Stowage/go
2
0
Fork 0
mirror of https://github.com/golang/go.git synced 2025-12-08 06:10:04 +00:00
Code Issues Projects Releases Packages Wiki Activity

[dev.simd] simd: correct SumAbsDiff documentation

Browse source 
Change-Id: I6bb093615f12bbac5ea4c013a1c47cd5d338fe43
Reviewed-on: https://go-review.googlesource.com/c/go/+/698516
Reviewed-by: David Chase <drchase@google.com>
LUCI-TryBot-Result: Go LUCI <golang-scoped@luci-project-accounts.iam.gserviceaccount.com>
This commit is contained in:
Junyang Shao 2025-08-22 20:33:28 +00:00
parent a5137ec92a
commit 5ebe2d05d5
2 changed files with 4 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

2
src/simd/_gen/simdgen/ops/MLOps/categories.yaml
View file

@ -49,5 +49,5 @@
commutative: false commutative: false
documentation: !string |- documentation: !string |-
// NAME sums the absolute distance of the two input vectors, each adjacent 8 bytes as a group. The output sum will // NAME sums the absolute distance of the two input vectors, each adjacent 8 bytes as a group. The output sum will
// be a vector of word-sized elements whose each 8*n-th element contains the sum of the n-th input group. // be a vector of word-sized elements whose each 4*n-th element contains the sum of the n-th input group. The other elements in the result vector are zeroed.
// This method could be seen as the norm of the L1 distance of each adjacent 8-byte vector group of the two input vectors. // This method could be seen as the norm of the L1 distance of each adjacent 8-byte vector group of the two input vectors.

6
src/simd/ops_amd64.go
View file

@ -6819,21 +6819,21 @@ func (x Uint16x32) SubSaturated(y Uint16x32) Uint16x32
/* SumAbsDiff */ /* SumAbsDiff */
// SumAbsDiff sums the absolute distance of the two input vectors, each adjacent 8 bytes as a group. The output sum will // SumAbsDiff sums the absolute distance of the two input vectors, each adjacent 8 bytes as a group. The output sum will
// be a vector of word-sized elements whose each 8*n-th element contains the sum of the n-th input group. // be a vector of word-sized elements whose each 4*n-th element contains the sum of the n-th input group. The other elements in the result vector are zeroed.
// This method could be seen as the norm of the L1 distance of each adjacent 8-byte vector group of the two input vectors. // This method could be seen as the norm of the L1 distance of each adjacent 8-byte vector group of the two input vectors.
// //
// Asm: VPSADBW, CPU Feature: AVX // Asm: VPSADBW, CPU Feature: AVX
func (x Uint8x16) SumAbsDiff(y Uint8x16) Uint16x8 func (x Uint8x16) SumAbsDiff(y Uint8x16) Uint16x8
// SumAbsDiff sums the absolute distance of the two input vectors, each adjacent 8 bytes as a group. The output sum will // SumAbsDiff sums the absolute distance of the two input vectors, each adjacent 8 bytes as a group. The output sum will
// be a vector of word-sized elements whose each 8*n-th element contains the sum of the n-th input group. // be a vector of word-sized elements whose each 4*n-th element contains the sum of the n-th input group. The other elements in the result vector are zeroed.
// This method could be seen as the norm of the L1 distance of each adjacent 8-byte vector group of the two input vectors. // This method could be seen as the norm of the L1 distance of each adjacent 8-byte vector group of the two input vectors.
// //
// Asm: VPSADBW, CPU Feature: AVX2 // Asm: VPSADBW, CPU Feature: AVX2
func (x Uint8x32) SumAbsDiff(y Uint8x32) Uint16x16 func (x Uint8x32) SumAbsDiff(y Uint8x32) Uint16x16
// SumAbsDiff sums the absolute distance of the two input vectors, each adjacent 8 bytes as a group. The output sum will // SumAbsDiff sums the absolute distance of the two input vectors, each adjacent 8 bytes as a group. The output sum will
// be a vector of word-sized elements whose each 8*n-th element contains the sum of the n-th input group. // be a vector of word-sized elements whose each 4*n-th element contains the sum of the n-th input group. The other elements in the result vector are zeroed.
// This method could be seen as the norm of the L1 distance of each adjacent 8-byte vector group of the two input vectors. // This method could be seen as the norm of the L1 distance of each adjacent 8-byte vector group of the two input vectors.
// //
// Asm: VPSADBW, CPU Feature: AVX512 // Asm: VPSADBW, CPU Feature: AVX512