Explicitly whitelist args of OpSelect{1|2} that zero upper 32 bits.
Use better values in corresponding test.
This should have been a part of CL 96815, but it was submitted, before
relevant comments.
Change-Id: Ic85d90a4471a17f6d64f8f5c405f21378bf3a30d
Reviewed-on: https://go-review.googlesource.com/97295
Run-TryBot: Ilya Tocar <ilya.tocar@intel.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Keith Randall <khr@golang.org>
Bit-test rules failed to match when matching the highest bit
of a word because operands in SSA are signed int64. Fix
them by treating them as unsigned (and correctly handling
32-bit operands as well).
Tests will be added in next CL.
Change-Id: I491c4e88e7e2f87e9bb72bd0d9fa5d4025b90736
Reviewed-on: https://go-review.googlesource.com/94765
Reviewed-by: Keith Randall <khr@golang.org>
Currently we generate NEGQ for DIV{Q,L,W}. By generating NEGL and NEGW,
we will reduce code size, because NEGL doesn't require rex prefix.
This also guarantees that upper 32 bits are zeroed, so we can revert CL 85736,
and remove zero-extensions of DIVL results.
Also adds test for redundant zero extend elimination.
Fixes#23310
Change-Id: Ic58c3104c255a71371a06e09d10a975bbe5df587
Reviewed-on: https://go-review.googlesource.com/96815
Run-TryBot: Ilya Tocar <ilya.tocar@intel.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Matthew Dempsky <mdempsky@google.com>
A Select Op could produce a value with upper 32 bits NOT zeroed,
for example, Div32 is lowered to (Select0 (DIVL x y)).
In theory, we could look into the argument of a Select to decide
whether the upper bits are zeroed. As it is late in release cycle,
just disable this optimization for Select for now.
Fixes#23305.
Change-Id: Icf665a2af9ccb0a7ba0ae00c683c9e349638bf85
Reviewed-on: https://go-review.googlesource.com/85736
Run-TryBot: Cherry Zhang <cherryyz@google.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Matthew Dempsky <mdempsky@google.com>
Reviewed-by: Ilya Tocar <ilya.tocar@intel.com>
Found a few functions in cmd/compile that aren't used.
Change-Id: I53957dae6f1a645feb8b95383f0f050964b4f7d4
Reviewed-on: https://go-review.googlesource.com/79975
Run-TryBot: Keith Randall <khr@golang.org>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Brad Fitzpatrick <bradfitz@golang.org>
We used to have {Arg,Auto,Extern}Symbol structs with which we wrapped
a *gc.Node or *obj.LSym before storing them in the Aux field
of an ssa.Value. This let the SSA part of the compiler distinguish
between autos and args, for example. We no longer need the wrappers
as we can query the underlying objects directly.
There was also some sloppy usage, where VarDef had a *gc.Node
directly in its Aux field, whereas the use of that variable had
that *gc.Node wrapped in an AutoSymbol. Thus the Aux fields didn't
match (using ==) when they probably should.
This sloppy usage cleanup is the only thing in the CL that changes the
generated code - we can get rid of some more unused auto variables if
the matching happens reliably.
Removing this wrapper also lets us get rid of the varsyms cache
(which was used to prevent wrapping the same *gc.Node twice).
Change-Id: I0dedf8f82f84bfee413d310342b777316bd1d478
Reviewed-on: https://go-review.googlesource.com/64452
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Matthew Dempsky <mdempsky@google.com>
Some instructions operating on <= 32 bits also zero out upper 32bits.
Remove zeroextensions of such values. Triggers a few times during
all.bash. Also removes ugly code like:
MOVL CX,CX
Change-Id: I66a46c190dd6929b7e3c52f3fe6b967768d00638
Reviewed-on: https://go-review.googlesource.com/58090
Run-TryBot: Ilya Tocar <ilya.tocar@intel.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Keith Randall <khr@golang.org>
Add support for generating TBZ/TBNZ instructions.
The bit-test-and-branch pattern shows up in a number of
important places, including the runtime (gc bitmaps).
Before this change, there were 3 TB[N]?Z instructions in the Go tool,
all of which were in hand-written assembly. After this change, there
are 285. Also, the go1 benchmark binary gets about 4.5kB smaller.
