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/combine-mul.ll

316 lines
10 KiB
LLVM
Raw Normal View History

[X86][SSE] Added vector mul combine tests llvm-svn: 281839
2016-09-18 04:06:16 +08:00
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse4.1 | FileCheck %s --check-prefix=SSE
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2 | FileCheck %s --check-prefix=AVX
; fold (mul x, 0) -> 0
define <4 x i32> @combine_vec_mul_zero(<4 x i32> %x) {
; SSE-LABEL: combine_vec_mul_zero:
[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
; SSE: # %bb.0:
[X86][SSE] Added vector mul combine tests llvm-svn: 281839
2016-09-18 04:06:16 +08:00
; SSE-NEXT: xorps %xmm0, %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: combine_vec_mul_zero:
[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] Added vector mul combine tests llvm-svn: 281839
2016-09-18 04:06:16 +08:00
; AVX-NEXT: vxorps %xmm0, %xmm0, %xmm0
; AVX-NEXT: retq
%1 = mul <4 x i32> %x, zeroinitializer
ret <4 x i32> %1
}
Copy+pasts typo in comment describing combine test Repeated the "fold (mul x, 0) -> 0" instead of "fold (mul x, 1) -> x" llvm-svn: 284118
2016-10-13 20:54:32 +08:00
; fold (mul x, 1) -> x
[X86][SSE] Added vector mul combine tests llvm-svn: 281839
2016-09-18 04:06:16 +08:00
define <4 x i32> @combine_vec_mul_one(<4 x i32> %x) {
; SSE-LABEL: combine_vec_mul_one:
[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
; SSE: # %bb.0:
[X86][SSE] Added vector mul combine tests llvm-svn: 281839
2016-09-18 04:06:16 +08:00
; SSE-NEXT: retq
;
; AVX-LABEL: combine_vec_mul_one:
[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] Added vector mul combine tests llvm-svn: 281839
2016-09-18 04:06:16 +08:00
; AVX-NEXT: retq
%1 = mul <4 x i32> %x, <i32 1, i32 1, i32 1, i32 1>
ret <4 x i32> %1
}
; fold (mul x, -1) -> 0-x
define <4 x i32> @combine_vec_mul_negone(<4 x i32> %x) {
; SSE-LABEL: combine_vec_mul_negone:
[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
; SSE: # %bb.0:
[X86][SSE] Added vector mul combine tests llvm-svn: 281839
2016-09-18 04:06:16 +08:00
; SSE-NEXT: pxor %xmm1, %xmm1
; SSE-NEXT: psubd %xmm0, %xmm1
; SSE-NEXT: movdqa %xmm1, %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: combine_vec_mul_negone:
[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] Added vector mul combine tests llvm-svn: 281839
2016-09-18 04:06:16 +08:00
; AVX-NEXT: vpxor %xmm1, %xmm1, %xmm1
; AVX-NEXT: vpsubd %xmm0, %xmm1, %xmm0
; AVX-NEXT: retq
%1 = mul <4 x i32> %x, <i32 -1, i32 -1, i32 -1, i32 -1>
ret <4 x i32> %1
}
; fold (mul x, (1 << c)) -> x << c
define <4 x i32> @combine_vec_mul_pow2a(<4 x i32> %x) {
; SSE-LABEL: combine_vec_mul_pow2a:
[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
; SSE: # %bb.0:
[X86][SSE] Added vector mul combine tests llvm-svn: 281839
2016-09-18 04:06:16 +08:00
; SSE-NEXT: paddd %xmm0, %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: combine_vec_mul_pow2a:
[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] Added vector mul combine tests llvm-svn: 281839
2016-09-18 04:06:16 +08:00
; AVX-NEXT: vpaddd %xmm0, %xmm0, %xmm0
; AVX-NEXT: retq
%1 = mul <4 x i32> %x, <i32 2, i32 2, i32 2, i32 2>
ret <4 x i32> %1
}
define <4 x i32> @combine_vec_mul_pow2b(<4 x i32> %x) {
