } | 
					
						
							| 
									
										
										
										
											2020-06-01 11:01:14 +00:00
										 |  |  | 
 | 
					
						
							|  |  |  | func CmpToZero_ex5(e, f int32, u uint32) int { | 
					
						
							|  |  |  | 	// arm:`CMN`,-`ADD`,`BEQ`,`(BMI|BPL)` | 
					
						
							|  |  |  | 	if e+f<<1 > 0 { | 
					
						
							|  |  |  | 		return 1 | 
					
						
							|  |  |  | 	} | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | 	// arm:`CMP`,-`SUB`,`(BMI|BPL)` | 
					
						
							|  |  |  | 	if f-int32(u>>2) >= 0 { | 
					
						
							|  |  |  | 		return 2 | 
					
						
							|  |  |  | 	} | 
					
						
							|  |  |  | 	return 0 | 
					
						
							|  |  |  | } | 
					
						
							| 
									
										
										
										
											2020-07-10 11:39:23 +08:00
										 |  |  | func UintLtZero(a uint8, b uint16, c uint32, d uint64) int { | 
					
						
							|  |  |  | 	// amd64: -`(TESTB|TESTW|TESTL|TESTQ|JCC|JCS)` | 
					
						
							|  |  |  | 	// arm64: -`(CMPW|CMP|BHS|BLO)` | 
					
						
							|  |  |  | 	if a < 0 || b < 0 || c < 0 || d < 0 { | 
					
						
							|  |  |  | 		return 1 | 
					
						
							|  |  |  | 	} | 
					
						
							|  |  |  | 	return 0 | 
					
						
							|  |  |  | } | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | func UintGeqZero(a uint8, b uint16, c uint32, d uint64) int { | 
					
						
							|  |  |  | 	// amd64: -`(TESTB|TESTW|TESTL|TESTQ|JCS|JCC)` | 
					
						
							|  |  |  | 	// arm64: -`(CMPW|CMP|BLO|BHS)` | 
					
						
							|  |  |  | 	if a >= 0 || b >= 0 || c >= 0 || d >= 0 { | 
					
						
							|  |  |  | 		return 1 | 
					
						
							|  |  |  | 	} | 
					
						
							|  |  |  | 	return 0 | 
					
						
							|  |  |  | } | 
					
						
							| 
									
										
										
										
											2020-07-10 11:39:23 +08:00
										 |  |  | 
 | 
					
						
							|  |  |  | func UintGtZero(a uint8, b uint16, c uint32, d uint64) int { | 
					
						
							| 
									
										
											  
