[dev.simd] cmd/compile: reorder operands for some simd operations

This adds support for one ad hoc reordering, which
requires a new intrinsic-to-ssa helper matching the
name that is used in the generator (and this in the
generated code).  In this case, it is opLen{2,3}Imm8_2I
which expects the immediate after the self (0) and
first (1) parameters to the method, and before the
mask if there is one.  I.e., the immediate is arg 2
in the call.

The changes to simdintrinsics and stubs are generated
by simdgen CL 684019.

Change-Id: Ia54aab9825d469a2f3efa6d1fb079242181c0ca6
Reviewed-on: https://go-review.googlesource.com/c/go/+/684776
Reviewed-by: Cherry Mui <cherryyz@google.com>
Reviewed-by: Junyang Shao <shaojunyang@google.com>
LUCI-TryBot-Result: Go LUCI <golang-scoped@luci-project-accounts.iam.gserviceaccount.com>

1 files changed, 24 insertions, 24 deletions

diff --git a/src/simd/stubs_amd64.go b/src/simd/stubs_amd64.go
index e589378c72..f0db32a07d 100644
--- a/src/simd/stubs_amd64.go
+++ b/src/simd/stubs_amd64.go
@@ -1430,56 +1430,56 @@ func (x Float64x8) FusedMultiplySubAdd(y Float64x8, z Float64x8) Float64x8
 
 // GaloisFieldAffineTransform computes an affine transformation in GF(2^8):
 // x is a vector of 8-bit vectors, with each adjacent 8 as a group; y is a vector of 8x8 1-bit matrixes;
-// imm is an 8-bit vector. The affine transformation is y * x + imm, with each element of y
+// b is an 8-bit vector. The affine transformation is y * x + b, with each element of y
 // corresponding to a group of 8 elements in x.
 //
 // Asm: VGF2P8AFFINEQB, CPU Feature: AVX512EVEX
-func (x Uint8x16) GaloisFieldAffineTransform(b uint8, y Uint64x2) Uint8x16
+func (x Uint8x16) GaloisFieldAffineTransform(y Uint64x2, b uint8) Uint8x16
 
 // GaloisFieldAffineTransform computes an affine transformation in GF(2^8):
 // x is a vector of 8-bit vectors, with each adjacent 8 as a group; y is a vector of 8x8 1-bit matrixes;
-// imm is an 8-bit vector. The affine transformation is y * x + imm, with each element of y
+// b is an 8-bit vector. The affine transformation is y * x + b, with each element of y
 // corresponding to a group of 8 elements in x.
 //
 // Asm: VGF2P8AFFINEQB, CPU Feature: AVX512EVEX
-func (x Uint8x32) GaloisFieldAffineTransform(b uint8, y Uint64x4) Uint8x32
+func (x Uint8x32) GaloisFieldAffineTransform(y Uint64x4, b uint8) Uint8x32
 
 // GaloisFieldAffineTransform computes an affine transformation in GF(2^8):
 // x is a vector of 8-bit vectors, with each adjacent 8 as a group; y is a vector of 8x8 1-bit matrixes;
-// imm is an 8-bit vector. The affine transformation is y * x + imm, with each element of y
+// b is an 8-bit vector. The affine transformation is y * x + b, with each element of y
 // corresponding to a group of 8 elements in x.
 //
 // Asm: VGF2P8AFFINEQB, CPU Feature: AVX512EVEX
-func (x Uint8x64) GaloisFieldAffineTransform(b uint8, y Uint64x8) Uint8x64
+func (x Uint8x64) GaloisFieldAffineTransform(y Uint64x8, b uint8) Uint8x64
 