Fixes#21361
Change-Id: I170c138b852754b9b8df149966ca5e62e6dfa771
Reviewed-on: https://go-review.googlesource.com/54470
Run-TryBot: Philip Hofer <phofer@umich.edu>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Cherry Zhang <cherryyz@google.com>
Eliminates stores of values that have just been loaded from the same
location. Handles the common case where there are up to 3 intermediate
stores to non-overlapping struct fields.
For example the loads and stores of x.a, x.b and x.d in the following
function are now removed:
type T struct {
a, b, c, d int
}
func f(x *T) {
y := *x
y.c += 8
*x = y
}
Before this CL (s390x):
TEXT "".f(SB)
MOVD "".x(R15), R5
MOVD (R5), R1
MOVD 8(R5), R2
MOVD 16(R5), R0
MOVD 24(R5), R4
ADD $8, R0, R3
STMG R1, R4, (R5)
RET
After this CL (s390x):
TEXT "".f(SB)
MOVD "".x(R15), R1
MOVD 16(R1), R0
ADD $8, R0, R0
MOVD R0, 16(R1)
RET
In total these rules are triggered ~5091 times during all.bash,
which is broken down as:
Intermediate stores | Triggered
--------------------+----------
0 | 1434
1 | 2508
2 | 888
3 | 261
--------------------+----------
Change-Id: Ia4721ae40146aceec1fdd3e65b0e9283770bfba5
Reviewed-on: https://go-review.googlesource.com/38793
Run-TryBot: Michael Munday <munday@ca.ibm.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Keith Randall <khr@golang.org>
When package ssa was created, Type was in package gc.
To avoid circular dependencies, we used an interface (ssa.Type)
to represent type information in SSA.
In the Go 1.9 cycle, gri extricated the Type type from package gc.
As a result, we can now use it in package ssa.
Now, instead of package types depending on package ssa,
it is the other way.
This is a more sensible dependency tree,
and helps compiler performance a bit.
Though this is a big CL, most of the changes are
mechanical and uninteresting.
Interesting bits:
* Add new singleton globals to package types for the special
SSA types Memory, Void, Invalid, Flags, and Int128.
* Add two new Types, TSSA for the special types,
and TTUPLE, for SSA tuple types.
ssa.MakeTuple is now types.NewTuple.
* Move type comparison result constants CMPlt, CMPeq, and CMPgt
to package types.
* We had picked the name "types" in our rules for the handy
list of types provided by ssa.Config. That conflicted with
the types package name, so change it to "typ".
* Update the type comparison routine to handle tuples and special
types inline.
* Teach gc/fmt.go how to print special types.
* We can now eliminate ElemTypes in favor of just Elem,
and probably also some other duplicated Type methods
designed to return ssa.Type instead of *types.Type.
* The ssa tests were using their own dummy types,
and they were not particularly careful about types in general.
Of necessity, this CL switches them to use *types.Type;
it does not make them more type-accurate.
Unfortunately, using types.Type means initializing a bit
of the types universe.
This is prime for refactoring and improvement.
This shrinks ssa.Value; it now fits in a smaller size class
on 64 bit systems. This doesn't have a giant impact,
though, since most Values are preallocated in a chunk.