											
												cmd/compile: use depth first topological sort algorithm for layout
The current layout algorithm tries to put consecutive blocks together,
so the priority of the successor block is higher than the priority of
the zero indegree block. This algorithm is beneficial for subsequent
register allocation, but will result in more branch instructions.
The depth-first topological sorting algorithm is a well-known layout
algorithm, which has applications in many languages, and it helps to
reduce branch instructions. This CL applies it to the layout pass.
The test results show that it helps to reduce the code size.
This CL also includes the following changes:
1, Removed the primary predecessor mechanism. The new layout algorithm is
  not very friendly to register allocator in some cases, in order to adapt
  to the new layout algorithm, a new primary predecessor selection strategy
  is introduced.
2, Since the new layout implementation may place non-loop blocks between
  loop blocks, some adaptive modifications have also been made to looprotate
  pass.
3, The layout also affects the results of codegen, so this CL also adjusted
  several codegen tests accordingly.
It is inevitable that this CL will cause the code size or performance of a
few functions to decrease, but the number of cases it improves is much larger
than the number of cases it drops.
Statistical data from compilecmp on linux/amd64 is as follow:
name                      old time/op       new time/op       delta
Template                        382ms ± 4%        382ms ± 4%    ~     (p=0.497 n=49+50)
Unicode                         170ms ± 9%        169ms ± 8%    ~     (p=0.344 n=48+50)
GoTypes                         2.01s ± 4%        2.01s ± 4%    ~     (p=0.628 n=50+48)
Compiler                        190ms ±10%        189ms ± 9%    ~     (p=0.734 n=50+50)
SSA                             11.8s ± 2%        11.8s ± 3%    ~     (p=0.877 n=50+50)
Flate                           241ms ± 9%        241ms ± 8%    ~     (p=0.897 n=50+49)
GoParser                        366ms ± 3%        361ms ± 4%  -1.21%  (p=0.004 n=47+50)
Reflect                         835ms ± 3%        838ms ± 3%    ~     (p=0.275 n=50+49)
Tar                             336ms ± 4%        335ms ± 3%    ~     (p=0.454 n=48+48)
XML                             433ms ± 4%        431ms ± 3%    ~     (p=0.071 n=49+48)
LinkCompiler                    706ms ± 4%        705ms ± 4%    ~     (p=0.608 n=50+49)
ExternalLinkCompiler            1.85s ± 3%        1.83s ± 2%  -1.47%  (p=0.000 n=49+48)
LinkWithoutDebugCompiler        437ms ± 5%        437ms ± 6%    ~     (p=0.953 n=49+50)
[Geo mean]                      615ms             613ms       -0.37%
name                      old alloc/op      new alloc/op      delta
Template                       38.7MB ± 1%       38.7MB ± 1%    ~     (p=0.834 n=50+50)
Unicode                        28.1MB ± 0%       28.1MB ± 0%  -0.22%  (p=0.000 n=49+50)
GoTypes                         168MB ± 1%        168MB ± 1%    ~     (p=0.054 n=47+47)
Compiler                       23.0MB ± 1%       23.0MB ± 1%    ~     (p=0.432 n=50+50)
SSA                            1.54GB ± 0%       1.54GB ± 0%  +0.21%  (p=0.000 n=50+50)
Flate                          23.6MB ± 1%       23.6MB ± 1%    ~     (p=0.153 n=43+46)
GoParser                       35.1MB ± 1%       35.1MB ± 2%    ~     (p=0.202 n=50+50)
Reflect                        84.7MB ± 1%       84.7MB ± 1%    ~     (p=0.333 n=48+49)
Tar                            34.5MB ± 1%       34.5MB ± 1%    ~     (p=0.406 n=46+49)
XML                            44.3MB ± 2%       44.2MB ± 3%    ~     (p=0.981 n=50+50)
LinkCompiler                    131MB ± 0%        128MB ± 0%  -2.74%  (p=0.000 n=50+50)
ExternalLinkCompiler            120MB ± 0%        120MB ± 0%  +0.01%  (p=0.007 n=50+50)
LinkWithoutDebugCompiler       77.3MB ± 0%       77.3MB ± 0%  -0.02%  (p=0.000 n=50+50)
[Geo mean]                     69.3MB            69.1MB       -0.22%
file      before    after     Δ        %
addr2line 4104220   4043684   -60536   -1.475%
api       5342502   5249678   -92824   -1.737%
asm       4973785   4858257   -115528  -2.323%
buildid   2667844   2625660   -42184   -1.581%
cgo       4686849   4616313   -70536   -1.505%
compile   23667431  23268406  -399025  -1.686%
cover     4959676   4874108   -85568   -1.725%
dist      3515934   3450422   -65512   -1.863%
doc       3995581   3925469   -70112   -1.755%
fix       3379202   3318522   -60680   -1.796%
link      6743249   6629913   -113336  -1.681%
nm        4047529   3991777   -55752   -1.377%
objdump   4456151   4388151   -68000   -1.526%
pack      2435040   2398072   -36968   -1.518%
pprof     13804080  13565808  -238272  -1.726%
test2json 2690043   2645987   -44056   -1.638%
trace     10418492  10232716  -185776  -1.783%
vet       7258259   7121259   -137000  -1.888%
total     113145867 111204202 -1941665 -1.716%
The situation on linux/arm64 is as follow:
name                      old time/op       new time/op       delta
Template                        280ms ± 1%        282ms ± 1%  +0.75%  (p=0.000 n=46+48)
Unicode                         124ms ± 2%        124ms ± 2%  +0.37%  (p=0.045 n=50+50)
GoTypes                         1.69s ± 1%        1.70s ± 1%  +0.56%  (p=0.000 n=49+50)
Compiler                        122ms ± 1%        123ms ± 1%  +0.93%  (p=0.000 n=50+50)
SSA                             12.6s ± 1%        12.7s ± 0%  +0.72%  (p=0.000 n=50+50)
Flate                           170ms ± 1%        172ms ± 1%  +0.97%  (p=0.000 n=49+49)
GoParser                        262ms ± 1%        263ms ± 1%  +0.39%  (p=0.000 n=49+48)
Reflect                         639ms ± 1%        650ms ± 1%  +1.63%  (p=0.000 n=49+49)
Tar                             243ms ± 1%        245ms ± 1%  +0.82%  (p=0.000 n=50+50)
XML                             324ms ± 1%        327ms ± 1%  +0.72%  (p=0.000 n=50+49)
LinkCompiler                    597ms ± 1%        596ms ± 1%  -0.27%  (p=0.001 n=48+47)
ExternalLinkCompiler            1.90s ± 1%        1.88s ± 1%  -1.00%  (p=0.000 n=50+50)
LinkWithoutDebugCompiler        364ms ± 1%        363ms ± 1%    ~     (p=0.220 n=49+50)
[Geo mean]                      485ms             488ms       +0.49%
name                      old alloc/op      new alloc/op      delta
Template                       38.7MB ± 0%       38.8MB ± 1%    ~     (p=0.093 n=43+49)
Unicode                        28.4MB ± 0%       28.4MB ± 0%  +0.03%  (p=0.000 n=49+45)
GoTypes                         169MB ± 1%        169MB ± 1%  +0.23%  (p=0.010 n=50+50)
Compiler                       23.2MB ± 1%       23.2MB ± 1%  +0.11%  (p=0.000 n=40+44)
SSA                            1.54GB ± 0%       1.55GB ± 0%  +0.45%  (p=0.000 n=47+49)
Flate                          23.8MB ± 2%       23.8MB ± 1%    ~     (p=0.543 n=50+50)
GoParser                       35.3MB ± 1%       35.4MB ± 1%    ~     (p=0.792 n=50+50)
Reflect                        85.2MB ± 1%       85.2MB ± 0%    ~     (p=0.055 n=50+47)
Tar                            34.5MB ± 1%       34.5MB ± 1%  +0.06%  (p=0.015 n=50+50)
XML                            43.8MB ± 2%       43.9MB ± 2%  +0.19%  (p=0.000 n=48+48)
LinkCompiler                    137MB ± 0%        136MB ± 0%  -0.92%  (p=0.000 n=50+50)
ExternalLinkCompiler            127MB ± 0%        127MB ± 0%    ~     (p=0.516 n=50+50)
LinkWithoutDebugCompiler       84.0MB ± 0%       84.0MB ± 0%    ~     (p=0.057 n=50+50)
[Geo mean]                     70.4MB            70.4MB       +0.01%
file      before    after     Δ        %
addr2line 4021557   4002933   -18624   -0.463%
api       5127847   5028503   -99344   -1.937%
asm       5034716   4936836   -97880   -1.944%
buildid   2608118   2594094   -14024   -0.538%
cgo       4488592   4398320   -90272   -2.011%
compile   22501129  22213592  -287537  -1.278%
cover     4742301   4713573   -28728   -0.606%
dist      3388071   3365311   -22760   -0.672%
doc       3802250   3776082   -26168   -0.688%
fix       3306147   3216939   -89208   -2.698%
link      6404483   6363699   -40784   -0.637%
nm        3941026   3921930   -19096   -0.485%
objdump   4383330   4295122   -88208   -2.012%
pack      2404547   2389515   -15032   -0.625%
pprof     12996234  12856818  -139416  -1.073%
test2json 2668500   2586788   -81712   -3.062%
trace     9816276   9609580   -206696  -2.106%
vet       6900682   6787338   -113344  -1.643%
total     108535806 107056973 -1478833 -1.363%
Change-Id: Iaec1cdcaacca8025e9babb0fb8a532fddb70c87d
Reviewed-on: https://go-review.googlesource.com/c/go/+/255239
Reviewed-by: eric fang <eric.fang@arm.com>
Reviewed-by: Keith Randall <khr@golang.org>
Trust: eric fang <eric.fang@arm.com>
											
										 
											2020-07-23 10:24:56 +08:00
										 |  |  | 	// arm64: `(CBN?ZW)`, `(CBN?Z[^W])`, -`(CMPW|CMP|BLS|BHI)` | 
					
						
							| 
									
										
										
										
											2020-07-10 11:39:23 +08:00
										 |  |  | 	if a > 0 || b > 0 || c > 0 || d > 0 { | 
					
						
							|  |  |  | 		return 1 | 
					
						
							|  |  |  | 	} | 
					
						
							|  |  |  | 	return 0 | 
					
						
							|  |  |  | } | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | func UintLeqZero(a uint8, b uint16, c uint32, d uint64) int { | 
					
						
							| 
									
										
											  
