maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/CodeGen/X86/var-permute-128.ll

1125 lines
52 KiB
LLVM
Raw Normal View History

X86 Tests: Add tests for vector permutes with variable indices. NFC. Basic tests which are the equivalent of single-source shufflevector with variable mask. llvm-svn: 316216
2017-10-20 23:32:14 +08:00
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
[X86][SSE] createVariablePermute - PSHUFB requires SSSE3 not just SSE3 llvm-svn: 327259
2018-03-12 20:30:04 +08:00
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse3 | FileCheck %s --check-prefixes=SSE,SSE3
Fix check-prefixes typo and line endings. llvm-svn: 324024
2018-02-02 06:32:41 +08:00
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+ssse3 | FileCheck %s --check-prefixes=SSE,SSSE3
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse4.1 | FileCheck %s --check-prefixes=SSE,SSE41
[X86][XOP] Add XOP to variable permute tests llvm-svn: 324015
2018-02-02 05:57:37 +08:00
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+xop | FileCheck %s --check-prefixes=AVX,AVXNOVLBW,XOP
X86 Tests: Add tests for vector permutes with variable indices. NFC. Basic tests which are the equivalent of single-source shufflevector with variable mask. llvm-svn: 316216
2017-10-20 23:32:14 +08:00
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx | FileCheck %s --check-prefixes=AVX,AVXNOVLBW,AVX1
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2 | FileCheck %s --check-prefixes=AVX,AVXNOVLBW,AVX2
[X86][AVX512] Added more non-VLX test cases Cleaned up check prefixes so that they actually share a bit more llvm-svn: 327246
2018-03-12 02:28:37 +08:00
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512f | FileCheck %s --check-prefixes=AVX,AVXNOVLBW,AVX512,AVX512F
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512bw | FileCheck %s --check-prefixes=AVX,AVXNOVLBW,AVX512,AVX512BW
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512vbmi | FileCheck %s --check-prefixes=AVX,AVXNOVLBW,AVX512,VBMI
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512bw,+avx512vl | FileCheck %s --check-prefixes=AVX,AVX512VL,AVX512VLBW
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512bw,+avx512vl,+avx512vbmi | FileCheck %s --check-prefixes=AVX,AVX512VL,VLVBMI
X86 Tests: Add tests for vector permutes with variable indices. NFC. Basic tests which are the equivalent of single-source shufflevector with variable mask. llvm-svn: 316216
2017-10-20 23:32:14 +08:00
define <2 x i64> @var_shuffle_v2i64(<2 x i64> %v, <2 x i64> %indices) nounwind {
[X86][SSE] createVariablePermute - PSHUFB requires SSSE3 not just SSE3 llvm-svn: 327259
2018-03-12 20:30:04 +08:00
; SSE3-LABEL: var_shuffle_v2i64:
; SSE3: # %bb.0:
; SSE3-NEXT: movq %xmm1, %rax
; SSE3-NEXT: andl $1, %eax
; SSE3-NEXT: pshufd {{.*#+}} xmm1 = xmm1[2,3,0,1]
; SSE3-NEXT: movq %xmm1, %rcx
; SSE3-NEXT: andl $1, %ecx
; SSE3-NEXT: movaps %xmm0, -{{[0-9]+}}(%rsp)
; SSE3-NEXT: movsd {{.*#+}} xmm0 = mem[0],zero
; SSE3-NEXT: movsd {{.*#+}} xmm1 = mem[0],zero
; SSE3-NEXT: movlhps {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; SSE3-NEXT: retq
;
X86 Tests: Add tests for vector permutes with variable indices. NFC. Basic tests which are the equivalent of single-source shufflevector with variable mask. llvm-svn: 316216
2017-10-20 23:32:14 +08:00
; SSSE3-LABEL: var_shuffle_v2i64:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; SSSE3: # %bb.0:
X86 Tests: Add tests for vector permutes with variable indices. NFC. Basic tests which are the equivalent of single-source shufflevector with variable mask. llvm-svn: 316216
2017-10-20 23:32:14 +08:00
; SSSE3-NEXT: movq %xmm1, %rax
; SSSE3-NEXT: andl $1, %eax
; SSSE3-NEXT: pshufd {{.*#+}} xmm1 = xmm1[2,3,0,1]
; SSSE3-NEXT: movq %xmm1, %rcx
; SSSE3-NEXT: andl $1, %ecx
; SSSE3-NEXT: movaps %xmm0, -{{[0-9]+}}(%rsp)
; SSSE3-NEXT: movsd {{.*#+}} xmm0 = mem[0],zero
; SSSE3-NEXT: movsd {{.*#+}} xmm1 = mem[0],zero
; SSSE3-NEXT: movlhps {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; SSSE3-NEXT: retq
;
[X86][SSE] Add SSE41 to variable permute tests llvm-svn: 324017
2018-02-02 06:05:44 +08:00
; SSE41-LABEL: var_shuffle_v2i64:
; SSE41: # %bb.0:
[X86][SSE41] createVariablePermute v2X64 - PCMPEQQ can test for index 0/1 and select between them. llvm-svn: 327385
2018-03-13 20:22:58 +08:00
; SSE41-NEXT: pxor %xmm2, %xmm2
; SSE41-NEXT: pcmpeqq %xmm1, %xmm2
; SSE41-NEXT: pshufd {{.*#+}} xmm3 = xmm0[0,1,0,1]
; SSE41-NEXT: pshufd {{.*#+}} xmm1 = xmm0[2,3,2,3]
; SSE41-NEXT: movdqa %xmm2, %xmm0
; SSE41-NEXT: blendvpd %xmm0, %xmm3, %xmm1
; SSE41-NEXT: movapd %xmm1, %xmm0
[X86][SSE] Add SSE41 to variable permute tests llvm-svn: 324017
2018-02-02 06:05:44 +08:00
; SSE41-NEXT: retq
;
X86 Tests: Add tests for vector permutes with variable indices. NFC. Basic tests which are the equivalent of single-source shufflevector with variable mask. llvm-svn: 316216
2017-10-20 23:32:14 +08:00
; AVX-LABEL: var_shuffle_v2i64:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; AVX: # %bb.0:
[X86][AVX] createVariablePermute - fix v2i64/v2f64 VPERMILPD index creation. The input indices vector will put the index in bit0, but VPERMILPD actually selects off bit1 - so we need to scale accordingly. llvm-svn: 327159
2018-03-10 02:37:56 +08:00
; AVX-NEXT: vpaddq %xmm1, %xmm1, %xmm1
[X86][AVX] LowerBUILD_VECTORAsVariablePermute - add support for VPERMILPV to v2i64/v2f64 Minor refactor to make it possible for LowerBUILD_VECTORAsVariablePermute to be used with a wider variety of shuffles op and types. I'd have liked to add v4i32/v4f32 support as well but we don't see v4i32 index extractions at the moment (which is why I created D42308) After this I intend to begin adding scaling support for PSHUFB (v8i16, v4i32, v2i64)) and VPERMPS (v4f64, v4i64). Differential Revision: https://reviews.llvm.org/D42431 llvm-svn: 323260
2018-01-24 05:33:24 +08:00
; AVX-NEXT: vpermilpd %xmm1, %xmm0, %xmm0
X86 Tests: Add tests for vector permutes with variable indices. NFC. Basic tests which are the equivalent of single-source shufflevector with variable mask. llvm-svn: 316216
2017-10-20 23:32:14 +08:00
; AVX-NEXT: retq
%index0 = extractelement <2 x i64> %indices, i32 0
%index1 = extractelement <2 x i64> %indices, i32 1
%v0 = extractelement <2 x i64> %v, i64 %index0
%v1 = extractelement <2 x i64> %v, i64 %index1
%ret0 = insertelement <2 x i64> undef, i64 %v0, i32 0
%ret1 = insertelement <2 x i64> %ret0, i64 %v1, i32 1
ret <2 x i64> %ret1
}
define <4 x i32> @var_shuffle_v4i32(<4 x i32> %v, <4 x i32> %indices) nounwind {
[X86][SSE] createVariablePermute - PSHUFB requires SSSE3 not just SSE3 llvm-svn: 327259
2018-03-12 20:30:04 +08:00
; SSE3-LABEL: var_shuffle_v4i32:
; SSE3: # %bb.0:
; SSE3-NEXT: movd %xmm1, %eax
; SSE3-NEXT: pshufd {{.*#+}} xmm2 = xmm1[1,1,2,3]
; SSE3-NEXT: movd %xmm2, %ecx
; SSE3-NEXT: pshufd {{.*#+}} xmm2 = xmm1[2,3,0,1]
; SSE3-NEXT: movd %xmm2, %edx
; SSE3-NEXT: pshufd {{.*#+}} xmm1 = xmm1[3,1,2,3]
; SSE3-NEXT: movd %xmm1, %esi
; SSE3-NEXT: movaps %xmm0, -{{[0-9]+}}(%rsp)
; SSE3-NEXT: andl $3, %eax
; SSE3-NEXT: andl $3, %ecx
; SSE3-NEXT: andl $3, %edx
; SSE3-NEXT: andl $3, %esi
; SSE3-NEXT: movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; SSE3-NEXT: movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; SSE3-NEXT: unpcklps {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1]
; SSE3-NEXT: movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; SSE3-NEXT: movss {{.*#+}} xmm2 = mem[0],zero,zero,zero
; SSE3-NEXT: unpcklps {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1]
; SSE3-NEXT: movlhps {{.*#+}} xmm0 = xmm0[0],xmm1[0]
; SSE3-NEXT: retq
;
X86 Tests: Add tests for vector permutes with variable indices. NFC. Basic tests which are the equivalent of single-source shufflevector with variable mask. llvm-svn: 316216
2017-10-20 23:32:14 +08:00
; SSSE3-LABEL: var_shuffle_v4i32:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; SSSE3: # %bb.0:
[X86][SSE] LowerBUILD_VECTORAsVariablePermute - add support for scaling index vectors This allows us to use PSHUFB for v8i16/v4i32 and VPERMD/PERMPS for v4i64/v4f64 variable shuffles. Differential Revision: https://reviews.llvm.org/D42487 llvm-svn: 323987
2018-02-02 02:10:30 +08:00
; SSSE3-NEXT: movdqa {{.*#+}} xmm2 = [67372036,67372036,67372036,67372036]
; SSSE3-NEXT: pshufd {{.*#+}} xmm3 = xmm1[1,1,3,3]
; SSSE3-NEXT: pmuludq %xmm2, %xmm1
; SSSE3-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
; SSSE3-NEXT: pmuludq %xmm2, %xmm3
; SSSE3-NEXT: pshufd {{.*#+}} xmm2 = xmm3[0,2,2,3]
; SSSE3-NEXT: punpckldq {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
; SSSE3-NEXT: paddd {{.*}}(%rip), %xmm1
; SSSE3-NEXT: pshufb %xmm1, %xmm0
X86 Tests: Add tests for vector permutes with variable indices. NFC. Basic tests which are the equivalent of single-source shufflevector with variable mask. llvm-svn: 316216
2017-10-20 23:32:14 +08:00
; SSSE3-NEXT: retq
;
[X86][SSE] Add SSE41 to variable permute tests llvm-svn: 324017
2018-02-02 06:05:44 +08:00
; SSE41-LABEL: var_shuffle_v4i32:
; SSE41: # %bb.0:
; SSE41-NEXT: pmulld {{.*}}(%rip), %xmm1
; SSE41-NEXT: paddd {{.*}}(%rip), %xmm1
; SSE41-NEXT: pshufb %xmm1, %xmm0
; SSE41-NEXT: retq
;
X86 Tests: Add tests for vector permutes with variable indices. NFC. Basic tests which are the equivalent of single-source shufflevector with variable mask. llvm-svn: 316216
2017-10-20 23:32:14 +08:00
; AVX-LABEL: var_shuffle_v4i32:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; AVX: # %bb.0:
[X86][AVX] LowerBUILD_VECTORAsVariablePermute - add support for VPERMILPV to v4i32/v4f32 Extension to D42431, adding support for v4i32/v4f32 as well as v2i64/v2f64 now that D42308 has landed llvm-svn: 323542
2018-01-27 01:19:59 +08:00
; AVX-NEXT: vpermilps %xmm1, %xmm0, %xmm0
X86 Tests: Add tests for vector permutes with variable indices. NFC. Basic tests which are the equivalent of single-source shufflevector with variable mask. llvm-svn: 316216
2017-10-20 23:32:14 +08:00
; AVX-NEXT: retq
%index0 = extractelement <4 x i32> %indices, i32 0
%index1 = extractelement <4 x i32> %indices, i32 1
%index2 = extractelement <4 x i32> %indices, i32 2
%index3 = extractelement <4 x i32> %indices, i32 3
%v0 = extractelement <4 x i32> %v, i32 %index0
