llvm-for-llvmta/test/CodeGen/X86/avx2-fma-fneg-combine.ll

160 lines
6.4 KiB
LLVM

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; 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
; 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) {
; X32-LABEL: test1:
; X32: # %bb.0: # %entry
; X32-NEXT: vfmsub213ps {{.*#+}} ymm0 = (ymm1 * ymm0) - ymm2
; X32-NEXT: retl
;
; X64-LABEL: test1:
; X64: # %bb.0: # %entry
; X64-NEXT: vfmsub213ps {{.*#+}} ymm0 = (ymm1 * ymm0) - ymm2
; X64-NEXT: retq
entry:
%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
%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> %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) {
; X32-LABEL: test2:
; X32: # %bb.0: # %entry
; X32-NEXT: vfnmsub213ps {{.*#+}} xmm0 = -(xmm1 * xmm0) - xmm2
; X32-NEXT: retl
;
; X64-LABEL: test2:
; X64: # %bb.0: # %entry
; X64-NEXT: vfnmsub213ps {{.*#+}} xmm0 = -(xmm1 * xmm0) - xmm2
; X64-NEXT: retq
entry:
%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 -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %0
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) {
; X32-LABEL: test3:
; X32: # %bb.0: # %entry
; 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: vxorps %xmm1, %xmm0, %xmm0
; X32-NEXT: retl
;
; X64-LABEL: test3:
; X64: # %bb.0: # %entry
; 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: vxorps %xmm1, %xmm0, %xmm0
; X64-NEXT: retq
entry:
%0 = tail call <4 x float> @llvm.x86.fma.vfnmadd.ss(<4 x float> %a, <4 x float> %b, <4 x float> %c) #2
%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
}
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) {
; X32-LABEL: test4:
; X32: # %bb.0: # %entry
; X32-NEXT: vfnmadd213ps {{.*#+}} ymm0 = -(ymm1 * ymm0) + ymm2
; X32-NEXT: retl
;
; X64-LABEL: test4:
; X64: # %bb.0: # %entry
; X64-NEXT: vfnmadd213ps {{.*#+}} ymm0 = -(ymm1 * ymm0) + ymm2
; X64-NEXT: retq
entry:
%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
%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
ret <8 x float> %sub.i
}
define <8 x float> @test5(<8 x float> %a, <8 x float> %b, <8 x float> %c) {
; X32-LABEL: test5:
; X32: # %bb.0: # %entry
; X32-NEXT: vfmadd213ps {{.*#+}} ymm0 = (ymm1 * ymm0) + ymm2
; X32-NEXT: retl
;
; X64-LABEL: test5:
; X64: # %bb.0: # %entry
; X64-NEXT: vfmadd213ps {{.*#+}} ymm0 = (ymm1 * ymm0) + ymm2
; X64-NEXT: retq
entry:
%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
%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
ret <8 x float> %0
}
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) {
; X32-LABEL: test6:
; X32: # %bb.0: # %entry
; X32-NEXT: vfnmsub213pd {{.*#+}} xmm0 = -(xmm1 * xmm0) - xmm2
; X32-NEXT: retl
;
; X64-LABEL: test6:
; X64: # %bb.0: # %entry
; X64-NEXT: vfnmsub213pd {{.*#+}} xmm0 = -(xmm1 * xmm0) - xmm2
; X64-NEXT: retq
entry:
%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 -0.000000e+00, double -0.000000e+00>, %0
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) {
; X32-LABEL: test7:
; X32: # %bb.0: # %entry
; X32-NEXT: vbroadcastss {{[0-9]+}}(%esp), %ymm2
; X32-NEXT: vfnmadd213ps {{.*#+}} ymm0 = -(ymm2 * ymm0) + ymm1
; X32-NEXT: retl
;
; X64-LABEL: test7:
; X64: # %bb.0: # %entry
; X64-NEXT: vbroadcastss %xmm0, %ymm0
; X64-NEXT: vfnmadd213ps {{.*#+}} ymm0 = -(ymm1 * ymm0) + ymm2
; X64-NEXT: retq
entry:
%0 = insertelement <8 x float> undef, float %a, i32 0
%1 = fsub <8 x float> <float -0.000000e+00, float undef, float undef, float undef, float undef, float undef, float undef, float undef>, %0
%2 = shufflevector <8 x float> %1, <8 x float> undef, <8 x i32> zeroinitializer
%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> %3
}
define <8 x float> @test8(float %a, <8 x float> %b, <8 x float> %c) {
; X32-LABEL: test8:
; X32: # %bb.0: # %entry
; X32-NEXT: vbroadcastss {{[0-9]+}}(%esp), %ymm2
; X32-NEXT: vfnmadd213ps {{.*#+}} ymm0 = -(ymm2 * ymm0) + ymm1
; X32-NEXT: retl
;
; X64-LABEL: test8:
; X64: # %bb.0: # %entry
; X64-NEXT: vbroadcastss %xmm0, %ymm0
; X64-NEXT: vfnmadd213ps {{.*#+}} ymm0 = -(ymm1 * ymm0) + ymm2
; X64-NEXT: retq
entry:
%0 = fsub float -0.0, %a
%1 = insertelement <8 x float> undef, float %0, i32 0
%2 = shufflevector <8 x float> %1, <8 x float> undef, <8 x i32> zeroinitializer
%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> %3
}
declare <8 x float> @llvm.fma.v8f32(<8 x float> %a, <8 x float> %b, <8 x float> %c)