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-and.ll

180 lines
5.4 KiB
LLVM
Raw Normal View History

Make utils/update_llc_test_checks.py note that the assertions are autogenerated. Also update existing test cases which appear to be generated by it and weren't modified (other than addition of the header) by rerunning it. llvm-svn: 253917
2015-11-24 05:33:58 +08:00
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
[X86] Teach method 'isVectorClearMaskLegal' how to check for legal blend masks. This patch improves the folding of vector AND nodes into blend operations for targets that feature SSE4.1. A vector AND node where one of the operands is a constant build_vector with elements that are either zero or all-ones can be converted into a blend. This allows for example to simplify the following code: define <4 x i32> @test(<4 x i32> %A, <4 x i32> %B) { %1 = and <4 x i32> %A, <i32 0, i32 0, i32 0, i32 -1> %2 = and <4 x i32> %B, <i32 -1, i32 -1, i32 -1, i32 0> %3 = or <4 x i32> %1, %2 ret <4 x i32> %3 } Before this patch llc (-mcpu=corei7) generated: andps LCPI1_0(%rip), %xmm0, %xmm0 andps LCPI1_1(%rip), %xmm1, %xmm1 orps %xmm1, %xmm0, %xmm0 retq With this patch we generate a single 'vpblendw'. llvm-svn: 221343
2014-11-05 21:04:14 +08:00
; RUN: llc -mtriple=x86_64-unknown-unknown -mattr=+sse4.1 < %s | FileCheck %s
;
; Verify that the DAGCombiner is able to fold a vector AND into a blend
; if one of the operands to the AND is a vector of all constants, and each
; constant element is either zero or all-ones.
define <4 x i32> @test1(<4 x i32> %A) {
[x86] Port this test to use utils/update_llc_test_checks.py. This will make it easy to update as I change some parts of the X86 backend, makes it more clear what instruction differences are introduced, and I find it makes it a bit easier to read as well. llvm-svn: 228095
2015-02-04 08:58:37 +08:00
; CHECK-LABEL: test1:
; CHECK: # BB#0:
; CHECK-NEXT: pxor %xmm1, %xmm1
; CHECK-NEXT: pblendw {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,3,4,5,6,7]
; CHECK-NEXT: retq
[X86] Teach method 'isVectorClearMaskLegal' how to check for legal blend masks. This patch improves the folding of vector AND nodes into blend operations for targets that feature SSE4.1. A vector AND node where one of the operands is a constant build_vector with elements that are either zero or all-ones can be converted into a blend. This allows for example to simplify the following code: define <4 x i32> @test(<4 x i32> %A, <4 x i32> %B) { %1 = and <4 x i32> %A, <i32 0, i32 0, i32 0, i32 -1> %2 = and <4 x i32> %B, <i32 -1, i32 -1, i32 -1, i32 0> %3 = or <4 x i32> %1, %2 ret <4 x i32> %3 } Before this patch llc (-mcpu=corei7) generated: andps LCPI1_0(%rip), %xmm0, %xmm0 andps LCPI1_1(%rip), %xmm1, %xmm1 orps %xmm1, %xmm0, %xmm0 retq With this patch we generate a single 'vpblendw'. llvm-svn: 221343
2014-11-05 21:04:14 +08:00
%1 = and <4 x i32> %A, <i32 -1, i32 0, i32 0, i32 0>
ret <4 x i32> %1
}
define <4 x i32> @test2(<4 x i32> %A) {
[x86] Port this test to use utils/update_llc_test_checks.py. This will make it easy to update as I change some parts of the X86 backend, makes it more clear what instruction differences are introduced, and I find it makes it a bit easier to read as well. llvm-svn: 228095
