maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[X86][SSE] Add UMIN/UMAX combine test 

As discussed on D43014, we need the ability to flip UMIN/UMAX to (legal) SMIN/SMAX

llvm-svn: 324826
This commit is contained in:
Simon Pilgrim 2018-02-10 22:27:35 +00:00
parent 19495198af
commit b781b2e24c
2 changed files with 95 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

47
llvm/test/CodeGen/X86/combine-umax.ll Normal file
View File

@ -0,0 +1,47 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse2 | FileCheck %s --check-prefix=ALL --check-prefix=SSE --check-prefix=SSE2
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse4.1 | FileCheck %s --check-prefix=ALL --check-prefix=SSE --check-prefix=SSE41
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse4.2 | FileCheck %s --check-prefix=ALL --check-prefix=SSE --check-prefix=SSE42
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx | FileCheck %s --check-prefix=ALL --check-prefix=AVX --check-prefix=AVX1
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2 | FileCheck %s --check-prefix=ALL --check-prefix=AVX --check-prefix=AVX2
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512f | FileCheck %s --check-prefix=ALL --check-prefix=AVX --check-prefix=AVX512 --check-prefix=AVX512F
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512bw | FileCheck %s --check-prefix=ALL --check-prefix=AVX --check-prefix=AVX512 --check-prefix=AVX512BW
define <8 x i16> @test_v8i16_nosignbit(<8 x i16> %a, <8 x i16> %b) {
; SSE2-LABEL: test_v8i16_nosignbit:
; SSE2: # %bb.0:
; SSE2-NEXT: pand {{.*}}(%rip), %xmm0
; SSE2-NEXT: psrlw $1, %xmm1
; SSE2-NEXT: movdqa %xmm1, %xmm2
; SSE2-NEXT: pcmpgtw %xmm0, %xmm2
; SSE2-NEXT: pand %xmm2, %xmm0
; SSE2-NEXT: pandn %xmm1, %xmm2
; SSE2-NEXT: por %xmm2, %xmm0
; SSE2-NEXT: retq
;
; SSE41-LABEL: test_v8i16_nosignbit:
; SSE41: # %bb.0:
; SSE41-NEXT: pand {{.*}}(%rip), %xmm0
; SSE41-NEXT: psrlw $1, %xmm1
; SSE41-NEXT: pminuw %xmm1, %xmm0
; SSE41-NEXT: retq
;
; SSE42-LABEL: test_v8i16_nosignbit:
; SSE42: # %bb.0:
; SSE42-NEXT: pand {{.*}}(%rip), %xmm0
; SSE42-NEXT: psrlw $1, %xmm1
; SSE42-NEXT: pminuw %xmm1, %xmm0
; SSE42-NEXT: retq
;
; AVX-LABEL: test_v8i16_nosignbit:
; AVX: # %bb.0:
; AVX-NEXT: vpand {{.*}}(%rip), %xmm0, %xmm0
; AVX-NEXT: vpsrlw $1, %xmm1, %xmm1
; AVX-NEXT: vpminuw %xmm1, %xmm0, %xmm0
; AVX-NEXT: retq
%1 = and <8 x i16> %a, <i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255>
%2 = lshr <8 x i16> %b, <i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1>
%3 = icmp ult <8 x i16> %1, %2
%4 = select <8 x i1> %3, <8 x i16> %1, <8 x i16> %2
ret <8 x i16> %4
}

48
llvm/test/CodeGen/X86/combine-umin.ll Normal file
View File

@ -0,0 +1,48 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse2 | FileCheck %s --check-prefix=ALL --check-prefix=SSE --check-prefix=SSE2
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse4.1 | FileCheck %s --check-prefix=ALL --check-prefix=SSE --check-prefix=SSE41
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse4.2 | FileCheck %s --check-prefix=ALL --check-prefix=SSE --check-prefix=SSE42
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx | FileCheck %s --check-prefix=ALL --check-prefix=AVX --check-prefix=AVX1
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2 | FileCheck %s --check-prefix=ALL --check-prefix=AVX --check-prefix=AVX2
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512f | FileCheck %s --check-prefix=ALL --check-prefix=AVX --check-prefix=AVX512 --check-prefix=AVX512F
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx512bw | FileCheck %s --check-prefix=ALL --check-prefix=AVX --check-prefix=AVX512 --check-prefix=AVX512BW
define <8 x i16> @test_v8i16_nosignbit(<8 x i16> %a, <8 x i16> %b) {
; SSE2-LABEL: test_v8i16_nosignbit:
; SSE2: # %bb.0:
; SSE2-NEXT: pand {{.*}}(%rip), %xmm0
; SSE2-NEXT: psrlw $1, %xmm1
; SSE2-NEXT: movdqa %xmm0, %xmm2
; SSE2-NEXT: pcmpgtw %xmm1, %xmm2
; SSE2-NEXT: pand %xmm2, %xmm0
; SSE2-NEXT: pandn %xmm1, %xmm2
; SSE2-NEXT: por %xmm0, %xmm2
; SSE2-NEXT: movdqa %xmm2, %xmm0
; SSE2-NEXT: retq
;
; SSE41-LABEL: test_v8i16_nosignbit:
; SSE41: # %bb.0:
; SSE41-NEXT: pand {{.*}}(%rip), %xmm0
; SSE41-NEXT: psrlw $1, %xmm1
; SSE41-NEXT: pmaxuw %xmm1, %xmm0
; SSE41-NEXT: retq
;
; SSE42-LABEL: test_v8i16_nosignbit:
; SSE42: # %bb.0:
; SSE42-NEXT: pand {{.*}}(%rip), %xmm0
; SSE42-NEXT: psrlw $1, %xmm1
; SSE42-NEXT: pmaxuw %xmm1, %xmm0
; SSE42-NEXT: retq
;
; AVX-LABEL: test_v8i16_nosignbit:
; AVX: # %bb.0:
; AVX-NEXT: vpand {{.*}}(%rip), %xmm0, %xmm0
; AVX-NEXT: vpsrlw $1, %xmm1, %xmm1
; AVX-NEXT: vpmaxuw %xmm1, %xmm0, %xmm0
; AVX-NEXT: retq
%1 = and <8 x i16> %a, <i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255, i16 255>
%2 = lshr <8 x i16> %b, <i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1, i16 1>
%3 = icmp ugt <8 x i16> %1, %2
%4 = select <8 x i1> %3, <8 x i16> %1, <8 x i16> %2
ret <8 x i16> %4
}