RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-23 03:02:36 +01:00
Code Issues Projects Releases Wiki Activity

[x86] update fma test with deprecated intrinsics; NFC

Browse Source 
All of the CHECK lines should be identical to before,
but without any of the x86-specific calls that were
replaced with generic FMA long ago.

The file still has value because it shows a miscompile
as demonstrated in D90901, but we probably need to
add tests with FMF to make that explicit without
losing coverage.
This commit is contained in:
Sanjay Patel 2021-05-17 10:39:33 -04:00
parent a3d5fb0749
commit afbea032ea
1 changed files with 52 additions and 61 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

113
test/CodeGen/X86/avx2-fma-fneg-combine.ll
View File

@ -2,158 +2,149 @@
; RUN: llc < %s -mtriple=i686-unknown-unknown -mattr=+avx2,+fma | FileCheck %s --check-prefix=X32 ; RUN: llc < %s -mtriple=i686-unknown-unknown -mattr=+avx2,+fma | FileCheck %s --check-prefix=X32
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2,+fma | FileCheck %s --check-prefix=X64 ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2,+fma | FileCheck %s --check-prefix=X64
declare <8 x float> @llvm.fma.v8f32(<8 x float>, <8 x float>, <8 x float>)
declare <4 x float> @llvm.fma.v4f32(<4 x float>, <4 x float>, <4 x float>)
declare float @llvm.fma.f32(float, float, float)
declare <2 x double> @llvm.fma.v2f64(<2 x double>, <2 x double>, <2 x double>)
; This test checks combinations of FNEG and FMA intrinsics ; This test checks combinations of FNEG and FMA intrinsics
define <8 x float> @test1(<8 x float> %a, <8 x float> %b, <8 x float> %c) { define <8 x float> @test1(<8 x float> %a, <8 x float> %b, <8 x float> %c) {
; X32-LABEL: test1: ; X32-LABEL: test1:
; X32: # %bb.0: # %entry ; X32: # %bb.0:
; X32-NEXT: vfmsub213ps {{.*#+}} ymm0 = (ymm1 * ymm0) - ymm2 ; X32-NEXT: vfmsub213ps {{.*#+}} ymm0 = (ymm1 * ymm0) - ymm2
; X32-NEXT: retl ; X32-NEXT: retl
; ;
; X64-LABEL: test1: ; X64-LABEL: test1:
; X64: # %bb.0: # %entry ; X64: # %bb.0:
; X64-NEXT: vfmsub213ps {{.*#+}} ymm0 = (ymm1 * ymm0) - ymm2 ; X64-NEXT: vfmsub213ps {{.*#+}} ymm0 = (ymm1 * ymm0) - ymm2
; X64-NEXT: retq ; X64-NEXT: retq
entry: %sub.i = fsub <8 x float> <float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0>, %c
%sub.i = fsub <8 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %c %r = tail call <8 x float> @llvm.fma.v8f32(<8 x float> %a, <8 x float> %b, <8 x float> %sub.i) #2
%0 = tail call <8 x float> @llvm.x86.fma.vfmadd.ps.256(<8 x float> %a, <8 x float> %b, <8 x float> %sub.i) #2 ret <8 x float> %r
ret <8 x float> %0
} }
declare <8 x float> @llvm.x86.fma.vfmadd.ps.256(<8 x float>, <8 x float>, <8 x float>)
define <4 x float> @test2(<4 x float> %a, <4 x float> %b, <4 x float> %c) { define <4 x float> @test2(<4 x float> %a, <4 x float> %b, <4 x float> %c) {
; X32-LABEL: test2: ; X32-LABEL: test2:
; X32: # %bb.0: # %entry ; X32: # %bb.0:
; X32-NEXT: vfnmsub213ps {{.*#+}} xmm0 = -(xmm1 * xmm0) - xmm2 ; X32-NEXT: vfnmsub213ps {{.*#+}} xmm0 = -(xmm1 * xmm0) - xmm2