%v1 = extractelement <4 x i32> %v, i32 %index1
%v2 = extractelement <4 x i32> %v, i32 %index2
%v3 = extractelement <4 x i32> %v, i32 %index3
%ret0 = insertelement <4 x i32> undef, i32 %v0, i32 0
%ret1 = insertelement <4 x i32> %ret0, i32 %v1, i32 1
%ret2 = insertelement <4 x i32> %ret1, i32 %v2, i32 2
%ret3 = insertelement <4 x i32> %ret2, i32 %v3, i32 3
ret <4 x i32> %ret3
}
define <8 x i16> @var_shuffle_v8i16(<8 x i16> %v, <8 x i16> %indices) nounwind {
[X86][SSE] createVariablePermute - PSHUFB requires SSSE3 not just SSE3 llvm-svn: 327259
2018-03-12 20:30:04 +08:00
; SSE3-LABEL: var_shuffle_v8i16:
; SSE3: # %bb.0:
; SSE3-NEXT: movd %xmm1, %r8d
; SSE3-NEXT: pextrw $1, %xmm1, %r9d
; SSE3-NEXT: pextrw $2, %xmm1, %r10d
; SSE3-NEXT: pextrw $3, %xmm1, %esi
; SSE3-NEXT: pextrw $4, %xmm1, %edi
; SSE3-NEXT: pextrw $5, %xmm1, %eax
; SSE3-NEXT: pextrw $6, %xmm1, %ecx
; SSE3-NEXT: pextrw $7, %xmm1, %edx
; SSE3-NEXT: movaps %xmm0, -{{[0-9]+}}(%rsp)
; SSE3-NEXT: andl $7, %r8d
; SSE3-NEXT: andl $7, %r9d
; SSE3-NEXT: andl $7, %r10d
; SSE3-NEXT: andl $7, %esi
; SSE3-NEXT: andl $7, %edi
; SSE3-NEXT: andl $7, %eax
; SSE3-NEXT: andl $7, %ecx
; SSE3-NEXT: andl $7, %edx
; SSE3-NEXT: movzwl -24(%rsp,%rdx,2), %edx
; SSE3-NEXT: movd %edx, %xmm0
; SSE3-NEXT: movzwl -24(%rsp,%rcx,2), %ecx
; SSE3-NEXT: movd %ecx, %xmm1
; SSE3-NEXT: punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3]
; SSE3-NEXT: movzwl -24(%rsp,%rax,2), %eax
; SSE3-NEXT: movd %eax, %xmm0
; SSE3-NEXT: movzwl -24(%rsp,%rdi,2), %eax
; SSE3-NEXT: movd %eax, %xmm2
; SSE3-NEXT: punpcklwd {{.*#+}} xmm2 = xmm2[0],xmm0[0],xmm2[1],xmm0[1],xmm2[2],xmm0[2],xmm2[3],xmm0[3]
; SSE3-NEXT: punpckldq {{.*#+}} xmm2 = xmm2[0],xmm1[0],xmm2[1],xmm1[1]
; SSE3-NEXT: movzwl -24(%rsp,%rsi,2), %eax
; SSE3-NEXT: movd %eax, %xmm0
; SSE3-NEXT: movzwl -24(%rsp,%r10,2), %eax
; SSE3-NEXT: movd %eax, %xmm1
; SSE3-NEXT: punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3]
; SSE3-NEXT: movzwl -24(%rsp,%r9,2), %eax
; SSE3-NEXT: movd %eax, %xmm3
; SSE3-NEXT: movzwl -24(%rsp,%r8,2), %eax
; SSE3-NEXT: movd %eax, %xmm0
; SSE3-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm3[0],xmm0[1],xmm3[1],xmm0[2],xmm3[2],xmm0[3],xmm3[3]
; SSE3-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; SSE3-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm2[0]
; SSE3-NEXT: retq
;
; SSSE3-LABEL: var_shuffle_v8i16:
; SSSE3: # %bb.0:
; SSSE3-NEXT: pmullw {{.*}}(%rip), %xmm1
; SSSE3-NEXT: paddw {{.*}}(%rip), %xmm1
; SSSE3-NEXT: pshufb %xmm1, %xmm0
; SSSE3-NEXT: retq
;
; SSE41-LABEL: var_shuffle_v8i16:
; SSE41: # %bb.0:
; SSE41-NEXT: pmullw {{.*}}(%rip), %xmm1
; SSE41-NEXT: paddw {{.*}}(%rip), %xmm1
; SSE41-NEXT: pshufb %xmm1, %xmm0
; SSE41-NEXT: retq
X86 Tests: Add tests for vector permutes with variable indices. NFC. Basic tests which are the equivalent of single-source shufflevector with variable mask. llvm-svn: 316216
2017-10-20 23:32:14 +08:00
;
X86 ISel: Basic support for variable-index vector permutations Summary: Try to lower a BUILD_VECTOR composed of extract-extract chains that can be reasoned to be a permutation of a vector by indices in a non-constant vector. We saw this pattern created by ISPC, which resolts to creating it due to the requirement that shufflevector's mask operand be a *constant* vector. I didn't check this but we could possibly use this pattern for lowering the X86 permute C-instrinsics instead of llvm.x86 instrinsics. This change can be followed by more improvements: 1. Handle vectors with undef elements. 2. Utilize pshufb and zero-mask-blending to support more effiecient construction of vectors with constant-0 elements. 3. Use smaller-element vectors of same width, and "interpolate" the indices, when no native operation available. Reviewers: RKSimon, craig.topper Reviewed By: RKSimon Subscribers: chandlerc, DavidKreitzer Differential Revision: https://reviews.llvm.org/D39126 llvm-svn: 317463
2017-11-06 16:25:46 +08:00
; AVXNOVLBW-LABEL: var_shuffle_v8i16:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; AVXNOVLBW: # %bb.0:
[X86][SSE] LowerBUILD_VECTORAsVariablePermute - add support for scaling index vectors This allows us to use PSHUFB for v8i16/v4i32 and VPERMD/PERMPS for v4i64/v4f64 variable shuffles. Differential Revision: https://reviews.llvm.org/D42487 llvm-svn: 323987
2018-02-02 02:10:30 +08:00
; AVXNOVLBW-NEXT: vpmullw {{.*}}(%rip), %xmm1, %xmm1
; AVXNOVLBW-NEXT: vpaddw {{.*}}(%rip), %xmm1, %xmm1
; AVXNOVLBW-NEXT: vpshufb %xmm1, %xmm0, %xmm0
X86 ISel: Basic support for variable-index vector permutations Summary: Try to lower a BUILD_VECTOR composed of extract-extract chains that can be reasoned to be a permutation of a vector by indices in a non-constant vector. We saw this pattern created by ISPC, which resolts to creating it due to the requirement that shufflevector's mask operand be a *constant* vector. I didn't check this but we could possibly use this pattern for lowering the X86 permute C-instrinsics instead of llvm.x86 instrinsics. This change can be followed by more improvements: 1. Handle vectors with undef elements. 2. Utilize pshufb and zero-mask-blending to support more effiecient construction of vectors with constant-0 elements. 3. Use smaller-element vectors of same width, and "interpolate" the indices, when no native operation available. Reviewers: RKSimon, craig.topper Reviewed By: RKSimon Subscribers: chandlerc, DavidKreitzer Differential Revision: https://reviews.llvm.org/D39126 llvm-svn: 317463
2017-11-06 16:25:46 +08:00
; AVXNOVLBW-NEXT: retq
;
[X86][AVX512] Added more non-VLX test cases Cleaned up check prefixes so that they actually share a bit more llvm-svn: 327246
2018-03-12 02:28:37 +08:00
; AVX512VL-LABEL: var_shuffle_v8i16:
; AVX512VL: # %bb.0:
; AVX512VL-NEXT: vpermw %xmm0, %xmm1, %xmm0
; AVX512VL-NEXT: retq
X86 Tests: Add tests for vector permutes with variable indices. NFC. Basic tests which are the equivalent of single-source shufflevector with variable mask. llvm-svn: 316216
2017-10-20 23:32:14 +08:00
%index0 = extractelement <8 x i16> %indices, i32 0
%index1 = extractelement <8 x i16> %indices, i32 1
%index2 = extractelement <8 x i16> %indices, i32 2
%index3 = extractelement <8 x i16> %indices, i32 3
%index4 = extractelement <8 x i16> %indices, i32 4
%index5 = extractelement <8 x i16> %indices, i32 5
%index6 = extractelement <8 x i16> %indices, i32 6
%index7 = extractelement <8 x i16> %indices, i32 7
%v0 = extractelement <8 x i16> %v, i16 %index0
%v1 = extractelement <8 x i16> %v, i16 %index1
%v2 = extractelement <8 x i16> %v, i16 %index2
%v3 = extractelement <8 x i16> %v, i16 %index3
%v4 = extractelement <8 x i16> %v, i16 %index4
%v5 = extractelement <8 x i16> %v, i16 %index5
%v6 = extractelement <8 x i16> %v, i16 %index6
%v7 = extractelement <8 x i16> %v, i16 %index7
%ret0 = insertelement <8 x i16> undef, i16 %v0, i32 0
%ret1 = insertelement <8 x i16> %ret0, i16 %v1, i32 1
%ret2 = insertelement <8 x i16> %ret1, i16 %v2, i32 2
%ret3 = insertelement <8 x i16> %ret2, i16 %v3, i32 3
%ret4 = insertelement <8 x i16> %ret3, i16 %v4, i32 4
%ret5 = insertelement <8 x i16> %ret4, i16 %v5, i32 5
%ret6 = insertelement <8 x i16> %ret5, i16 %v6, i32 6
%ret7 = insertelement <8 x i16> %ret6, i16 %v7, i32 7
ret <8 x i16> %ret7
}
define <16 x i8> @var_shuffle_v16i8(<16 x i8> %v, <16 x i8> %indices) nounwind {
[X86][SSE] createVariablePermute - PSHUFB requires SSSE3 not just SSE3 llvm-svn: 327259
2018-03-12 20:30:04 +08:00
; SSE3-LABEL: var_shuffle_v16i8:
; SSE3: # %bb.0:
; SSE3-NEXT: movaps %xmm1, -{{[0-9]+}}(%rsp)
; SSE3-NEXT: movaps %xmm0, -{{[0-9]+}}(%rsp)
; SSE3-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE3-NEXT: andl $15, %eax
; SSE3-NEXT: movzbl -24(%rsp,%rax), %eax
; SSE3-NEXT: movd %eax, %xmm8
; SSE3-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE3-NEXT: andl $15, %eax
; SSE3-NEXT: movzbl -24(%rsp,%rax), %eax
; SSE3-NEXT: movd %eax, %xmm15
; SSE3-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE3-NEXT: andl $15, %eax
; SSE3-NEXT: movzbl -24(%rsp,%rax), %eax
; SSE3-NEXT: movd %eax, %xmm9
; SSE3-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE3-NEXT: andl $15, %eax
; SSE3-NEXT: movzbl -24(%rsp,%rax), %eax
; SSE3-NEXT: movd %eax, %xmm3
; SSE3-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE3-NEXT: andl $15, %eax
; SSE3-NEXT: movzbl -24(%rsp,%rax), %eax
; SSE3-NEXT: movd %eax, %xmm10
; SSE3-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE3-NEXT: andl $15, %eax
; SSE3-NEXT: movzbl -24(%rsp,%rax), %eax
; SSE3-NEXT: movd %eax, %xmm7
; SSE3-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE3-NEXT: andl $15, %eax
; SSE3-NEXT: movzbl -24(%rsp,%rax), %eax
; SSE3-NEXT: movd %eax, %xmm11
; SSE3-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE3-NEXT: andl $15, %eax
; SSE3-NEXT: movzbl -24(%rsp,%rax), %eax
; SSE3-NEXT: movd %eax, %xmm6
; SSE3-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE3-NEXT: andl $15, %eax
; SSE3-NEXT: movzbl -24(%rsp,%rax), %eax
; SSE3-NEXT: movd %eax, %xmm12
; SSE3-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE3-NEXT: andl $15, %eax
; SSE3-NEXT: movzbl -24(%rsp,%rax), %eax
; SSE3-NEXT: movd %eax, %xmm5
; SSE3-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE3-NEXT: andl $15, %eax
; SSE3-NEXT: movzbl -24(%rsp,%rax), %eax
; SSE3-NEXT: movd %eax, %xmm13
; SSE3-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE3-NEXT: andl $15, %eax
; SSE3-NEXT: movzbl -24(%rsp,%rax), %eax
; SSE3-NEXT: movd %eax, %xmm4
; SSE3-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE3-NEXT: andl $15, %eax
; SSE3-NEXT: movzbl -24(%rsp,%rax), %eax
; SSE3-NEXT: movd %eax, %xmm14
; SSE3-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE3-NEXT: andl $15, %eax
; SSE3-NEXT: movzbl -24(%rsp,%rax), %eax
; SSE3-NEXT: movd %eax, %xmm1
; SSE3-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE3-NEXT: andl $15, %eax
; SSE3-NEXT: movzbl -24(%rsp,%rax), %eax
; SSE3-NEXT: movd %eax, %xmm2
; SSE3-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE3-NEXT: andl $15, %eax
; SSE3-NEXT: movzbl -24(%rsp,%rax), %eax
; SSE3-NEXT: movd %eax, %xmm0
; SSE3-NEXT: punpcklbw {{.*#+}} xmm15 = xmm15[0],xmm8[0],xmm15[1],xmm8[1],xmm15[2],xmm8[2],xmm15[3],xmm8[3],xmm15[4],xmm8[4],xmm15[5],xmm8[5],xmm15[6],xmm8[6],xmm15[7],xmm8[7]