; SSE-LABEL: combine_vec_mul_pow2b:
[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
; SSE: # %bb.0:
[X86][SSE] Added vector mul combine tests llvm-svn: 281839
2016-09-18 04:06:16 +08:00
; SSE-NEXT: pmulld {{.*}}(%rip), %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: combine_vec_mul_pow2b:
[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:
[DAGCombiner] Add support for non-uniform constant vectors to (mul x, (1 << c)) -> x << c llvm-svn: 311083
2017-08-17 21:03:34 +08:00
; AVX-NEXT: vpsllvd {{.*}}(%rip), %xmm0, %xmm0
[X86][SSE] Added vector mul combine tests llvm-svn: 281839
2016-09-18 04:06:16 +08:00
; AVX-NEXT: retq
%1 = mul <4 x i32> %x, <i32 1, i32 2, i32 4, i32 16>
ret <4 x i32> %1
}
[X86][SSE] Added extra (mul x, (1 << c)) -> x << c style vector tests vXi64 will benefit more from lowering to shifts than multiplies llvm-svn: 284461
2016-10-18 17:29:13 +08:00
define <4 x i64> @combine_vec_mul_pow2c(<4 x i64> %x) {
; SSE-LABEL: combine_vec_mul_pow2c:
[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
; SSE: # %bb.0:
[DAGCombiner] Add support for non-uniform constant vectors to (mul x, (1 << c)) -> x << c llvm-svn: 311083
2017-08-17 21:03:34 +08:00
; SSE-NEXT: movdqa %xmm0, %xmm2
; SSE-NEXT: psllq $1, %xmm2
; SSE-NEXT: pblendw {{.*#+}} xmm2 = xmm0[0,1,2,3],xmm2[4,5,6,7]
; SSE-NEXT: movdqa %xmm1, %xmm0
; SSE-NEXT: psllq $4, %xmm0
; SSE-NEXT: psllq $2, %xmm1
; SSE-NEXT: pblendw {{.*#+}} xmm1 = xmm1[0,1,2,3],xmm0[4,5,6,7]
; SSE-NEXT: movdqa %xmm2, %xmm0
[X86][SSE] Added extra (mul x, (1 << c)) -> x << c style vector tests vXi64 will benefit more from lowering to shifts than multiplies llvm-svn: 284461
2016-10-18 17:29:13 +08:00
; SSE-NEXT: retq
;
; AVX-LABEL: combine_vec_mul_pow2c:
[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:
[DAGCombiner] Add support for non-uniform constant vectors to (mul x, (1 << c)) -> x << c llvm-svn: 311083
2017-08-17 21:03:34 +08:00
; AVX-NEXT: vpsllvq {{.*}}(%rip), %ymm0, %ymm0
[X86][SSE] Added extra (mul x, (1 << c)) -> x << c style vector tests vXi64 will benefit more from lowering to shifts than multiplies llvm-svn: 284461
2016-10-18 17:29:13 +08:00
; AVX-NEXT: retq
%1 = mul <4 x i64> %x, <i64 1, i64 2, i64 4, i64 16>
ret <4 x i64> %1
}
[X86][SSE] Added vector mul combine tests llvm-svn: 281839
2016-09-18 04:06:16 +08:00
; fold (mul x, -(1 << c)) -> -(x << c) or (-x) << c
define <4 x i32> @combine_vec_mul_negpow2a(<4 x i32> %x) {
; SSE-LABEL: combine_vec_mul_negpow2a:
[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
; SSE: # %bb.0:
[X86][SSE] Added vector mul combine tests llvm-svn: 281839
2016-09-18 04:06:16 +08:00
; SSE-NEXT: paddd %xmm0, %xmm0
; SSE-NEXT: pxor %xmm1, %xmm1
; SSE-NEXT: psubd %xmm0, %xmm1
; SSE-NEXT: movdqa %xmm1, %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: combine_vec_mul_negpow2a:
[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] Added vector mul combine tests llvm-svn: 281839
2016-09-18 04:06:16 +08:00
; AVX-NEXT: vpaddd %xmm0, %xmm0, %xmm0
; AVX-NEXT: vpxor %xmm1, %xmm1, %xmm1
; AVX-NEXT: vpsubd %xmm0, %xmm1, %xmm0
; AVX-NEXT: retq
%1 = mul <4 x i32> %x, <i32 -2, i32 -2, i32 -2, i32 -2>
ret <4 x i32> %1
}
define <4 x i32> @combine_vec_mul_negpow2b(<4 x i32> %x) {