name old alloc/op new alloc/op delta
Template 37.9MB ± 0% 37.7MB ± 0% -0.57% (p=0.000 n=10+8)
Unicode 28.9MB ± 0% 28.7MB ± 0% -0.52% (p=0.000 n=10+10)
GoTypes 110MB ± 0% 109MB ± 0% -0.88% (p=0.000 n=10+10)
Flate 24.7MB ± 0% 24.6MB ± 0% -0.66% (p=0.000 n=10+10)
GoParser 31.1MB ± 0% 30.9MB ± 0% -0.61% (p=0.000 n=10+9)
Reflect 73.9MB ± 0% 73.4MB ± 0% -0.62% (p=0.000 n=10+8)
Tar 25.8MB ± 0% 25.6MB ± 0% -0.77% (p=0.000 n=9+10)
XML 41.2MB ± 0% 40.9MB ± 0% -0.80% (p=0.000 n=10+10)
[Geo mean] 40.5MB 40.3MB -0.68%
name old allocs/op new allocs/op delta
Template 385k ± 0% 386k ± 0% ~ (p=0.356 n=10+9)
Unicode 343k ± 1% 344k ± 0% ~ (p=0.481 n=10+10)
GoTypes 1.16M ± 0% 1.16M ± 0% -0.16% (p=0.004 n=10+10)
Flate 238k ± 1% 238k ± 1% ~ (p=0.853 n=10+10)
GoParser 320k ± 0% 320k ± 0% ~ (p=0.720 n=10+9)
Reflect 957k ± 0% 957k ± 0% ~ (p=0.460 n=10+8)
Tar 252k ± 0% 252k ± 0% ~ (p=0.133 n=9+10)
XML 400k ± 0% 400k ± 0% ~ (p=0.796 n=10+10)
[Geo mean] 428k 428k -0.01%
Removing all the interface calls helps non-trivially with CPU, though.
name old time/op new time/op delta
Template 178ms ± 4% 173ms ± 3% -2.90% (p=0.000 n=94+96)
Unicode 85.0ms ± 4% 83.9ms ± 4% -1.23% (p=0.000 n=96+96)
GoTypes 543ms ± 3% 528ms ± 3% -2.73% (p=0.000 n=98+96)
Flate 116ms ± 3% 113ms ± 4% -2.34% (p=0.000 n=96+99)
GoParser 144ms ± 3% 140ms ± 4% -2.80% (p=0.000 n=99+97)
Reflect 344ms ± 3% 334ms ± 4% -3.02% (p=0.000 n=100+99)
Tar 106ms ± 5% 103ms ± 4% -3.30% (p=0.000 n=98+94)
XML 198ms ± 5% 192ms ± 4% -2.88% (p=0.000 n=92+95)
[Geo mean] 178ms 173ms -2.65%
name old user-time/op new user-time/op delta
Template 229ms ± 5% 224ms ± 5% -2.36% (p=0.000 n=95+99)
Unicode 107ms ± 6% 106ms ± 5% -1.13% (p=0.001 n=93+95)
GoTypes 696ms ± 4% 679ms ± 4% -2.45% (p=0.000 n=97+99)
Flate 137ms ± 4% 134ms ± 5% -2.66% (p=0.000 n=99+96)
GoParser 176ms ± 5% 172ms ± 8% -2.27% (p=0.000 n=98+100)
Reflect 430ms ± 6% 411ms ± 5% -4.46% (p=0.000 n=100+92)
Tar 128ms ±13% 123ms ±13% -4.21% (p=0.000 n=100+100)
XML 239ms ± 6% 233ms ± 6% -2.50% (p=0.000 n=95+97)
[Geo mean] 220ms 213ms -2.76%
Change-Id: I15c7d6268347f8358e75066dfdbd77db24e8d0c1
Reviewed-on: https://go-review.googlesource.com/42145
Run-TryBot: Josh Bleecher Snyder <josharian@gmail.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Keith Randall <khr@golang.org>
ARM64 assembler backend only accepts loads and stores with small
or aligned offset. The compiler therefore can only fold small or
aligned offsets into loads and stores. For locals and args, their
offsets to SP are not known until very late, and the compiler
makes conservative decision not folding some of them. However,
in most cases, the offset is indeed small or aligned, and can
be folded into load and store (but actually not).
This CL adds support of loads and stores with large and unaligned
offsets. When the offset doesn't fit into the instruction, it
uses two instructions and (for very large offset) the constant
pool. This way, the compiler doesn't need to be conservative,
and can simply fold the offset.
To make it work, the assembler's optab matching rules need to be
changed. Before, MOVD accepts C_UAUTO32K which matches multiple
of 8 between 0 and 32K, and also C_UAUTO16K, which may not be
multiple of 8 and does not fit into MOVD instruction. The
assembler errors in the latter case. This change makes it only
matches multiple of 8 (or offsets within ±256, which also fits
in instruction), and uses the large-or-unaligned-offset rule
for things doesn't fit (without error). Other sized move rules
are changed similarly.
Class C_UAUTO64K and C_UOREG64K are removed, as they are never
used.