; X32-NEXT: retl ; X32-NEXT: retl
; ;
; X64-LABEL: test2: ; X64-LABEL: test2:
; X64: # %bb.0: # %entry ; X64: # %bb.0:
; X64-NEXT: vfnmsub213ps {{.*#+}} xmm0 = -(xmm1 * xmm0) - xmm2 ; X64-NEXT: vfnmsub213ps {{.*#+}} xmm0 = -(xmm1 * xmm0) - xmm2
; X64-NEXT: retq ; X64-NEXT: retq
entry: %t0 = tail call <4 x float> @llvm.fma.v4f32(<4 x float> %a, <4 x float> %b, <4 x float> %c) #2
%0 = tail call <4 x float> @llvm.x86.fma.vfmadd.ps(<4 x float> %a, <4 x float> %b, <4 x float> %c) #2 %sub.i = fsub <4 x float> <float -0.0, float -0.0, float -0.0, float -0.0>, %t0
%sub.i = fsub <4 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %0
ret <4 x float> %sub.i ret <4 x float> %sub.i
} }
declare <4 x float> @llvm.x86.fma.vfmadd.ps(<4 x float> %a, <4 x float> %b, <4 x float> %c)
define <4 x float> @test3(<4 x float> %a, <4 x float> %b, <4 x float> %c) { define <4 x float> @test3(<4 x float> %a, <4 x float> %b, <4 x float> %c) {
; X32-LABEL: test3: ; X32-LABEL: test3:
; X32: # %bb.0: # %entry ; X32: # %bb.0:
; X32-NEXT: vfnmadd213ss {{.*#+}} xmm0 = -(xmm1 * xmm0) + xmm2 ; X32-NEXT: vfnmadd213ss {{.*#+}} xmm0 = -(xmm1 * xmm0) + xmm2
; X32-NEXT: vbroadcastss {{.*#+}} xmm1 = [-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0] ; X32-NEXT: vbroadcastss {{.*#+}} xmm1 = [-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0]
; X32-NEXT: vxorps %xmm1, %xmm0, %xmm0 ; X32-NEXT: vxorps %xmm1, %xmm0, %xmm0
; X32-NEXT: retl ; X32-NEXT: retl
; ;
; X64-LABEL: test3: ; X64-LABEL: test3:
; X64: # %bb.0: # %entry ; X64: # %bb.0:
; X64-NEXT: vfnmadd213ss {{.*#+}} xmm0 = -(xmm1 * xmm0) + xmm2 ; X64-NEXT: vfnmadd213ss {{.*#+}} xmm0 = -(xmm1 * xmm0) + xmm2
; X64-NEXT: vbroadcastss {{.*#+}} xmm1 = [-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0] ; X64-NEXT: vbroadcastss {{.*#+}} xmm1 = [-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0]
; X64-NEXT: vxorps %xmm1, %xmm0, %xmm0 ; X64-NEXT: vxorps %xmm1, %xmm0, %xmm0
; X64-NEXT: retq ; X64-NEXT: retq
entry: %a0 = extractelement <4 x float> %a, i64 0
%0 = tail call <4 x float> @llvm.x86.fma.vfnmadd.ss(<4 x float> %a, <4 x float> %b, <4 x float> %c) #2 %b0 = extractelement <4 x float> %b, i64 0
%sub.i = fsub <4 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %0 %c0 = extractelement <4 x float> %c, i64 0
%negb0 = fneg float %b0
%t0 = tail call float @llvm.fma.f32(float %a0, float %negb0, float %c0) #2
%i = insertelement <4 x float> %a, float %t0, i64 0
%sub.i = fsub <4 x float> <float -0.0, float -0.0, float -0.0, float -0.0>, %i
ret <4 x float> %sub.i ret <4 x float> %sub.i
} }
declare <4 x float> @llvm.x86.fma.vfnmadd.ss(<4 x float> %a, <4 x float> %b, <4 x float> %c)
define <8 x float> @test4(<8 x float> %a, <8 x float> %b, <8 x float> %c) { define <8 x float> @test4(<8 x float> %a, <8 x float> %b, <8 x float> %c) {
; X32-LABEL: test4: ; X32-LABEL: test4:
; X32: # %bb.0: # %entry ; X32: # %bb.0:
; X32-NEXT: vfnmadd213ps {{.*#+}} ymm0 = -(ymm1 * ymm0) + ymm2 ; X32-NEXT: vfnmadd213ps {{.*#+}} ymm0 = -(ymm1 * ymm0) + ymm2