; SSE-LABEL: combine_vec_mul_negpow2b:
[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
; SSE: # %bb.0:
[X86][SSE] Added vector mul combine tests llvm-svn: 281839
2016-09-18 04:06:16 +08:00
; SSE-NEXT: pmulld {{.*}}(%rip), %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: combine_vec_mul_negpow2b:
[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] Added vector mul combine tests llvm-svn: 281839
2016-09-18 04:06:16 +08:00
; AVX-NEXT: vpmulld {{.*}}(%rip), %xmm0, %xmm0
; AVX-NEXT: retq
%1 = mul <4 x i32> %x, <i32 -1, i32 -2, i32 -4, i32 -16>
ret <4 x i32> %1
}
[X86][SSE] Added extra (mul x, (1 << c)) -> x << c style vector tests vXi64 will benefit more from lowering to shifts than multiplies llvm-svn: 284461
2016-10-18 17:29:13 +08:00
define <4 x i64> @combine_vec_mul_negpow2c(<4 x i64> %x) {
; SSE-LABEL: combine_vec_mul_negpow2c:
[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
; SSE: # %bb.0:
[X86][SSE] Improve lowering of vXi64 multiplies As mentioned on PR30845, we were performing our vXi64 multiplication as: AloBlo = pmuludq(a, b); AloBhi = pmuludq(a, psrlqi(b, 32)); AhiBlo = pmuludq(psrlqi(a, 32), b); return AloBlo + psllqi(AloBhi, 32)+ psllqi(AhiBlo, 32); when we could avoid one of the upper shifts with: AloBlo = pmuludq(a, b); AloBhi = pmuludq(a, psrlqi(b, 32)); AhiBlo = pmuludq(psrlqi(a, 32), b); return AloBlo + psllqi(AloBhi + AhiBlo, 32); This matches the lowering on gcc/icc. Differential Revision: https://reviews.llvm.org/D27756 llvm-svn: 290267
2016-12-22 04:00:10 +08:00
; SSE-NEXT: movdqa {{.*#+}} xmm2 = [4294967295,4294967295]
[X86][SSE] Added extra (mul x, (1 << c)) -> x << c style vector tests vXi64 will benefit more from lowering to shifts than multiplies llvm-svn: 284461
2016-10-18 17:29:13 +08:00
; SSE-NEXT: movdqa %xmm0, %xmm3
; SSE-NEXT: pmuludq %xmm2, %xmm3
[X86][SSE] Improve lowering of vXi64 multiplies As mentioned on PR30845, we were performing our vXi64 multiplication as: AloBlo = pmuludq(a, b); AloBhi = pmuludq(a, psrlqi(b, 32)); AhiBlo = pmuludq(psrlqi(a, 32), b); return AloBlo + psllqi(AloBhi, 32)+ psllqi(AhiBlo, 32); when we could avoid one of the upper shifts with: AloBlo = pmuludq(a, b); AloBhi = pmuludq(a, psrlqi(b, 32)); AhiBlo = pmuludq(psrlqi(a, 32), b); return AloBlo + psllqi(AloBhi + AhiBlo, 32); This matches the lowering on gcc/icc. Differential Revision: https://reviews.llvm.org/D27756 llvm-svn: 290267
2016-12-22 04:00:10 +08:00
; SSE-NEXT: movdqa %xmm0, %xmm4
; SSE-NEXT: psrlq $32, %xmm4
; SSE-NEXT: movdqa {{.*#+}} xmm5 = [18446744073709551615,18446744073709551614]
; SSE-NEXT: pmuludq %xmm5, %xmm4
; SSE-NEXT: paddq %xmm3, %xmm4
[X86][SSE] Added extra (mul x, (1 << c)) -> x << c style vector tests vXi64 will benefit more from lowering to shifts than multiplies llvm-svn: 284461
2016-10-18 17:29:13 +08:00
; SSE-NEXT: psllq $32, %xmm4
[X86][SSE] Improve lowering of vXi64 multiplies As mentioned on PR30845, we were performing our vXi64 multiplication as: AloBlo = pmuludq(a, b); AloBhi = pmuludq(a, psrlqi(b, 32)); AhiBlo = pmuludq(psrlqi(a, 32), b); return AloBlo + psllqi(AloBhi, 32)+ psllqi(AhiBlo, 32); when we could avoid one of the upper shifts with: AloBlo = pmuludq(a, b); AloBhi = pmuludq(a, psrlqi(b, 32)); AhiBlo = pmuludq(psrlqi(a, 32), b); return AloBlo + psllqi(AloBhi + AhiBlo, 32); This matches the lowering on gcc/icc. Differential Revision: https://reviews.llvm.org/D27756 llvm-svn: 290267