In shared library, load/store of global is rewritten to using
GOT and temp register, which conflicts with the use of temp
register for assembling large offset. So the folding is disabled
for globals in shared library mode.
Reduce cmd/go binary size by 2%.
name old time/op new time/op delta
BinaryTree17-8 8.67s ± 0% 8.61s ± 0% -0.60% (p=0.000 n=9+10)
Fannkuch11-8 6.24s ± 0% 6.19s ± 0% -0.83% (p=0.000 n=10+9)
FmtFprintfEmpty-8 116ns ± 0% 116ns ± 0% ~ (all equal)
FmtFprintfString-8 196ns ± 0% 192ns ± 0% -1.89% (p=0.000 n=10+10)
FmtFprintfInt-8 199ns ± 0% 198ns ± 0% -0.35% (p=0.001 n=9+10)
FmtFprintfIntInt-8 294ns ± 0% 293ns ± 0% -0.34% (p=0.000 n=8+8)
FmtFprintfPrefixedInt-8 318ns ± 1% 318ns ± 1% ~ (p=1.000 n=10+10)
FmtFprintfFloat-8 537ns ± 0% 531ns ± 0% -1.17% (p=0.000 n=9+10)
FmtManyArgs-8 1.19µs ± 1% 1.18µs ± 1% -1.41% (p=0.001 n=10+10)
GobDecode-8 17.2ms ± 1% 17.3ms ± 2% ~ (p=0.165 n=10+10)
GobEncode-8 14.7ms ± 1% 14.7ms ± 2% ~ (p=0.631 n=10+10)
Gzip-8 837ms ± 0% 836ms ± 0% -0.14% (p=0.006 n=9+10)
Gunzip-8 141ms ± 0% 139ms ± 0% -1.24% (p=0.000 n=9+10)
HTTPClientServer-8 256µs ± 1% 253µs ± 1% -1.35% (p=0.000 n=10+10)
JSONEncode-8 40.1ms ± 1% 41.3ms ± 1% +3.06% (p=0.000 n=10+9)
JSONDecode-8 157ms ± 1% 156ms ± 1% -0.83% (p=0.001 n=9+8)
Mandelbrot200-8 8.94ms ± 0% 8.94ms ± 0% +0.02% (p=0.000 n=9+9)
GoParse-8 8.69ms ± 0% 8.54ms ± 1% -1.69% (p=0.000 n=8+10)
RegexpMatchEasy0_32-8 227ns ± 1% 228ns ± 1% +0.48% (p=0.016 n=10+9)
RegexpMatchEasy0_1K-8 1.92µs ± 0% 1.63µs ± 0% -15.08% (p=0.000 n=10+9)
RegexpMatchEasy1_32-8 256ns ± 0% 251ns ± 0% -2.19% (p=0.000 n=10+9)
RegexpMatchEasy1_1K-8 2.38µs ± 0% 2.09µs ± 0% -12.49% (p=0.000 n=10+9)
RegexpMatchMedium_32-8 352ns ± 0% 354ns ± 0% +0.39% (p=0.002 n=10+9)
RegexpMatchMedium_1K-8 106µs ± 0% 106µs ± 0% -0.05% (p=0.005 n=10+9)
RegexpMatchHard_32-8 5.92µs ± 0% 5.89µs ± 0% -0.40% (p=0.000 n=9+8)
RegexpMatchHard_1K-8 180µs ± 0% 179µs ± 0% -0.14% (p=0.000 n=10+9)
Revcomp-8 1.20s ± 0% 1.13s ± 0% -6.29% (p=0.000 n=9+8)
Template-8 159ms ± 1% 154ms ± 1% -3.14% (p=0.000 n=9+10)
TimeParse-8 800ns ± 3% 769ns ± 1% -3.91% (p=0.000 n=10+10)
TimeFormat-8 826ns ± 2% 817ns ± 2% -1.04% (p=0.050 n=10+10)
[Geo mean] 145µs 143µs -1.79%
Change-Id: I5fc42087cee9b54ea414f8ef6d6d020b80eb5985
Reviewed-on: https://go-review.googlesource.com/42172
Run-TryBot: Cherry Zhang <cherryyz@google.com>
Reviewed-by: David Chase <drchase@google.com>
This CL modifies how MOV[DWHB] instructions that store a constant to
memory are assembled to avoid them clobbering the condition code
(flags). It also modifies zeroAuto to use MOVD instructions instead of
CLEAR (which is assembled as XC).