; SSE3-NEXT: punpcklbw {{.*#+}} xmm3 = xmm3[0],xmm9[0],xmm3[1],xmm9[1],xmm3[2],xmm9[2],xmm3[3],xmm9[3],xmm3[4],xmm9[4],xmm3[5],xmm9[5],xmm3[6],xmm9[6],xmm3[7],xmm9[7]
; SSE3-NEXT: punpcklwd {{.*#+}} xmm3 = xmm3[0],xmm15[0],xmm3[1],xmm15[1],xmm3[2],xmm15[2],xmm3[3],xmm15[3]
; SSE3-NEXT: punpcklbw {{.*#+}} xmm7 = xmm7[0],xmm10[0],xmm7[1],xmm10[1],xmm7[2],xmm10[2],xmm7[3],xmm10[3],xmm7[4],xmm10[4],xmm7[5],xmm10[5],xmm7[6],xmm10[6],xmm7[7],xmm10[7]
; SSE3-NEXT: punpcklbw {{.*#+}} xmm6 = xmm6[0],xmm11[0],xmm6[1],xmm11[1],xmm6[2],xmm11[2],xmm6[3],xmm11[3],xmm6[4],xmm11[4],xmm6[5],xmm11[5],xmm6[6],xmm11[6],xmm6[7],xmm11[7]
; SSE3-NEXT: punpcklwd {{.*#+}} xmm6 = xmm6[0],xmm7[0],xmm6[1],xmm7[1],xmm6[2],xmm7[2],xmm6[3],xmm7[3]
; SSE3-NEXT: punpckldq {{.*#+}} xmm6 = xmm6[0],xmm3[0],xmm6[1],xmm3[1]
; SSE3-NEXT: punpcklbw {{.*#+}} xmm5 = xmm5[0],xmm12[0],xmm5[1],xmm12[1],xmm5[2],xmm12[2],xmm5[3],xmm12[3],xmm5[4],xmm12[4],xmm5[5],xmm12[5],xmm5[6],xmm12[6],xmm5[7],xmm12[7]
; SSE3-NEXT: punpcklbw {{.*#+}} xmm4 = xmm4[0],xmm13[0],xmm4[1],xmm13[1],xmm4[2],xmm13[2],xmm4[3],xmm13[3],xmm4[4],xmm13[4],xmm4[5],xmm13[5],xmm4[6],xmm13[6],xmm4[7],xmm13[7]
; SSE3-NEXT: punpcklwd {{.*#+}} xmm4 = xmm4[0],xmm5[0],xmm4[1],xmm5[1],xmm4[2],xmm5[2],xmm4[3],xmm5[3]
; SSE3-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm14[0],xmm1[1],xmm14[1],xmm1[2],xmm14[2],xmm1[3],xmm14[3],xmm1[4],xmm14[4],xmm1[5],xmm14[5],xmm1[6],xmm14[6],xmm1[7],xmm14[7]
; SSE3-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3],xmm0[4],xmm2[4],xmm0[5],xmm2[5],xmm0[6],xmm2[6],xmm0[7],xmm2[7]
; SSE3-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
; SSE3-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm4[0],xmm0[1],xmm4[1]
; SSE3-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm6[0]
; SSE3-NEXT: retq
;
; SSSE3-LABEL: var_shuffle_v16i8:
; SSSE3: # %bb.0:
; SSSE3-NEXT: pshufb %xmm1, %xmm0
; SSSE3-NEXT: retq
;
; SSE41-LABEL: var_shuffle_v16i8:
; SSE41: # %bb.0:
; SSE41-NEXT: pshufb %xmm1, %xmm0
; SSE41-NEXT: retq
X86 Tests: Add tests for vector permutes with variable indices. NFC. Basic tests which are the equivalent of single-source shufflevector with variable mask. llvm-svn: 316216
2017-10-20 23:32:14 +08:00
;
; AVX-LABEL: var_shuffle_v16i8:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; AVX: # %bb.0:
[X86][SSE] LowerBUILD_VECTORAsVariablePermute - fix PSHUFB source/index operand ordering As detailed in rL317463, PSHUFB (like most variable shuffle instructions) uses Op[0] for the source vector and Op[1] for the shuffle index vector, VPERMV works in reverse which is probably where the confusion comes from. Differential Revision: https://reviews.llvm.org/D42380 llvm-svn: 323190
2018-01-23 19:39:06 +08:00
; AVX-NEXT: vpshufb %xmm1, %xmm0, %xmm0
X86 Tests: Add tests for vector permutes with variable indices. NFC. Basic tests which are the equivalent of single-source shufflevector with variable mask. llvm-svn: 316216
2017-10-20 23:32:14 +08:00
; AVX-NEXT: retq
%index0 = extractelement <16 x i8> %indices, i32 0
%index1 = extractelement <16 x i8> %indices, i32 1
%index2 = extractelement <16 x i8> %indices, i32 2
%index3 = extractelement <16 x i8> %indices, i32 3
%index4 = extractelement <16 x i8> %indices, i32 4
%index5 = extractelement <16 x i8> %indices, i32 5
%index6 = extractelement <16 x i8> %indices, i32 6
%index7 = extractelement <16 x i8> %indices, i32 7
%index8 = extractelement <16 x i8> %indices, i32 8
%index9 = extractelement <16 x i8> %indices, i32 9
%index10 = extractelement <16 x i8> %indices, i32 10
%index11 = extractelement <16 x i8> %indices, i32 11
%index12 = extractelement <16 x i8> %indices, i32 12
%index13 = extractelement <16 x i8> %indices, i32 13
%index14 = extractelement <16 x i8> %indices, i32 14
%index15 = extractelement <16 x i8> %indices, i32 15
%v0 = extractelement <16 x i8> %v, i8 %index0
%v1 = extractelement <16 x i8> %v, i8 %index1
%v2 = extractelement <16 x i8> %v, i8 %index2
%v3 = extractelement <16 x i8> %v, i8 %index3
%v4 = extractelement <16 x i8> %v, i8 %index4
%v5 = extractelement <16 x i8> %v, i8 %index5
%v6 = extractelement <16 x i8> %v, i8 %index6
%v7 = extractelement <16 x i8> %v, i8 %index7
%v8 = extractelement <16 x i8> %v, i8 %index8
%v9 = extractelement <16 x i8> %v, i8 %index9
%v10 = extractelement <16 x i8> %v, i8 %index10
%v11 = extractelement <16 x i8> %v, i8 %index11
%v12 = extractelement <16 x i8> %v, i8 %index12
%v13 = extractelement <16 x i8> %v, i8 %index13
%v14 = extractelement <16 x i8> %v, i8 %index14
%v15 = extractelement <16 x i8> %v, i8 %index15
%ret0 = insertelement <16 x i8> undef, i8 %v0, i32 0
%ret1 = insertelement <16 x i8> %ret0, i8 %v1, i32 1
%ret2 = insertelement <16 x i8> %ret1, i8 %v2, i32 2
%ret3 = insertelement <16 x i8> %ret2, i8 %v3, i32 3
%ret4 = insertelement <16 x i8> %ret3, i8 %v4, i32 4
%ret5 = insertelement <16 x i8> %ret4, i8 %v5, i32 5
%ret6 = insertelement <16 x i8> %ret5, i8 %v6, i32 6
%ret7 = insertelement <16 x i8> %ret6, i8 %v7, i32 7
%ret8 = insertelement <16 x i8> %ret7, i8 %v8, i32 8
%ret9 = insertelement <16 x i8> %ret8, i8 %v9, i32 9
%ret10 = insertelement <16 x i8> %ret9, i8 %v10, i32 10
%ret11 = insertelement <16 x i8> %ret10, i8 %v11, i32 11
%ret12 = insertelement <16 x i8> %ret11, i8 %v12, i32 12
%ret13 = insertelement <16 x i8> %ret12, i8 %v13, i32 13
%ret14 = insertelement <16 x i8> %ret13, i8 %v14, i32 14
%ret15 = insertelement <16 x i8> %ret14, i8 %v15, i32 15
ret <16 x i8> %ret15
}
X86 Tests: Update the variable-index permute tests with FP types. NFC. These cases will be addressed in a future update to D39126. llvm-svn: 316946
2017-10-31 03:29:15 +08:00
define <2 x double> @var_shuffle_v2f64(<2 x double> %v, <2 x i64> %indices) nounwind {
[X86][SSE] createVariablePermute - PSHUFB requires SSSE3 not just SSE3 llvm-svn: 327259
2018-03-12 20:30:04 +08:00
; SSE3-LABEL: var_shuffle_v2f64:
; SSE3: # %bb.0:
; SSE3-NEXT: movq %xmm1, %rax
; SSE3-NEXT: andl $1, %eax
; SSE3-NEXT: pshufd {{.*#+}} xmm1 = xmm1[2,3,0,1]
; SSE3-NEXT: movq %xmm1, %rcx
; SSE3-NEXT: andl $1, %ecx
; SSE3-NEXT: movaps %xmm0, -{{[0-9]+}}(%rsp)
; SSE3-NEXT: movsd {{.*#+}} xmm0 = mem[0],zero
; SSE3-NEXT: movhpd {{.*#+}} xmm0 = xmm0[0],mem[0]
; SSE3-NEXT: retq
;
X86 Tests: Update the variable-index permute tests with FP types. NFC. These cases will be addressed in a future update to D39126. llvm-svn: 316946
2017-10-31 03:29:15 +08:00
; SSSE3-LABEL: var_shuffle_v2f64:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; SSSE3: # %bb.0:
X86 Tests: Update the variable-index permute tests with FP types. NFC. These cases will be addressed in a future update to D39126. llvm-svn: 316946
2017-10-31 03:29:15 +08:00
; SSSE3-NEXT: movq %xmm1, %rax
; SSSE3-NEXT: andl $1, %eax
; SSSE3-NEXT: pshufd {{.*#+}} xmm1 = xmm1[2,3,0,1]
; SSSE3-NEXT: movq %xmm1, %rcx
; SSSE3-NEXT: andl $1, %ecx
; SSSE3-NEXT: movaps %xmm0, -{{[0-9]+}}(%rsp)
; SSSE3-NEXT: movsd {{.*#+}} xmm0 = mem[0],zero
; SSSE3-NEXT: movhpd {{.*#+}} xmm0 = xmm0[0],mem[0]
; SSSE3-NEXT: retq
;
[X86][SSE] Add SSE41 to variable permute tests llvm-svn: 324017
2018-02-02 06:05:44 +08:00
; SSE41-LABEL: var_shuffle_v2f64:
; SSE41: # %bb.0:
[X86][SSE41] createVariablePermute v2X64 - PCMPEQQ can test for index 0/1 and select between them. llvm-svn: 327385
2018-03-13 20:22:58 +08:00
; SSE41-NEXT: movdqa %xmm0, %xmm2
; SSE41-NEXT: pxor %xmm0, %xmm0
; SSE41-NEXT: pcmpeqq %xmm1, %xmm0
; SSE41-NEXT: movddup {{.*#+}} xmm1 = xmm2[0,0]
[X86] Allow fake unary unpckhpd and movhlps to be commuted for execution domain fixing purposes These instructions perform the same operation, but the semantic of which operand is destroyed is reversed. If the same register is used as both operands we can change the execution domain without worrying about this difference. Unfortunately, this really only works in cases where the input register is killed by the instruction. If its not killed, the two address isntruction pass inserts a copy that will become a move instruction. This makes the instruction use different physical registers that contain the same data at the time the unpck/movhlps executes. I've considered using a unary pseudo instruction with tied operand to trick the two address instruction pass. We could then expand the pseudo post regalloc to get the same physical register on both inputs. Differential Revision: https://reviews.llvm.org/D50157 llvm-svn: 338735
2018-08-03 00:48:01 +08:00
; SSE41-NEXT: unpckhpd {{.*#+}} xmm2 = xmm2[1,1]
[X86][SSE41] createVariablePermute v2X64 - PCMPEQQ can test for index 0/1 and select between them. llvm-svn: 327385
2018-03-13 20:22:58 +08:00
; SSE41-NEXT: blendvpd %xmm0, %xmm1, %xmm2
; SSE41-NEXT: movapd %xmm2, %xmm0
[X86][SSE] Add SSE41 to variable permute tests llvm-svn: 324017
2018-02-02 06:05:44 +08:00
; SSE41-NEXT: retq
;
X86 Tests: Update the variable-index permute tests with FP types. NFC. These cases will be addressed in a future update to D39126. llvm-svn: 316946
2017-10-31 03:29:15 +08:00
; AVX-LABEL: var_shuffle_v2f64:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; AVX: # %bb.0:
[X86][AVX] createVariablePermute - fix v2i64/v2f64 VPERMILPD index creation. The input indices vector will put the index in bit0, but VPERMILPD actually selects off bit1 - so we need to scale accordingly. llvm-svn: 327159
2018-03-10 02:37:56 +08:00
; AVX-NEXT: vpaddq %xmm1, %xmm1, %xmm1
[X86][AVX] LowerBUILD_VECTORAsVariablePermute - add support for VPERMILPV to v2i64/v2f64 Minor refactor to make it possible for LowerBUILD_VECTORAsVariablePermute to be used with a wider variety of shuffles op and types. I'd have liked to add v4i32/v4f32 support as well but we don't see v4i32 index extractions at the moment (which is why I created D42308) After this I intend to begin adding scaling support for PSHUFB (v8i16, v4i32, v2i64)) and VPERMPS (v4f64, v4i64). Differential Revision: https://reviews.llvm.org/D42431 llvm-svn: 323260
2018-01-24 05:33:24 +08:00
; AVX-NEXT: vpermilpd %xmm1, %xmm0, %xmm0
X86 Tests: Update the variable-index permute tests with FP types. NFC. These cases will be addressed in a future update to D39126. llvm-svn: 316946
2017-10-31 03:29:15 +08:00
; AVX-NEXT: retq