2015-02-04 08:58:37 +08:00
; CHECK-LABEL: test2:
; CHECK: # BB#0:
; CHECK-NEXT: pxor %xmm1, %xmm1
; CHECK-NEXT: pblendw {{.*#+}} xmm0 = xmm1[0,1],xmm0[2,3],xmm1[4,5,6,7]
; CHECK-NEXT: retq
[X86] Teach method 'isVectorClearMaskLegal' how to check for legal blend masks. This patch improves the folding of vector AND nodes into blend operations for targets that feature SSE4.1. A vector AND node where one of the operands is a constant build_vector with elements that are either zero or all-ones can be converted into a blend. This allows for example to simplify the following code: define <4 x i32> @test(<4 x i32> %A, <4 x i32> %B) { %1 = and <4 x i32> %A, <i32 0, i32 0, i32 0, i32 -1> %2 = and <4 x i32> %B, <i32 -1, i32 -1, i32 -1, i32 0> %3 = or <4 x i32> %1, %2 ret <4 x i32> %3 } Before this patch llc (-mcpu=corei7) generated: andps LCPI1_0(%rip), %xmm0, %xmm0 andps LCPI1_1(%rip), %xmm1, %xmm1 orps %xmm1, %xmm0, %xmm0 retq With this patch we generate a single 'vpblendw'. llvm-svn: 221343
2014-11-05 21:04:14 +08:00
%1 = and <4 x i32> %A, <i32 0, i32 -1, i32 0, i32 0>
ret <4 x i32> %1
}
define <4 x i32> @test3(<4 x i32> %A) {
[x86] Port this test to use utils/update_llc_test_checks.py. This will make it easy to update as I change some parts of the X86 backend, makes it more clear what instruction differences are introduced, and I find it makes it a bit easier to read as well. llvm-svn: 228095
2015-02-04 08:58:37 +08:00
; CHECK-LABEL: test3:
; CHECK: # BB#0:
; CHECK-NEXT: pxor %xmm1, %xmm1
; CHECK-NEXT: pblendw {{.*#+}} xmm0 = xmm1[0,1,2,3],xmm0[4,5],xmm1[6,7]
; CHECK-NEXT: retq
[X86] Teach method 'isVectorClearMaskLegal' how to check for legal blend masks. This patch improves the folding of vector AND nodes into blend operations for targets that feature SSE4.1. A vector AND node where one of the operands is a constant build_vector with elements that are either zero or all-ones can be converted into a blend. This allows for example to simplify the following code: define <4 x i32> @test(<4 x i32> %A, <4 x i32> %B) { %1 = and <4 x i32> %A, <i32 0, i32 0, i32 0, i32 -1> %2 = and <4 x i32> %B, <i32 -1, i32 -1, i32 -1, i32 0> %3 = or <4 x i32> %1, %2 ret <4 x i32> %3 } Before this patch llc (-mcpu=corei7) generated: andps LCPI1_0(%rip), %xmm0, %xmm0 andps LCPI1_1(%rip), %xmm1, %xmm1 orps %xmm1, %xmm0, %xmm0 retq With this patch we generate a single 'vpblendw'. llvm-svn: 221343
2014-11-05 21:04:14 +08:00
%1 = and <4 x i32> %A, <i32 0, i32 0, i32 -1, i32 0>
ret <4 x i32> %1
}
define <4 x i32> @test4(<4 x i32> %A) {
[x86] Port this test to use utils/update_llc_test_checks.py. This will make it easy to update as I change some parts of the X86 backend, makes it more clear what instruction differences are introduced, and I find it makes it a bit easier to read as well. llvm-svn: 228095
2015-02-04 08:58:37 +08:00
; CHECK-LABEL: test4:
; CHECK: # BB#0:
; CHECK-NEXT: pxor %xmm1, %xmm1
; CHECK-NEXT: pblendw {{.*#+}} xmm0 = xmm1[0,1,2,3,4,5],xmm0[6,7]
; CHECK-NEXT: retq