 /* GaloisFieldAffineTransformInversed */
 
 // GaloisFieldAffineTransform computes an affine transformation in GF(2^8),
 // with x inversed with reduction polynomial x^8 + x^4 + x^3 + x + 1:
 // x is a vector of 8-bit vectors, with each adjacent 8 as a group; y is a vector of 8x8 1-bit matrixes;
-// imm is an 8-bit vector. The affine transformation is y * x + imm, with each element of y
+// b is an 8-bit vector. The affine transformation is y * x + b, with each element of y
 // corresponding to a group of 8 elements in x.
 //
 // Asm: VGF2P8AFFINEINVQB, CPU Feature: AVX512EVEX
-func (x Uint8x16) GaloisFieldAffineTransformInversed(b uint8, y Uint64x2) Uint8x16
+func (x Uint8x16) GaloisFieldAffineTransformInversed(y Uint64x2, b uint8) Uint8x16
 
 // GaloisFieldAffineTransform computes an affine transformation in GF(2^8),
 // with x inversed with reduction polynomial x^8 + x^4 + x^3 + x + 1:
 // x is a vector of 8-bit vectors, with each adjacent 8 as a group; y is a vector of 8x8 1-bit matrixes;
-// imm is an 8-bit vector. The affine transformation is y * x + imm, with each element of y
+// b is an 8-bit vector. The affine transformation is y * x + b, with each element of y
 // corresponding to a group of 8 elements in x.
 //
 // Asm: VGF2P8AFFINEINVQB, CPU Feature: AVX512EVEX
-func (x Uint8x32) GaloisFieldAffineTransformInversed(b uint8, y Uint64x4) Uint8x32
+func (x Uint8x32) GaloisFieldAffineTransformInversed(y Uint64x4, b uint8) Uint8x32
 
 // GaloisFieldAffineTransform computes an affine transformation in GF(2^8),
 // with x inversed with reduction polynomial x^8 + x^4 + x^3 + x + 1:
 // x is a vector of 8-bit vectors, with each adjacent 8 as a group; y is a vector of 8x8 1-bit matrixes;
-// imm is an 8-bit vector. The affine transformation is y * x + imm, with each element of y
+// b is an 8-bit vector. The affine transformation is y * x + b, with each element of y
 // corresponding to a group of 8 elements in x.
 //
 // Asm: VGF2P8AFFINEINVQB, CPU Feature: AVX512EVEX
-func (x Uint8x64) GaloisFieldAffineTransformInversed(b uint8, y Uint64x8) Uint8x64
+func (x Uint8x64) GaloisFieldAffineTransformInversed(y Uint64x8, b uint8) Uint8x64
 
 /* GaloisFieldMul */
 
@@ -3573,56 +3573,56 @@ func (x Float64x8) MaskedFusedMultiplySubAdd(y Float64x8, z Float64x8, u Mask64x
 
 // GaloisFieldAffineTransform computes an affine transformation in GF(2^8):
 // x is a vector of 8-bit vectors, with each adjacent 8 as a group; y is a vector of 8x8 1-bit matrixes;
-// imm is an 8-bit vector. The affine transformation is y * x + imm, with each element of y
+// b is an 8-bit vector. The affine transformation is y * x + b, with each element of y
 // corresponding to a group of 8 elements in x.
 //
 // Asm: VGF2P8AFFINEQB, CPU Feature: AVX512EVEX
-func (x Uint8x16) MaskedGaloisFieldAffineTransform(b uint8, y Uint64x2, m Mask8x16) Uint8x16
+func (x Uint8x16) MaskedGaloisFieldAffineTransform(y Uint64x2, b uint8, m Mask8x16) Uint8x16
 
 // GaloisFieldAffineTransform computes an affine transformation in GF(2^8):
 // x is a vector of 8-bit vectors, with each adjacent 8 as a group; y is a vector of 8x8 1-bit matrixes;
-// imm is an 8-bit vector. The affine transformation is y * x + imm, with each element of y
+// b is an 8-bit vector. The affine transformation is y * x + b, with each element of y
 // corresponding to a group of 8 elements in x.
 //
 // Asm: VGF2P8AFFINEQB, CPU Feature: AVX512EVEX
-func (x Uint8x32) MaskedGaloisFieldAffineTransform(b uint8, y Uint64x4, m Mask8x32) Uint8x32
+func (x Uint8x32) MaskedGaloisFieldAffineTransform(y Uint64x4, b uint8, m Mask8x32) Uint8x32
 
