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/insertelement-shuffle.ll

133 lines
5.5 KiB
LLVM
Raw Normal View History

[x86] add tests for possible insertelement to shuffle transform; NFC See PR34716 and D38316 for more discussion. llvm-svn: 314466
2017-09-29 06:27:25 +08:00
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=i686-unknown-unknown -mattr=avx2 | FileCheck %s --check-prefix=X32_AVX256
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=avx2 | FileCheck %s --check-prefix=X64_AVX256
; RUN: llc < %s -mtriple=i686-unknown-unknown -mattr=avx512f | FileCheck %s --check-prefix=X32_AVX512
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=avx512f | FileCheck %s --check-prefix=X64_AVX512
define <8 x float> @insert_subvector_256(i16 %x0, i16 %x1, <8 x float> %v) nounwind {
; X32_AVX256-LABEL: insert_subvector_256:
[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
; X32_AVX256: # %bb.0:
[x86] add tests for possible insertelement to shuffle transform; NFC See PR34716 and D38316 for more discussion. llvm-svn: 314466
2017-09-29 06:27:25 +08:00
; X32_AVX256-NEXT: vmovd {{.*#+}} xmm1 = mem[0],zero,zero,zero
; X32_AVX256-NEXT: vpinsrw $1, {{[0-9]+}}(%esp), %xmm1, %xmm1
[DAGCombiner] convert insertelement of bitcasted vector into shuffle Eg: insert v4i32 V, (v2i16 X), 2 --> shuffle v8i16 V', X', {0,1,2,3,8,9,6,7} This is a generalization of the IR fold in D38316 to handle insertion into a non-undef vector. We may want to abandon that one if we can't find value in squashing the more specific pattern sooner. We're using the existing legal shuffle target hook to avoid AVX512 horror with vXi1 shuffles. There may be room for improvement in the shuffle lowering here, but that would be follow-up work. Differential Revision: https://reviews.llvm.org/D38388 llvm-svn: 315460
2017-10-11 22:12:16 +08:00
; X32_AVX256-NEXT: vpbroadcastd %xmm1, %xmm1
; X32_AVX256-NEXT: vpblendd {{.*#+}} ymm0 = ymm0[0],ymm1[1],ymm0[2,3,4,5,6,7]
[x86] add tests for possible insertelement to shuffle transform; NFC See PR34716 and D38316 for more discussion. llvm-svn: 314466
2017-09-29 06:27:25 +08:00
; X32_AVX256-NEXT: retl
;
; X64_AVX256-LABEL: insert_subvector_256:
[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
; X64_AVX256: # %bb.0:
[x86] add tests for possible insertelement to shuffle transform; NFC See PR34716 and D38316 for more discussion. llvm-svn: 314466
2017-09-29 06:27:25 +08:00
; X64_AVX256-NEXT: vmovd %edi, %xmm1
; X64_AVX256-NEXT: vpinsrw $1, %esi, %xmm1, %xmm1
[DAGCombiner] convert insertelement of bitcasted vector into shuffle Eg: insert v4i32 V, (v2i16 X), 2 --> shuffle v8i16 V', X', {0,1,2,3,8,9,6,7} This is a generalization of the IR fold in D38316 to handle insertion into a non-undef vector. We may want to abandon that one if we can't find value in squashing the more specific pattern sooner. We're using the existing legal shuffle target hook to avoid AVX512 horror with vXi1 shuffles. There may be room for improvement in the shuffle lowering here, but that would be follow-up work. Differential Revision: https://reviews.llvm.org/D38388 llvm-svn: 315460
2017-10-11 22:12:16 +08:00
; X64_AVX256-NEXT: vpbroadcastd %xmm1, %xmm1
; X64_AVX256-NEXT: vpblendd {{.*#+}} ymm0 = ymm0[0],ymm1[1],ymm0[2,3,4,5,6,7]
[x86] add tests for possible insertelement to shuffle transform; NFC See PR34716 and D38316 for more discussion. llvm-svn: 314466
2017-09-29 06:27:25 +08:00
; X64_AVX256-NEXT: retq
;
; X32_AVX512-LABEL: insert_subvector_256:
[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
; X32_AVX512: # %bb.0:
[x86] add tests for possible insertelement to shuffle transform; NFC See PR34716 and D38316 for more discussion. llvm-svn: 314466
2017-09-29 06:27:25 +08:00
; X32_AVX512-NEXT: vmovd {{.*#+}} xmm1 = mem[0],zero,zero,zero
; X32_AVX512-NEXT: vpinsrw $1, {{[0-9]+}}(%esp), %xmm1, %xmm1
[DAGCombiner] convert insertelement of bitcasted vector into shuffle Eg: insert v4i32 V, (v2i16 X), 2 --> shuffle v8i16 V', X', {0,1,2,3,8,9,6,7} This is a generalization of the IR fold in D38316 to handle insertion into a non-undef vector. We may want to abandon that one if we can't find value in squashing the more specific pattern sooner. We're using the existing legal shuffle target hook to avoid AVX512 horror with vXi1 shuffles. There may be room for improvement in the shuffle lowering here, but that would be follow-up work. Differential Revision: https://reviews.llvm.org/D38388 llvm-svn: 315460
2017-10-11 22:12:16 +08:00
; X32_AVX512-NEXT: vpbroadcastd %xmm1, %xmm1
; X32_AVX512-NEXT: vpblendd {{.*#+}} ymm0 = ymm0[0],ymm1[1],ymm0[2,3,4,5,6,7]
[x86] add tests for possible insertelement to shuffle transform; NFC See PR34716 and D38316 for more discussion. llvm-svn: 314466
2017-09-29 06:27:25 +08:00
; X32_AVX512-NEXT: retl
;
; X64_AVX512-LABEL: insert_subvector_256:
[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
; X64_AVX512: # %bb.0:
[x86] add tests for possible insertelement to shuffle transform; NFC See PR34716 and D38316 for more discussion. llvm-svn: 314466
2017-09-29 06:27:25 +08:00
; X64_AVX512-NEXT: vmovd %edi, %xmm1
; X64_AVX512-NEXT: vpinsrw $1, %esi, %xmm1, %xmm1
[DAGCombiner] convert insertelement of bitcasted vector into shuffle Eg: insert v4i32 V, (v2i16 X), 2 --> shuffle v8i16 V', X', {0,1,2,3,8,9,6,7} This is a generalization of the IR fold in D38316 to handle insertion into a non-undef vector. We may want to abandon that one if we can't find value in squashing the more specific pattern sooner. We're using the existing legal shuffle target hook to avoid AVX512 horror with vXi1 shuffles. There may be room for improvement in the shuffle lowering here, but that would be follow-up work. Differential Revision: https://reviews.llvm.org/D38388 llvm-svn: 315460
2017-10-11 22:12:16 +08:00
; X64_AVX512-NEXT: vpbroadcastd %xmm1, %xmm1
; X64_AVX512-NEXT: vpblendd {{.*#+}} ymm0 = ymm0[0],ymm1[1],ymm0[2,3,4,5,6,7]
[x86] add tests for possible insertelement to shuffle transform; NFC See PR34716 and D38316 for more discussion. llvm-svn: 314466
2017-09-29 06:27:25 +08:00
; X64_AVX512-NEXT: retq
%ins1 = insertelement <2 x i16> undef, i16 %x0, i32 0
%ins2 = insertelement <2 x i16> %ins1, i16 %x1, i32 1
%bc = bitcast <2 x i16> %ins2 to float
%ins3 = insertelement <8 x float> %v, float %bc, i32 1
ret <8 x float> %ins3
}
define <8 x i64> @insert_subvector_512(i32 %x0, i32 %x1, <8 x i64> %v) nounwind {
; X32_AVX256-LABEL: insert_subvector_512:
[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
; X32_AVX256: # %bb.0:
[x86] add tests for possible insertelement to shuffle transform; NFC See PR34716 and D38316 for more discussion. llvm-svn: 314466
2017-09-29 06:27:25 +08:00
; X32_AVX256-NEXT: pushl %ebp
; X32_AVX256-NEXT: movl %esp, %ebp
; X32_AVX256-NEXT: andl $-8, %esp
; X32_AVX256-NEXT: subl $8, %esp
; X32_AVX256-NEXT: vmovsd {{.*#+}} xmm2 = mem[0],zero
; X32_AVX256-NEXT: vmovlps %xmm2, (%esp)
; X32_AVX256-NEXT: vextracti128 $1, %ymm0, %xmm2
; X32_AVX256-NEXT: vpinsrd $0, (%esp), %xmm2, %xmm2
