OSchip
/
llvm-project
mirror of https://github.com/THU-DSP-LAB/llvm-project.git
13
0
Fork 6
Code Issues Packages Projects Releases Wiki Activity

Tighten checks so we can see existing codegen 

The 2-element vector case shows a surprising bug: we failed to
eliminate ops on undefs, so there are 4 fmax calls even though
there can only be 2 valid elements in the inputs.

llvm-svn: 254920
This commit is contained in:
Sanjay Patel 2015-12-07 17:39:48 +00:00
parent dc7b6c3623
commit fe2e9121e2
1 changed files with 106 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

114
llvm/test/CodeGen/X86/fmaxnum.ll
View File

@ -1,5 +1,5 @@
; RUN: llc -mtriple=x86_64-unknown-unknown -mattr=sse2 < %s | FileCheck %s ; RUN: llc -mtriple=x86_64-unknown-unknown -mattr=sse2 < %s | FileCheck %s --check-prefix=CHECK --check-prefix=SSE
; RUN: llc -mtriple=x86_64-unknown-unknown -mattr=avx < %s | FileCheck %s ; RUN: llc -mtriple=x86_64-unknown-unknown -mattr=avx < %s | FileCheck %s --check-prefix=CHECK --check-prefix=AVX
declare float @fmaxf(float, float) declare float @fmaxf(float, float)
declare double @fmax(double, double) declare double @fmax(double, double)
@ -58,18 +58,116 @@ define x86_fp80 @test_intrinsic_fmaxl(x86_fp80 %x, x86_fp80 %y) {
} }
; CHECK-LABEL: @test_intrinsic_fmax_v2f32 ; CHECK-LABEL: @test_intrinsic_fmax_v2f32
; CHECK: callq fmaxf ; SSE: movaps %xmm1, {{[0-9]+}}(%rsp) # 16-byte Spill
; CHECK: callq fmaxf ; SSE-NEXT: movaps %xmm0, {{[0-9]+}}(%rsp) # 16-byte Spill
; SSE-NEXT: shufps {{.*#+}} xmm0 = xmm0[3,1,2,3]
; SSE-NEXT: shufps {{.*#+}} xmm1 = xmm1[3,1,2,3]
; SSE-NEXT: callq fmaxf
; SSE-NEXT: movaps %xmm0, {{[0-9]+}}(%rsp) # 16-byte Spill
; SSE-NEXT: movaps {{[0-9]+}}(%rsp), %xmm0 # 16-byte Reload
; SSE-NEXT: shufps {{.*#+}} xmm0 = xmm0[1,1,2,3]
; SSE-NEXT: movaps {{[0-9]+}}(%rsp), %xmm1 # 16-byte Reload
; SSE-NEXT: shufps {{.*#+}} xmm1 = xmm1[1,1,2,3]
; SSE-NEXT: callq fmaxf
; SSE-NEXT: unpcklps {{[0-9]+}}(%rsp), %xmm0 # 16-byte Folded Reload
; SSE: movaps %xmm0, {{[0-9]+}}(%rsp) # 16-byte Spill
; SSE-NEXT: movaps {{[0-9]+}}(%rsp), %xmm0 # 16-byte Reload
; SSE-NEXT: movaps {{[0-9]+}}(%rsp), %xmm1 # 16-byte Reload
; SSE-NEXT: callq fmaxf
; SSE-NEXT: movaps %xmm0, (%rsp) # 16-byte Spill
; SSE-NEXT: movapd {{[0-9]+}}(%rsp), %xmm0 # 16-byte Reload
; SSE-NEXT: shufpd {{.*#+}} xmm0 = xmm0[1,0]
; SSE-NEXT: movapd {{[0-9]+}}(%rsp), %xmm1 # 16-byte Reload
; SSE-NEXT: shufpd {{.*#+}} xmm1 = xmm1[1,0]