[X86] Teach method 'isVectorClearMaskLegal' how to check for legal blend masks. This patch improves the folding of vector AND nodes into blend operations for targets that feature SSE4.1. A vector AND node where one of the operands is a constant build_vector with elements that are either zero or all-ones can be converted into a blend. This allows for example to simplify the following code: define <4 x i32> @test(<4 x i32> %A, <4 x i32> %B) { %1 = and <4 x i32> %A, <i32 0, i32 0, i32 0, i32 -1> %2 = and <4 x i32> %B, <i32 -1, i32 -1, i32 -1, i32 0> %3 = or <4 x i32> %1, %2 ret <4 x i32> %3 } Before this patch llc (-mcpu=corei7) generated: andps LCPI1_0(%rip), %xmm0, %xmm0 andps LCPI1_1(%rip), %xmm1, %xmm1 orps %xmm1, %xmm0, %xmm0 retq With this patch we generate a single 'vpblendw'. llvm-svn: 221343
2014-11-05 21:04:14 +08:00
%1 = and <4 x i32> %A, <i32 0, i32 0, i32 0, i32 -1>
ret <4 x i32> %1
}
define <4 x i32> @test5(<4 x i32> %A) {
[x86] Port this test to use utils/update_llc_test_checks.py. This will make it easy to update as I change some parts of the X86 backend, makes it more clear what instruction differences are introduced, and I find it makes it a bit easier to read as well. llvm-svn: 228095
2015-02-04 08:58:37 +08:00
; CHECK-LABEL: test5:
; CHECK: # BB#0:
; CHECK-NEXT: pxor %xmm1, %xmm1
; CHECK-NEXT: pblendw {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,3],xmm0[4,5],xmm1[6,7]
; CHECK-NEXT: retq
[X86] Teach method 'isVectorClearMaskLegal' how to check for legal blend masks. This patch improves the folding of vector AND nodes into blend operations for targets that feature SSE4.1. A vector AND node where one of the operands is a constant build_vector with elements that are either zero or all-ones can be converted into a blend. This allows for example to simplify the following code: define <4 x i32> @test(<4 x i32> %A, <4 x i32> %B) { %1 = and <4 x i32> %A, <i32 0, i32 0, i32 0, i32 -1> %2 = and <4 x i32> %B, <i32 -1, i32 -1, i32 -1, i32 0> %3 = or <4 x i32> %1, %2 ret <4 x i32> %3 } Before this patch llc (-mcpu=corei7) generated: andps LCPI1_0(%rip), %xmm0, %xmm0 andps LCPI1_1(%rip), %xmm1, %xmm1 orps %xmm1, %xmm0, %xmm0 retq With this patch we generate a single 'vpblendw'. llvm-svn: 221343
2014-11-05 21:04:14 +08:00
%1 = and <4 x i32> %A, <i32 -1, i32 0, i32 -1, i32 0>
ret <4 x i32> %1
}
define <4 x i32> @test6(<4 x i32> %A) {
[x86] Port this test to use utils/update_llc_test_checks.py. This will make it easy to update as I change some parts of the X86 backend, makes it more clear what instruction differences are introduced, and I find it makes it a bit easier to read as well. llvm-svn: 228095
2015-02-04 08:58:37 +08:00
; CHECK-LABEL: test6:
; CHECK: # BB#0:
; CHECK-NEXT: pxor %xmm1, %xmm1
; CHECK-NEXT: pblendw {{.*#+}} xmm0 = xmm1[0,1],xmm0[2,3],xmm1[4,5],xmm0[6,7]
; CHECK-NEXT: retq
[X86] Teach method 'isVectorClearMaskLegal' how to check for legal blend masks. This patch improves the folding of vector AND nodes into blend operations for targets that feature SSE4.1. A vector AND node where one of the operands is a constant build_vector with elements that are either zero or all-ones can be converted into a blend. This allows for example to simplify the following code: define <4 x i32> @test(<4 x i32> %A, <4 x i32> %B) { %1 = and <4 x i32> %A, <i32 0, i32 0, i32 0, i32 -1> %2 = and <4 x i32> %B, <i32 -1, i32 -1, i32 -1, i32 0> %3 = or <4 x i32> %1, %2 ret <4 x i32> %3 } Before this patch llc (-mcpu=corei7) generated: andps LCPI1_0(%rip), %xmm0, %xmm0 andps LCPI1_1(%rip), %xmm1, %xmm1 orps %xmm1, %xmm0, %xmm0 retq With this patch we generate a single 'vpblendw'. llvm-svn: 221343