2016-12-22 04:00:10 +08:00
; SSE-NEXT: pmuludq %xmm5, %xmm0
; SSE-NEXT: paddq %xmm4, %xmm0
; SSE-NEXT: pmuludq %xmm1, %xmm2
; SSE-NEXT: movdqa %xmm1, %xmm3
; SSE-NEXT: psrlq $32, %xmm3
; SSE-NEXT: movdqa {{.*#+}} xmm4 = [18446744073709551612,18446744073709551600]
; SSE-NEXT: pmuludq %xmm4, %xmm3
; SSE-NEXT: paddq %xmm2, %xmm3
; SSE-NEXT: psllq $32, %xmm3
; SSE-NEXT: pmuludq %xmm4, %xmm1
[X86][SSE] Added extra (mul x, (1 << c)) -> x << c style vector tests vXi64 will benefit more from lowering to shifts than multiplies llvm-svn: 284461
2016-10-18 17:29:13 +08:00
; SSE-NEXT: paddq %xmm3, %xmm1
; SSE-NEXT: retq
;
; AVX-LABEL: combine_vec_mul_negpow2c:
[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:
Regenerate mul combine tests to update broadcast comment. llvm-svn: 314607
2017-10-01 06:27:46 +08:00
; AVX-NEXT: vpbroadcastq {{.*#+}} ymm1 = [4294967295,4294967295,4294967295,4294967295]
[X86][SSE] Improve lowering of vXi64 multiplies As mentioned on PR30845, we were performing our vXi64 multiplication as: AloBlo = pmuludq(a, b); AloBhi = pmuludq(a, psrlqi(b, 32)); AhiBlo = pmuludq(psrlqi(a, 32), b); return AloBlo + psllqi(AloBhi, 32)+ psllqi(AhiBlo, 32); when we could avoid one of the upper shifts with: AloBlo = pmuludq(a, b); AloBhi = pmuludq(a, psrlqi(b, 32)); AhiBlo = pmuludq(psrlqi(a, 32), b); return AloBlo + psllqi(AloBhi + AhiBlo, 32); This matches the lowering on gcc/icc. Differential Revision: https://reviews.llvm.org/D27756 llvm-svn: 290267
2016-12-22 04:00:10 +08:00
; AVX-NEXT: vpmuludq %ymm1, %ymm0, %ymm1
; AVX-NEXT: vpsrlq $32, %ymm0, %ymm2
; AVX-NEXT: vmovdqa {{.*#+}} ymm3 = [18446744073709551615,18446744073709551614,18446744073709551612,18446744073709551600]
; AVX-NEXT: vpmuludq %ymm3, %ymm2, %ymm2
; AVX-NEXT: vpaddq %ymm2, %ymm1, %ymm1
; AVX-NEXT: vpsllq $32, %ymm1, %ymm1
; AVX-NEXT: vpmuludq %ymm3, %ymm0, %ymm0
; AVX-NEXT: vpaddq %ymm1, %ymm0, %ymm0
[X86][SSE] Added extra (mul x, (1 << c)) -> x << c style vector tests vXi64 will benefit more from lowering to shifts than multiplies llvm-svn: 284461
2016-10-18 17:29:13 +08:00
; AVX-NEXT: retq
%1 = mul <4 x i64> %x, <i64 -1, i64 -2, i64 -4, i64 -16>
ret <4 x i64> %1
}
[X86][SSE] Added vector mul combine tests llvm-svn: 281839
2016-09-18 04:06:16 +08:00
; (mul (shl X, c1), c2) -> (mul X, c2 << c1)
define <4 x i32> @combine_vec_mul_shl_const(<4 x i32> %x) {
; SSE-LABEL: combine_vec_mul_shl_const:
[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
; SSE: # %bb.0:
[X86][SSE] Added vector mul combine tests llvm-svn: 281839
2016-09-18 04:06:16 +08:00
; SSE-NEXT: pmulld {{.*}}(%rip), %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: combine_vec_mul_shl_const:
[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] Added vector mul combine tests llvm-svn: 281839
2016-09-18 04:06:16 +08:00
; AVX-NEXT: vpmulld {{.*}}(%rip), %xmm0, %xmm0
; AVX-NEXT: retq
%1 = shl <4 x i32> %x, <i32 1, i32 2, i32 8, i32 16>
%2 = mul <4 x i32> %1, <i32 1, i32 3, i32 5, i32 7>
ret <4 x i32> %2
}
; (mul (shl X, C), Y) -> (shl (mul X, Y), C) when the shift has one use.