%index0 = extractelement <2 x i64> %indices, i32 0
%index1 = extractelement <2 x i64> %indices, i32 1
%v0 = extractelement <2 x double> %v, i64 %index0
%v1 = extractelement <2 x double> %v, i64 %index1
%ret0 = insertelement <2 x double> undef, double %v0, i32 0
%ret1 = insertelement <2 x double> %ret0, double %v1, i32 1
ret <2 x double> %ret1
}
define <4 x float> @var_shuffle_v4f32(<4 x float> %v, <4 x i32> %indices) nounwind {
[X86][SSE] createVariablePermute - PSHUFB requires SSSE3 not just SSE3 llvm-svn: 327259
2018-03-12 20:30:04 +08:00
; SSE3-LABEL: var_shuffle_v4f32:
; SSE3: # %bb.0:
; SSE3-NEXT: movd %xmm1, %eax
; SSE3-NEXT: pshufd {{.*#+}} xmm2 = xmm1[1,1,2,3]
; SSE3-NEXT: movd %xmm2, %ecx
; SSE3-NEXT: pshufd {{.*#+}} xmm2 = xmm1[2,3,0,1]
; SSE3-NEXT: movd %xmm2, %edx
; SSE3-NEXT: pshufd {{.*#+}} xmm1 = xmm1[3,1,2,3]
; SSE3-NEXT: movd %xmm1, %esi
; SSE3-NEXT: movaps %xmm0, -{{[0-9]+}}(%rsp)
; SSE3-NEXT: andl $3, %eax
; SSE3-NEXT: movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
[X86] Remove some composite MOVSS/MOVSD isel patterns. These patterns looked for a MOVSS/SD followed by a scalar_to_vector. Or a scalar_to_vector followed by a load. In both cases we emitted a MOVSS/SD for the MOVSS/SD part, a REG_CLASS for the scalar_to_vector, and a MOVSS/SD for the load. But we have patterns that do each of those 3 things individually so there's no reason to build large patterns. Most of the test changes are just reorderings. The one test that had a meaningful change is pr30430.ll and it appears to be a regression. But its doing -O0 so I think it missed a lot of opportunities and was just getting lucky before. llvm-svn: 336762
2018-07-11 12:51:40 +08:00
; SSE3-NEXT: andl $3, %ecx
[X86][SSE] createVariablePermute - PSHUFB requires SSSE3 not just SSE3 llvm-svn: 327259
2018-03-12 20:30:04 +08:00
; SSE3-NEXT: movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
[X86] Merge the FR128 and VR128 regclass since they have identical spill and alignment characteristics. This unfortunately requires a bunch of bitcasts to be added added to SUBREG_TO_REG, COPY_TO_REGCLASS, and instructions in output patterns. Otherwise tablegen seems to default to picking f128 and then we fail when something tries to get the register class for f128 which isn't always valid. The test changes are because we were previously mixing fr128 and vr128 due to contrainRegClass finding FR128 first and passes like live range shrinking weren't handling that well. llvm-svn: 337147
2018-07-16 14:56:09 +08:00
; SSE3-NEXT: unpcklps {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
[X86] Remove some composite MOVSS/MOVSD isel patterns. These patterns looked for a MOVSS/SD followed by a scalar_to_vector. Or a scalar_to_vector followed by a load. In both cases we emitted a MOVSS/SD for the MOVSS/SD part, a REG_CLASS for the scalar_to_vector, and a MOVSS/SD for the load. But we have patterns that do each of those 3 things individually so there's no reason to build large patterns. Most of the test changes are just reorderings. The one test that had a meaningful change is pr30430.ll and it appears to be a regression. But its doing -O0 so I think it missed a lot of opportunities and was just getting lucky before. llvm-svn: 336762
2018-07-11 12:51:40 +08:00
; SSE3-NEXT: andl $3, %edx
[X86] Merge the FR128 and VR128 regclass since they have identical spill and alignment characteristics. This unfortunately requires a bunch of bitcasts to be added added to SUBREG_TO_REG, COPY_TO_REGCLASS, and instructions in output patterns. Otherwise tablegen seems to default to picking f128 and then we fail when something tries to get the register class for f128 which isn't always valid. The test changes are because we were previously mixing fr128 and vr128 due to contrainRegClass finding FR128 first and passes like live range shrinking weren't handling that well. llvm-svn: 337147
2018-07-16 14:56:09 +08:00
; SSE3-NEXT: movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
[X86] Remove some composite MOVSS/MOVSD isel patterns. These patterns looked for a MOVSS/SD followed by a scalar_to_vector. Or a scalar_to_vector followed by a load. In both cases we emitted a MOVSS/SD for the MOVSS/SD part, a REG_CLASS for the scalar_to_vector, and a MOVSS/SD for the load. But we have patterns that do each of those 3 things individually so there's no reason to build large patterns. Most of the test changes are just reorderings. The one test that had a meaningful change is pr30430.ll and it appears to be a regression. But its doing -O0 so I think it missed a lot of opportunities and was just getting lucky before. llvm-svn: 336762
2018-07-11 12:51:40 +08:00
; SSE3-NEXT: andl $3, %esi
[X86] Merge the FR128 and VR128 regclass since they have identical spill and alignment characteristics. This unfortunately requires a bunch of bitcasts to be added added to SUBREG_TO_REG, COPY_TO_REGCLASS, and instructions in output patterns. Otherwise tablegen seems to default to picking f128 and then we fail when something tries to get the register class for f128 which isn't always valid. The test changes are because we were previously mixing fr128 and vr128 due to contrainRegClass finding FR128 first and passes like live range shrinking weren't handling that well. llvm-svn: 337147
2018-07-16 14:56:09 +08:00
; SSE3-NEXT: movss {{.*#+}} xmm2 = mem[0],zero,zero,zero
; SSE3-NEXT: unpcklps {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
; SSE3-NEXT: movlhps {{.*#+}} xmm0 = xmm0[0],xmm1[0]
[X86][SSE] createVariablePermute - PSHUFB requires SSSE3 not just SSE3 llvm-svn: 327259
2018-03-12 20:30:04 +08:00
; SSE3-NEXT: retq
;
X86 Tests: Update the variable-index permute tests with FP types. NFC. These cases will be addressed in a future update to D39126. llvm-svn: 316946
2017-10-31 03:29:15 +08:00
; SSSE3-LABEL: var_shuffle_v4f32:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; SSSE3: # %bb.0:
[X86][SSE] LowerBUILD_VECTORAsVariablePermute - add support for scaling index vectors This allows us to use PSHUFB for v8i16/v4i32 and VPERMD/PERMPS for v4i64/v4f64 variable shuffles. Differential Revision: https://reviews.llvm.org/D42487 llvm-svn: 323987
2018-02-02 02:10:30 +08:00
; SSSE3-NEXT: movdqa {{.*#+}} xmm2 = [67372036,67372036,67372036,67372036]
; SSSE3-NEXT: pshufd {{.*#+}} xmm3 = xmm1[1,1,3,3]
; SSSE3-NEXT: pmuludq %xmm2, %xmm1
; SSSE3-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
; SSSE3-NEXT: pmuludq %xmm2, %xmm3
; SSSE3-NEXT: pshufd {{.*#+}} xmm2 = xmm3[0,2,2,3]
; SSSE3-NEXT: punpckldq {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
; SSSE3-NEXT: paddd {{.*}}(%rip), %xmm1
; SSSE3-NEXT: pshufb %xmm1, %xmm0
X86 Tests: Update the variable-index permute tests with FP types. NFC. These cases will be addressed in a future update to D39126. llvm-svn: 316946
2017-10-31 03:29:15 +08:00
; SSSE3-NEXT: retq
;
[X86][SSE] Add SSE41 to variable permute tests llvm-svn: 324017
2018-02-02 06:05:44 +08:00
; SSE41-LABEL: var_shuffle_v4f32:
; SSE41: # %bb.0:
; SSE41-NEXT: pmulld {{.*}}(%rip), %xmm1
; SSE41-NEXT: paddd {{.*}}(%rip), %xmm1
; SSE41-NEXT: pshufb %xmm1, %xmm0
; SSE41-NEXT: retq
;
X86 Tests: Update the variable-index permute tests with FP types. NFC. These cases will be addressed in a future update to D39126. llvm-svn: 316946
2017-10-31 03:29:15 +08:00
; AVX-LABEL: var_shuffle_v4f32:
[CodeGen] Unify MBB reference format in both MIR and debug output As part of the unification of the debug format and the MIR format, print MBB references as '%bb.5'. The MIR printer prints the IR name of a MBB only for block definitions. * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)->getNumber\(\)/" << printMBBReference(*\1)/g' * find . \( -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#" << ([a-zA-Z0-9_]+)\.getNumber\(\)/" << printMBBReference(\1)/g' * find . \( -name "*.txt" -o -name "*.s" -o -name "*.mir" -o -name "*.cpp" -o -name "*.h" -o -name "*.ll" \) -type f -print0 | xargs -0 sed -i '' -E 's/BB#([0-9]+)/%bb.\1/g' * grep -nr 'BB#' and fix Differential Revision: https://reviews.llvm.org/D40422 llvm-svn: 319665
2017-12-05 01:18:51 +08:00
; AVX: # %bb.0:
[X86][AVX] LowerBUILD_VECTORAsVariablePermute - add support for VPERMILPV to v4i32/v4f32 Extension to D42431, adding support for v4i32/v4f32 as well as v2i64/v2f64 now that D42308 has landed llvm-svn: 323542
2018-01-27 01:19:59 +08:00
; AVX-NEXT: vpermilps %xmm1, %xmm0, %xmm0
X86 Tests: Update the variable-index permute tests with FP types. NFC. These cases will be addressed in a future update to D39126. llvm-svn: 316946
2017-10-31 03:29:15 +08:00
; AVX-NEXT: retq
%index0 = extractelement <4 x i32> %indices, i32 0
%index1 = extractelement <4 x i32> %indices, i32 1
%index2 = extractelement <4 x i32> %indices, i32 2
%index3 = extractelement <4 x i32> %indices, i32 3
%v0 = extractelement <4 x float> %v, i32 %index0
%v1 = extractelement <4 x float> %v, i32 %index1
%v2 = extractelement <4 x float> %v, i32 %index2
%v3 = extractelement <4 x float> %v, i32 %index3
%ret0 = insertelement <4 x float> undef, float %v0, i32 0
%ret1 = insertelement <4 x float> %ret0, float %v1, i32 1
%ret2 = insertelement <4 x float> %ret1, float %v2, i32 2
%ret3 = insertelement <4 x float> %ret2, float %v3, i32 3
ret <4 x float> %ret3
}
[X86][SSE] LowerBUILD_VECTORAsVariablePermute - ensure that the index vector has the correct number of elements llvm-svn: 323206
2018-01-23 23:13:37 +08:00
define <16 x i8> @var_shuffle_v16i8_from_v16i8_v32i8(<16 x i8> %v, <32 x i8> %indices) nounwind {
[X86][SSE] createVariablePermute - PSHUFB requires SSSE3 not just SSE3 llvm-svn: 327259
2018-03-12 20:30:04 +08:00
; SSE3-LABEL: var_shuffle_v16i8_from_v16i8_v32i8:
; SSE3: # %bb.0:
; SSE3-NEXT: movaps %xmm1, -{{[0-9]+}}(%rsp)
; SSE3-NEXT: movaps %xmm0, -{{[0-9]+}}(%rsp)
; SSE3-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE3-NEXT: andl $15, %eax
; SSE3-NEXT: movzbl -24(%rsp,%rax), %eax
; SSE3-NEXT: movd %eax, %xmm8
; SSE3-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE3-NEXT: andl $15, %eax
; SSE3-NEXT: movzbl -24(%rsp,%rax), %eax
; SSE3-NEXT: movd %eax, %xmm15
; SSE3-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE3-NEXT: andl $15, %eax