											
												cmd/compile: use depth first topological sort algorithm for layout
The current layout algorithm tries to put consecutive blocks together,
so the priority of the successor block is higher than the priority of
the zero indegree block. This algorithm is beneficial for subsequent
register allocation, but will result in more branch instructions.
The depth-first topological sorting algorithm is a well-known layout
algorithm, which has applications in many languages, and it helps to
reduce branch instructions. This CL applies it to the layout pass.
The test results show that it helps to reduce the code size.
This CL also includes the following changes:
1, Removed the primary predecessor mechanism. The new layout algorithm is
  not very friendly to register allocator in some cases, in order to adapt
  to the new layout algorithm, a new primary predecessor selection strategy
  is introduced.
2, Since the new layout implementation may place non-loop blocks between
  loop blocks, some adaptive modifications have also been made to looprotate
  pass.
3, The layout also affects the results of codegen, so this CL also adjusted
  several codegen tests accordingly.
It is inevitable that this CL will cause the code size or performance of a
few functions to decrease, but the number of cases it improves is much larger
than the number of cases it drops.
Statistical data from compilecmp on linux/amd64 is as follow:
name                      old time/op       new time/op       delta
Template                        382ms ± 4%        382ms ± 4%    ~     (p=0.497 n=49+50)
Unicode                         170ms ± 9%        169ms ± 8%    ~     (p=0.344 n=48+50)
GoTypes                         2.01s ± 4%        2.01s ± 4%    ~     (p=0.628 n=50+48)
Compiler                        190ms ±10%        189ms ± 9%    ~     (p=0.734 n=50+50)
SSA                             11.8s ± 2%        11.8s ± 3%    ~     (p=0.877 n=50+50)
Flate                           241ms ± 9%        241ms ± 8%    ~     (p=0.897 n=50+49)
GoParser                        366ms ± 3%        361ms ± 4%  -1.21%  (p=0.004 n=47+50)
Reflect                         835ms ± 3%        838ms ± 3%    ~     (p=0.275 n=50+49)
Tar                             336ms ± 4%        335ms ± 3%    ~     (p=0.454 n=48+48)
XML                             433ms ± 4%        431ms ± 3%    ~     (p=0.071 n=49+48)
LinkCompiler                    706ms ± 4%        705ms ± 4%    ~     (p=0.608 n=50+49)
ExternalLinkCompiler            1.85s ± 3%        1.83s ± 2%  -1.47%  (p=0.000 n=49+48)
LinkWithoutDebugCompiler        437ms ± 5%        437ms ± 6%    ~     (p=0.953 n=49+50)
[Geo mean]                      615ms             613ms       -0.37%
name                      old alloc/op      new alloc/op      delta
Template                       38.7MB ± 1%       38.7MB ± 1%    ~     (p=0.834 n=50+50)
Unicode                        28.1MB ± 0%       28.1MB ± 0%  -0.22%  (p=0.000 n=49+50)
GoTypes                         168MB ± 1%        168MB ± 1%    ~     (p=0.054 n=47+47)
Compiler                       23.0MB ± 1%       23.0MB ± 1%    ~     (p=0.432 n=50+50)
SSA                            1.54GB ± 0%       1.54GB ± 0%  +0.21%  (p=0.000 n=50+50)
Flate                          23.6MB ± 1%       23.6MB ± 1%    ~     (p=0.153 n=43+46)
GoParser                       35.1MB ± 1%       35.1MB ± 2%    ~     (p=0.202 n=50+50)
Reflect                        84.7MB ± 1%       84.7MB ± 1%    ~     (p=0.333 n=48+49)
Tar                            34.5MB ± 1%       34.5MB ± 1%    ~     (p=0.406 n=46+49)
XML                            44.3MB ± 2%       44.2MB ± 3%    ~     (p=0.981 n=50+50)
LinkCompiler                    131MB ± 0%        128MB ± 0%  -2.74%  (p=0.000 n=50+50)
ExternalLinkCompiler            120MB ± 0%        120MB ± 0%  +0.01%  (p=0.007 n=50+50)
LinkWithoutDebugCompiler       77.3MB ± 0%       77.3MB ± 0%  -0.02%  (p=0.000 n=50+50)
[Geo mean]                     69.3MB            69.1MB       -0.22%
file      before    after     Δ        %
addr2line 4104220   4043684   -60536   -1.475%
api       5342502   5249678   -92824   -1.737%
asm       4973785   4858257   -115528  -2.323%
buildid   2667844   2625660   -42184   -1.581%
cgo       4686849   4616313   -70536   -1.505%
compile   23667431  23268406  -399025  -1.686%
cover     4959676   4874108   -85568   -1.725%
dist      3515934   3450422   -65512   -1.863%
doc       3995581   3925469   -70112   -1.755%
fix       3379202   3318522   -60680   -1.796%
link      6743249   6629913   -113336  -1.681%
nm        4047529   3991777   -55752   -1.377%
objdump   4456151   4388151   -68000   -1.526%
pack      2435040   2398072   -36968   -1.518%
pprof     13804080  13565808  -238272  -1.726%
test2json 2690043   2645987   -44056   -1.638%
trace     10418492  10232716  -185776  -1.783%
vet       7258259   7121259   -137000  -1.888%
total     113145867 111204202 -1941665 -1.716%
The situation on linux/arm64 is as follow:
name                      old time/op       new time/op       delta
Template                        280ms ± 1%        282ms ± 1%  +0.75%  (p=0.000 n=46+48)
Unicode                         124ms ± 2%        124ms ± 2%  +0.37%  (p=0.045 n=50+50)
GoTypes                         1.69s ± 1%        1.70s ± 1%  +0.56%  (p=0.000 n=49+50)
Compiler                        122ms ± 1%        123ms ± 1%  +0.93%  (p=0.000 n=50+50)
SSA                             12.6s ± 1%        12.7s ± 0%  +0.72%  (p=0.000 n=50+50)
Flate                           170ms ± 1%        172ms ± 1%  +0.97%  (p=0.000 n=49+49)
GoParser                        262ms ± 1%        263ms ± 1%  +0.39%  (p=0.000 n=49+48)
Reflect                         639ms ± 1%        650ms ± 1%  +1.63%  (p=0.000 n=49+49)
Tar                             243ms ± 1%        245ms ± 1%  +0.82%  (p=0.000 n=50+50)
XML                             324ms ± 1%        327ms ± 1%  +0.72%  (p=0.000 n=50+49)
LinkCompiler                    597ms ± 1%        596ms ± 1%  -0.27%  (p=0.001 n=48+47)
ExternalLinkCompiler            1.90s ± 1%        1.88s ± 1%  -1.00%  (p=0.000 n=50+50)
LinkWithoutDebugCompiler        364ms ± 1%        363ms ± 1%    ~     (p=0.220 n=49+50)
[Geo mean]                      485ms             488ms       +0.49%
name                      old alloc/op      new alloc/op      delta
Template                       38.7MB ± 0%       38.8MB ± 1%    ~     (p=0.093 n=43+49)
Unicode                        28.4MB ± 0%       28.4MB ± 0%  +0.03%  (p=0.000 n=49+45)
GoTypes                         169MB ± 1%        169MB ± 1%  +0.23%  (p=0.010 n=50+50)
Compiler                       23.2MB ± 1%       23.2MB ± 1%  +0.11%  (p=0.000 n=40+44)
SSA                            1.54GB ± 0%       1.55GB ± 0%  +0.45%  (p=0.000 n=47+49)
Flate                          23.8MB ± 2%       23.8MB ± 1%    ~     (p=0.543 n=50+50)
GoParser                       35.3MB ± 1%       35.4MB ± 1%    ~     (p=0.792 n=50+50)
Reflect                        85.2MB ± 1%       85.2MB ± 0%    ~     (p=0.055 n=50+47)
Tar                            34.5MB ± 1%       34.5MB ± 1%  +0.06%  (p=0.015 n=50+50)
XML                            43.8MB ± 2%       43.9MB ± 2%  +0.19%  (p=0.000 n=48+48)
LinkCompiler                    137MB ± 0%        136MB ± 0%  -0.92%  (p=0.000 n=50+50)
ExternalLinkCompiler            127MB ± 0%        127MB ± 0%    ~     (p=0.516 n=50+50)
LinkWithoutDebugCompiler       84.0MB ± 0%       84.0MB ± 0%    ~     (p=0.057 n=50+50)
[Geo mean]                     70.4MB            70.4MB       +0.01%
file      before    after     Δ        %
addr2line 4021557   4002933   -18624   -0.463%
api       5127847   5028503   -99344   -1.937%
asm       5034716   4936836   -97880   -1.944%
buildid   2608118   2594094   -14024   -0.538%
cgo       4488592   4398320   -90272   -2.011%
compile   22501129  22213592  -287537  -1.278%
cover     4742301   4713573   -28728   -0.606%
dist      3388071   3365311   -22760   -0.672%
doc       3802250   3776082   -26168   -0.688%
fix       3306147   3216939   -89208   -2.698%
link      6404483   6363699   -40784   -0.637%
nm        3941026   3921930   -19096   -0.485%
objdump   4383330   4295122   -88208   -2.012%
pack      2404547   2389515   -15032   -0.625%
pprof     12996234  12856818  -139416  -1.073%
test2json 2668500   2586788   -81712   -3.062%
trace     9816276   9609580   -206696  -2.106%
vet       6900682   6787338   -113344  -1.643%
total     108535806 107056973 -1478833 -1.363%
Change-Id: Iaec1cdcaacca8025e9babb0fb8a532fddb70c87d
Reviewed-on: https://go-review.googlesource.com/c/go/+/255239
Reviewed-by: eric fang <eric.fang@arm.com>
Reviewed-by: Keith Randall <khr@golang.org>
Trust: eric fang <eric.fang@arm.com>
											