MOV[DWHB]storeconst ops also no longer clobbers flags.
Note: this CL modifies the assembler so that it can no longer handle
immediates outside the range of an int16 or offsets from SB, which
reflects what the machine instructions support. The compiler doesn't
need this capability any more and I don't think this affects any existing
assembly, but it is easy to workaround if it does.
Fixes#20187.
Change-Id: Ie54947ff38367bd6a19962bf1a6d0296a4accffb
Reviewed-on: https://go-review.googlesource.com/42179
Reviewed-by: David Chase <drchase@google.com>
Run-TryBot: David Chase <drchase@google.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
(ADDconst [c] x) && !isARMImmRot(uint32(c)) && isARMImmRot(uint32(-c)) -> (SUBconst [int64(int32(-c))] x)
(SUBconst [c] x) && !isARMImmRot(uint32(c)) && isARMImmRot(uint32(-c)) -> (ADDconst [int64(int32(-c))] x)
Currently
a = a + 0xfffffff1 is compiled to （variable a is in R0)
MVN $14, R11
ADD R11, R0, R0
After applying the above 2 rules, it becomes
SUB $15, R0, R0
(BICconst [c] (BICconst [d] x)) -> (BICconst [int64(int32(c|d))] x)
This rule also optimizes the generated ARM code.
The other rules are added to avoid to generate less optimized ARM code
when substitutions ADD->SUB happen.
Change-Id: I3ead9aae2b446b674e2ab42d37259d38ceb93a4d
Reviewed-on: https://go-review.googlesource.com/41679
Reviewed-by: Keith Randall <khr@golang.org>
Type.Size and Type.Alignment are for the front end:
They calculate size and alignment if needed.
Type.MustSize and Type.MustAlignment are for the back end:
They call Fatal if size and alignment are not already calculated.
Most uses are of MustSize and MustAlignment,
but that's because the back end is newer,
and this API was added to support it.
This CL was mostly generated with sed and selective reversion.
The only mildly interesting bit is the change of the ssa.Type interface
and the supporting ssa dummy types.
Follow-up to review feedback on CL 41970.
Passes toolstash-check.
Change-Id: I0d9b9505e57453dae8fb6a236a07a7a02abd459e
Reviewed-on: https://go-review.googlesource.com/42016
Run-TryBot: Josh Bleecher Snyder <josharian@gmail.com>
Reviewed-by: Matthew Dempsky <mdempsky@google.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
This reduces the size of the ssa export data
by 10%, from 76154 to 67886.
It doesn't appear that #20084, which would do this automatically,
is going to be fixed soon. Do it manually for now.
This speeds up compiling cmd/compile/internal/amd64
and presumably its comrades as well:
name old time/op new time/op delta
CompileAMD64 89.6ms ± 6% 86.7ms ± 5% -3.29% (p=0.000 n=49+47)
name old user-time/op new user-time/op delta
CompileAMD64 116ms ± 5% 112ms ± 5% -3.51% (p=0.000 n=45+42)
name old alloc/op new alloc/op delta
CompileAMD64 26.7MB ± 0% 25.8MB ± 0% -3.26% (p=0.008 n=5+5)
name old allocs/op new allocs/op delta
CompileAMD64 223k ± 0% 213k ± 0% -4.46% (p=0.008 n=5+5)
Updates #20084
Change-Id: I49e8951c5bfce63ad2b7f4fc3bfa0868c53114f9
Reviewed-on: https://go-review.googlesource.com/41493
Run-TryBot: Josh Bleecher Snyder <josharian@gmail.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Brad Fitzpatrick <bradfitz@golang.org>
These patterns are the only uses of isArg and isAuto, and they all
follow a common pattern too. Extract out so that we can more easily
tweak the interface for isArg/isAuto.
Passes toolstash -cmp for linux/arm64.