; X32-NEXT: retl ; X32-NEXT: retl
; ;
; X64-LABEL: test4: ; X64-LABEL: test4:
; X64: # %bb.0: # %entry ; X64: # %bb.0:
; X64-NEXT: vfnmadd213ps {{.*#+}} ymm0 = -(ymm1 * ymm0) + ymm2 ; X64-NEXT: vfnmadd213ps {{.*#+}} ymm0 = -(ymm1 * ymm0) + ymm2
; X64-NEXT: retq ; X64-NEXT: retq
entry: %negc = fneg <8 x float> %c
%0 = tail call <8 x float> @llvm.x86.fma.vfmsub.ps.256(<8 x float> %a, <8 x float> %b, <8 x float> %c) #2 %t0 = tail call <8 x float> @llvm.fma.v8f32(<8 x float> %a, <8 x float> %b, <8 x float> %negc) #2
%sub.i = fsub <8 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %0 %sub.i = fsub <8 x float> <float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0>, %t0
ret <8 x float> %sub.i ret <8 x float> %sub.i
} }
define <8 x float> @test5(<8 x float> %a, <8 x float> %b, <8 x float> %c) { define <8 x float> @test5(<8 x float> %a, <8 x float> %b, <8 x float> %c) {
; X32-LABEL: test5: ; X32-LABEL: test5:
; X32: # %bb.0: # %entry ; X32: # %bb.0:
; X32-NEXT: vfmadd213ps {{.*#+}} ymm0 = (ymm1 * ymm0) + ymm2 ; X32-NEXT: vfmadd213ps {{.*#+}} ymm0 = (ymm1 * ymm0) + ymm2
; X32-NEXT: retl ; X32-NEXT: retl
; ;
; X64-LABEL: test5: ; X64-LABEL: test5:
; X64: # %bb.0: # %entry ; X64: # %bb.0:
; X64-NEXT: vfmadd213ps {{.*#+}} ymm0 = (ymm1 * ymm0) + ymm2 ; X64-NEXT: vfmadd213ps {{.*#+}} ymm0 = (ymm1 * ymm0) + ymm2
; X64-NEXT: retq ; X64-NEXT: retq
entry: %sub.c = fsub <8 x float> <float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0>, %c
%sub.c = fsub <8 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %c %negsubc = fneg <8 x float> %sub.c
%0 = tail call <8 x float> @llvm.x86.fma.vfmsub.ps.256(<8 x float> %a, <8 x float> %b, <8 x float> %sub.c) #2 %t0 = tail call <8 x float> @llvm.fma.v8f32(<8 x float> %a, <8 x float> %b, <8 x float> %negsubc) #2
ret <8 x float> %0 ret <8 x float> %t0
} }
declare <8 x float> @llvm.x86.fma.vfmsub.ps.256(<8 x float>, <8 x float>, <8 x float>)
define <2 x double> @test6(<2 x double> %a, <2 x double> %b, <2 x double> %c) { define <2 x double> @test6(<2 x double> %a, <2 x double> %b, <2 x double> %c) {
; X32-LABEL: test6: ; X32-LABEL: test6:
; X32: # %bb.0: # %entry ; X32: # %bb.0:
; X32-NEXT: vfnmsub213pd {{.*#+}} xmm0 = -(xmm1 * xmm0) - xmm2 ; X32-NEXT: vfnmsub213pd {{.*#+}} xmm0 = -(xmm1 * xmm0) - xmm2
; X32-NEXT: retl ; X32-NEXT: retl
; ;
; X64-LABEL: test6: ; X64-LABEL: test6:
; X64: # %bb.0: # %entry ; X64: # %bb.0:
; X64-NEXT: vfnmsub213pd {{.*#+}} xmm0 = -(xmm1 * xmm0) - xmm2 ; X64-NEXT: vfnmsub213pd {{.*#+}} xmm0 = -(xmm1 * xmm0) - xmm2
; X64-NEXT: retq ; X64-NEXT: retq
entry: %t0 = tail call <2 x double> @llvm.fma.v2f64(<2 x double> %a, <2 x double> %b, <2 x double> %c) #2
%0 = tail call <2 x double> @llvm.x86.fma.vfmadd.pd(<2 x double> %a, <2 x double> %b, <2 x double> %c) #2 %sub.i = fsub <2 x double> <double -0.0, double -0.0>, %t0
%sub.i = fsub <2 x double> <double -0.000000e+00, double -0.000000e+00>, %0
ret <2 x double> %sub.i ret <2 x double> %sub.i
} }
declare <2 x double> @llvm.x86.fma.vfmadd.pd(<2 x double> %a, <2 x double> %b, <2 x double> %c)