										 
											2020-07-23 10:24:56 +08:00
										 |  |  | 	// arm64: `(CBN?ZW)`, `(CBN?Z[^W])`, -`(CMPW|CMP|BHI|BLS)` | 
					
						
							| 
									
										
										
										
											2020-07-10 11:39:23 +08:00
										 |  |  | 	if a <= 0 || b <= 0 || c <= 0 || d <= 0 { | 
					
						
							|  |  |  | 		return 1 | 
					
						
							|  |  |  | 	} | 
					
						
							|  |  |  | 	return 0 | 
					
						
							|  |  |  | } | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | func UintLtOne(a uint8, b uint16, c uint32, d uint64) int { | 
					
						
							| 
									
										
											  
											
												cmd/compile: use depth first topological sort algorithm for layout
The current layout algorithm tries to put consecutive blocks together,
so the priority of the successor block is higher than the priority of
the zero indegree block. This algorithm is beneficial for subsequent
register allocation, but will result in more branch instructions.
The depth-first topological sorting algorithm is a well-known layout
algorithm, which has applications in many languages, and it helps to
reduce branch instructions. This CL applies it to the layout pass.
The test results show that it helps to reduce the code size.
This CL also includes the following changes:
1, Removed the primary predecessor mechanism. The new layout algorithm is
  not very friendly to register allocator in some cases, in order to adapt
  to the new layout algorithm, a new primary predecessor selection strategy
  is introduced.
2, Since the new layout implementation may place non-loop blocks between
  loop blocks, some adaptive modifications have also been made to looprotate
  pass.
3, The layout also affects the results of codegen, so this CL also adjusted
  several codegen tests accordingly.
It is inevitable that this CL will cause the code size or performance of a
few functions to decrease, but the number of cases it improves is much larger
than the number of cases it drops.
Statistical data from compilecmp on linux/amd64 is as follow:
name                      old time/op       new time/op       delta
Template                        382ms ± 4%        382ms ± 4%    ~     (p=0.497 n=49+50)
Unicode                         170ms ± 9%        169ms ± 8%    ~     (p=0.344 n=48+50)
GoTypes                         2.01s ± 4%        2.01s ± 4%    ~     (p=0.628 n=50+48)
Compiler                        190ms ±10%        189ms ± 9%    ~     (p=0.734 n=50+50)
SSA                             11.8s ± 2%        11.8s ± 3%    ~     (p=0.877 n=50+50)
Flate                           241ms ± 9%        241ms ± 8%    ~     (p=0.897 n=50+49)
GoParser                        366ms ± 3%        361ms ± 4%  -1.21%  (p=0.004 n=47+50)
Reflect                         835ms ± 3%        838ms ± 3%    ~     (p=0.275 n=50+49)
Tar                             336ms ± 4%        335ms ± 3%    ~     (p=0.454 n=48+48)
XML                             433ms ± 4%        431ms ± 3%    ~     (p=0.071 n=49+48)
LinkCompiler                    706ms ± 4%        705ms ± 4%    ~     (p=0.608 n=50+49)
ExternalLinkCompiler            1.85s ± 3%        1.83s ± 2%  -1.47%  (p=0.000 n=49+48)
LinkWithoutDebugCompiler        437ms ± 5%        437ms ± 6%    ~     (p=0.953 n=49+50)
[Geo mean]                      615ms             613ms       -0.37%
name                      old alloc/op      new alloc/op      delta
Template                       38.7MB ± 1%       38.7MB ± 1%    ~     (p=0.834 n=50+50)
Unicode                        28.1MB ± 0%       28.1MB ± 0%  -0.22%  (p=0.000 n=49+50)
GoTypes                         168MB ± 1%        168MB ± 1%    ~     (p=0.054 n=47+47)
Compiler                       23.0MB ± 1%       23.0MB ± 1%    ~     (p=0.432 n=50+50)
SSA                            1.54GB ± 0%       1.54GB ± 0%  +0.21%  (p=0.000 n=50+50)
Flate                          23.6MB ± 1%       23.6MB ± 1%    ~     (p=0.153 n=43+46)
GoParser                       35.1MB ± 1%       35.1MB ± 2%    ~     (p=0.202 n=50+50)
Reflect                        84.7MB ± 1%       84.7MB ± 1%    ~     (p=0.333 n=48+49)
Tar                            34.5MB ± 1%       34.5MB ± 1%    ~     (p=0.406 n=46+49)
XML                            44.3MB ± 2%       44.2MB ± 3%    ~     (p=0.981 n=50+50)
LinkCompiler                    131MB ± 0%        128MB ± 0%  -2.74%  (p=0.000 n=50+50)
ExternalLinkCompiler            120MB ± 0%        120MB ± 0%  +0.01%  (p=0.007 n=50+50)
LinkWithoutDebugCompiler       77.3MB ± 0%       77.3MB ± 0%  -0.02%  (p=0.000 n=50+50)
[Geo mean]                     69.3MB            69.1MB       -0.22%
file      before    after     Δ        %