; SSE3-NEXT: movzbl -24(%rsp,%rax), %eax
; SSE3-NEXT: movd %eax, %xmm9
; SSE3-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE3-NEXT: andl $15, %eax
; SSE3-NEXT: movzbl -24(%rsp,%rax), %eax
; SSE3-NEXT: movd %eax, %xmm3
; SSE3-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE3-NEXT: andl $15, %eax
; SSE3-NEXT: movzbl -24(%rsp,%rax), %eax
; SSE3-NEXT: movd %eax, %xmm10
; SSE3-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE3-NEXT: andl $15, %eax
; SSE3-NEXT: movzbl -24(%rsp,%rax), %eax
; SSE3-NEXT: movd %eax, %xmm7
; SSE3-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE3-NEXT: andl $15, %eax
; SSE3-NEXT: movzbl -24(%rsp,%rax), %eax
; SSE3-NEXT: movd %eax, %xmm11
; SSE3-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE3-NEXT: andl $15, %eax
; SSE3-NEXT: movzbl -24(%rsp,%rax), %eax
; SSE3-NEXT: movd %eax, %xmm6
; SSE3-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE3-NEXT: andl $15, %eax
; SSE3-NEXT: movzbl -24(%rsp,%rax), %eax
; SSE3-NEXT: movd %eax, %xmm12
; SSE3-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE3-NEXT: andl $15, %eax
; SSE3-NEXT: movzbl -24(%rsp,%rax), %eax
; SSE3-NEXT: movd %eax, %xmm5
; SSE3-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE3-NEXT: andl $15, %eax
; SSE3-NEXT: movzbl -24(%rsp,%rax), %eax
; SSE3-NEXT: movd %eax, %xmm13
; SSE3-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE3-NEXT: andl $15, %eax
; SSE3-NEXT: movzbl -24(%rsp,%rax), %eax
; SSE3-NEXT: movd %eax, %xmm4
; SSE3-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE3-NEXT: andl $15, %eax
; SSE3-NEXT: movzbl -24(%rsp,%rax), %eax
; SSE3-NEXT: movd %eax, %xmm14
; SSE3-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE3-NEXT: andl $15, %eax
; SSE3-NEXT: movzbl -24(%rsp,%rax), %eax
; SSE3-NEXT: movd %eax, %xmm1
; SSE3-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE3-NEXT: andl $15, %eax
; SSE3-NEXT: movzbl -24(%rsp,%rax), %eax
; SSE3-NEXT: movd %eax, %xmm2
; SSE3-NEXT: movzbl -{{[0-9]+}}(%rsp), %eax
; SSE3-NEXT: andl $15, %eax
; SSE3-NEXT: movzbl -24(%rsp,%rax), %eax
; SSE3-NEXT: movd %eax, %xmm0
; SSE3-NEXT: punpcklbw {{.*#+}} xmm15 = xmm15[0],xmm8[0],xmm15[1],xmm8[1],xmm15[2],xmm8[2],xmm15[3],xmm8[3],xmm15[4],xmm8[4],xmm15[5],xmm8[5],xmm15[6],xmm8[6],xmm15[7],xmm8[7]
; SSE3-NEXT: punpcklbw {{.*#+}} xmm3 = xmm3[0],xmm9[0],xmm3[1],xmm9[1],xmm3[2],xmm9[2],xmm3[3],xmm9[3],xmm3[4],xmm9[4],xmm3[5],xmm9[5],xmm3[6],xmm9[6],xmm3[7],xmm9[7]
; SSE3-NEXT: punpcklwd {{.*#+}} xmm3 = xmm3[0],xmm15[0],xmm3[1],xmm15[1],xmm3[2],xmm15[2],xmm3[3],xmm15[3]
; SSE3-NEXT: punpcklbw {{.*#+}} xmm7 = xmm7[0],xmm10[0],xmm7[1],xmm10[1],xmm7[2],xmm10[2],xmm7[3],xmm10[3],xmm7[4],xmm10[4],xmm7[5],xmm10[5],xmm7[6],xmm10[6],xmm7[7],xmm10[7]
; SSE3-NEXT: punpcklbw {{.*#+}} xmm6 = xmm6[0],xmm11[0],xmm6[1],xmm11[1],xmm6[2],xmm11[2],xmm6[3],xmm11[3],xmm6[4],xmm11[4],xmm6[5],xmm11[5],xmm6[6],xmm11[6],xmm6[7],xmm11[7]
; SSE3-NEXT: punpcklwd {{.*#+}} xmm6 = xmm6[0],xmm7[0],xmm6[1],xmm7[1],xmm6[2],xmm7[2],xmm6[3],xmm7[3]
; SSE3-NEXT: punpckldq {{.*#+}} xmm6 = xmm6[0],xmm3[0],xmm6[1],xmm3[1]
; SSE3-NEXT: punpcklbw {{.*#+}} xmm5 = xmm5[0],xmm12[0],xmm5[1],xmm12[1],xmm5[2],xmm12[2],xmm5[3],xmm12[3],xmm5[4],xmm12[4],xmm5[5],xmm12[5],xmm5[6],xmm12[6],xmm5[7],xmm12[7]
; SSE3-NEXT: punpcklbw {{.*#+}} xmm4 = xmm4[0],xmm13[0],xmm4[1],xmm13[1],xmm4[2],xmm13[2],xmm4[3],xmm13[3],xmm4[4],xmm13[4],xmm4[5],xmm13[5],xmm4[6],xmm13[6],xmm4[7],xmm13[7]
; SSE3-NEXT: punpcklwd {{.*#+}} xmm4 = xmm4[0],xmm5[0],xmm4[1],xmm5[1],xmm4[2],xmm5[2],xmm4[3],xmm5[3]
; SSE3-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm14[0],xmm1[1],xmm14[1],xmm1[2],xmm14[2],xmm1[3],xmm14[3],xmm1[4],xmm14[4],xmm1[5],xmm14[5],xmm1[6],xmm14[6],xmm1[7],xmm14[7]
; SSE3-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3],xmm0[4],xmm2[4],xmm0[5],xmm2[5],xmm0[6],xmm2[6],xmm0[7],xmm2[7]
; SSE3-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
; SSE3-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm4[0],xmm0[1],xmm4[1]
; SSE3-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm6[0]
; SSE3-NEXT: retq
;
; SSSE3-LABEL: var_shuffle_v16i8_from_v16i8_v32i8:
; SSSE3: # %bb.0:
; SSSE3-NEXT: pshufb %xmm1, %xmm0
; SSSE3-NEXT: retq
;
; SSE41-LABEL: var_shuffle_v16i8_from_v16i8_v32i8:
; SSE41: # %bb.0:
; SSE41-NEXT: pshufb %xmm1, %xmm0
; SSE41-NEXT: retq
[X86][SSE] LowerBUILD_VECTORAsVariablePermute - ensure that the index vector has the correct number of elements llvm-svn: 323206
2018-01-23 23:13:37 +08:00
;
; AVX-LABEL: var_shuffle_v16i8_from_v16i8_v32i8:
; AVX: # %bb.0:
[X86][SSE] LowerBUILD_VECTORAsVariablePermute - extract subvector from oversized index vectors llvm-svn: 323223
2018-01-24 01:02:15 +08:00
; AVX-NEXT: vpshufb %xmm1, %xmm0, %xmm0
[X86][SSE] LowerBUILD_VECTORAsVariablePermute - ensure that the index vector has the correct number of elements llvm-svn: 323206
2018-01-23 23:13:37 +08:00
; AVX-NEXT: vzeroupper
; AVX-NEXT: retq
%index0 = extractelement <32 x i8> %indices, i32 0
%index1 = extractelement <32 x i8> %indices, i32 1
%index2 = extractelement <32 x i8> %indices, i32 2
%index3 = extractelement <32 x i8> %indices, i32 3
%index4 = extractelement <32 x i8> %indices, i32 4
%index5 = extractelement <32 x i8> %indices, i32 5
%index6 = extractelement <32 x i8> %indices, i32 6
%index7 = extractelement <32 x i8> %indices, i32 7
%index8 = extractelement <32 x i8> %indices, i32 8
%index9 = extractelement <32 x i8> %indices, i32 9
%index10 = extractelement <32 x i8> %indices, i32 10
%index11 = extractelement <32 x i8> %indices, i32 11
%index12 = extractelement <32 x i8> %indices, i32 12
%index13 = extractelement <32 x i8> %indices, i32 13
%index14 = extractelement <32 x i8> %indices, i32 14
%index15 = extractelement <32 x i8> %indices, i32 15
%v0 = extractelement <16 x i8> %v, i8 %index0
%v1 = extractelement <16 x i8> %v, i8 %index1
%v2 = extractelement <16 x i8> %v, i8 %index2
%v3 = extractelement <16 x i8> %v, i8 %index3
%v4 = extractelement <16 x i8> %v, i8 %index4
%v5 = extractelement <16 x i8> %v, i8 %index5
%v6 = extractelement <16 x i8> %v, i8 %index6
%v7 = extractelement <16 x i8> %v, i8 %index7
%v8 = extractelement <16 x i8> %v, i8 %index8
%v9 = extractelement <16 x i8> %v, i8 %index9
%v10 = extractelement <16 x i8> %v, i8 %index10
%v11 = extractelement <16 x i8> %v, i8 %index11
%v12 = extractelement <16 x i8> %v, i8 %index12
%v13 = extractelement <16 x i8> %v, i8 %index13
%v14 = extractelement <16 x i8> %v, i8 %index14
%v15 = extractelement <16 x i8> %v, i8 %index15
%ret0 = insertelement <16 x i8> undef, i8 %v0, i32 0
%ret1 = insertelement <16 x i8> %ret0, i8 %v1, i32 1
%ret2 = insertelement <16 x i8> %ret1, i8 %v2, i32 2
%ret3 = insertelement <16 x i8> %ret2, i8 %v3, i32 3
%ret4 = insertelement <16 x i8> %ret3, i8 %v4, i32 4
%ret5 = insertelement <16 x i8> %ret4, i8 %v5, i32 5
%ret6 = insertelement <16 x i8> %ret5, i8 %v6, i32 6
%ret7 = insertelement <16 x i8> %ret6, i8 %v7, i32 7
%ret8 = insertelement <16 x i8> %ret7, i8 %v8, i32 8
%ret9 = insertelement <16 x i8> %ret8, i8 %v9, i32 9
%ret10 = insertelement <16 x i8> %ret9, i8 %v10, i32 10
%ret11 = insertelement <16 x i8> %ret10, i8 %v11, i32 11
%ret12 = insertelement <16 x i8> %ret11, i8 %v12, i32 12
%ret13 = insertelement <16 x i8> %ret12, i8 %v13, i32 13
%ret14 = insertelement <16 x i8> %ret13, i8 %v14, i32 14
%ret15 = insertelement <16 x i8> %ret14, i8 %v15, i32 15
ret <16 x i8> %ret15
}
[X86][SSE] LowerBUILD_VECTORAsVariablePermute - ensure that the source vector is not larger than the destination We might be able to support this in the future with VPERMV3, OR(PSHUFB, PSHUFB) etc. llvm-svn: 323210
2018-01-23 23:51:03 +08:00
define <16 x i8> @var_shuffle_v16i8_from_v32i8_v16i8(<32 x i8> %v, <16 x i8> %indices) nounwind {
[X86][SSE] createVariablePermute - PSHUFB requires SSSE3 not just SSE3 llvm-svn: 327259
2018-03-12 20:30:04 +08:00
; SSE3-LABEL: var_shuffle_v16i8_from_v32i8_v16i8:
; SSE3: # %bb.0:
; SSE3-NEXT: pushq %rbp
; SSE3-NEXT: movq %rsp, %rbp
; SSE3-NEXT: pushq %r15
; SSE3-NEXT: pushq %r14
; SSE3-NEXT: pushq %r13
; SSE3-NEXT: pushq %r12
; SSE3-NEXT: pushq %rbx
; SSE3-NEXT: andq $-32, %rsp
; SSE3-NEXT: subq $608, %rsp # imm = 0x260
; SSE3-NEXT: movaps %xmm2, {{[0-9]+}}(%rsp)
; SSE3-NEXT: movaps %xmm1, {{[0-9]+}}(%rsp)
; SSE3-NEXT: movaps %xmm0, {{[0-9]+}}(%rsp)
; SSE3-NEXT: movzbl {{[0-9]+}}(%rsp), %eax
[X86] Merge the FR128 and VR128 regclass since they have identical spill and alignment characteristics. This unfortunately requires a bunch of bitcasts to be added added to SUBREG_TO_REG, COPY_TO_REGCLASS, and instructions in output patterns. Otherwise tablegen seems to default to picking f128 and then we fail when something tries to get the register class for f128 which isn't always valid. The test changes are because we were previously mixing fr128 and vr128 due to contrainRegClass finding FR128 first and passes like live range shrinking weren't handling that well. llvm-svn: 337147
2018-07-16 14:56:09 +08:00
; SSE3-NEXT: movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
[X86][SSE] createVariablePermute - PSHUFB requires SSSE3 not just SSE3 llvm-svn: 327259
2018-03-12 20:30:04 +08:00
; SSE3-NEXT: movaps %xmm1, {{[0-9]+}}(%rsp)
; SSE3-NEXT: movaps %xmm0, {{[0-9]+}}(%rsp)
; SSE3-NEXT: movzbl {{[0-9]+}}(%rsp), %eax
[X86] Merge the FR128 and VR128 regclass since they have identical spill and alignment characteristics. This unfortunately requires a bunch of bitcasts to be added added to SUBREG_TO_REG, COPY_TO_REGCLASS, and instructions in output patterns. Otherwise tablegen seems to default to picking f128 and then we fail when something tries to get the register class for f128 which isn't always valid. The test changes are because we were previously mixing fr128 and vr128 due to contrainRegClass finding FR128 first and passes like live range shrinking weren't handling that well. llvm-svn: 337147
2018-07-16 14:56:09 +08:00
; SSE3-NEXT: movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
[X86][SSE] createVariablePermute - PSHUFB requires SSSE3 not just SSE3 llvm-svn: 327259
2018-03-12 20:30:04 +08:00
; SSE3-NEXT: movaps %xmm1, {{[0-9]+}}(%rsp)
; SSE3-NEXT: movaps %xmm0, {{[0-9]+}}(%rsp)
; SSE3-NEXT: movzbl {{[0-9]+}}(%rsp), %eax
