summaryrefslogtreecommitdiffstats
path: root/llvm/test/CodeGen
diff options
context:
space:
mode:
Diffstat (limited to 'llvm/test/CodeGen')
-rw-r--r--llvm/test/CodeGen/Mips/msa/arithmetic_float.ll10
-rw-r--r--llvm/test/CodeGen/X86/fmul-combines.ll99
2 files changed, 103 insertions, 6 deletions
diff --git a/llvm/test/CodeGen/Mips/msa/arithmetic_float.ll b/llvm/test/CodeGen/Mips/msa/arithmetic_float.ll
index 86e57ac85a3..9aae284fe53 100644
--- a/llvm/test/CodeGen/Mips/msa/arithmetic_float.ll
+++ b/llvm/test/CodeGen/Mips/msa/arithmetic_float.ll
@@ -276,8 +276,8 @@ define void @fexp2_v4f32_2(<4 x float>* %c, <4 x float>* %a) nounwind {
; CHECK-DAG: ld.w [[R1:\$w[0-9]+]], 0($5)
%2 = tail call <4 x float> @llvm.exp2.v4f32 (<4 x float> %1)
%3 = fmul <4 x float> <float 2.0, float 2.0, float 2.0, float 2.0>, %2
- ; CHECK-DAG: lui [[R3:\$[0-9]+]], 16384
- ; CHECK-DAG: fill.w [[R4:\$w[0-9]+]], [[R3]]
+ ; CHECK-DAG: ldi.w [[R3:\$w[0-9]+]], 1
+ ; CHECK-DAG: ffint_u.w [[R4:\$w[0-9]+]], [[R3]]
; CHECK-DAG: fexp2.w [[R5:\$w[0-9]+]], [[R4]], [[R1]]
store <4 x float> %3, <4 x float>* %c
; CHECK-DAG: st.w [[R5]], 0($4)
@@ -287,16 +287,14 @@ define void @fexp2_v4f32_2(<4 x float>* %c, <4 x float>* %a) nounwind {
}
define void @fexp2_v2f64_2(<2 x double>* %c, <2 x double>* %a) nounwind {
- ; CHECK: .8byte 4611686018427387904
- ; CHECK-NEXT: .8byte 4611686018427387904
; CHECK: fexp2_v2f64_2:
%1 = load <2 x double>* %a
; CHECK-DAG: ld.d [[R1:\$w[0-9]+]], 0($5)
%2 = tail call <2 x double> @llvm.exp2.v2f64 (<2 x double> %1)
%3 = fmul <2 x double> <double 2.0, double 2.0>, %2
- ; CHECK-DAG: addiu [[G_PTR:\$[0-9]+]], {{.*}}, %lo($
- ; CHECK-DAG: ld.d [[R3:\$w[0-9]+]], 0([[G_PTR]])
+ ; CHECK-DAG: ldi.d [[R2:\$w[0-9]+]], 1
+ ; CHECK-DAG: ffint_u.d [[R3:\$w[0-9]+]], [[R2]]
; CHECK-DAG: fexp2.d [[R4:\$w[0-9]+]], [[R3]], [[R1]]
store <2 x double> %3, <2 x double>* %c
; CHECK-DAG: st.d [[R4]], 0($4)
diff --git a/llvm/test/CodeGen/X86/fmul-combines.ll b/llvm/test/CodeGen/X86/fmul-combines.ll
new file mode 100644
index 00000000000..22632d3dd3e
--- /dev/null
+++ b/llvm/test/CodeGen/X86/fmul-combines.ll
@@ -0,0 +1,99 @@
+; RUN: llc -march=x86-64 < %s | FileCheck %s
+
+; CHECK-LABEL: fmul2_f32:
+; CHECK: addss %xmm0, %xmm0
+define float @fmul2_f32(float %x) {
+ %y = fmul float %x, 2.0
+ ret float %y
+}
+
+; fmul 2.0, x -> fadd x, x for vectors.