addr2line 4104220   4043684   -60536   -1.475%
api       5342502   5249678   -92824   -1.737%
asm       4973785   4858257   -115528  -2.323%
buildid   2667844   2625660   -42184   -1.581%
cgo       4686849   4616313   -70536   -1.505%
compile   23667431  23268406  -399025  -1.686%
cover     4959676   4874108   -85568   -1.725%
dist      3515934   3450422   -65512   -1.863%
doc       3995581   3925469   -70112   -1.755%
fix       3379202   3318522   -60680   -1.796%
link      6743249   6629913   -113336  -1.681%
nm        4047529   3991777   -55752   -1.377%
objdump   4456151   4388151   -68000   -1.526%
pack      2435040   2398072   -36968   -1.518%
pprof     13804080  13565808  -238272  -1.726%
test2json 2690043   2645987   -44056   -1.638%
trace     10418492  10232716  -185776  -1.783%
vet       7258259   7121259   -137000  -1.888%
total     113145867 111204202 -1941665 -1.716%
The situation on linux/arm64 is as follow:
name                      old time/op       new time/op       delta
Template                        280ms ± 1%        282ms ± 1%  +0.75%  (p=0.000 n=46+48)
Unicode                         124ms ± 2%        124ms ± 2%  +0.37%  (p=0.045 n=50+50)
GoTypes                         1.69s ± 1%        1.70s ± 1%  +0.56%  (p=0.000 n=49+50)
Compiler                        122ms ± 1%        123ms ± 1%  +0.93%  (p=0.000 n=50+50)
SSA                             12.6s ± 1%        12.7s ± 0%  +0.72%  (p=0.000 n=50+50)
Flate                           170ms ± 1%        172ms ± 1%  +0.97%  (p=0.000 n=49+49)
GoParser                        262ms ± 1%        263ms ± 1%  +0.39%  (p=0.000 n=49+48)
Reflect                         639ms ± 1%        650ms ± 1%  +1.63%  (p=0.000 n=49+49)
Tar                             243ms ± 1%        245ms ± 1%  +0.82%  (p=0.000 n=50+50)
XML                             324ms ± 1%        327ms ± 1%  +0.72%  (p=0.000 n=50+49)
LinkCompiler                    597ms ± 1%        596ms ± 1%  -0.27%  (p=0.001 n=48+47)
ExternalLinkCompiler            1.90s ± 1%        1.88s ± 1%  -1.00%  (p=0.000 n=50+50)
LinkWithoutDebugCompiler        364ms ± 1%        363ms ± 1%    ~     (p=0.220 n=49+50)
[Geo mean]                      485ms             488ms       +0.49%
name                      old alloc/op      new alloc/op      delta
Template                       38.7MB ± 0%       38.8MB ± 1%    ~     (p=0.093 n=43+49)
Unicode                        28.4MB ± 0%       28.4MB ± 0%  +0.03%  (p=0.000 n=49+45)
GoTypes                         169MB ± 1%        169MB ± 1%  +0.23%  (p=0.010 n=50+50)
Compiler                       23.2MB ± 1%       23.2MB ± 1%  +0.11%  (p=0.000 n=40+44)
SSA                            1.54GB ± 0%       1.55GB ± 0%  +0.45%  (p=0.000 n=47+49)
Flate                          23.8MB ± 2%       23.8MB ± 1%    ~     (p=0.543 n=50+50)
GoParser                       35.3MB ± 1%       35.4MB ± 1%    ~     (p=0.792 n=50+50)
Reflect                        85.2MB ± 1%       85.2MB ± 0%    ~     (p=0.055 n=50+47)
Tar                            34.5MB ± 1%       34.5MB ± 1%  +0.06%  (p=0.015 n=50+50)
XML                            43.8MB ± 2%       43.9MB ± 2%  +0.19%  (p=0.000 n=48+48)
LinkCompiler                    137MB ± 0%        136MB ± 0%  -0.92%  (p=0.000 n=50+50)
ExternalLinkCompiler            127MB ± 0%        127MB ± 0%    ~     (p=0.516 n=50+50)
LinkWithoutDebugCompiler       84.0MB ± 0%       84.0MB ± 0%    ~     (p=0.057 n=50+50)
[Geo mean]                     70.4MB            70.4MB       +0.01%
file      before    after     Δ        %
addr2line 4021557   4002933   -18624   -0.463%
api       5127847   5028503   -99344   -1.937%
asm       5034716   4936836   -97880   -1.944%
buildid   2608118   2594094   -14024   -0.538%
cgo       4488592   4398320   -90272   -2.011%
compile   22501129  22213592  -287537  -1.278%
cover     4742301   4713573   -28728   -0.606%
dist      3388071   3365311   -22760   -0.672%
doc       3802250   3776082   -26168   -0.688%
fix       3306147   3216939   -89208   -2.698%
link      6404483   6363699   -40784   -0.637%
nm        3941026   3921930   -19096   -0.485%
objdump   4383330   4295122   -88208   -2.012%
pack      2404547   2389515   -15032   -0.625%
pprof     12996234  12856818  -139416  -1.073%
test2json 2668500   2586788   -81712   -3.062%
trace     9816276   9609580   -206696  -2.106%
vet       6900682   6787338   -113344  -1.643%
total     108535806 107056973 -1478833 -1.363%
Change-Id: Iaec1cdcaacca8025e9babb0fb8a532fddb70c87d
Reviewed-on: https://go-review.googlesource.com/c/go/+/255239
Reviewed-by: eric fang <eric.fang@arm.com>
Reviewed-by: Keith Randall <khr@golang.org>
Trust: eric fang <eric.fang@arm.com>
											