2014-11-05 21:04:14 +08:00
%1 = and <4 x i32> %A, <i32 0, i32 -1, i32 0, i32 -1>
ret <4 x i32> %1
}
define <4 x i32> @test7(<4 x i32> %A) {
[x86] Port this test to use utils/update_llc_test_checks.py. This will make it easy to update as I change some parts of the X86 backend, makes it more clear what instruction differences are introduced, and I find it makes it a bit easier to read as well. llvm-svn: 228095
2015-02-04 08:58:37 +08:00
; CHECK-LABEL: test7:
; CHECK: # BB#0:
; CHECK-NEXT: pxor %xmm1, %xmm1
; CHECK-NEXT: pblendw {{.*#+}} xmm0 = xmm1[0,1,2,3],xmm0[4,5,6,7]
; CHECK-NEXT: retq
[X86] Teach method 'isVectorClearMaskLegal' how to check for legal blend masks. This patch improves the folding of vector AND nodes into blend operations for targets that feature SSE4.1. A vector AND node where one of the operands is a constant build_vector with elements that are either zero or all-ones can be converted into a blend. This allows for example to simplify the following code: define <4 x i32> @test(<4 x i32> %A, <4 x i32> %B) { %1 = and <4 x i32> %A, <i32 0, i32 0, i32 0, i32 -1> %2 = and <4 x i32> %B, <i32 -1, i32 -1, i32 -1, i32 0> %3 = or <4 x i32> %1, %2 ret <4 x i32> %3 } Before this patch llc (-mcpu=corei7) generated: andps LCPI1_0(%rip), %xmm0, %xmm0 andps LCPI1_1(%rip), %xmm1, %xmm1 orps %xmm1, %xmm0, %xmm0 retq With this patch we generate a single 'vpblendw'. llvm-svn: 221343
2014-11-05 21:04:14 +08:00
%1 = and <4 x i32> %A, <i32 0, i32 0, i32 -1, i32 -1>
ret <4 x i32> %1
}
define <4 x i32> @test8(<4 x i32> %A) {
[x86] Port this test to use utils/update_llc_test_checks.py. This will make it easy to update as I change some parts of the X86 backend, makes it more clear what instruction differences are introduced, and I find it makes it a bit easier to read as well. llvm-svn: 228095
2015-02-04 08:58:37 +08:00
; CHECK-LABEL: test8:
; CHECK: # BB#0:
; CHECK-NEXT: pxor %xmm1, %xmm1
; CHECK-NEXT: pblendw {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,3,4,5],xmm0[6,7]
; CHECK-NEXT: retq
[X86] Teach method 'isVectorClearMaskLegal' how to check for legal blend masks. This patch improves the folding of vector AND nodes into blend operations for targets that feature SSE4.1. A vector AND node where one of the operands is a constant build_vector with elements that are either zero or all-ones can be converted into a blend. This allows for example to simplify the following code: define <4 x i32> @test(<4 x i32> %A, <4 x i32> %B) { %1 = and <4 x i32> %A, <i32 0, i32 0, i32 0, i32 -1> %2 = and <4 x i32> %B, <i32 -1, i32 -1, i32 -1, i32 0> %3 = or <4 x i32> %1, %2 ret <4 x i32> %3 } Before this patch llc (-mcpu=corei7) generated: andps LCPI1_0(%rip), %xmm0, %xmm0 andps LCPI1_1(%rip), %xmm1, %xmm1 orps %xmm1, %xmm0, %xmm0 retq With this patch we generate a single 'vpblendw'. llvm-svn: 221343
2014-11-05 21:04:14 +08:00
%1 = and <4 x i32> %A, <i32 -1, i32 0, i32 0, i32 -1>
ret <4 x i32> %1
}