; X32_AVX256-NEXT: vpinsrd $1, {{[0-9]+}}(%esp), %xmm2, %xmm2
; X32_AVX256-NEXT: vinserti128 $1, %xmm2, %ymm0, %ymm0
; X32_AVX256-NEXT: movl %ebp, %esp
; X32_AVX256-NEXT: popl %ebp
; X32_AVX256-NEXT: retl
;
; X64_AVX256-LABEL: insert_subvector_512:
[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
; X64_AVX256: # %bb.0:
[x86] add tests for possible insertelement to shuffle transform; NFC See PR34716 and D38316 for more discussion. llvm-svn: 314466
2017-09-29 06:27:25 +08:00
; X64_AVX256-NEXT: vmovd %edi, %xmm2
; X64_AVX256-NEXT: vpinsrd $1, %esi, %xmm2, %xmm2
; X64_AVX256-NEXT: vmovq %xmm2, %rax
; X64_AVX256-NEXT: vextracti128 $1, %ymm0, %xmm2
; X64_AVX256-NEXT: vpinsrq $0, %rax, %xmm2, %xmm2
; X64_AVX256-NEXT: vinserti128 $1, %xmm2, %ymm0, %ymm0
; X64_AVX256-NEXT: retq
;
; X32_AVX512-LABEL: insert_subvector_512:
[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
; X32_AVX512: # %bb.0:
[DAGCombiner] convert insertelement of bitcasted vector into shuffle Eg: insert v4i32 V, (v2i16 X), 2 --> shuffle v8i16 V', X', {0,1,2,3,8,9,6,7} This is a generalization of the IR fold in D38316 to handle insertion into a non-undef vector. We may want to abandon that one if we can't find value in squashing the more specific pattern sooner. We're using the existing legal shuffle target hook to avoid AVX512 horror with vXi1 shuffles. There may be room for improvement in the shuffle lowering here, but that would be follow-up work. Differential Revision: https://reviews.llvm.org/D38388 llvm-svn: 315460
2017-10-11 22:12:16 +08:00
; X32_AVX512-NEXT: vmovq {{.*#+}} xmm1 = mem[0],zero
; X32_AVX512-NEXT: vmovdqa64 {{.*#+}} zmm2 = [0,0,1,0,8,0,3,0,4,0,5,0,6,0,7,0]
; X32_AVX512-NEXT: vpermt2q %zmm1, %zmm2, %zmm0
[x86] add tests for possible insertelement to shuffle transform; NFC See PR34716 and D38316 for more discussion. llvm-svn: 314466
2017-09-29 06:27:25 +08:00
; X32_AVX512-NEXT: retl
;
; X64_AVX512-LABEL: insert_subvector_512:
[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
; X64_AVX512: # %bb.0:
[x86] add tests for possible insertelement to shuffle transform; NFC See PR34716 and D38316 for more discussion. llvm-svn: 314466
2017-09-29 06:27:25 +08:00
; X64_AVX512-NEXT: vmovd %edi, %xmm1
; X64_AVX512-NEXT: vpinsrd $1, %esi, %xmm1, %xmm1
[DAGCombiner] convert insertelement of bitcasted vector into shuffle Eg: insert v4i32 V, (v2i16 X), 2 --> shuffle v8i16 V', X', {0,1,2,3,8,9,6,7} This is a generalization of the IR fold in D38316 to handle insertion into a non-undef vector. We may want to abandon that one if we can't find value in squashing the more specific pattern sooner. We're using the existing legal shuffle target hook to avoid AVX512 horror with vXi1 shuffles. There may be room for improvement in the shuffle lowering here, but that would be follow-up work. Differential Revision: https://reviews.llvm.org/D38388 llvm-svn: 315460
2017-10-11 22:12:16 +08:00
; X64_AVX512-NEXT: vmovdqa64 {{.*#+}} zmm2 = [0,1,8,3,4,5,6,7]
; X64_AVX512-NEXT: vpermt2q %zmm1, %zmm2, %zmm0
[x86] add tests for possible insertelement to shuffle transform; NFC See PR34716 and D38316 for more discussion. llvm-svn: 314466
2017-09-29 06:27:25 +08:00
; X64_AVX512-NEXT: retq
%ins1 = insertelement <2 x i32> undef, i32 %x0, i32 0
%ins2 = insertelement <2 x i32> %ins1, i32 %x1, i32 1
%bc = bitcast <2 x i32> %ins2 to i64
%ins3 = insertelement <8 x i64> %v, i64 %bc, i32 2
ret <8 x i64> %ins3
}
; PR34716 - https://bugs.llvm.org/show_bug.cgi?id=34716
; Special case: if we're inserting into an undef vector, we can optimize more.