 // GaloisFieldAffineTransform computes an affine transformation in GF(2^8):
 // x is a vector of 8-bit vectors, with each adjacent 8 as a group; y is a vector of 8x8 1-bit matrixes;
-// imm is an 8-bit vector. The affine transformation is y * x + imm, with each element of y
+// b is an 8-bit vector. The affine transformation is y * x + b, with each element of y
 // corresponding to a group of 8 elements in x.
 //
 // Asm: VGF2P8AFFINEQB, CPU Feature: AVX512EVEX
-func (x Uint8x64) MaskedGaloisFieldAffineTransform(b uint8, y Uint64x8, m Mask8x64) Uint8x64
+func (x Uint8x64) MaskedGaloisFieldAffineTransform(y Uint64x8, b uint8, m Mask8x64) Uint8x64
 
 /* MaskedGaloisFieldAffineTransformInversed */
 
 // GaloisFieldAffineTransform computes an affine transformation in GF(2^8),
 // with x inversed with reduction polynomial x^8 + x^4 + x^3 + x + 1:
 // x is a vector of 8-bit vectors, with each adjacent 8 as a group; y is a vector of 8x8 1-bit matrixes;
-// imm is an 8-bit vector. The affine transformation is y * x + imm, with each element of y
+// b is an 8-bit vector. The affine transformation is y * x + b, with each element of y
 // corresponding to a group of 8 elements in x.
 //
 // Asm: VGF2P8AFFINEINVQB, CPU Feature: AVX512EVEX
-func (x Uint8x16) MaskedGaloisFieldAffineTransformInversed(b uint8, y Uint64x2, m Mask8x16) Uint8x16
+func (x Uint8x16) MaskedGaloisFieldAffineTransformInversed(y Uint64x2, b uint8, m Mask8x16) Uint8x16
 
 // GaloisFieldAffineTransform computes an affine transformation in GF(2^8),
 // with x inversed with reduction polynomial x^8 + x^4 + x^3 + x + 1:
 // x is a vector of 8-bit vectors, with each adjacent 8 as a group; y is a vector of 8x8 1-bit matrixes;
-// imm is an 8-bit vector. The affine transformation is y * x + imm, with each element of y
+// b is an 8-bit vector. The affine transformation is y * x + b, with each element of y
 // corresponding to a group of 8 elements in x.
 //
 // Asm: VGF2P8AFFINEINVQB, CPU Feature: AVX512EVEX
-func (x Uint8x32) MaskedGaloisFieldAffineTransformInversed(b uint8, y Uint64x4, m Mask8x32) Uint8x32
+func (x Uint8x32) MaskedGaloisFieldAffineTransformInversed(y Uint64x4, b uint8, m Mask8x32) Uint8x32
 
 // GaloisFieldAffineTransform computes an affine transformation in GF(2^8),
 // with x inversed with reduction polynomial x^8 + x^4 + x^3 + x + 1:
 // x is a vector of 8-bit vectors, with each adjacent 8 as a group; y is a vector of 8x8 1-bit matrixes;
-// imm is an 8-bit vector. The affine transformation is y * x + imm, with each element of y
+// b is an 8-bit vector. The affine transformation is y * x + b, with each element of y
 // corresponding to a group of 8 elements in x.
 //
 // Asm: VGF2P8AFFINEINVQB, CPU Feature: AVX512EVEX
-func (x Uint8x64) MaskedGaloisFieldAffineTransformInversed(b uint8, y Uint64x8, m Mask8x64) Uint8x64
+func (x Uint8x64) MaskedGaloisFieldAffineTransformInversed(y Uint64x8, b uint8, m Mask8x64) Uint8x64
 
 /* MaskedGaloisFieldMul */