[X86] Merge the FR128 and VR128 regclass since they have identical spill and alignment characteristics. This unfortunately requires a bunch of bitcasts to be added added to SUBREG_TO_REG, COPY_TO_REGCLASS, and instructions in output patterns. Otherwise tablegen seems to default to picking f128 and then we fail when something tries to get the register class for f128 which isn't always valid. The test changes are because we were previously mixing fr128 and vr128 due to contrainRegClass finding FR128 first and passes like live range shrinking weren't handling that well. llvm-svn: 337147
2018-07-16 14:56:09 +08:00
; SSE3-NEXT: movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
[X86][SSE] createVariablePermute - PSHUFB requires SSSE3 not just SSE3 llvm-svn: 327259
2018-03-12 20:30:04 +08:00
; SSE3-NEXT: movaps %xmm1, {{[0-9]+}}(%rsp)
; SSE3-NEXT: movaps %xmm0, {{[0-9]+}}(%rsp)
; SSE3-NEXT: movzbl {{[0-9]+}}(%rsp), %r11d
; SSE3-NEXT: movaps %xmm1, {{[0-9]+}}(%rsp)
; SSE3-NEXT: movaps %xmm0, {{[0-9]+}}(%rsp)
; SSE3-NEXT: movzbl {{[0-9]+}}(%rsp), %r14d
; SSE3-NEXT: movaps %xmm1, {{[0-9]+}}(%rsp)
; SSE3-NEXT: movaps %xmm0, {{[0-9]+}}(%rsp)
; SSE3-NEXT: movzbl {{[0-9]+}}(%rsp), %r15d
; SSE3-NEXT: movaps %xmm1, {{[0-9]+}}(%rsp)
; SSE3-NEXT: movaps %xmm0, {{[0-9]+}}(%rsp)
; SSE3-NEXT: movzbl {{[0-9]+}}(%rsp), %r12d
; SSE3-NEXT: movaps %xmm1, {{[0-9]+}}(%rsp)
; SSE3-NEXT: movaps %xmm0, {{[0-9]+}}(%rsp)
; SSE3-NEXT: movzbl {{[0-9]+}}(%rsp), %r13d
; SSE3-NEXT: movaps %xmm1, {{[0-9]+}}(%rsp)
; SSE3-NEXT: movaps %xmm0, {{[0-9]+}}(%rsp)
; SSE3-NEXT: movzbl {{[0-9]+}}(%rsp), %r10d
; SSE3-NEXT: movaps %xmm1, {{[0-9]+}}(%rsp)
; SSE3-NEXT: movaps %xmm0, {{[0-9]+}}(%rsp)
; SSE3-NEXT: movzbl {{[0-9]+}}(%rsp), %r8d
; SSE3-NEXT: movaps %xmm1, {{[0-9]+}}(%rsp)
; SSE3-NEXT: movaps %xmm0, {{[0-9]+}}(%rsp)
; SSE3-NEXT: movzbl {{[0-9]+}}(%rsp), %edi
; SSE3-NEXT: movaps %xmm1, {{[0-9]+}}(%rsp)
; SSE3-NEXT: movaps %xmm0, {{[0-9]+}}(%rsp)
; SSE3-NEXT: movzbl {{[0-9]+}}(%rsp), %esi
; SSE3-NEXT: movaps %xmm1, {{[0-9]+}}(%rsp)
; SSE3-NEXT: movaps %xmm0, {{[0-9]+}}(%rsp)
; SSE3-NEXT: movzbl {{[0-9]+}}(%rsp), %ecx
; SSE3-NEXT: movaps %xmm1, {{[0-9]+}}(%rsp)
; SSE3-NEXT: movaps %xmm0, {{[0-9]+}}(%rsp)
; SSE3-NEXT: movzbl {{[0-9]+}}(%rsp), %edx
; SSE3-NEXT: movaps %xmm1, {{[0-9]+}}(%rsp)
; SSE3-NEXT: movaps %xmm0, {{[0-9]+}}(%rsp)
; SSE3-NEXT: movzbl {{[0-9]+}}(%rsp), %eax
; SSE3-NEXT: movaps %xmm1, {{[0-9]+}}(%rsp)
; SSE3-NEXT: movaps %xmm0, {{[0-9]+}}(%rsp)
; SSE3-NEXT: movzbl {{[0-9]+}}(%rsp), %r9d
; SSE3-NEXT: andl $31, %r9d
; SSE3-NEXT: movzbl 64(%rsp,%r9), %ebx
; SSE3-NEXT: movd %ebx, %xmm8
; SSE3-NEXT: andl $31, %eax
; SSE3-NEXT: movzbl 96(%rsp,%rax), %eax
; SSE3-NEXT: movd %eax, %xmm15
; SSE3-NEXT: andl $31, %edx
; SSE3-NEXT: movzbl 128(%rsp,%rdx), %eax
; SSE3-NEXT: movd %eax, %xmm9
; SSE3-NEXT: andl $31, %ecx
; SSE3-NEXT: movzbl 160(%rsp,%rcx), %eax
; SSE3-NEXT: movd %eax, %xmm3
; SSE3-NEXT: andl $31, %esi
; SSE3-NEXT: movzbl 192(%rsp,%rsi), %eax
; SSE3-NEXT: movd %eax, %xmm10
; SSE3-NEXT: andl $31, %edi
; SSE3-NEXT: movzbl 224(%rsp,%rdi), %eax
; SSE3-NEXT: movd %eax, %xmm7
; SSE3-NEXT: andl $31, %r8d
; SSE3-NEXT: movzbl 256(%rsp,%r8), %eax
; SSE3-NEXT: movd %eax, %xmm11
; SSE3-NEXT: andl $31, %r10d
; SSE3-NEXT: movzbl 288(%rsp,%r10), %eax
; SSE3-NEXT: movd %eax, %xmm6
; SSE3-NEXT: andl $31, %r13d
; SSE3-NEXT: movzbl 320(%rsp,%r13), %eax
; SSE3-NEXT: movd %eax, %xmm12
; SSE3-NEXT: andl $31, %r12d
; SSE3-NEXT: movzbl 352(%rsp,%r12), %eax
; SSE3-NEXT: movd %eax, %xmm5
; SSE3-NEXT: andl $31, %r15d
; SSE3-NEXT: movzbl 384(%rsp,%r15), %eax
; SSE3-NEXT: movd %eax, %xmm13
; SSE3-NEXT: andl $31, %r14d
; SSE3-NEXT: movzbl 416(%rsp,%r14), %eax
; SSE3-NEXT: movd %eax, %xmm4
; SSE3-NEXT: andl $31, %r11d
; SSE3-NEXT: movzbl 448(%rsp,%r11), %eax
; SSE3-NEXT: movd %eax, %xmm14
[X86] Merge the FR128 and VR128 regclass since they have identical spill and alignment characteristics. This unfortunately requires a bunch of bitcasts to be added added to SUBREG_TO_REG, COPY_TO_REGCLASS, and instructions in output patterns. Otherwise tablegen seems to default to picking f128 and then we fail when something tries to get the register class for f128 which isn't always valid. The test changes are because we were previously mixing fr128 and vr128 due to contrainRegClass finding FR128 first and passes like live range shrinking weren't handling that well. llvm-svn: 337147
2018-07-16 14:56:09 +08:00
; SSE3-NEXT: movq {{[-0-9]+}}(%r{{[sb]}}p), %rax # 8-byte Reload
[X86][SSE] createVariablePermute - PSHUFB requires SSSE3 not just SSE3 llvm-svn: 327259
2018-03-12 20:30:04 +08:00
; SSE3-NEXT: andl $31, %eax
; SSE3-NEXT: movzbl 480(%rsp,%rax), %eax
; SSE3-NEXT: movd %eax, %xmm1
[X86] Merge the FR128 and VR128 regclass since they have identical spill and alignment characteristics. This unfortunately requires a bunch of bitcasts to be added added to SUBREG_TO_REG, COPY_TO_REGCLASS, and instructions in output patterns. Otherwise tablegen seems to default to picking f128 and then we fail when something tries to get the register class for f128 which isn't always valid. The test changes are because we were previously mixing fr128 and vr128 due to contrainRegClass finding FR128 first and passes like live range shrinking weren't handling that well. llvm-svn: 337147
2018-07-16 14:56:09 +08:00
; SSE3-NEXT: movq {{[-0-9]+}}(%r{{[sb]}}p), %rax # 8-byte Reload
[X86][SSE] createVariablePermute - PSHUFB requires SSSE3 not just SSE3 llvm-svn: 327259
2018-03-12 20:30:04 +08:00
; SSE3-NEXT: andl $31, %eax
; SSE3-NEXT: movzbl 512(%rsp,%rax), %eax
; SSE3-NEXT: movd %eax, %xmm2
[X86] Merge the FR128 and VR128 regclass since they have identical spill and alignment characteristics. This unfortunately requires a bunch of bitcasts to be added added to SUBREG_TO_REG, COPY_TO_REGCLASS, and instructions in output patterns. Otherwise tablegen seems to default to picking f128 and then we fail when something tries to get the register class for f128 which isn't always valid. The test changes are because we were previously mixing fr128 and vr128 due to contrainRegClass finding FR128 first and passes like live range shrinking weren't handling that well. llvm-svn: 337147
2018-07-16 14:56:09 +08:00
; SSE3-NEXT: movq {{[-0-9]+}}(%r{{[sb]}}p), %rax # 8-byte Reload
[X86][SSE] createVariablePermute - PSHUFB requires SSSE3 not just SSE3 llvm-svn: 327259
2018-03-12 20:30:04 +08:00
; SSE3-NEXT: andl $31, %eax
; SSE3-NEXT: movzbl 544(%rsp,%rax), %eax
; SSE3-NEXT: movd %eax, %xmm0
; SSE3-NEXT: punpcklbw {{.*#+}} xmm15 = xmm15[0],xmm8[0],xmm15[1],xmm8[1],xmm15[2],xmm8[2],xmm15[3],xmm8[3],xmm15[4],xmm8[4],xmm15[5],xmm8[5],xmm15[6],xmm8[6],xmm15[7],xmm8[7]
; SSE3-NEXT: punpcklbw {{.*#+}} xmm3 = xmm3[0],xmm9[0],xmm3[1],xmm9[1],xmm3[2],xmm9[2],xmm3[3],xmm9[3],xmm3[4],xmm9[4],xmm3[5],xmm9[5],xmm3[6],xmm9[6],xmm3[7],xmm9[7]
; SSE3-NEXT: punpcklwd {{.*#+}} xmm3 = xmm3[0],xmm15[0],xmm3[1],xmm15[1],xmm3[2],xmm15[2],xmm3[3],xmm15[3]
; SSE3-NEXT: punpcklbw {{.*#+}} xmm7 = xmm7[0],xmm10[0],xmm7[1],xmm10[1],xmm7[2],xmm10[2],xmm7[3],xmm10[3],xmm7[4],xmm10[4],xmm7[5],xmm10[5],xmm7[6],xmm10[6],xmm7[7],xmm10[7]
; SSE3-NEXT: punpcklbw {{.*#+}} xmm6 = xmm6[0],xmm11[0],xmm6[1],xmm11[1],xmm6[2],xmm11[2],xmm6[3],xmm11[3],xmm6[4],xmm11[4],xmm6[5],xmm11[5],xmm6[6],xmm11[6],xmm6[7],xmm11[7]
; SSE3-NEXT: punpcklwd {{.*#+}} xmm6 = xmm6[0],xmm7[0],xmm6[1],xmm7[1],xmm6[2],xmm7[2],xmm6[3],xmm7[3]
; SSE3-NEXT: punpckldq {{.*#+}} xmm6 = xmm6[0],xmm3[0],xmm6[1],xmm3[1]
; SSE3-NEXT: punpcklbw {{.*#+}} xmm5 = xmm5[0],xmm12[0],xmm5[1],xmm12[1],xmm5[2],xmm12[2],xmm5[3],xmm12[3],xmm5[4],xmm12[4],xmm5[5],xmm12[5],xmm5[6],xmm12[6],xmm5[7],xmm12[7]
; SSE3-NEXT: punpcklbw {{.*#+}} xmm4 = xmm4[0],xmm13[0],xmm4[1],xmm13[1],xmm4[2],xmm13[2],xmm4[3],xmm13[3],xmm4[4],xmm13[4],xmm4[5],xmm13[5],xmm4[6],xmm13[6],xmm4[7],xmm13[7]
; SSE3-NEXT: punpcklwd {{.*#+}} xmm4 = xmm4[0],xmm5[0],xmm4[1],xmm5[1],xmm4[2],xmm5[2],xmm4[3],xmm5[3]
; SSE3-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm14[0],xmm1[1],xmm14[1],xmm1[2],xmm14[2],xmm1[3],xmm14[3],xmm1[4],xmm14[4],xmm1[5],xmm14[5],xmm1[6],xmm14[6],xmm1[7],xmm14[7]
; SSE3-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3],xmm0[4],xmm2[4],xmm0[5],xmm2[5],xmm0[6],xmm2[6],xmm0[7],xmm2[7]
; SSE3-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
; SSE3-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm4[0],xmm0[1],xmm4[1]
; SSE3-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm6[0]
; SSE3-NEXT: leaq -40(%rbp), %rsp
; SSE3-NEXT: popq %rbx
; SSE3-NEXT: popq %r12
; SSE3-NEXT: popq %r13
; SSE3-NEXT: popq %r14
; SSE3-NEXT: popq %r15
; SSE3-NEXT: popq %rbp
; SSE3-NEXT: retq
;
[X86][SSE] LowerBUILD_VECTORAsVariablePermute - ensure that the source vector is not larger than the destination We might be able to support this in the future with VPERMV3, OR(PSHUFB, PSHUFB) etc. llvm-svn: 323210
2018-01-23 23:51:03 +08:00
; SSSE3-LABEL: var_shuffle_v16i8_from_v32i8_v16i8:
; SSSE3: # %bb.0:
; SSSE3-NEXT: pushq %rbp
; SSSE3-NEXT: movq %rsp, %rbp
; SSSE3-NEXT: pushq %r15
; SSSE3-NEXT: pushq %r14
; SSSE3-NEXT: pushq %r13
; SSSE3-NEXT: pushq %r12
; SSSE3-NEXT: pushq %rbx
; SSSE3-NEXT: andq $-32, %rsp
; SSSE3-NEXT: subq $608, %rsp # imm = 0x260
; SSSE3-NEXT: movaps %xmm2, {{[0-9]+}}(%rsp)
; SSSE3-NEXT: movaps %xmm1, {{[0-9]+}}(%rsp)
; SSSE3-NEXT: movaps %xmm0, {{[0-9]+}}(%rsp)
; SSSE3-NEXT: movzbl {{[0-9]+}}(%rsp), %eax
[X86] Merge the FR128 and VR128 regclass since they have identical spill and alignment characteristics. This unfortunately requires a bunch of bitcasts to be added added to SUBREG_TO_REG, COPY_TO_REGCLASS, and instructions in output patterns. Otherwise tablegen seems to default to picking f128 and then we fail when something tries to get the register class for f128 which isn't always valid. The test changes are because we were previously mixing fr128 and vr128 due to contrainRegClass finding FR128 first and passes like live range shrinking weren't handling that well. llvm-svn: 337147
2018-07-16 14:56:09 +08:00
; SSSE3-NEXT: movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
[X86][SSE] LowerBUILD_VECTORAsVariablePermute - ensure that the source vector is not larger than the destination We might be able to support this in the future with VPERMV3, OR(PSHUFB, PSHUFB) etc. llvm-svn: 323210