										 
											2020-07-23 10:24:56 +08:00
										 |  |  | 	// arm64: `(CBN?ZW)`, `(CBN?Z[^W])`, -`(CMPW|CMP|BHS|BLO)` | 
					
						
							| 
									
										
										
										
											2020-07-10 11:39:23 +08:00
										 |  |  | 	if a < 1 || b < 1 || c < 1 || d < 1 { | 
					
						
							|  |  |  | 		return 1 | 
					
						
							|  |  |  | 	} | 
					
						
							|  |  |  | 	return 0 | 
					
						
							|  |  |  | } | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | func UintGeqOne(a uint8, b uint16, c uint32, d uint64) int { | 
					
						
							| 
									
										
											  
											
												cmd/compile: use depth first topological sort algorithm for layout
The current layout algorithm tries to put consecutive blocks together,
so the priority of the successor block is higher than the priority of
the zero indegree block. This algorithm is beneficial for subsequent
register allocation, but will result in more branch instructions.
The depth-first topological sorting algorithm is a well-known layout
algorithm, which has applications in many languages, and it helps to
reduce branch instructions. This CL applies it to the layout pass.
The test results show that it helps to reduce the code size.
This CL also includes the following changes:
1, Removed the primary predecessor mechanism. The new layout algorithm is
  not very friendly to register allocator in some cases, in order to adapt
  to the new layout algorithm, a new primary predecessor selection strategy
  is introduced.
2, Since the new layout implementation may place non-loop blocks between
  loop blocks, some adaptive modifications have also been made to looprotate
  pass.
3, The layout also affects the results of codegen, so this CL also adjusted
  several codegen tests accordingly.
It is inevitable that this CL will cause the code size or performance of a
few functions to decrease, but the number of cases it improves is much larger
than the number of cases it drops.
Statistical data from compilecmp on linux/amd64 is as follow:
name                      old time/op       new time/op       delta
Template                        382ms ± 4%        382ms ± 4%    ~     (p=0.497 n=49+50)
Unicode                         170ms ± 9%        169ms ± 8%    ~     (p=0.344 n=48+50)
GoTypes                         2.01s ± 4%        2.01s ± 4%    ~     (p=0.628 n=50+48)
Compiler                        190ms ±10%        189ms ± 9%    ~     (p=0.734 n=50+50)
SSA                             11.8s ± 2%        11.8s ± 3%    ~     (p=0.877 n=50+50)
Flate                           241ms ± 9%        241ms ± 8%    ~     (p=0.897 n=50+49)
GoParser                        366ms ± 3%        361ms ± 4%  -1.21%  (p=0.004 n=47+50)
Reflect                         835ms ± 3%        838ms ± 3%    ~     (p=0.275 n=50+49)
Tar                             336ms ± 4%        335ms ± 3%    ~     (p=0.454 n=48+48)
XML                             433ms ± 4%        431ms ± 3%    ~     (p=0.071 n=49+48)
LinkCompiler                    706ms ± 4%        705ms ± 4%    ~     (p=0.608 n=50+49)
ExternalLinkCompiler            1.85s ± 3%        1.83s ± 2%  -1.47%  (p=0.000 n=49+48)
LinkWithoutDebugCompiler        437ms ± 5%        437ms ± 6%    ~     (p=0.953 n=49+50)
[Geo mean]                      615ms             613ms       -0.37%
name                      old alloc/op      new alloc/op      delta
Template                       38.7MB ± 1%       38.7MB ± 1%    ~     (p=0.834 n=50+50)
Unicode                        28.1MB ± 0%       28.1MB ± 0%  -0.22%  (p=0.000 n=49+50)
GoTypes                         168MB ± 1%        168MB ± 1%    ~     (p=0.054 n=47+47)
Compiler                       23.0MB ± 1%       23.0MB ± 1%    ~     (p=0.432 n=50+50)
SSA                            1.54GB ± 0%       1.54GB ± 0%  +0.21%  (p=0.000 n=50+50)
Flate                          23.6MB ± 1%       23.6MB ± 1%    ~     (p=0.153 n=43+46)
GoParser                       35.1MB ± 1%       35.1MB ± 2%    ~     (p=0.202 n=50+50)
Reflect                        84.7MB ± 1%       84.7MB ± 1%    ~     (p=0.333 n=48+49)
Tar                            34.5MB ± 1%       34.5MB ± 1%    ~     (p=0.406 n=46+49)
XML                            44.3MB ± 2%       44.2MB ± 3%    ~     (p=0.981 n=50+50)
LinkCompiler                    131MB ± 0%        128MB ± 0%  -2.74%  (p=0.000 n=50+50)
ExternalLinkCompiler            120MB ± 0%        120MB ± 0%  +0.01%  (p=0.007 n=50+50)
LinkWithoutDebugCompiler       77.3MB ± 0%       77.3MB ± 0%  -0.02%  (p=0.000 n=50+50)
[Geo mean]                     69.3MB            69.1MB       -0.22%
file      before    after     Δ        %
addr2line 4104220   4043684   -60536   -1.475%
api       5342502   5249678   -92824   -1.737%
asm       4973785   4858257   -115528  -2.323%
buildid   2667844   2625660   -42184   -1.581%
cgo       4686849   4616313   -70536   -1.505%
compile   23667431  23268406  -399025  -1.686%
cover     4959676   4874108   -85568   -1.725%
dist      3515934   3450422   -65512   -1.863%
doc       3995581   3925469   -70112   -1.755%
fix       3379202   3318522   -60680   -1.796%
link      6743249   6629913   -113336  -1.681%
nm        4047529   3991777   -55752   -1.377%
objdump   4456151   4388151   -68000   -1.526%
pack      2435040   2398072   -36968   -1.518%
pprof     13804080  13565808  -238272  -1.726%
test2json 2690043   2645987   -44056   -1.638%
trace     10418492  10232716  -185776  -1.783%
vet       7258259   7121259   -137000  -1.888%
total     113145867 111204202 -1941665 -1.716%
The situation on linux/arm64 is as follow:
name                      old time/op       new time/op       delta
Template                        280ms ± 1%        282ms ± 1%  +0.75%  (p=0.000 n=46+48)
Unicode                         124ms ± 2%        124ms ± 2%  +0.37%  (p=0.045 n=50+50)
GoTypes                         1.69s ± 1%        1.70s ± 1%  +0.56%  (p=0.000 n=49+50)
Compiler                        122ms ± 1%        123ms ± 1%  +0.93%  (p=0.000 n=50+50)
SSA                             12.6s ± 1%        12.7s ± 0%  +0.72%  (p=0.000 n=50+50)
Flate                           170ms ± 1%        172ms ± 1%  +0.97%  (p=0.000 n=49+49)
GoParser                        262ms ± 1%        263ms ± 1%  +0.39%  (p=0.000 n=49+48)
Reflect                         639ms ± 1%        650ms ± 1%  +1.63%  (p=0.000 n=49+49)
Tar                             243ms ± 1%        245ms ± 1%  +0.82%  (p=0.000 n=50+50)
XML                             324ms ± 1%        327ms ± 1%  +0.72%  (p=0.000 n=50+49)
LinkCompiler                    597ms ± 1%        596ms ± 1%  -0.27%  (p=0.001 n=48+47)
ExternalLinkCompiler            1.90s ± 1%        1.88s ± 1%  -1.00%  (p=0.000 n=50+50)
LinkWithoutDebugCompiler        364ms ± 1%        363ms ± 1%    ~     (p=0.220 n=49+50)
[Geo mean]                      485ms             488ms       +0.49%
name                      old alloc/op      new alloc/op      delta
Template                       38.7MB ± 0%       38.8MB ± 1%    ~     (p=0.093 n=43+49)
Unicode                        28.4MB ± 0%       28.4MB ± 0%  +0.03%  (p=0.000 n=49+45)
GoTypes                         169MB ± 1%        169MB ± 1%  +0.23%  (p=0.010 n=50+50)
Compiler                       23.2MB ± 1%       23.2MB ± 1%  +0.11%  (p=0.000 n=40+44)
SSA                            1.54GB ± 0%       1.55GB ± 0%  +0.45%  (p=0.000 n=47+49)
Flate                          23.8MB ± 2%       23.8MB ± 1%    ~     (p=0.543 n=50+50)
GoParser                       35.3MB ± 1%       35.4MB ± 1%    ~     (p=0.792 n=50+50)
Reflect                        85.2MB ± 1%       85.2MB ± 0%    ~     (p=0.055 n=50+47)
Tar                            34.5MB ± 1%       34.5MB ± 1%  +0.06%  (p=0.015 n=50+50)
XML                            43.8MB ± 2%       43.9MB ± 2%  +0.19%  (p=0.000 n=48+48)
LinkCompiler                    137MB ± 0%        136MB ± 0%  -0.92%  (p=0.000 n=50+50)
ExternalLinkCompiler            127MB ± 0%        127MB ± 0%    ~     (p=0.516 n=50+50)
LinkWithoutDebugCompiler       84.0MB ± 0%       84.0MB ± 0%    ~     (p=0.057 n=50+50)
[Geo mean]                     70.4MB            70.4MB       +0.01%
file      before    after     Δ        %
addr2line 4021557   4002933   -18624   -0.463%
api       5127847   5028503   -99344   -1.937%
asm       5034716   4936836   -97880   -1.944%
buildid   2608118   2594094   -14024   -0.538%
cgo       4488592   4398320   -90272   -2.011%
compile   22501129  22213592  -287537  -1.278%
cover     4742301   4713573   -28728   -0.606%
dist      3388071   3365311   -22760   -0.672%
doc       3802250   3776082   -26168   -0.688%
fix       3306147   3216939   -89208   -2.698%
link      6404483   6363699   -40784   -0.637%
nm        3941026   3921930   -19096   -0.485%
objdump   4383330   4295122   -88208   -2.012%
pack      2404547   2389515   -15032   -0.625%
pprof     12996234  12856818  -139416  -1.073%
test2json 2668500   2586788   -81712   -3.062%
trace     9816276   9609580   -206696  -2.106%
vet       6900682   6787338   -113344  -1.643%
total     108535806 107056973 -1478833 -1.363%
Change-Id: Iaec1cdcaacca8025e9babb0fb8a532fddb70c87d
Reviewed-on: https://go-review.googlesource.com/c/go/+/255239
Reviewed-by: eric fang <eric.fang@arm.com>
Reviewed-by: Keith Randall <khr@golang.org>
Trust: eric fang <eric.fang@arm.com>
											
