CodeGen peephole: fold redundant phys reg copies

[oota-llvm.git] / test / CodeGen / X86 / avx512-round.ll

diff --git a/test/CodeGen/X86/avx512-round.ll b/test/CodeGen/X86/avx512-round.ll
index 19d9f18b80a0b7c89e97db86910688ecdeb44615..c4f417e75ab0975f0d0ef43ce1468876488873f7 100644 (file)
--- a/test/CodeGen/X86/avx512-round.ll
+++ b/test/CodeGen/X86/avx512-round.ll
@@ -79,3 +79,28 @@ define <8 x double> @nearbyint_v8f64(<8 x double> %a) {
   ret <8 x double> %res
 }
 declare <8 x double> @llvm.nearbyint.v8f64(<8 x double> %p)
+
+define double @nearbyint_f64(double %a) {
+; CHECK-LABEL: nearbyint_f64
+; CHECK: vrndscalesd $12, {{.*}}encoding: [0x62,0xf3,0xfd,0x08,0x0b,0xc0,0x0c]
+  %res = call double @llvm.nearbyint.f64(double %a)
+  ret double %res
+}
+declare double @llvm.nearbyint.f64(double %p)
+
+define float @floor_f32(float %a) {
+; CHECK-LABEL: floor_f32
+; CHECK: vrndscaless $1, {{.*}}encoding: [0x62,0xf3,0x7d,0x08,0x0a,0xc0,0x01]
+  %res = call float @llvm.floor.f32(float %a)
+  ret float %res
+}
+declare float @llvm.floor.f32(float %p)
+
+define float @floor_f32m(float* %aptr) {
+; CHECK-LABEL: floor_f32m
+; CHECK: vrndscaless $1, (%rdi), {{.*}}encoding: [0x62,0xf3,0x7d,0x08,0x0a,0x07,0x01]
+  %a = load float, float* %aptr, align 4
+  %res = call float @llvm.floor.f32(float %a)
+  ret float %res
+}
+