define <4 x i32> @test9(<4 x i32> %A) {
[x86] Port this test to use utils/update_llc_test_checks.py. This will make it easy to update as I change some parts of the X86 backend, makes it more clear what instruction differences are introduced, and I find it makes it a bit easier to read as well. llvm-svn: 228095
2015-02-04 08:58:37 +08:00
; CHECK-LABEL: test9:
; CHECK: # BB#0:
; CHECK-NEXT: movq {{.*#+}} xmm0 = xmm0[0],zero
; CHECK-NEXT: retq
[X86] Teach method 'isVectorClearMaskLegal' how to check for legal blend masks. This patch improves the folding of vector AND nodes into blend operations for targets that feature SSE4.1. A vector AND node where one of the operands is a constant build_vector with elements that are either zero or all-ones can be converted into a blend. This allows for example to simplify the following code: define <4 x i32> @test(<4 x i32> %A, <4 x i32> %B) { %1 = and <4 x i32> %A, <i32 0, i32 0, i32 0, i32 -1> %2 = and <4 x i32> %B, <i32 -1, i32 -1, i32 -1, i32 0> %3 = or <4 x i32> %1, %2 ret <4 x i32> %3 } Before this patch llc (-mcpu=corei7) generated: andps LCPI1_0(%rip), %xmm0, %xmm0 andps LCPI1_1(%rip), %xmm1, %xmm1 orps %xmm1, %xmm0, %xmm0 retq With this patch we generate a single 'vpblendw'. llvm-svn: 221343
2014-11-05 21:04:14 +08:00
%1 = and <4 x i32> %A, <i32 -1, i32 -1, i32 0, i32 0>
ret <4 x i32> %1
}
define <4 x i32> @test10(<4 x i32> %A) {
[x86] Port this test to use utils/update_llc_test_checks.py. This will make it easy to update as I change some parts of the X86 backend, makes it more clear what instruction differences are introduced, and I find it makes it a bit easier to read as well. llvm-svn: 228095
2015-02-04 08:58:37 +08:00
; CHECK-LABEL: test10:
; CHECK: # BB#0:
; CHECK-NEXT: pxor %xmm1, %xmm1
; CHECK-NEXT: pblendw {{.*#+}} xmm0 = xmm1[0,1],xmm0[2,3,4,5],xmm1[6,7]
; CHECK-NEXT: retq
[X86] Teach method 'isVectorClearMaskLegal' how to check for legal blend masks. This patch improves the folding of vector AND nodes into blend operations for targets that feature SSE4.1. A vector AND node where one of the operands is a constant build_vector with elements that are either zero or all-ones can be converted into a blend. This allows for example to simplify the following code: define <4 x i32> @test(<4 x i32> %A, <4 x i32> %B) { %1 = and <4 x i32> %A, <i32 0, i32 0, i32 0, i32 -1> %2 = and <4 x i32> %B, <i32 -1, i32 -1, i32 -1, i32 0> %3 = or <4 x i32> %1, %2 ret <4 x i32> %3 } Before this patch llc (-mcpu=corei7) generated: andps LCPI1_0(%rip), %xmm0, %xmm0 andps LCPI1_1(%rip), %xmm1, %xmm1 orps %xmm1, %xmm0, %xmm0 retq With this patch we generate a single 'vpblendw'. llvm-svn: 221343
2014-11-05 21:04:14 +08:00
%1 = and <4 x i32> %A, <i32 0, i32 -1, i32 -1, i32 0>
ret <4 x i32> %1
}
define <4 x i32> @test11(<4 x i32> %A) {
[x86] Port this test to use utils/update_llc_test_checks.py. This will make it easy to update as I change some parts of the X86 backend, makes it more clear what instruction differences are introduced, and I find it makes it a bit easier to read as well. llvm-svn: 228095
2015-02-04 08:58:37 +08:00
; CHECK-LABEL: test11:
; CHECK: # BB#0:
; CHECK-NEXT: pxor %xmm1, %xmm1
; CHECK-NEXT: pblendw {{.*#+}} xmm0 = xmm1[0,1],xmm0[2,3,4,5,6,7]