define <8 x i64> @insert_subvector_into_undef(i32 %x0, i32 %x1) nounwind {
; X32_AVX256-LABEL: insert_subvector_into_undef:
[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
; X32_AVX256: # %bb.0:
[X86] Teach LowerBUILD_VECTOR to recognize pair-wise splats of 32-bit elements and use a 64-bit broadcast If we are splatting pairs of 32-bit elements, we can use a 64-bit broadcast to get the job done. We could probably could probably do this with other sizes too, for example four 16-bit elements. Or we could broadcast pairs of 16-bit elements using a 32-bit element broadcast. But I've left that as a future improvement. I've also restricted this to AVX2 only because we can only broadcast loads under AVX. Differential Revision: https://reviews.llvm.org/D42086 llvm-svn: 322730
2018-01-18 02:58:22 +08:00
; X32_AVX256-NEXT: vmovsd {{.*#+}} xmm0 = mem[0],zero
; X32_AVX256-NEXT: vbroadcastsd %xmm0, %ymm0
; X32_AVX256-NEXT: vmovaps %ymm0, %ymm1
[x86] add tests for possible insertelement to shuffle transform; NFC See PR34716 and D38316 for more discussion. llvm-svn: 314466
2017-09-29 06:27:25 +08:00
; X32_AVX256-NEXT: retl
;
; X64_AVX256-LABEL: insert_subvector_into_undef:
[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
; X64_AVX256: # %bb.0:
[x86] add tests for possible insertelement to shuffle transform; NFC See PR34716 and D38316 for more discussion. llvm-svn: 314466
2017-09-29 06:27:25 +08:00
; X64_AVX256-NEXT: vmovd %edi, %xmm0
; X64_AVX256-NEXT: vpinsrd $1, %esi, %xmm0, %xmm0
; X64_AVX256-NEXT: vpbroadcastq %xmm0, %ymm0
; X64_AVX256-NEXT: vmovdqa %ymm0, %ymm1
; X64_AVX256-NEXT: retq
;
; X32_AVX512-LABEL: insert_subvector_into_undef:
[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
; X32_AVX512: # %bb.0:
[x86] add tests for possible insertelement to shuffle transform; NFC See PR34716 and D38316 for more discussion. llvm-svn: 314466
2017-09-29 06:27:25 +08:00
; X32_AVX512-NEXT: vmovsd {{.*#+}} xmm0 = mem[0],zero
[DAGCombiner] convert insertelement of bitcasted vector into shuffle Eg: insert v4i32 V, (v2i16 X), 2 --> shuffle v8i16 V', X', {0,1,2,3,8,9,6,7} This is a generalization of the IR fold in D38316 to handle insertion into a non-undef vector. We may want to abandon that one if we can't find value in squashing the more specific pattern sooner. We're using the existing legal shuffle target hook to avoid AVX512 horror with vXi1 shuffles. There may be room for improvement in the shuffle lowering here, but that would be follow-up work. Differential Revision: https://reviews.llvm.org/D38388 llvm-svn: 315460
2017-10-11 22:12:16 +08:00
; X32_AVX512-NEXT: vbroadcastsd %xmm0, %zmm0
[x86] add tests for possible insertelement to shuffle transform; NFC See PR34716 and D38316 for more discussion. llvm-svn: 314466
2017-09-29 06:27:25 +08:00
; X32_AVX512-NEXT: retl
;
; X64_AVX512-LABEL: insert_subvector_into_undef:
[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
; X64_AVX512: # %bb.0:
[x86] add tests for possible insertelement to shuffle transform; NFC See PR34716 and D38316 for more discussion. llvm-svn: 314466
2017-09-29 06:27:25 +08:00
; X64_AVX512-NEXT: vmovd %edi, %xmm0
; X64_AVX512-NEXT: vpinsrd $1, %esi, %xmm0, %xmm0
; X64_AVX512-NEXT: vpbroadcastq %xmm0, %zmm0
; X64_AVX512-NEXT: retq
%ins1 = insertelement <2 x i32> undef, i32 %x0, i32 0
%ins2 = insertelement <2 x i32> %ins1, i32 %x1, i32 1
%bc = bitcast <2 x i32> %ins2 to i64
%ins3 = insertelement <8 x i64> undef, i64 %bc, i32 0
%splat = shufflevector <8 x i64> %ins3, <8 x i64> undef, <8 x i32> zeroinitializer
ret <8 x i64> %splat
}