define <4 x i32> @combine_vec_mul_shl_oneuse0(<4 x i32> %x, <4 x i32> %y) {
; SSE-LABEL: combine_vec_mul_shl_oneuse0:
[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
; SSE: # %bb.0:
[X86][SSE] Added vector mul combine tests llvm-svn: 281839
2016-09-18 04:06:16 +08:00
; SSE-NEXT: pmulld %xmm1, %xmm0
; SSE-NEXT: pmulld {{.*}}(%rip), %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: combine_vec_mul_shl_oneuse0:
[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] Added vector mul combine tests llvm-svn: 281839
2016-09-18 04:06:16 +08:00
; AVX-NEXT: vpmulld %xmm1, %xmm0, %xmm0
[DAGCombiner] Add vector support to (mul (shl X, Y), Z) -> (shl (mul X, Z), Y) style combines llvm-svn: 284122
2016-10-13 22:04:35 +08:00
; AVX-NEXT: vpsllvd {{.*}}(%rip), %xmm0, %xmm0
[X86][SSE] Added vector mul combine tests llvm-svn: 281839
2016-09-18 04:06:16 +08:00
; AVX-NEXT: retq
%1 = shl <4 x i32> %x, <i32 1, i32 2, i32 8, i32 16>
%2 = mul <4 x i32> %1, %y
ret <4 x i32> %2
}
define <4 x i32> @combine_vec_mul_shl_oneuse1(<4 x i32> %x, <4 x i32> %y) {
; SSE-LABEL: combine_vec_mul_shl_oneuse1:
[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
; SSE: # %bb.0:
[X86][SSE] Added vector mul combine tests llvm-svn: 281839
2016-09-18 04:06:16 +08:00
; SSE-NEXT: pmulld %xmm1, %xmm0
; SSE-NEXT: pmulld {{.*}}(%rip), %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: combine_vec_mul_shl_oneuse1:
[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:
[DAGCombiner] Add vector support to (mul (shl X, Y), Z) -> (shl (mul X, Z), Y) style combines llvm-svn: 284122
2016-10-13 22:04:35 +08:00
; AVX-NEXT: vpmulld %xmm1, %xmm0, %xmm0
[X86][SSE] Added vector mul combine tests llvm-svn: 281839
2016-09-18 04:06:16 +08:00
; AVX-NEXT: vpsllvd {{.*}}(%rip), %xmm0, %xmm0
; AVX-NEXT: retq
%1 = shl <4 x i32> %x, <i32 1, i32 2, i32 8, i32 16>
%2 = mul <4 x i32> %y, %1
ret <4 x i32> %2
}
define <4 x i32> @combine_vec_mul_shl_multiuse0(<4 x i32> %x, <4 x i32> %y) {
; SSE-LABEL: combine_vec_mul_shl_multiuse0:
[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
; SSE: # %bb.0:
[X86][SSE] Added vector mul combine tests llvm-svn: 281839
2016-09-18 04:06:16 +08:00
; SSE-NEXT: pmulld {{.*}}(%rip), %xmm0
; SSE-NEXT: pmulld %xmm0, %xmm1
; SSE-NEXT: paddd %xmm1, %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: combine_vec_mul_shl_multiuse0:
[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] Added vector mul combine tests llvm-svn: 281839
2016-09-18 04:06:16 +08:00
; AVX-NEXT: vpsllvd {{.*}}(%rip), %xmm0, %xmm0
; AVX-NEXT: vpmulld %xmm1, %xmm0, %xmm1
; AVX-NEXT: vpaddd %xmm1, %xmm0, %xmm0
; AVX-NEXT: retq
%1 = shl <4 x i32> %x, <i32 1, i32 2, i32 8, i32 16>
%2 = mul <4 x i32> %1, %y
%3 = add <4 x i32> %1, %2