; CHECK-NEXT: retq
[X86] Teach method 'isVectorClearMaskLegal' how to check for legal blend masks. This patch improves the folding of vector AND nodes into blend operations for targets that feature SSE4.1. A vector AND node where one of the operands is a constant build_vector with elements that are either zero or all-ones can be converted into a blend. This allows for example to simplify the following code: define <4 x i32> @test(<4 x i32> %A, <4 x i32> %B) { %1 = and <4 x i32> %A, <i32 0, i32 0, i32 0, i32 -1> %2 = and <4 x i32> %B, <i32 -1, i32 -1, i32 -1, i32 0> %3 = or <4 x i32> %1, %2 ret <4 x i32> %3 } Before this patch llc (-mcpu=corei7) generated: andps LCPI1_0(%rip), %xmm0, %xmm0 andps LCPI1_1(%rip), %xmm1, %xmm1 orps %xmm1, %xmm0, %xmm0 retq With this patch we generate a single 'vpblendw'. llvm-svn: 221343
2014-11-05 21:04:14 +08:00
%1 = and <4 x i32> %A, <i32 0, i32 -1, i32 -1, i32 -1>
ret <4 x i32> %1
}
define <4 x i32> @test12(<4 x i32> %A) {
[x86] Port this test to use utils/update_llc_test_checks.py. This will make it easy to update as I change some parts of the X86 backend, makes it more clear what instruction differences are introduced, and I find it makes it a bit easier to read as well. llvm-svn: 228095
2015-02-04 08:58:37 +08:00
; CHECK-LABEL: test12:
; CHECK: # BB#0:
; CHECK-NEXT: pxor %xmm1, %xmm1
; CHECK-NEXT: pblendw {{.*#+}} xmm0 = xmm0[0,1,2,3,4,5],xmm1[6,7]
; CHECK-NEXT: retq
[X86] Teach method 'isVectorClearMaskLegal' how to check for legal blend masks. This patch improves the folding of vector AND nodes into blend operations for targets that feature SSE4.1. A vector AND node where one of the operands is a constant build_vector with elements that are either zero or all-ones can be converted into a blend. This allows for example to simplify the following code: define <4 x i32> @test(<4 x i32> %A, <4 x i32> %B) { %1 = and <4 x i32> %A, <i32 0, i32 0, i32 0, i32 -1> %2 = and <4 x i32> %B, <i32 -1, i32 -1, i32 -1, i32 0> %3 = or <4 x i32> %1, %2 ret <4 x i32> %3 } Before this patch llc (-mcpu=corei7) generated: andps LCPI1_0(%rip), %xmm0, %xmm0 andps LCPI1_1(%rip), %xmm1, %xmm1 orps %xmm1, %xmm0, %xmm0 retq With this patch we generate a single 'vpblendw'. llvm-svn: 221343
2014-11-05 21:04:14 +08:00
%1 = and <4 x i32> %A, <i32 -1, i32 -1, i32 -1, i32 0>
ret <4 x i32> %1
}
define <4 x i32> @test13(<4 x i32> %A) {
[x86] Port this test to use utils/update_llc_test_checks.py. This will make it easy to update as I change some parts of the X86 backend, makes it more clear what instruction differences are introduced, and I find it makes it a bit easier to read as well. llvm-svn: 228095
2015-02-04 08:58:37 +08:00
; CHECK-LABEL: test13:
; CHECK: # BB#0:
; CHECK-NEXT: pxor %xmm1, %xmm1
; CHECK-NEXT: pblendw {{.*#+}} xmm0 = xmm0[0,1,2,3],xmm1[4,5],xmm0[6,7]
; CHECK-NEXT: retq