; SSE-NEXT: callq fmaxf
; SSE-NEXT: movaps (%rsp), %xmm1 # 16-byte Reload
; SSE-NEXT: unpcklps {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1]
; SSE-NEXT: unpcklps {{[0-9]+}}(%rsp), %xmm1 # 16-byte Folded Reload
; SSE: movaps %xmm1, %xmm0
; SSE-NEXT: addq $72, %rsp
; SSE-NEXT: retq
;
; AVX: vmovaps %xmm1, {{[0-9]+}}(%rsp) # 16-byte Spill
; AVX-NEXT: vmovaps %xmm0, {{[0-9]+}}(%rsp) # 16-byte Spill
; AVX-NEXT: callq fmaxf
; AVX-NEXT: vmovaps %xmm0, (%rsp) # 16-byte Spill
; AVX-NEXT: vmovshdup {{[0-9]+}}(%rsp), %xmm0 # 16-byte Folded Reload
; AVX: vmovshdup {{[0-9]+}}(%rsp), %xmm1 # 16-byte Folded Reload
; AVX: callq fmaxf
; AVX-NEXT: vmovaps (%rsp), %xmm1 # 16-byte Reload
; AVX-NEXT: vinsertps {{.*#+}} xmm0 = xmm1[0],xmm0[0],xmm1[2,3]
; AVX-NEXT: vmovaps %xmm0, (%rsp) # 16-byte Spill
; AVX-NEXT: vpermilpd $1, {{[0-9]+}}(%rsp), %xmm0 # 16-byte Folded Reload
; AVX: vpermilpd $1, {{[0-9]+}}(%rsp), %xmm1 # 16-byte Folded Reload
; AVX: callq fmaxf
; AVX-NEXT: vmovaps (%rsp), %xmm1 # 16-byte Reload
; AVX-NEXT: vinsertps {{.*#+}} xmm0 = xmm1[0,1],xmm0[0],xmm1[3]
; AVX-NEXT: vmovaps %xmm0, (%rsp) # 16-byte Spill
; AVX-NEXT: vpermilps $231, {{[0-9]+}}(%rsp), %xmm0 # 16-byte Folded Reload
; AVX: vpermilps $231, {{[0-9]+}}(%rsp), %xmm1 # 16-byte Folded Reload
; AVX: callq fmaxf
; AVX-NEXT: vmovaps (%rsp), %xmm1 # 16-byte Reload
; AVX-NEXT: vinsertps {{.*#+}} xmm0 = xmm1[0,1,2],xmm0[0]
; AVX-NEXT: addq $56, %rsp
; AVX-NEXT: retq
define <2 x float> @test_intrinsic_fmax_v2f32(<2 x float> %x, <2 x float> %y) { define <2 x float> @test_intrinsic_fmax_v2f32(<2 x float> %x, <2 x float> %y) {
%z = call <2 x float> @llvm.maxnum.v2f32(<2 x float> %x, <2 x float> %y) readnone %z = call <2 x float> @llvm.maxnum.v2f32(<2 x float> %x, <2 x float> %y) readnone
ret <2 x float> %z ret <2 x float> %z
} }
; CHECK-LABEL: @test_intrinsic_fmax_v4f32 ; CHECK-LABEL: @test_intrinsic_fmax_v4f32
; CHECK: callq fmaxf ; SSE: movaps %xmm1, {{[0-9]+}}(%rsp) # 16-byte Spill
; CHECK: callq fmaxf ; SSE-NEXT: movaps %xmm0, {{[0-9]+}}(%rsp) # 16-byte Spill
; CHECK: callq fmaxf ; SSE-NEXT: shufps {{.*#+}} xmm0 = xmm0[3,1,2,3]
; CHECK: callq fmaxf ; SSE-NEXT: shufps {{.*#+}} xmm1 = xmm1[3,1,2,3]
; SSE-NEXT: callq fmaxf
; SSE-NEXT: movaps %xmm0, {{[0-9]+}}(%rsp) # 16-byte Spill
; SSE-NEXT: movaps {{[0-9]+}}(%rsp), %xmm0 # 16-byte Reload
; SSE-NEXT: shufps {{.*#+}} xmm0 = xmm0[1,1,2,3]
; SSE-NEXT: movaps {{[0-9]+}}(%rsp), %xmm1 # 16-byte Reload