Change-Id: I9c509dabdc123c93cb1ad2f34fe8c12a9f313f6d
Reviewed-on: https://go-review.googlesource.com/40490
Run-TryBot: Matthew Dempsky <mdempsky@google.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Cherry Zhang <cherryyz@google.com>
This is a holdover from the days when we did not
have full SSA coverage and compiled things optimistically,
and catching the panic obscures useful information.
Change-Id: I196790cb6b97419d92b318a2dfa7f1e1097cefb7
Reviewed-on: https://go-review.googlesource.com/39534
Run-TryBot: Josh Bleecher Snyder <josharian@gmail.com>
Reviewed-by: Keith Randall <khr@golang.org>
We want to merge a load and op into a single instruction
l = LOAD ptr mem
y = OP x l
into
y = OPload x ptr mem
However, all of our OPload instructions require that y uses
the same register as x. If x is needed past this instruction, then
we must copy x somewhere else, losing the whole benefit of merging
the instructions in the first place.
Disable this optimization if x is live past the OP.
Also disable this optimization if the OP is in a deeper loop than the load.
Update #19595
Change-Id: I87f596aad7e91c9127bfb4705cbae47106e1e77a
Reviewed-on: https://go-review.googlesource.com/38337
Reviewed-by: Ilya Tocar <ilya.tocar@intel.com>
Suggested by mdempsky in CL 38232.
This allows us to use the Frontend field
to associate frontend state and information
with a function.
See the following CL in the series for examples.
This is a giant CL, but it is almost entirely routine refactoring.
The ssa test API is starting to feel a bit unwieldy.
I will clean it up separately, once the dust has settled.
Passes toolstash -cmp.
Updates #15756
Change-Id: I71c573bd96ff7251935fce1391b06b1f133c3caf
Reviewed-on: https://go-review.googlesource.com/38327
Run-TryBot: Josh Bleecher Snyder <josharian@gmail.com>
Reviewed-by: Matthew Dempsky <mdempsky@google.com>
Prior to this CL, config was an explicit argument
to the SSA rewrite rules, and rules that needed
a Frontend got at it via config.
An upcoming CL moves Frontend from Config to Func,
so rules can no longer reach Frontend via Config.
Passing a Frontend as an argument to the rewrite rules
causes a 2-3% regression in compile times.
This CL takes a different approach:
It treats the variable names "config" and "fe"
as special and calculates them as needed.
The "as needed part" is also important to performance:
If they are calculated eagerly, the nilchecks themselves
cause a regression.
This introduces a little bit of magic into the rewrite
generator. However, from the perspective of the rules,
the config variable was already more or less magic.
And it makes the upcoming changes much clearer.
Passes toolstash -cmp.
Change-Id: I173f2bcc124cba43d53138bfa3775e21316a9107
Reviewed-on: https://go-review.googlesource.com/38326
Run-TryBot: Josh Bleecher Snyder <josharian@gmail.com>
Reviewed-by: Matthew Dempsky <mdempsky@google.com>
With this change, code like
h := sha1.New()
h.Write(buf)
sum := h.Sum()
gets compiled into static calls rather than
interface calls, because the compiler is able
to prove that 'h' is really a *sha1.digest.
The InterCall re-write rule hits a few dozen times
during make.bash, and hundreds of times during all.bash.
The most common pattern identified by the compiler
is a constructor like
func New() Interface { return &impl{...} }
where the constructor gets inlined into the caller,
and the result is used immediately. Examples include
{sha1,md5,crc32,crc64,...}.New, base64.NewEncoder,
base64.NewDecoder, errors.New, net.Pipe, and so on.
Some existing benchmarks that change on darwin/amd64:
Crc64/ISO4KB-8 2.67µs ± 1% 2.66µs ± 0% -0.36% (p=0.015 n=10+10)
Crc64/ISO1KB-8 694ns ± 0% 690ns ± 1% -0.59% (p=0.001 n=10+10)
Adler32KB-8 473ns ± 1% 471ns ± 0% -0.39% (p=0.010 n=10+9)
On architectures like amd64, the reduction in code size
appears to contribute more to benchmark improvements than just
removing the indirect call, since that branch gets predicted
accurately when called in a loop.