2018-01-23 23:51:03 +08:00
; SSSE3-NEXT: movaps %xmm1, {{[0-9]+}}(%rsp)
; SSSE3-NEXT: movaps %xmm0, {{[0-9]+}}(%rsp)
; SSSE3-NEXT: movzbl {{[0-9]+}}(%rsp), %eax
[X86] Merge the FR128 and VR128 regclass since they have identical spill and alignment characteristics. This unfortunately requires a bunch of bitcasts to be added added to SUBREG_TO_REG, COPY_TO_REGCLASS, and instructions in output patterns. Otherwise tablegen seems to default to picking f128 and then we fail when something tries to get the register class for f128 which isn't always valid. The test changes are because we were previously mixing fr128 and vr128 due to contrainRegClass finding FR128 first and passes like live range shrinking weren't handling that well. llvm-svn: 337147
2018-07-16 14:56:09 +08:00
; SSSE3-NEXT: movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
[X86][SSE] LowerBUILD_VECTORAsVariablePermute - ensure that the source vector is not larger than the destination We might be able to support this in the future with VPERMV3, OR(PSHUFB, PSHUFB) etc. llvm-svn: 323210
2018-01-23 23:51:03 +08:00
; SSSE3-NEXT: movaps %xmm1, {{[0-9]+}}(%rsp)
; SSSE3-NEXT: movaps %xmm0, {{[0-9]+}}(%rsp)
; SSSE3-NEXT: movzbl {{[0-9]+}}(%rsp), %eax
[X86] Merge the FR128 and VR128 regclass since they have identical spill and alignment characteristics. This unfortunately requires a bunch of bitcasts to be added added to SUBREG_TO_REG, COPY_TO_REGCLASS, and instructions in output patterns. Otherwise tablegen seems to default to picking f128 and then we fail when something tries to get the register class for f128 which isn't always valid. The test changes are because we were previously mixing fr128 and vr128 due to contrainRegClass finding FR128 first and passes like live range shrinking weren't handling that well. llvm-svn: 337147
2018-07-16 14:56:09 +08:00
; SSSE3-NEXT: movq %rax, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
[X86][SSE] LowerBUILD_VECTORAsVariablePermute - ensure that the source vector is not larger than the destination We might be able to support this in the future with VPERMV3, OR(PSHUFB, PSHUFB) etc. llvm-svn: 323210
2018-01-23 23:51:03 +08:00
; SSSE3-NEXT: movaps %xmm1, {{[0-9]+}}(%rsp)
; SSSE3-NEXT: movaps %xmm0, {{[0-9]+}}(%rsp)
; SSSE3-NEXT: movzbl {{[0-9]+}}(%rsp), %r11d
; SSSE3-NEXT: movaps %xmm1, {{[0-9]+}}(%rsp)
; SSSE3-NEXT: movaps %xmm0, {{[0-9]+}}(%rsp)
; SSSE3-NEXT: movzbl {{[0-9]+}}(%rsp), %r14d
; SSSE3-NEXT: movaps %xmm1, {{[0-9]+}}(%rsp)
; SSSE3-NEXT: movaps %xmm0, {{[0-9]+}}(%rsp)
; SSSE3-NEXT: movzbl {{[0-9]+}}(%rsp), %r15d
; SSSE3-NEXT: movaps %xmm1, {{[0-9]+}}(%rsp)
; SSSE3-NEXT: movaps %xmm0, {{[0-9]+}}(%rsp)
; SSSE3-NEXT: movzbl {{[0-9]+}}(%rsp), %r12d
; SSSE3-NEXT: movaps %xmm1, {{[0-9]+}}(%rsp)
; SSSE3-NEXT: movaps %xmm0, {{[0-9]+}}(%rsp)
; SSSE3-NEXT: movzbl {{[0-9]+}}(%rsp), %r13d
; SSSE3-NEXT: movaps %xmm1, {{[0-9]+}}(%rsp)
; SSSE3-NEXT: movaps %xmm0, {{[0-9]+}}(%rsp)
; SSSE3-NEXT: movzbl {{[0-9]+}}(%rsp), %r10d
; SSSE3-NEXT: movaps %xmm1, {{[0-9]+}}(%rsp)
; SSSE3-NEXT: movaps %xmm0, {{[0-9]+}}(%rsp)
; SSSE3-NEXT: movzbl {{[0-9]+}}(%rsp), %r8d
; SSSE3-NEXT: movaps %xmm1, {{[0-9]+}}(%rsp)
; SSSE3-NEXT: movaps %xmm0, {{[0-9]+}}(%rsp)
; SSSE3-NEXT: movzbl {{[0-9]+}}(%rsp), %edi
; SSSE3-NEXT: movaps %xmm1, {{[0-9]+}}(%rsp)
; SSSE3-NEXT: movaps %xmm0, {{[0-9]+}}(%rsp)
; SSSE3-NEXT: movzbl {{[0-9]+}}(%rsp), %esi
; SSSE3-NEXT: movaps %xmm1, {{[0-9]+}}(%rsp)
; SSSE3-NEXT: movaps %xmm0, {{[0-9]+}}(%rsp)
; SSSE3-NEXT: movzbl {{[0-9]+}}(%rsp), %ecx
; SSSE3-NEXT: movaps %xmm1, {{[0-9]+}}(%rsp)
; SSSE3-NEXT: movaps %xmm0, {{[0-9]+}}(%rsp)
; SSSE3-NEXT: movzbl {{[0-9]+}}(%rsp), %edx
; SSSE3-NEXT: movaps %xmm1, {{[0-9]+}}(%rsp)
; SSSE3-NEXT: movaps %xmm0, {{[0-9]+}}(%rsp)
; SSSE3-NEXT: movzbl {{[0-9]+}}(%rsp), %eax
; SSSE3-NEXT: movaps %xmm1, {{[0-9]+}}(%rsp)
; SSSE3-NEXT: movaps %xmm0, {{[0-9]+}}(%rsp)
; SSSE3-NEXT: movzbl {{[0-9]+}}(%rsp), %r9d
; SSSE3-NEXT: andl $31, %r9d
; SSSE3-NEXT: movzbl 64(%rsp,%r9), %ebx
; SSSE3-NEXT: movd %ebx, %xmm8
; SSSE3-NEXT: andl $31, %eax
; SSSE3-NEXT: movzbl 96(%rsp,%rax), %eax
; SSSE3-NEXT: movd %eax, %xmm15
; SSSE3-NEXT: andl $31, %edx
; SSSE3-NEXT: movzbl 128(%rsp,%rdx), %eax
; SSSE3-NEXT: movd %eax, %xmm9
; SSSE3-NEXT: andl $31, %ecx
; SSSE3-NEXT: movzbl 160(%rsp,%rcx), %eax
; SSSE3-NEXT: movd %eax, %xmm3
; SSSE3-NEXT: andl $31, %esi
; SSSE3-NEXT: movzbl 192(%rsp,%rsi), %eax
; SSSE3-NEXT: movd %eax, %xmm10
; SSSE3-NEXT: andl $31, %edi
; SSSE3-NEXT: movzbl 224(%rsp,%rdi), %eax
; SSSE3-NEXT: movd %eax, %xmm7
; SSSE3-NEXT: andl $31, %r8d
; SSSE3-NEXT: movzbl 256(%rsp,%r8), %eax
; SSSE3-NEXT: movd %eax, %xmm11
; SSSE3-NEXT: andl $31, %r10d
; SSSE3-NEXT: movzbl 288(%rsp,%r10), %eax
; SSSE3-NEXT: movd %eax, %xmm6
; SSSE3-NEXT: andl $31, %r13d
; SSSE3-NEXT: movzbl 320(%rsp,%r13), %eax
; SSSE3-NEXT: movd %eax, %xmm12
; SSSE3-NEXT: andl $31, %r12d
; SSSE3-NEXT: movzbl 352(%rsp,%r12), %eax
; SSSE3-NEXT: movd %eax, %xmm5
; SSSE3-NEXT: andl $31, %r15d
; SSSE3-NEXT: movzbl 384(%rsp,%r15), %eax
; SSSE3-NEXT: movd %eax, %xmm13
; SSSE3-NEXT: andl $31, %r14d
; SSSE3-NEXT: movzbl 416(%rsp,%r14), %eax
; SSSE3-NEXT: movd %eax, %xmm4
; SSSE3-NEXT: andl $31, %r11d
; SSSE3-NEXT: movzbl 448(%rsp,%r11), %eax
; SSSE3-NEXT: movd %eax, %xmm14
[X86] Merge the FR128 and VR128 regclass since they have identical spill and alignment characteristics. This unfortunately requires a bunch of bitcasts to be added added to SUBREG_TO_REG, COPY_TO_REGCLASS, and instructions in output patterns. Otherwise tablegen seems to default to picking f128 and then we fail when something tries to get the register class for f128 which isn't always valid. The test changes are because we were previously mixing fr128 and vr128 due to contrainRegClass finding FR128 first and passes like live range shrinking weren't handling that well. llvm-svn: 337147
2018-07-16 14:56:09 +08:00
; SSSE3-NEXT: movq {{[-0-9]+}}(%r{{[sb]}}p), %rax # 8-byte Reload
[X86][SSE] LowerBUILD_VECTORAsVariablePermute - ensure that the source vector is not larger than the destination We might be able to support this in the future with VPERMV3, OR(PSHUFB, PSHUFB) etc. llvm-svn: 323210
2018-01-23 23:51:03 +08:00
; SSSE3-NEXT: andl $31, %eax
; SSSE3-NEXT: movzbl 480(%rsp,%rax), %eax
; SSSE3-NEXT: movd %eax, %xmm1
[X86] Merge the FR128 and VR128 regclass since they have identical spill and alignment characteristics. This unfortunately requires a bunch of bitcasts to be added added to SUBREG_TO_REG, COPY_TO_REGCLASS, and instructions in output patterns. Otherwise tablegen seems to default to picking f128 and then we fail when something tries to get the register class for f128 which isn't always valid. The test changes are because we were previously mixing fr128 and vr128 due to contrainRegClass finding FR128 first and passes like live range shrinking weren't handling that well. llvm-svn: 337147
2018-07-16 14:56:09 +08:00
; SSSE3-NEXT: movq {{[-0-9]+}}(%r{{[sb]}}p), %rax # 8-byte Reload
[X86][SSE] LowerBUILD_VECTORAsVariablePermute - ensure that the source vector is not larger than the destination We might be able to support this in the future with VPERMV3, OR(PSHUFB, PSHUFB) etc. llvm-svn: 323210
2018-01-23 23:51:03 +08:00
; SSSE3-NEXT: andl $31, %eax
; SSSE3-NEXT: movzbl 512(%rsp,%rax), %eax
; SSSE3-NEXT: movd %eax, %xmm2
[X86] Merge the FR128 and VR128 regclass since they have identical spill and alignment characteristics. This unfortunately requires a bunch of bitcasts to be added added to SUBREG_TO_REG, COPY_TO_REGCLASS, and instructions in output patterns. Otherwise tablegen seems to default to picking f128 and then we fail when something tries to get the register class for f128 which isn't always valid. The test changes are because we were previously mixing fr128 and vr128 due to contrainRegClass finding FR128 first and passes like live range shrinking weren't handling that well. llvm-svn: 337147
2018-07-16 14:56:09 +08:00
; SSSE3-NEXT: movq {{[-0-9]+}}(%r{{[sb]}}p), %rax # 8-byte Reload
[X86][SSE] LowerBUILD_VECTORAsVariablePermute - ensure that the source vector is not larger than the destination We might be able to support this in the future with VPERMV3, OR(PSHUFB, PSHUFB) etc. llvm-svn: 323210
2018-01-23 23:51:03 +08:00
; SSSE3-NEXT: andl $31, %eax
; SSSE3-NEXT: movzbl 544(%rsp,%rax), %eax
; SSSE3-NEXT: movd %eax, %xmm0
; SSSE3-NEXT: punpcklbw {{.*#+}} xmm15 = xmm15[0],xmm8[0],xmm15[1],xmm8[1],xmm15[2],xmm8[2],xmm15[3],xmm8[3],xmm15[4],xmm8[4],xmm15[5],xmm8[5],xmm15[6],xmm8[6],xmm15[7],xmm8[7]
; SSSE3-NEXT: punpcklbw {{.*#+}} xmm3 = xmm3[0],xmm9[0],xmm3[1],xmm9[1],xmm3[2],xmm9[2],xmm3[3],xmm9[3],xmm3[4],xmm9[4],xmm3[5],xmm9[5],xmm3[6],xmm9[6],xmm3[7],xmm9[7]
; SSSE3-NEXT: punpcklwd {{.*#+}} xmm3 = xmm3[0],xmm15[0],xmm3[1],xmm15[1],xmm3[2],xmm15[2],xmm3[3],xmm15[3]
; SSSE3-NEXT: punpcklbw {{.*#+}} xmm7 = xmm7[0],xmm10[0],xmm7[1],xmm10[1],xmm7[2],xmm10[2],xmm7[3],xmm10[3],xmm7[4],xmm10[4],xmm7[5],xmm10[5],xmm7[6],xmm10[6],xmm7[7],xmm10[7]
; SSSE3-NEXT: punpcklbw {{.*#+}} xmm6 = xmm6[0],xmm11[0],xmm6[1],xmm11[1],xmm6[2],xmm11[2],xmm6[3],xmm11[3],xmm6[4],xmm11[4],xmm6[5],xmm11[5],xmm6[6],xmm11[6],xmm6[7],xmm11[7]
; SSSE3-NEXT: punpcklwd {{.*#+}} xmm6 = xmm6[0],xmm7[0],xmm6[1],xmm7[1],xmm6[2],xmm7[2],xmm6[3],xmm7[3]
; SSSE3-NEXT: punpckldq {{.*#+}} xmm6 = xmm6[0],xmm3[0],xmm6[1],xmm3[1]
; SSSE3-NEXT: punpcklbw {{.*#+}} xmm5 = xmm5[0],xmm12[0],xmm5[1],xmm12[1],xmm5[2],xmm12[2],xmm5[3],xmm12[3],xmm5[4],xmm12[4],xmm5[5],xmm12[5],xmm5[6],xmm12[6],xmm5[7],xmm12[7]
; SSSE3-NEXT: punpcklbw {{.*#+}} xmm4 = xmm4[0],xmm13[0],xmm4[1],xmm13[1],xmm4[2],xmm13[2],xmm4[3],xmm13[3],xmm4[4],xmm13[4],xmm4[5],xmm13[5],xmm4[6],xmm13[6],xmm4[7],xmm13[7]
; SSSE3-NEXT: punpcklwd {{.*#+}} xmm4 = xmm4[0],xmm5[0],xmm4[1],xmm5[1],xmm4[2],xmm5[2],xmm4[3],xmm5[3]
; SSSE3-NEXT: punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm14[0],xmm1[1],xmm14[1],xmm1[2],xmm14[2],xmm1[3],xmm14[3],xmm1[4],xmm14[4],xmm1[5],xmm14[5],xmm1[6],xmm14[6],xmm1[7],xmm14[7]
; SSSE3-NEXT: punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3],xmm0[4],xmm2[4],xmm0[5],xmm2[5],xmm0[6],xmm2[6],xmm0[7],xmm2[7]
; SSSE3-NEXT: punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