+
+; CHECK-LABEL: fmul2_v4f32:
+; CHECK: addps %xmm0, %xmm0
+; CHECK-NEXT: retq
+define <4 x float> @fmul2_v4f32(<4 x float> %x) {
+ %y = fmul <4 x float> %x, <float 2.0, float 2.0, float 2.0, float 2.0>
+ ret <4 x float> %y
+}
+
+; CHECK-LABEL: constant_fold_fmul_v4f32:
+; CHECK: movaps
+; CHECK-NEXT: ret
+define <4 x float> @constant_fold_fmul_v4f32(<4 x float> %x) {
+ %y = fmul <4 x float> <float 4.0, float 4.0, float 4.0, float 4.0>, <float 2.0, float 2.0, float 2.0, float 2.0>
+ ret <4 x float> %y
+}
+
+; CHECK-LABEL: fmul0_v4f32:
+; CHECK: xorps %xmm0, %xmm0
+; CHECK-NEXT: retq
+define <4 x float> @fmul0_v4f32(<4 x float> %x) #0 {
+ %y = fmul <4 x float> %x, <float 0.0, float 0.0, float 0.0, float 0.0>
+ ret <4 x float> %y
+}
+
+; CHECK-LABEL: fmul_c2_c4_v4f32:
+; CHECK-NOT: addps
+; CHECK: mulps
+; CHECK-NOT: mulps
+; CHECK-NEXT: ret
+define <4 x float> @fmul_c2_c4_v4f32(<4 x float> %x) #0 {
+ %y = fmul <4 x float> %x, <float 2.0, float 2.0, float 2.0, float 2.0>
+ %z = fmul <4 x float> %y, <float 4.0, float 4.0, float 4.0, float 4.0>
+ ret <4 x float> %z
+}
+
+; CHECK-LABEL: fmul_c3_c4_v4f32:
+; CHECK-NOT: addps
+; CHECK: mulps
+; CHECK-NOT: mulps
+; CHECK-NEXT: ret
+define <4 x float> @fmul_c3_c4_v4f32(<4 x float> %x) #0 {
+ %y = fmul <4 x float> %x, <float 3.0, float 3.0, float 3.0, float 3.0>
+ %z = fmul <4 x float> %y, <float 4.0, float 4.0, float 4.0, float 4.0>
+ ret <4 x float> %z
+}
+
+; CHECK-LABEL: fmul_c2_c4_f32:
+; CHECK-NOT: addss
+; CHECK: mulss
+; CHECK-NOT: mulss
+; CHECK-NEXT: ret
+define float @fmul_c2_c4_f32(float %x) #0 {
+ %y = fmul float %x, 2.0
+ %z = fmul float %y, 4.0
+ ret float %z
+}
+
+; CHECK-LABEL: fmul_c3_c4_f32:
+; CHECK-NOT: addss
+; CHECK: mulss
+; CHECK-NOT: mulss
+; CHECK-NET: ret
+define float @fmul_c3_c4_f32(float %x) #0 {
+ %y = fmul float %x, 3.0
+ %z = fmul float %y, 4.0
+ ret float %z
+}
+
+; CHECK-LABEL: fmul_fneg_fneg_f32:
+; CHECK: mulss %xmm1, %xmm0
+; CHECK-NEXT: retq
+define float @fmul_fneg_fneg_f32(float %x, float %y) {
+ %x.neg = fsub float -0.0, %x
+ %y.neg = fsub float -0.0, %y
+ %mul = fmul float %x.neg, %y.neg
+ ret float %mul
+}
+; CHECK-LABEL: fmul_fneg_fneg_v4f32:
+; CHECK: mulps %xmm1, %xmm0
+; CHECK-NEXT: retq
+define <4 x float> @fmul_fneg_fneg_v4f32(<4 x float> %x, <4 x float> %y) {
+ %x.neg = fsub <4 x float> <float -0.0, float -0.0, float -0.0, float -0.0>, %x
+ %y.neg = fsub <4 x float> <float -0.0, float -0.0, float -0.0, float -0.0>, %y
+ %mul = fmul <4 x float> %x.neg, %y.neg
+ ret <4 x float> %mul
+}
+
+attributes #0 = { "less-precise-fpmad"="true" "no-infs-fp-math"="true" "no-nans-fp-math"="true" "unsafe-fp-math"="true" }
OpenPOWER on IntegriCloud