Updates #19361
Change-Id: I57d4dc21ef40a05ec0fbd55a9bb0eb74cdc67a3d
Reviewed-on: https://go-review.googlesource.com/38139
Run-TryBot: Philip Hofer <phofer@umich.edu>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: David Chase <drchase@google.com>
This reverts commit 4e0c7c3f61.
Reason for revert: The presence-of-optimization test program is fragile, breaks under noopt, and might break if the Go libraries are tweaked. It needs to be (re)written without reference to other packages.
Change-Id: I3aaf1ab006a1a255f961a978e9c984341740e3c7
Reviewed-on: https://go-review.googlesource.com/38097
Reviewed-by: Keith Randall <khr@golang.org>
With this change, code like
h := sha1.New()
h.Write(buf)
sum := h.Sum()
gets compiled into static calls rather than
interface calls, because the compiler is able
to prove that 'h' is really a *sha1.digest.
The InterCall re-write rule hits a few dozen times
during make.bash, and hundreds of times during all.bash.
The most common pattern identified by the compiler
is a constructor like
func New() Interface { return &impl{...} }
where the constructor gets inlined into the caller,
and the result is used immediately. Examples include
{sha1,md5,crc32,crc64,...}.New, base64.NewEncoder,
base64.NewDecoder, errors.New, net.Pipe, and so on.
Some existing benchmarks that change on darwin/amd64:
Crc64/ISO4KB-8 2.67µs ± 1% 2.66µs ± 0% -0.36% (p=0.015 n=10+10)
Crc64/ISO1KB-8 694ns ± 0% 690ns ± 1% -0.59% (p=0.001 n=10+10)
Adler32KB-8 473ns ± 1% 471ns ± 0% -0.39% (p=0.010 n=10+9)
On architectures like amd64, the reduction in code size
appears to contribute more to benchmark improvements than just
removing the indirect call, since that branch gets predicted
accurately when called in a loop.
Updates #19361
Change-Id: Ia9d30afdd5f6b4d38d38b14b88f308acae8ce7ed
Reviewed-on: https://go-review.googlesource.com/37751
Run-TryBot: Philip Hofer <phofer@umich.edu>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Keith Randall <khr@golang.org>
This change adds a method to replace expressions
of the form
v.Args[len(v.Args)-1]
so that the code's intention to walk memory arguments
is explicit.
Passes toolstash-check.
Change-Id: I0c80d73bc00989dd3cdf72b4f2c8e1075a2515e0
Reviewed-on: https://go-review.googlesource.com/37757
Run-TryBot: Matthew Dempsky <mdempsky@google.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Keith Randall <khr@golang.org>
The Zero op right after newobject has been removed. But this rule
does not cover Store of constant zero (for SSA-able types). Add
rules to cover Store op as well.
Updates #19027.
Change-Id: I5d2b62eeca0aa9ce8dc7205b264b779de01c660b
Reviewed-on: https://go-review.googlesource.com/36836
Run-TryBot: Cherry Zhang <cherryyz@google.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Keith Randall <khr@golang.org>
Currently the conversion from constant divides to multiplies is mostly
done during the walk pass. This is suboptimal because SSA can
determine that the value being divided by is constant more often
(e.g. after inlining).
Change-Id: If1a9b993edd71be37396b9167f77da271966f85f
Reviewed-on: https://go-review.googlesource.com/37015
Run-TryBot: Keith Randall <khr@golang.org>
Reviewed-by: Josh Bleecher Snyder <josharian@gmail.com>
Remove rotate generation from walk. Remove OLROT and ssa.Lrot* opcodes.
Generate rotates during SSA lowering for architectures that have them.
This CL will allow rotates to be generated in more situations,
like when the shift values are determined to be constant
only after some analysis.
Fixes#18254
Change-Id: I8d6d684ff5ce2511aceaddfda98b908007851079
Reviewed-on: https://go-review.googlesource.com/34232
Run-TryBot: Keith Randall <khr@golang.org>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Cherry Zhang <cherryyz@google.com>
This is a mostly mechanical rename followed by manual fixes where necessary.