[X86] Teach method 'isVectorClearMaskLegal' how to check for legal blend masks. This patch improves the folding of vector AND nodes into blend operations for targets that feature SSE4.1. A vector AND node where one of the operands is a constant build_vector with elements that are either zero or all-ones can be converted into a blend. This allows for example to simplify the following code: define <4 x i32> @test(<4 x i32> %A, <4 x i32> %B) { %1 = and <4 x i32> %A, <i32 0, i32 0, i32 0, i32 -1> %2 = and <4 x i32> %B, <i32 -1, i32 -1, i32 -1, i32 0> %3 = or <4 x i32> %1, %2 ret <4 x i32> %3 } Before this patch llc (-mcpu=corei7) generated: andps LCPI1_0(%rip), %xmm0, %xmm0 andps LCPI1_1(%rip), %xmm1, %xmm1 orps %xmm1, %xmm0, %xmm0 retq With this patch we generate a single 'vpblendw'. llvm-svn: 221343
2014-11-05 21:04:14 +08:00
%1 = and <4 x i32> %A, <i32 -1, i32 -1, i32 0, i32 -1>
ret <4 x i32> %1
}
define <4 x i32> @test14(<4 x i32> %A) {
[x86] Port this test to use utils/update_llc_test_checks.py. This will make it easy to update as I change some parts of the X86 backend, makes it more clear what instruction differences are introduced, and I find it makes it a bit easier to read as well. llvm-svn: 228095
2015-02-04 08:58:37 +08:00
; CHECK-LABEL: test14:
; CHECK: # BB#0:
; CHECK-NEXT: pxor %xmm1, %xmm1
; CHECK-NEXT: pblendw {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,3],xmm0[4,5,6,7]
; CHECK-NEXT: retq
[X86] Teach method 'isVectorClearMaskLegal' how to check for legal blend masks. This patch improves the folding of vector AND nodes into blend operations for targets that feature SSE4.1. A vector AND node where one of the operands is a constant build_vector with elements that are either zero or all-ones can be converted into a blend. This allows for example to simplify the following code: define <4 x i32> @test(<4 x i32> %A, <4 x i32> %B) { %1 = and <4 x i32> %A, <i32 0, i32 0, i32 0, i32 -1> %2 = and <4 x i32> %B, <i32 -1, i32 -1, i32 -1, i32 0> %3 = or <4 x i32> %1, %2 ret <4 x i32> %3 } Before this patch llc (-mcpu=corei7) generated: andps LCPI1_0(%rip), %xmm0, %xmm0 andps LCPI1_1(%rip), %xmm1, %xmm1 orps %xmm1, %xmm0, %xmm0 retq With this patch we generate a single 'vpblendw'. llvm-svn: 221343
2014-11-05 21:04:14 +08:00
%1 = and <4 x i32> %A, <i32 -1, i32 0, i32 -1, i32 -1>
ret <4 x i32> %1
}
define <4 x i32> @test15(<4 x i32> %A, <4 x i32> %B) {
[x86] Port this test to use utils/update_llc_test_checks.py. This will make it easy to update as I change some parts of the X86 backend, makes it more clear what instruction differences are introduced, and I find it makes it a bit easier to read as well. llvm-svn: 228095
2015-02-04 08:58:37 +08:00
; CHECK-LABEL: test15:
; CHECK: # BB#0:
; CHECK-NEXT: pblendw {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,3],xmm0[4,5,6,7]
; CHECK-NEXT: retq
[X86] Teach method 'isVectorClearMaskLegal' how to check for legal blend masks. This patch improves the folding of vector AND nodes into blend operations for targets that feature SSE4.1. A vector AND node where one of the operands is a constant build_vector with elements that are either zero or all-ones can be converted into a blend. This allows for example to simplify the following code: define <4 x i32> @test(<4 x i32> %A, <4 x i32> %B) { %1 = and <4 x i32> %A, <i32 0, i32 0, i32 0, i32 -1> %2 = and <4 x i32> %B, <i32 -1, i32 -1, i32 -1, i32 0> %3 = or <4 x i32> %1, %2 ret <4 x i32> %3 } Before this patch llc (-mcpu=corei7) generated: andps LCPI1_0(%rip), %xmm0, %xmm0 andps LCPI1_1(%rip), %xmm1, %xmm1 orps %xmm1, %xmm0, %xmm0 retq With this patch we generate a single 'vpblendw'. llvm-svn: 221343