; SSSE3-NEXT: punpckldq {{.*#+}} xmm0 = xmm0[0],xmm4[0],xmm0[1],xmm4[1]
; SSSE3-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm6[0]
; SSSE3-NEXT: leaq -40(%rbp), %rsp
; SSSE3-NEXT: popq %rbx
; SSSE3-NEXT: popq %r12
; SSSE3-NEXT: popq %r13
; SSSE3-NEXT: popq %r14
; SSSE3-NEXT: popq %r15
; SSSE3-NEXT: popq %rbp
; SSSE3-NEXT: retq
;
[X86][SSE] Add SSE41 to variable permute tests llvm-svn: 324017
2018-02-02 06:05:44 +08:00
; SSE41-LABEL: var_shuffle_v16i8_from_v32i8_v16i8:
; SSE41: # %bb.0:
; SSE41-NEXT: pushq %rbp
; SSE41-NEXT: movq %rsp, %rbp
; SSE41-NEXT: andq $-32, %rsp
; SSE41-NEXT: subq $544, %rsp # imm = 0x220
; SSE41-NEXT: pextrb $0, %xmm2, %eax
; SSE41-NEXT: movaps %xmm1, {{[0-9]+}}(%rsp)
; SSE41-NEXT: movaps %xmm0, {{[0-9]+}}(%rsp)
; SSE41-NEXT: andl $31, %eax
; SSE41-NEXT: movaps %xmm1, {{[0-9]+}}(%rsp)
; SSE41-NEXT: movaps %xmm0, {{[0-9]+}}(%rsp)
; SSE41-NEXT: movaps %xmm1, {{[0-9]+}}(%rsp)
; SSE41-NEXT: movaps %xmm0, {{[0-9]+}}(%rsp)
; SSE41-NEXT: movaps %xmm1, {{[0-9]+}}(%rsp)
; SSE41-NEXT: movaps %xmm0, {{[0-9]+}}(%rsp)
; SSE41-NEXT: movaps %xmm1, {{[0-9]+}}(%rsp)
; SSE41-NEXT: movaps %xmm0, {{[0-9]+}}(%rsp)
; SSE41-NEXT: movaps %xmm1, {{[0-9]+}}(%rsp)
; SSE41-NEXT: movaps %xmm0, {{[0-9]+}}(%rsp)
; SSE41-NEXT: movaps %xmm1, {{[0-9]+}}(%rsp)
; SSE41-NEXT: movaps %xmm0, {{[0-9]+}}(%rsp)
; SSE41-NEXT: movaps %xmm1, {{[0-9]+}}(%rsp)
; SSE41-NEXT: movaps %xmm0, {{[0-9]+}}(%rsp)
; SSE41-NEXT: movaps %xmm1, {{[0-9]+}}(%rsp)
; SSE41-NEXT: movaps %xmm0, {{[0-9]+}}(%rsp)
; SSE41-NEXT: movaps %xmm1, {{[0-9]+}}(%rsp)
; SSE41-NEXT: movaps %xmm0, {{[0-9]+}}(%rsp)
; SSE41-NEXT: movaps %xmm1, {{[0-9]+}}(%rsp)
; SSE41-NEXT: movaps %xmm0, {{[0-9]+}}(%rsp)
; SSE41-NEXT: movaps %xmm1, {{[0-9]+}}(%rsp)
; SSE41-NEXT: movaps %xmm0, {{[0-9]+}}(%rsp)
; SSE41-NEXT: movaps %xmm1, {{[0-9]+}}(%rsp)
; SSE41-NEXT: movaps %xmm0, {{[0-9]+}}(%rsp)
; SSE41-NEXT: movaps %xmm1, {{[0-9]+}}(%rsp)
; SSE41-NEXT: movaps %xmm0, {{[0-9]+}}(%rsp)
; SSE41-NEXT: movaps %xmm1, {{[0-9]+}}(%rsp)
; SSE41-NEXT: movaps %xmm0, {{[0-9]+}}(%rsp)
; SSE41-NEXT: movaps %xmm1, {{[0-9]+}}(%rsp)
; SSE41-NEXT: movaps %xmm0, (%rsp)
; SSE41-NEXT: movzbl 480(%rsp,%rax), %eax
; SSE41-NEXT: movd %eax, %xmm0
; SSE41-NEXT: pextrb $1, %xmm2, %eax
; SSE41-NEXT: andl $31, %eax
; SSE41-NEXT: pinsrb $1, 448(%rsp,%rax), %xmm0
; SSE41-NEXT: pextrb $2, %xmm2, %eax
; SSE41-NEXT: andl $31, %eax
; SSE41-NEXT: pinsrb $2, 416(%rsp,%rax), %xmm0
; SSE41-NEXT: pextrb $3, %xmm2, %eax
; SSE41-NEXT: andl $31, %eax
; SSE41-NEXT: pinsrb $3, 384(%rsp,%rax), %xmm0
; SSE41-NEXT: pextrb $4, %xmm2, %eax
; SSE41-NEXT: andl $31, %eax
; SSE41-NEXT: pinsrb $4, 352(%rsp,%rax), %xmm0
; SSE41-NEXT: pextrb $5, %xmm2, %eax
; SSE41-NEXT: andl $31, %eax
; SSE41-NEXT: pinsrb $5, 320(%rsp,%rax), %xmm0
; SSE41-NEXT: pextrb $6, %xmm2, %eax
; SSE41-NEXT: andl $31, %eax
; SSE41-NEXT: pinsrb $6, 288(%rsp,%rax), %xmm0
; SSE41-NEXT: pextrb $7, %xmm2, %eax
; SSE41-NEXT: andl $31, %eax
; SSE41-NEXT: pinsrb $7, 256(%rsp,%rax), %xmm0
; SSE41-NEXT: pextrb $8, %xmm2, %eax
; SSE41-NEXT: andl $31, %eax
; SSE41-NEXT: pinsrb $8, 224(%rsp,%rax), %xmm0
; SSE41-NEXT: pextrb $9, %xmm2, %eax
; SSE41-NEXT: andl $31, %eax
; SSE41-NEXT: pinsrb $9, 192(%rsp,%rax), %xmm0
; SSE41-NEXT: pextrb $10, %xmm2, %eax
; SSE41-NEXT: andl $31, %eax
; SSE41-NEXT: pinsrb $10, 160(%rsp,%rax), %xmm0
; SSE41-NEXT: pextrb $11, %xmm2, %eax
; SSE41-NEXT: andl $31, %eax
; SSE41-NEXT: pinsrb $11, 128(%rsp,%rax), %xmm0
; SSE41-NEXT: pextrb $12, %xmm2, %eax
; SSE41-NEXT: andl $31, %eax
; SSE41-NEXT: pinsrb $12, 96(%rsp,%rax), %xmm0
; SSE41-NEXT: pextrb $13, %xmm2, %eax
; SSE41-NEXT: andl $31, %eax
; SSE41-NEXT: pinsrb $13, 64(%rsp,%rax), %xmm0
; SSE41-NEXT: pextrb $14, %xmm2, %eax
; SSE41-NEXT: andl $31, %eax
; SSE41-NEXT: pinsrb $14, 32(%rsp,%rax), %xmm0
; SSE41-NEXT: pextrb $15, %xmm2, %eax
; SSE41-NEXT: andl $31, %eax
; SSE41-NEXT: pinsrb $15, (%rsp,%rax), %xmm0
; SSE41-NEXT: movq %rbp, %rsp
; SSE41-NEXT: popq %rbp
; SSE41-NEXT: retq
;
[X86][AVX] createVariablePermute - widen permutes for cases where the source vector is wider than the destination type llvm-svn: 327244
2018-03-12 01:00:46 +08:00
; XOP-LABEL: var_shuffle_v16i8_from_v32i8_v16i8:
; XOP: # %bb.0:
; XOP-NEXT: vextractf128 $1, %ymm0, %xmm2
; XOP-NEXT: vpperm %xmm1, %xmm2, %xmm0, %xmm0
; XOP-NEXT: vzeroupper
; XOP-NEXT: retq
;
; AVX1-LABEL: var_shuffle_v16i8_from_v32i8_v16i8:
; AVX1: # %bb.0:
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm2
; AVX1-NEXT: vpshufb %xmm1, %xmm2, %xmm2
; AVX1-NEXT: vpshufb %xmm1, %xmm0, %xmm0
; AVX1-NEXT: vpcmpgtb {{.*}}(%rip), %xmm1, %xmm1
; AVX1-NEXT: vpblendvb %xmm1, %xmm2, %xmm0, %xmm0
; AVX1-NEXT: vzeroupper
; AVX1-NEXT: retq
;
; AVX2-LABEL: var_shuffle_v16i8_from_v32i8_v16i8:
; AVX2: # %bb.0:
; AVX2-NEXT: # kill: def $xmm1 killed $xmm1 def $ymm1
; AVX2-NEXT: vinserti128 $1, %xmm0, %ymm0, %ymm2
; AVX2-NEXT: vpshufb %ymm1, %ymm2, %ymm2
; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm3
; AVX2-NEXT: vpblendd {{.*#+}} ymm0 = ymm3[0,1,2,3],ymm0[4,5,6,7]
; AVX2-NEXT: vpshufb %ymm1, %ymm0, %ymm0
; AVX2-NEXT: vpcmpgtb {{.*}}(%rip), %ymm1, %ymm1
; AVX2-NEXT: vpblendvb %ymm1, %ymm0, %ymm2, %ymm0
; AVX2-NEXT: # kill: def $xmm0 killed $xmm0 killed $ymm0
; AVX2-NEXT: vzeroupper
; AVX2-NEXT: retq
;
[X86][AVX512] Added more non-VLX test cases Cleaned up check prefixes so that they actually share a bit more llvm-svn: 327246
2018-03-12 02:28:37 +08:00
; AVX512-LABEL: var_shuffle_v16i8_from_v32i8_v16i8:
; AVX512: # %bb.0:
; AVX512-NEXT: # kill: def $xmm1 killed $xmm1 def $ymm1
; AVX512-NEXT: vinserti128 $1, %xmm0, %ymm0, %ymm2
; AVX512-NEXT: vpshufb %ymm1, %ymm2, %ymm2
; AVX512-NEXT: vextracti128 $1, %ymm0, %xmm3
; AVX512-NEXT: vpblendd {{.*#+}} ymm0 = ymm3[0,1,2,3],ymm0[4,5,6,7]
; AVX512-NEXT: vpshufb %ymm1, %ymm0, %ymm0
; AVX512-NEXT: vpcmpgtb {{.*}}(%rip), %ymm1, %ymm1
; AVX512-NEXT: vpblendvb %ymm1, %ymm0, %ymm2, %ymm0
; AVX512-NEXT: # kill: def $xmm0 killed $xmm0 killed $ymm0
; AVX512-NEXT: vzeroupper
; AVX512-NEXT: retq
[X86][AVX] createVariablePermute - widen permutes for cases where the source vector is wider than the destination type llvm-svn: 327244
2018-03-12 01:00:46 +08:00
;
[X86][AVX512] Added more non-VLX test cases Cleaned up check prefixes so that they actually share a bit more llvm-svn: 327246
2018-03-12 02:28:37 +08:00
; AVX512VLBW-LABEL: var_shuffle_v16i8_from_v32i8_v16i8:
; AVX512VLBW: # %bb.0:
; AVX512VLBW-NEXT: # kill: def $xmm1 killed $xmm1 def $ymm1
; AVX512VLBW-NEXT: vinserti128 $1, %xmm0, %ymm0, %ymm2
; AVX512VLBW-NEXT: vpshufb %ymm1, %ymm2, %ymm2
; AVX512VLBW-NEXT: vextracti128 $1, %ymm0, %xmm3
; AVX512VLBW-NEXT: vpblendd {{.*#+}} ymm0 = ymm3[0,1,2,3],ymm0[4,5,6,7]
; AVX512VLBW-NEXT: vpcmpgtb {{.*}}(%rip), %ymm1, %k1
; AVX512VLBW-NEXT: vpshufb %ymm1, %ymm0, %ymm2 {%k1}
; AVX512VLBW-NEXT: vmovdqa %xmm2, %xmm0
; AVX512VLBW-NEXT: vzeroupper
; AVX512VLBW-NEXT: retq
[X86][AVX] createVariablePermute - widen permutes for cases where the source vector is wider than the destination type llvm-svn: 327244
2018-03-12 01:00:46 +08:00
;
[X86][AVX512] Added more non-VLX test cases Cleaned up check prefixes so that they actually share a bit more llvm-svn: 327246
2018-03-12 02:28:37 +08:00
; VLVBMI-LABEL: var_shuffle_v16i8_from_v32i8_v16i8:
; VLVBMI: # %bb.0:
; VLVBMI-NEXT: # kill: def $xmm1 killed $xmm1 def $ymm1
; VLVBMI-NEXT: vpermb %ymm0, %ymm1, %ymm0
; VLVBMI-NEXT: # kill: def $xmm0 killed $xmm0 killed $ymm0
; VLVBMI-NEXT: vzeroupper
; VLVBMI-NEXT: retq
[X86][SSE] LowerBUILD_VECTORAsVariablePermute - ensure that the source vector is not larger than the destination We might be able to support this in the future with VPERMV3, OR(PSHUFB, PSHUFB) etc. llvm-svn: 323210
2018-01-23 23:51:03 +08:00
%index0 = extractelement <16 x i8> %indices, i32 0
%index1 = extractelement <16 x i8> %indices, i32 1
%index2 = extractelement <16 x i8> %indices, i32 2
%index3 = extractelement <16 x i8> %indices, i32 3
%index4 = extractelement <16 x i8> %indices, i32 4
%index5 = extractelement <16 x i8> %indices, i32 5
%index6 = extractelement <16 x i8> %indices, i32 6
%index7 = extractelement <16 x i8> %indices, i32 7
%index8 = extractelement <16 x i8> %indices, i32 8
%index9 = extractelement <16 x i8> %indices, i32 9
%index10 = extractelement <16 x i8> %indices, i32 10
%index11 = extractelement <16 x i8> %indices, i32 11
%index12 = extractelement <16 x i8> %indices, i32 12
%index13 = extractelement <16 x i8> %indices, i32 13
%index14 = extractelement <16 x i8> %indices, i32 14
%index15 = extractelement <16 x i8> %indices, i32 15
%v0 = extractelement <32 x i8> %v, i8 %index0
%v1 = extractelement <32 x i8> %v, i8 %index1
%v2 = extractelement <32 x i8> %v, i8 %index2
%v3 = extractelement <32 x i8> %v, i8 %index3
%v4 = extractelement <32 x i8> %v, i8 %index4
%v5 = extractelement <32 x i8> %v, i8 %index5
%v6 = extractelement <32 x i8> %v, i8 %index6
%v7 = extractelement <32 x i8> %v, i8 %index7
%v8 = extractelement <32 x i8> %v, i8 %index8
%v9 = extractelement <32 x i8> %v, i8 %index9
%v10 = extractelement <32 x i8> %v, i8 %index10
%v11 = extractelement <32 x i8> %v, i8 %index11
%v12 = extractelement <32 x i8> %v, i8 %index12
%v13 = extractelement <32 x i8> %v, i8 %index13
%v14 = extractelement <32 x i8> %v, i8 %index14
%v15 = extractelement <32 x i8> %v, i8 %index15
%ret0 = insertelement <16 x i8> undef, i8 %v0, i32 0
%ret1 = insertelement <16 x i8> %ret0, i8 %v1, i32 1
%ret2 = insertelement <16 x i8> %ret1, i8 %v2, i32 2
%ret3 = insertelement <16 x i8> %ret2, i8 %v3, i32 3
%ret4 = insertelement <16 x i8> %ret3, i8 %v4, i32 4
%ret5 = insertelement <16 x i8> %ret4, i8 %v5, i32 5
%ret6 = insertelement <16 x i8> %ret5, i8 %v6, i32 6
%ret7 = insertelement <16 x i8> %ret6, i8 %v7, i32 7
%ret8 = insertelement <16 x i8> %ret7, i8 %v8, i32 8
%ret9 = insertelement <16 x i8> %ret8, i8 %v9, i32 9
%ret10 = insertelement <16 x i8> %ret9, i8 %v10, i32 10
%ret11 = insertelement <16 x i8> %ret10, i8 %v11, i32 11
%ret12 = insertelement <16 x i8> %ret11, i8 %v12, i32 12
%ret13 = insertelement <16 x i8> %ret12, i8 %v13, i32 13
%ret14 = insertelement <16 x i8> %ret13, i8 %v14, i32 14
%ret15 = insertelement <16 x i8> %ret14, i8 %v15, i32 15
ret <16 x i8> %ret15
}