; SSE-NEXT: shufps {{.*#+}} xmm1 = xmm1[1,1,2,3]
; SSE-NEXT: callq fmaxf
; SSE-NEXT: unpcklps {{[0-9]+}}(%rsp), %xmm0 # 16-byte Folded Reload
; SSE: movaps %xmm0, {{[0-9]+}}(%rsp) # 16-byte Spill
; SSE-NEXT: movaps {{[0-9]+}}(%rsp), %xmm0 # 16-byte Reload
; SSE-NEXT: movaps {{[0-9]+}}(%rsp), %xmm1 # 16-byte Reload
; SSE-NEXT: callq fmaxf
; SSE-NEXT: movaps %xmm0, (%rsp) # 16-byte Spill
; SSE-NEXT: movapd {{[0-9]+}}(%rsp), %xmm0 # 16-byte Reload
; SSE-NEXT: shufpd {{.*#+}} xmm0 = xmm0[1,0]
; SSE-NEXT: movapd {{[0-9]+}}(%rsp), %xmm1 # 16-byte Reload
; SSE-NEXT: shufpd {{.*#+}} xmm1 = xmm1[1,0]
; SSE-NEXT: callq fmaxf
; SSE-NEXT: movaps (%rsp), %xmm1 # 16-byte Reload
; SSE-NEXT: unpcklps {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1]
; SSE-NEXT: unpcklps {{[0-9]+}}(%rsp), %xmm1 # 16-byte Folded Reload
; SSE: movaps %xmm1, %xmm0
; SSE-NEXT: addq $72, %rsp
; SSE-NEXT: retq
;
; AVX: vmovaps %xmm1, {{[0-9]+}}(%rsp) # 16-byte Spill
; AVX-NEXT: vmovaps %xmm0, {{[0-9]+}}(%rsp) # 16-byte Spill
; AVX-NEXT: callq fmaxf
; AVX-NEXT: vmovaps %xmm0, (%rsp) # 16-byte Spill
; AVX-NEXT: vmovshdup {{[0-9]+}}(%rsp), %xmm0 # 16-byte Folded Reload
; AVX: vmovshdup {{[0-9]+}}(%rsp), %xmm1 # 16-byte Folded Reload
; AVX: callq fmaxf
; AVX-NEXT: vmovaps (%rsp), %xmm1 # 16-byte Reload
; AVX-NEXT: vinsertps {{.*#+}} xmm0 = xmm1[0],xmm0[0],xmm1[2,3]
; AVX-NEXT: vmovaps %xmm0, (%rsp) # 16-byte Spill
; AVX-NEXT: vpermilpd $1, {{[0-9]+}}(%rsp), %xmm0 # 16-byte Folded Reload
; AVX: vpermilpd $1, {{[0-9]+}}(%rsp), %xmm1 # 16-byte Folded Reload
; AVX: callq fmaxf
; AVX-NEXT: vmovaps (%rsp), %xmm1 # 16-byte Reload
; AVX-NEXT: vinsertps {{.*#+}} xmm0 = xmm1[0,1],xmm0[0],xmm1[3]
; AVX-NEXT: vmovaps %xmm0, (%rsp) # 16-byte Spill
; AVX-NEXT: vpermilps $231, {{[0-9]+}}(%rsp), %xmm0 # 16-byte Folded Reload
; AVX: vpermilps $231, {{[0-9]+}}(%rsp), %xmm1 # 16-byte Folded Reload
; AVX: callq fmaxf
; AVX-NEXT: vmovaps (%rsp), %xmm1 # 16-byte Reload
; AVX-NEXT: vinsertps {{.*#+}} xmm0 = xmm1[0,1,2],xmm0[0]
; AVX-NEXT: addq $56, %rsp
; AVX-NEXT: retq
define <4 x float> @test_intrinsic_fmax_v4f32(<4 x float> %x, <4 x float> %y) { define <4 x float> @test_intrinsic_fmax_v4f32(<4 x float> %x, <4 x float> %y) {
%z = call <4 x float> @llvm.maxnum.v4f32(<4 x float> %x, <4 x float> %y) readnone %z = call <4 x float> @llvm.maxnum.v4f32(<4 x float> %x, <4 x float> %y) readnone
ret <4 x float> %z ret <4 x float> %z