2014-11-05 21:04:14 +08:00
%1 = and <4 x i32> %A, <i32 -1, i32 0, i32 -1, i32 -1>
%2 = and <4 x i32> %B, <i32 0, i32 -1, i32 0, i32 0>
%3 = or <4 x i32> %1, %2
ret <4 x i32> %3
}
define <4 x i32> @test16(<4 x i32> %A, <4 x i32> %B) {
[x86] Port this test to use utils/update_llc_test_checks.py. This will make it easy to update as I change some parts of the X86 backend, makes it more clear what instruction differences are introduced, and I find it makes it a bit easier to read as well. llvm-svn: 228095
2015-02-04 08:58:37 +08:00
; CHECK-LABEL: test16:
; CHECK: # BB#0:
; CHECK-NEXT: pblendw {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,3],xmm0[4,5],xmm1[6,7]
; CHECK-NEXT: retq
[X86] Teach method 'isVectorClearMaskLegal' how to check for legal blend masks. This patch improves the folding of vector AND nodes into blend operations for targets that feature SSE4.1. A vector AND node where one of the operands is a constant build_vector with elements that are either zero or all-ones can be converted into a blend. This allows for example to simplify the following code: define <4 x i32> @test(<4 x i32> %A, <4 x i32> %B) { %1 = and <4 x i32> %A, <i32 0, i32 0, i32 0, i32 -1> %2 = and <4 x i32> %B, <i32 -1, i32 -1, i32 -1, i32 0> %3 = or <4 x i32> %1, %2 ret <4 x i32> %3 } Before this patch llc (-mcpu=corei7) generated: andps LCPI1_0(%rip), %xmm0, %xmm0 andps LCPI1_1(%rip), %xmm1, %xmm1 orps %xmm1, %xmm0, %xmm0 retq With this patch we generate a single 'vpblendw'. llvm-svn: 221343
2014-11-05 21:04:14 +08:00
%1 = and <4 x i32> %A, <i32 -1, i32 0, i32 -1, i32 0>
%2 = and <4 x i32> %B, <i32 0, i32 -1, i32 0, i32 -1>
%3 = or <4 x i32> %1, %2
ret <4 x i32> %3
}
define <4 x i32> @test17(<4 x i32> %A, <4 x i32> %B) {
[x86] Port this test to use utils/update_llc_test_checks.py. This will make it easy to update as I change some parts of the X86 backend, makes it more clear what instruction differences are introduced, and I find it makes it a bit easier to read as well. llvm-svn: 228095
2015-02-04 08:58:37 +08:00
; CHECK-LABEL: test17:
; CHECK: # BB#0:
; CHECK-NEXT: pblendw {{.*#+}} xmm0 = xmm1[0,1],xmm0[2,3],xmm1[4,5],xmm0[6,7]
; CHECK-NEXT: retq
[X86] Teach method 'isVectorClearMaskLegal' how to check for legal blend masks. This patch improves the folding of vector AND nodes into blend operations for targets that feature SSE4.1. A vector AND node where one of the operands is a constant build_vector with elements that are either zero or all-ones can be converted into a blend. This allows for example to simplify the following code: define <4 x i32> @test(<4 x i32> %A, <4 x i32> %B) { %1 = and <4 x i32> %A, <i32 0, i32 0, i32 0, i32 -1> %2 = and <4 x i32> %B, <i32 -1, i32 -1, i32 -1, i32 0> %3 = or <4 x i32> %1, %2 ret <4 x i32> %3 } Before this patch llc (-mcpu=corei7) generated: andps LCPI1_0(%rip), %xmm0, %xmm0 andps LCPI1_1(%rip), %xmm1, %xmm1 orps %xmm1, %xmm0, %xmm0 retq With this patch we generate a single 'vpblendw'. llvm-svn: 221343
2014-11-05 21:04:14 +08:00
%1 = and <4 x i32> %A, <i32 0, i32 -1, i32 0, i32 -1>
%2 = and <4 x i32> %B, <i32 -1, i32 0, i32 -1, i32 0>
%3 = or <4 x i32> %1, %2
ret <4 x i32> %3
}