										 
											2020-07-23 10:24:56 +08:00
										 |  |  | 	// arm64: `(CBN?ZW)`, `(CBN?Z[^W])`, -`(CMPW|CMP|BLO|BHS)` | 
					
						
							| 
									
										
										
										
											2020-07-10 11:39:23 +08:00
										 |  |  | 	if a >= 1 || b >= 1 || c >= 1 || d >= 1 { | 
					
						
							|  |  |  | 		return 1 | 
					
						
							|  |  |  | 	} | 
					
						
							|  |  |  | 	return 0 | 
					
						
							|  |  |  | } | 
					
						
							| 
									
										
										
										
											2020-08-08 15:19:42 +05:30
										 |  |  | 
 | 
					
						
							|  |  |  | func CmpToZeroU_ex1(a uint8, b uint16, c uint32, d uint64) int { | 
					
						
							|  |  |  | 	// wasm:"I64Eqz"-"I64LtU" | 
					
						
							|  |  |  | 	if 0 < a { | 
					
						
							|  |  |  | 		return 1 | 
					
						
							|  |  |  | 	} | 
					
						
							|  |  |  | 	// wasm:"I64Eqz"-"I64LtU" | 
					
						
							|  |  |  | 	if 0 < b { | 
					
						
							|  |  |  | 		return 1 | 
					
						
							|  |  |  | 	} | 
					
						
							|  |  |  | 	// wasm:"I64Eqz"-"I64LtU" | 
					
						
							|  |  |  | 	if 0 < c { | 
					
						
							|  |  |  | 		return 1 | 
					
						
							|  |  |  | 	} | 
					
						
							|  |  |  | 	// wasm:"I64Eqz"-"I64LtU" | 
					
						
							|  |  |  | 	if 0 < d { | 
					
						
							|  |  |  | 		return 1 | 
					
						
							|  |  |  | 	} | 
					
						
							|  |  |  | 	return 0 | 
					
						
							|  |  |  | } | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | func CmpToZeroU_ex2(a uint8, b uint16, c uint32, d uint64) int { | 
					
						
							|  |  |  | 	// wasm:"I64Eqz"-"I64LeU" | 
					
						
							|  |  |  | 	if a <= 0 { | 
					
						
							|  |  |  | 		return 1 | 
					
						
							|  |  |  | 	} | 
					
						
							|  |  |  | 	// wasm:"I64Eqz"-"I64LeU" | 
					
						
							|  |  |  | 	if b <= 0 { | 
					
						
							|  |  |  | 		return 1 | 
					
						
							|  |  |  | 	} | 
					
						
							|  |  |  | 	// wasm:"I64Eqz"-"I64LeU" | 
					
						
							|  |  |  | 	if c <= 0 { | 
					
						
							|  |  |  | 		return 1 | 
					
						
							|  |  |  | 	} | 
					
						
							|  |  |  | 	// wasm:"I64Eqz"-"I64LeU" | 
					
						
							|  |  |  | 	if d <= 0 { | 
					
						
							|  |  |  | 		return 1 | 
					
						
							|  |  |  | 	} | 
					
						
							|  |  |  | 	return 0 | 
					
						
							|  |  |  | } | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | func CmpToOneU_ex1(a uint8, b uint16, c uint32, d uint64) int { | 
					
						
							|  |  |  | 	// wasm:"I64Eqz"-"I64LtU" | 
					
						
							|  |  |  | 	if a < 1 { | 
					
						
							|  |  |  | 		return 1 | 
					
						
							|  |  |  | 	} | 
					
						
							|  |  |  | 	// wasm:"I64Eqz"-"I64LtU" | 
					
						
							|  |  |  | 	if b < 1 { | 
					
						
							|  |  |  | 		return 1 | 
					
						
							|  |  |  | 	} | 
					
						
							|  |  |  | 	// wasm:"I64Eqz"-"I64LtU" | 
					
						
							|  |  |  | 	if c < 1 { | 
					
						
							|  |  |  | 		return 1 | 
					
						
							|  |  |  | 	} | 
					
						
							|  |  |  | 	// wasm:"I64Eqz"-"I64LtU" | 
					
						
							|  |  |  | 	if d < 1 { | 
					
						
							|  |  |  | 		return 1 | 
					
						
							|  |  |  | 	} | 
					
						
							|  |  |  | 	return 0 | 
					
						
							|  |  |  | } | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | func CmpToOneU_ex2(a uint8, b uint16, c uint32, d uint64) int { | 
					
						
							|  |  |  | 	// wasm:"I64Eqz"-"I64LeU" | 
					
						
							|  |  |  | 	if 1 <= a { | 
					
						
							|  |  |  | 		return 1 | 
					
						
							|  |  |  | 	} | 
					
						
							|  |  |  | 	// wasm:"I64Eqz"-"I64LeU" | 
					
						
							|  |  |  | 	if 1 <= b { | 
					
						
							|  |  |  | 		return 1 | 
					
						
							|  |  |  | 	} | 
					
						
							|  |  |  | 	// wasm:"I64Eqz"-"I64LeU" | 
					
						
							|  |  |  | 	if 1 <= c { | 
					
						
							|  |  |  | 		return 1 | 
					
						
							|  |  |  | 	} | 
					
						
							|  |  |  | 	// wasm:"I64Eqz"-"I64LeU" | 
					
						
							|  |  |  | 	if 1 <= d { | 
					
						
							|  |  |  | 		return 1 | 
					
						
							|  |  |  | 	} | 
					
						
							|  |  |  | 	return 0 | 
					
						
							|  |  |  | } | 
					
						
							| 
									
										
										
										
											2021-06-16 16:25:57 +00:00
										 |  |  | 
 | 
					
						
							|  |  |  | // Check that small memequals are replaced with eq instructions | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | func equalConstString1() bool { | 
					
						
							|  |  |  | 	a := string("A") | 
					
						
							|  |  |  | 	b := string("Z") | 
					
						
							|  |  |  | 	// amd64:-".*memequal" | 
					
						
							|  |  |  | 	// arm64:-".*memequal" | 
					
						
							| 
									
										
										
										
											2021-10-20 04:11:57 -05:00
										 |  |  | 	// ppc64:-".*memequal" | 
					
						
							|  |  |  | 	// ppc64le:-".*memequal" | 
					
						
							| 
									
										
										
										
											2021-06-16 16:25:57 +00:00
										 |  |  | 	return a == b | 
					
						
							|  |  |  | } | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | func equalVarString1(a string) bool { | 
					
						
							|  |  |  | 	b := string("Z") | 
					
						
							|  |  |  | 	// amd64:-".*memequal" | 
					
						
							|  |  |  | 	// arm64:-".*memequal" | 
					
						
							| 
									
										
										
										
											2021-10-20 04:11:57 -05:00
										 |  |  | 	// ppc64:-".*memequal" | 
					
						
							|  |  |  | 	// ppc64le:-".*memequal" | 
					
						
							| 
									
										
										
										
											2021-06-16 16:25:57 +00:00
										 |  |  | 	return a[:1] == b | 
					
						
							|  |  |  | } | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | func equalConstString2() bool { | 
					
						
							|  |  |  | 	a := string("AA") | 
					
						
							|  |  |  | 	b := string("ZZ") | 
					
						
							|  |  |  | 	// amd64:-".*memequal" | 
					
						
							|  |  |  | 	// arm64:-".*memequal" | 
					
						
							| 
									
										
										