define <8 x float> @test7(float %a, <8 x float> %b, <8 x float> %c) { define <8 x float> @test7(float %a, <8 x float> %b, <8 x float> %c) {
; X32-LABEL: test7: ; X32-LABEL: test7:
; X32: # %bb.0: # %entry ; X32: # %bb.0:
; X32-NEXT: vbroadcastss {{[0-9]+}}(%esp), %ymm2 ; X32-NEXT: vbroadcastss {{[0-9]+}}(%esp), %ymm2
; X32-NEXT: vfnmadd213ps {{.*#+}} ymm0 = -(ymm2 * ymm0) + ymm1 ; X32-NEXT: vfnmadd213ps {{.*#+}} ymm0 = -(ymm2 * ymm0) + ymm1
; X32-NEXT: retl ; X32-NEXT: retl
; ;
; X64-LABEL: test7: ; X64-LABEL: test7:
; X64: # %bb.0: # %entry ; X64: # %bb.0:
; X64-NEXT: vbroadcastss %xmm0, %ymm0 ; X64-NEXT: vbroadcastss %xmm0, %ymm0
; X64-NEXT: vfnmadd213ps {{.*#+}} ymm0 = -(ymm1 * ymm0) + ymm2 ; X64-NEXT: vfnmadd213ps {{.*#+}} ymm0 = -(ymm1 * ymm0) + ymm2
; X64-NEXT: retq ; X64-NEXT: retq
entry: %t0 = insertelement <8 x float> undef, float %a, i32 0
%0 = insertelement <8 x float> undef, float %a, i32 0 %t1 = fsub <8 x float> <float -0.0, float undef, float undef, float undef, float undef, float undef, float undef, float undef>, %t0
%1 = fsub <8 x float> <float -0.000000e+00, float undef, float undef, float undef, float undef, float undef, float undef, float undef>, %0 %t2 = shufflevector <8 x float> %t1, <8 x float> undef, <8 x i32> zeroinitializer
%2 = shufflevector <8 x float> %1, <8 x float> undef, <8 x i32> zeroinitializer %t3 = tail call <8 x float> @llvm.fma.v8f32(<8 x float> %t2, <8 x float> %b, <8 x float> %c)
%3 = tail call <8 x float> @llvm.fma.v8f32(<8 x float> %2, <8 x float> %b, <8 x float> %c) ret <8 x float> %t3
ret <8 x float> %3
} }
define <8 x float> @test8(float %a, <8 x float> %b, <8 x float> %c) { define <8 x float> @test8(float %a, <8 x float> %b, <8 x float> %c) {
; X32-LABEL: test8: ; X32-LABEL: test8:
; X32: # %bb.0: # %entry ; X32: # %bb.0:
; X32-NEXT: vbroadcastss {{[0-9]+}}(%esp), %ymm2 ; X32-NEXT: vbroadcastss {{[0-9]+}}(%esp), %ymm2
; X32-NEXT: vfnmadd213ps {{.*#+}} ymm0 = -(ymm2 * ymm0) + ymm1 ; X32-NEXT: vfnmadd213ps {{.*#+}} ymm0 = -(ymm2 * ymm0) + ymm1
; X32-NEXT: retl ; X32-NEXT: retl
; ;
; X64-LABEL: test8: ; X64-LABEL: test8:
; X64: # %bb.0: # %entry ; X64: # %bb.0:
; X64-NEXT: vbroadcastss %xmm0, %ymm0 ; X64-NEXT: vbroadcastss %xmm0, %ymm0
; X64-NEXT: vfnmadd213ps {{.*#+}} ymm0 = -(ymm1 * ymm0) + ymm2 ; X64-NEXT: vfnmadd213ps {{.*#+}} ymm0 = -(ymm1 * ymm0) + ymm2
; X64-NEXT: retq ; X64-NEXT: retq
entry: %t0 = fsub float -0.0, %a
%0 = fsub float -0.0, %a %t1 = insertelement <8 x float> undef, float %t0, i32 0
%1 = insertelement <8 x float> undef, float %0, i32 0 %t2 = shufflevector <8 x float> %t1, <8 x float> undef, <8 x i32> zeroinitializer
%2 = shufflevector <8 x float> %1, <8 x float> undef, <8 x i32> zeroinitializer %t3 = tail call <8 x float> @llvm.fma.v8f32(<8 x float> %t2, <8 x float> %b, <8 x float> %c)
%3 = tail call <8 x float> @llvm.fma.v8f32(<8 x float> %2, <8 x float> %b, <8 x float> %c) ret <8 x float> %t3
ret <8 x float> %3
} }
declare <8 x float> @llvm.fma.v8f32(<8 x float> %a, <8 x float> %b, <8 x float> %c)