ret <4 x i32> %3
}
define <4 x i32> @combine_vec_mul_shl_multiuse1(<4 x i32> %x, <4 x i32> %y) {
; SSE-LABEL: combine_vec_mul_shl_multiuse1:
[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
; SSE: # %bb.0:
[X86][SSE] Added vector mul combine tests llvm-svn: 281839
2016-09-18 04:06:16 +08:00
; SSE-NEXT: pmulld {{.*}}(%rip), %xmm0
; SSE-NEXT: pmulld %xmm0, %xmm1
; SSE-NEXT: paddd %xmm1, %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: combine_vec_mul_shl_multiuse1:
[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] Added vector mul combine tests llvm-svn: 281839
2016-09-18 04:06:16 +08:00
; AVX-NEXT: vpsllvd {{.*}}(%rip), %xmm0, %xmm0
; AVX-NEXT: vpmulld %xmm0, %xmm1, %xmm1
; AVX-NEXT: vpaddd %xmm1, %xmm0, %xmm0
; AVX-NEXT: retq
%1 = shl <4 x i32> %x, <i32 1, i32 2, i32 8, i32 16>
%2 = mul <4 x i32> %y, %1
%3 = add <4 x i32> %1, %2
ret <4 x i32> %3
}
; fold (mul (add x, c1), c2) -> (add (mul x, c2), c1*c2)
define <4 x i32> @combine_vec_mul_add(<4 x i32> %x) {
; SSE-LABEL: combine_vec_mul_add:
[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
; SSE: # %bb.0:
[X86][SSE] Added vector mul combine tests llvm-svn: 281839
2016-09-18 04:06:16 +08:00
; SSE-NEXT: pmulld {{.*}}(%rip), %xmm0
; SSE-NEXT: paddd {{.*}}(%rip), %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: combine_vec_mul_add:
[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] Added vector mul combine tests llvm-svn: 281839
2016-09-18 04:06:16 +08:00
; AVX-NEXT: vpmulld {{.*}}(%rip), %xmm0, %xmm0
; AVX-NEXT: vpaddd {{.*}}(%rip), %xmm0, %xmm0
; AVX-NEXT: retq
%1 = add <4 x i32> %x, <i32 1, i32 2, i32 8, i32 16>
%2 = mul <4 x i32> %1, <i32 4, i32 6, i32 2, i32 0>
ret <4 x i32> %2
}
[DAGCombiner] protect against an infinite loop between shl <--> mul (PR35579) At first, I tried to thread the x86 needle and use a target hook (isVectorShiftByScalarCheap()) to disable the transform only for non-splat pow-of-2 constants, but not AVX2, but only some element types, but...it's difficult. Here we just avoid the loop with the x86 vector transform that conflicts with the general DAG combine and preserve all of the existing behavior AFAICT otherwise. Some tests that will probably fail if someone does try to restrict this in a more targeted way for x86-only may be found in: test/CodeGen/X86/combine-mul.ll test/CodeGen/X86/vector-mul.ll test/CodeGen/X86/widen_arith-5.ll This should prevent the infinite looping seen with: https://bugs.llvm.org/show_bug.cgi?id=35579 Differential Revision: https://reviews.llvm.org/D41040 llvm-svn: 320374
2017-12-11 23:19:31 +08:00
; This would infinite loop because DAGCombiner wants to turn this into a shift,
; but x86 lowering wants to avoid non-uniform vector shift amounts.