										
											2021-10-20 04:11:57 -05:00
										 |  |  | 	// ppc64:-".*memequal" | 
					
						
							|  |  |  | 	// ppc64le:-".*memequal" | 
					
						
							| 
									
										
										
										
											2021-06-16 16:25:57 +00:00
										 |  |  | 	return a == b | 
					
						
							|  |  |  | } | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | func equalVarString2(a string) bool { | 
					
						
							|  |  |  | 	b := string("ZZ") | 
					
						
							|  |  |  | 	// amd64:-".*memequal" | 
					
						
							|  |  |  | 	// arm64:-".*memequal" | 
					
						
							| 
									
										
										
										
											2021-10-20 04:11:57 -05:00
										 |  |  | 	// ppc64:-".*memequal" | 
					
						
							|  |  |  | 	// ppc64le:-".*memequal" | 
					
						
							| 
									
										
										
										
											2021-06-16 16:25:57 +00:00
										 |  |  | 	return a[:2] == b | 
					
						
							|  |  |  | } | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | func equalConstString4() bool { | 
					
						
							|  |  |  | 	a := string("AAAA") | 
					
						
							|  |  |  | 	b := string("ZZZZ") | 
					
						
							|  |  |  | 	// amd64:-".*memequal" | 
					
						
							|  |  |  | 	// arm64:-".*memequal" | 
					
						
							| 
									
										
										
										
											2021-10-20 04:11:57 -05:00
										 |  |  | 	// ppc64:-".*memequal" | 
					
						
							|  |  |  | 	// ppc64le:-".*memequal" | 
					
						
							| 
									
										
										
										
											2021-06-16 16:25:57 +00:00
										 |  |  | 	return a == b | 
					
						
							|  |  |  | } | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | func equalVarString4(a string) bool { | 
					
						
							|  |  |  | 	b := string("ZZZZ") | 
					
						
							|  |  |  | 	// amd64:-".*memequal" | 
					
						
							|  |  |  | 	// arm64:-".*memequal" | 
					
						
							| 
									
										
										
										
											2021-10-20 04:11:57 -05:00
										 |  |  | 	// ppc64:-".*memequal" | 
					
						
							|  |  |  | 	// ppc64le:-".*memequal" | 
					
						
							| 
									
										
										
										
											2021-06-16 16:25:57 +00:00
										 |  |  | 	return a[:4] == b | 
					
						
							|  |  |  | } | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | func equalConstString8() bool { | 
					
						
							|  |  |  | 	a := string("AAAAAAAA") | 
					
						
							|  |  |  | 	b := string("ZZZZZZZZ") | 
					
						
							|  |  |  | 	// amd64:-".*memequal" | 
					
						
							|  |  |  | 	// arm64:-".*memequal" | 
					
						
							| 
									
										
										
										
											2021-10-20 04:11:57 -05:00
										 |  |  | 	// ppc64:-".*memequal" | 
					
						
							|  |  |  | 	// ppc64le:-".*memequal" | 
					
						
							| 
									
										
										
										
											2021-06-16 16:25:57 +00:00
										 |  |  | 	return a == b | 
					
						
							|  |  |  | } | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | func equalVarString8(a string) bool { | 
					
						
							|  |  |  | 	b := string("ZZZZZZZZ") | 
					
						
							|  |  |  | 	// amd64:-".*memequal" | 
					
						
							|  |  |  | 	// arm64:-".*memequal" | 
					
						
							| 
									
										
										
										
											2021-10-20 04:11:57 -05:00
										 |  |  | 	// ppc64:-".*memequal" | 
					
						
							|  |  |  | 	// ppc64le:-".*memequal" | 
					
						
							| 
									
										
										
										
											2021-06-16 16:25:57 +00:00
										 |  |  | 	return a[:8] == b | 
					
						
							|  |  |  | } | 
					
						
							| 
									
										
										
										
											2022-09-07 08:34:52 +00:00
										 |  |  | 
 | 
					
						
							|  |  |  | func cmpToCmn(a, b, c, d int) int { | 
					
						
							|  |  |  | 	var c1, c2, c3, c4, c5, c6, c7, c8, c9, c10, c11 int | 
					
						
							|  |  |  | 	// arm64:`CMN`,-`CMP` | 
					
						
							|  |  |  | 	if a < -8 { | 
					
						
							|  |  |  | 		c1 = 1 | 
					
						
							|  |  |  | 	} | 
					
						
							|  |  |  | 	// arm64:`CMN`,-`CMP` | 
					
						
							|  |  |  | 	if a+1 == 0 { | 
					
						
							|  |  |  | 		c2 = 1 | 
					
						
							|  |  |  | 	} | 
					
						
							|  |  |  | 	// arm64:`CMN`,-`CMP` | 
					
						
							|  |  |  | 	if a+3 != 0 { | 
					
						
							|  |  |  | 		c3 = 1 | 
					
						
							|  |  |  | 	} | 
					
						
							|  |  |  | 	// arm64:`CMN`,-`CMP` | 
					
						
							|  |  |  | 	if a+b == 0 { | 
					
						
							|  |  |  | 		c4 = 1 | 
					
						
							|  |  |  | 	} | 
					
						
							|  |  |  | 	// arm64:`CMN`,-`CMP` | 
					
						
							|  |  |  | 	if b+c != 0 { | 
					
						
							|  |  |  | 		c5 = 1 | 
					
						
							|  |  |  | 	} | 
					
						
							|  |  |  | 	// arm64:`CMN`,-`CMP` | 
					
						
							|  |  |  | 	if a == -c { | 
					
						
							|  |  |  | 		c6 = 1 | 
					
						
							|  |  |  | 	} | 
					
						
							|  |  |  | 	// arm64:`CMN`,-`CMP` | 
					
						
							|  |  |  | 	if b != -d { | 
					
						
							|  |  |  | 		c7 = 1 | 
					
						
							|  |  |  | 	} | 
					
						
							|  |  |  | 	// arm64:`CMN`,-`CMP` | 
					
						
							|  |  |  | 	if a*b+c == 0 { | 
					
						
							|  |  |  | 		c8 = 1 | 
					
						
							|  |  |  | 	} | 
					
						
							|  |  |  | 	// arm64:`CMN`,-`CMP` | 
					
						
							|  |  |  | 	if a*c+b != 0 { | 
					
						
							|  |  |  | 		c9 = 1 | 
					
						
							|  |  |  | 	} | 
					
						
							|  |  |  | 	// arm64:`CMP`,-`CMN` | 
					
						
							|  |  |  | 	if b*c-a == 0 { | 
					
						
							|  |  |  | 		c10 = 1 | 
					
						
							|  |  |  | 	} | 
					
						
							|  |  |  | 	// arm64:`CMP`,-`CMN` | 
					
						
							|  |  |  | 	if a*d-b != 0 { | 
					
						
							|  |  |  | 		c11 = 1 | 
					
						
							|  |  |  | 	} | 
					
						
							|  |  |  | 	return c1 + c2 + c3 + c4 + c5 + c6 + c7 + c8 + c9 + c10 + c11 | 
					
						
							|  |  |  | } |