Change-Id: Ie5c670b133db978f15dc03e50dc2da0c80fc8842
Reviewed-on: https://go-review.googlesource.com/34137
Reviewed-by: David Lazar <lazard@golang.org>
Adds the new canMergeLoad function which can be used by rules to
decide whether a load can be merged into an operation. The function
ensures that the merge will not reorder the load relative to memory
operations (for example, stores) in such a way that the block can no
longer be scheduled.
This new function enables transformations such as:
MOVD 0(R1), R2
ADD R2, R3
to:
ADD 0(R1), R3
The two-operand form of the following instructions can now read a
single memory operand:
- ADD
- ADDC
- ADDW
- MULLD
- MULLW
- SUB
- SUBC
- SUBE
- SUBW
- AND
- ANDW
- OR
- ORW
- XOR
- XORW
Improves SHA3 performance by 6-8%.
Updates #15054.
Change-Id: Ibcb9122126cd1a26f2c01c0dfdbb42fe5e7b5b94
Reviewed-on: https://go-review.googlesource.com/29272
Run-TryBot: Michael Munday <munday@ca.ibm.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Keith Randall <khr@golang.org>
Inputs to store[BHW] and cmpW(U) need not be correct
in more bits than are used by the instruction.
Added a pattern tailored to what appears to be cgo boilerplate.
Added a pattern (also seen in cgo boilerplate and hashing)
to replace {EQ,NE}-CMP-ANDconst with {EQ-NE}-ANDCCconst.
Added a pattern to clean up ANDconst shift distance inputs
(this was seen in hashing).
Simplify repeated and,or,xor.
Fixes#17109.
Change-Id: I68eac83e3e614d69ffe473a08953048c8b066d88
Reviewed-on: https://go-review.googlesource.com/30455
Run-TryBot: David Chase <drchase@google.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Keith Randall <khr@golang.org>
Added rules for compare double and word immediate,
including those that use invertflags to cope with
flipped operands.
Change-Id: I594430a210e076e52299a2cc6ab074dbb04a02bd
Reviewed-on: https://go-review.googlesource.com/29763
Run-TryBot: David Chase <drchase@google.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Cherry Zhang <cherryyz@google.com>
Reviewed-by: Lynn Boger <laboger@linux.vnet.ibm.com>
Abandoned earlier efforts to expose zero register,
but left it in numbering to decrease squirrelyness of
register allocator.
ISELrelOp used in code generation of bool := x relOp y.
Some patterns added to better elide zero case and
some sign extension.
Updates: #17109
Change-Id: Ida7839f0023ca8f0ffddc0545f0ac269e65b05d9
Reviewed-on: https://go-review.googlesource.com/29380
Run-TryBot: David Chase <drchase@google.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Keith Randall <khr@golang.org>
Reviewed-by: Cherry Zhang <cherryyz@google.com>
The new SSA backend modifies the ABI slightly: R0 is now a usable
general purpose register.
Fixes#16677.
Change-Id: I367435ce921e0c7e79e021c80cf8ef5d1d1466cf
Reviewed-on: https://go-review.googlesource.com/28978
Run-TryBot: Michael Munday <munday@ca.ibm.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Keith Randall <khr@golang.org>
- Use machine instructions for uint64<->float conversions
- Do not enforce alignment on Zero/Move
ARM64 supports unaligned load/stores, but only aligned offset
or small offset can be encoded into instructions.
- Do combined loads
Change-Id: Iffca7dd0f13070b17b784861ce5a30af584680eb
Reviewed-on: https://go-review.googlesource.com/27086
Reviewed-by: David Chase <drchase@google.com>
SSA compiler on AMD64 may spill Duff-adjusted address as scalar. If
the object is on stack and the stack moves, the spilled address become
invalid.
Making the spill pointer-typed does not work. The Duff-adjusted address
points to the memory before the area to be zeroed and may be invalid.
This may cause stack scanning code panic.
Fix it by doing Duff-adjustment in genValue, so the intermediate value
is not seen by the reg allocator, and will not be spilled.
Add a test to cover both cases. As it depends on allocation, it may
be not always triggered.
Fixes#16515.
Change-Id: Ia81d60204782de7405b7046165ad063384ede0db
Reviewed-on: https://go-review.googlesource.com/25309
Run-TryBot: Cherry Zhang <cherryyz@google.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: David Chase <drchase@google.com>