define <16 x i8> @PR35579(<16 x i8> %x) {
; SSE-LABEL: PR35579:
; SSE: # %bb.0:
[X86] Remove sse41 specific code from lowering v16i8 multiply With the SRAs removed from the SSE2 code in D44267, then there doesn't appear to be any advantage to the sse41 code. The punpcklbw instruction and pmovsx seem to have the same latency and throughput on most CPUs. And the SSE41 code requires moving the upper 64-bits into the lower 64-bit before the sign extend can be done. The unpckhbw in sse2 code can do better than that. llvm-svn: 327869
2018-03-20 01:31:41 +08:00
; SSE-NEXT: pmovzxbw {{.*#+}} xmm1 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero
; SSE-NEXT: punpckhbw {{.*#+}} xmm0 = xmm0[8,8,9,9,10,10,11,11,12,12,13,13,14,14,15,15]
[X86] Teach LowerMUL/LowerMULH for vXi8 to unpack constant RHS. Summary: We need to unpackl and unpackh the operands to use two vXi16 multiplies. Previously it looks like the low unpack would get constant folded at least in the 128-bit case after shuffle lowering turned the unpackl into ZERO_EXTEND_VECTOR_INREG and X86 custom DAG combined it. The same doesn't happen for the high half. So we'd load a constant and then shuffle it. But the low half would just be loaded and used by the multiply directly. After this patch we now end up with a constant pool entry for the low and high unpacks separately with no shuffle operations. This is a step towards removing custom constant folding for ZERO_EXTEND_VECTOR_INREG/SIGN_EXTEND_VECTOR_INREG in the X86 backend. Reviewers: RKSimon, spatel Reviewed By: RKSimon Subscribers: llvm-commits Differential Revision: https://reviews.llvm.org/D55165 llvm-svn: 348159
2018-12-04 02:26:27 +08:00
; SSE-NEXT: pmullw {{.*}}(%rip), %xmm0
[DAGCombiner] protect against an infinite loop between shl <--> mul (PR35579) At first, I tried to thread the x86 needle and use a target hook (isVectorShiftByScalarCheap()) to disable the transform only for non-splat pow-of-2 constants, but not AVX2, but only some element types, but...it's difficult. Here we just avoid the loop with the x86 vector transform that conflicts with the general DAG combine and preserve all of the existing behavior AFAICT otherwise. Some tests that will probably fail if someone does try to restrict this in a more targeted way for x86-only may be found in: test/CodeGen/X86/combine-mul.ll test/CodeGen/X86/vector-mul.ll test/CodeGen/X86/widen_arith-5.ll This should prevent the infinite looping seen with: https://bugs.llvm.org/show_bug.cgi?id=35579 Differential Revision: https://reviews.llvm.org/D41040 llvm-svn: 320374
2017-12-11 23:19:31 +08:00
; SSE-NEXT: movdqa {{.*#+}} xmm2 = [255,255,255,255,255,255,255,255]
; SSE-NEXT: pand %xmm2, %xmm0
[X86] Remove sse41 specific code from lowering v16i8 multiply With the SRAs removed from the SSE2 code in D44267, then there doesn't appear to be any advantage to the sse41 code. The punpcklbw instruction and pmovsx seem to have the same latency and throughput on most CPUs. And the SSE41 code requires moving the upper 64-bits into the lower 64-bit before the sign extend can be done. The unpckhbw in sse2 code can do better than that. llvm-svn: 327869
2018-03-20 01:31:41 +08:00
; SSE-NEXT: pmullw {{.*}}(%rip), %xmm1
; SSE-NEXT: pand %xmm2, %xmm1
[DAGCombiner] protect against an infinite loop between shl <--> mul (PR35579) At first, I tried to thread the x86 needle and use a target hook (isVectorShiftByScalarCheap()) to disable the transform only for non-splat pow-of-2 constants, but not AVX2, but only some element types, but...it's difficult. Here we just avoid the loop with the x86 vector transform that conflicts with the general DAG combine and preserve all of the existing behavior AFAICT otherwise. Some tests that will probably fail if someone does try to restrict this in a more targeted way for x86-only may be found in: test/CodeGen/X86/combine-mul.ll test/CodeGen/X86/vector-mul.ll test/CodeGen/X86/widen_arith-5.ll This should prevent the infinite looping seen with: https://bugs.llvm.org/show_bug.cgi?id=35579 Differential Revision: https://reviews.llvm.org/D41040 llvm-svn: 320374
2017-12-11 23:19:31 +08:00
; SSE-NEXT: packuswb %xmm0, %xmm1
; SSE-NEXT: movdqa %xmm1, %xmm0
; SSE-NEXT: retq
;
; AVX-LABEL: PR35579:
; AVX: # %bb.0:
[X86] Use ANY_EXTEND instead of SIGN_EXTEND in the AVX2 and later path for legalizing vXi8 multiply. We aren't going to use the upper bits of the multiply result that the extend would effect. So we don't need a specific type of extend. This makes some reduction test cases shorter because we were previously trying to sign_extend a truncate which we can't eliminate. llvm-svn: 347011
2018-11-16 09:16:59 +08:00
; AVX-NEXT: vpmovzxbw {{.*#+}} ymm0 = xmm0[0],zero,xmm0[1],zero,xmm0[2],zero,xmm0[3],zero,xmm0[4],zero,xmm0[5],zero,xmm0[6],zero,xmm0[7],zero,xmm0[8],zero,xmm0[9],zero,xmm0[10],zero,xmm0[11],zero,xmm0[12],zero,xmm0[13],zero,xmm0[14],zero,xmm0[15],zero
[DAGCombiner] protect against an infinite loop between shl <--> mul (PR35579) At first, I tried to thread the x86 needle and use a target hook (isVectorShiftByScalarCheap()) to disable the transform only for non-splat pow-of-2 constants, but not AVX2, but only some element types, but...it's difficult. Here we just avoid the loop with the x86 vector transform that conflicts with the general DAG combine and preserve all of the existing behavior AFAICT otherwise. Some tests that will probably fail if someone does try to restrict this in a more targeted way for x86-only may be found in: test/CodeGen/X86/combine-mul.ll test/CodeGen/X86/vector-mul.ll test/CodeGen/X86/widen_arith-5.ll This should prevent the infinite looping seen with: https://bugs.llvm.org/show_bug.cgi?id=35579 Differential Revision: https://reviews.llvm.org/D41040 llvm-svn: 320374
2017-12-11 23:19:31 +08:00
; AVX-NEXT: vpmullw {{.*}}(%rip), %ymm0, %ymm0
[X86] Lower v16i16->v8i16 truncate using an 'and' with 255, an extract_subvector, and a packuswb instruction. Summary: This is an improvement over the two pshufbs and punpcklqdq we'd get otherwise. Reviewers: RKSimon, spatel Reviewed By: RKSimon Subscribers: llvm-commits Differential Revision: https://reviews.llvm.org/D54671 llvm-svn: 347171
2018-11-19 01:59:28 +08:00
; AVX-NEXT: vpand {{.*}}(%rip), %ymm0, %ymm0
[DAGCombiner] protect against an infinite loop between shl <--> mul (PR35579) At first, I tried to thread the x86 needle and use a target hook (isVectorShiftByScalarCheap()) to disable the transform only for non-splat pow-of-2 constants, but not AVX2, but only some element types, but...it's difficult. Here we just avoid the loop with the x86 vector transform that conflicts with the general DAG combine and preserve all of the existing behavior AFAICT otherwise. Some tests that will probably fail if someone does try to restrict this in a more targeted way for x86-only may be found in: test/CodeGen/X86/combine-mul.ll test/CodeGen/X86/vector-mul.ll test/CodeGen/X86/widen_arith-5.ll This should prevent the infinite looping seen with: https://bugs.llvm.org/show_bug.cgi?id=35579 Differential Revision: https://reviews.llvm.org/D41040 llvm-svn: 320374
2017-12-11 23:19:31 +08:00
; AVX-NEXT: vextracti128 $1, %ymm0, %xmm1
[X86] Lower v16i16->v8i16 truncate using an 'and' with 255, an extract_subvector, and a packuswb instruction. Summary: This is an improvement over the two pshufbs and punpcklqdq we'd get otherwise. Reviewers: RKSimon, spatel Reviewed By: RKSimon Subscribers: llvm-commits Differential Revision: https://reviews.llvm.org/D54671 llvm-svn: 347171
2018-11-19 01:59:28 +08:00
; AVX-NEXT: vpackuswb %xmm1, %xmm0, %xmm0
[DAGCombiner] protect against an infinite loop between shl <--> mul (PR35579) At first, I tried to thread the x86 needle and use a target hook (isVectorShiftByScalarCheap()) to disable the transform only for non-splat pow-of-2 constants, but not AVX2, but only some element types, but...it's difficult. Here we just avoid the loop with the x86 vector transform that conflicts with the general DAG combine and preserve all of the existing behavior AFAICT otherwise. Some tests that will probably fail if someone does try to restrict this in a more targeted way for x86-only may be found in: test/CodeGen/X86/combine-mul.ll test/CodeGen/X86/vector-mul.ll test/CodeGen/X86/widen_arith-5.ll This should prevent the infinite looping seen with: https://bugs.llvm.org/show_bug.cgi?id=35579 Differential Revision: https://reviews.llvm.org/D41040 llvm-svn: 320374
2017-12-11 23:19:31 +08:00
; AVX-NEXT: vzeroupper
; AVX-NEXT: retq
%r = mul <16 x i8> %x, <i8 0, i8 1, i8 2, i8 1, i8 4, i8 1, i8 2, i8 1, i8 8, i8 1, i8 2, i8 1, i8 4, i8 1, i8 2, i8 1>
ret <16 x i8> %r
}