2 files changed, 237 insertions, 0 deletions
diff --git a/llvm/test/CodeGen/AArch64/recp-fastmath.ll b/llvm/test/CodeGen/AArch64/recp-fastmath.ll
new file mode 100644
index 00000000000..710739b2cc5
--- /dev/null
+++ b/llvm/test/CodeGen/AArch64/recp-fastmath.ll
@@ -0,0 +1,79 @@
+; RUN: llc < %s -mtriple=aarch64 -mattr=neon -recip=!div,!vec-div | FileCheck %s --check-prefix=FAULT
+; RUN: llc < %s -mtriple=aarch64 -mattr=neon -recip=div,vec-div   | FileCheck %s
+
+define float @frecp(float %x) #0 {
+  %div = fdiv fast float 1.0, %x
+  ret float %div
+
+; FAULT-LABEL: frecp:
+; FAULT-NEXT: BB#0
+; FAULT-NEXT: fmov
+; FAULT-NEXT: fdiv
+
+; CHECK-LABEL: frecp:
+; CHECK-NEXT: BB#0
+; CHECK-NEXT: frecpe
+; CHECK-NEXT: fmov
+}
+
+define <2 x float> @f2recp(<2 x float> %x) #0 {
+  %div = fdiv fast <2 x float> <float 1.0, float 1.0>, %x
+  ret <2 x float> %div
+
+; FAULT-LABEL: f2recp:
+; FAULT-NEXT: BB#0
+; FAULT-NEXT: fmov
+; FAULT-NEXT: fdiv
+
+; CHECK-LABEL: f2recp:
+; CHECK-NEXT: BB#0
+; CHECK-NEXT: fmov
+; CHECK-NEXT: frecpe
+}
+
+define <4 x float> @f4recp(<4 x float> %x) #0 {
+  %div = fdiv fast <4 x float> <float 1.0, float 1.0, float 1.0, float 1.0>, %x
+  ret <4 x float> %div
+
+; FAULT-LABEL: f4recp:
+; FAULT-NEXT: BB#0
+; FAULT-NEXT: fmov
+; FAULT-NEXT: fdiv
+
+; CHECK-LABEL: f4recp:
+; CHECK-NEXT: BB#0
+; CHECK-NEXT: fmov
+; CHECK-NEXT: frecpe
+}
+
+define double @drecp(double %x) #0 {
+  %div = fdiv fast double 1.0, %x
+  ret double %div
+
+; FAULT-LABEL: drecp:
+; FAULT-NEXT: BB#0
+; FAULT-NEXT: fmov
+; FAULT-NEXT: fdiv
+
+; CHECK-LABEL: drecp:
+; CHECK-NEXT: BB#0
+; CHECK-NEXT: frecpe
+; CHECK-NEXT: fmov
+}
+
+define <2 x double> @d2recp(<2 x double> %x) #0 {
+  %div = fdiv fast <2 x double> <double 1.0, double 1.0>, %x
+  ret <2 x double> %div
+
+; FAULT-LABEL: d2recp:
+; FAULT-NEXT: BB#0
+; FAULT-NEXT: fmov
+; FAULT-NEXT: fdiv
+
+; CHECK-LABEL: d2recp:
+; CHECK-NEXT: BB#0
+; CHECK-NEXT: fmov
+; CHECK-NEXT: frecpe
+}
+
+attributes #0 = { nounwind "unsafe-fp-math"="true" }
diff --git a/llvm/test/CodeGen/AArch64/sqrt-fastmath.ll b/llvm/test/CodeGen/AArch64/sqrt-fastmath.ll
new file mode 100644
index 00000000000..8bc85a5628c
--- /dev/null
+++ b/llvm/test/CodeGen/AArch64/sqrt-fastmath.ll
@@ -0,0 +1,158 @@
+; RUN: llc < %s -mtriple=aarch64 -mattr=neon -recip=!sqrt,!vec-sqrt | FileCheck %s --check-prefix=FAULT
+; RUN: llc < %s -mtriple=aarch64 -mattr=neon -recip=sqrt,vec-sqrt   | FileCheck %s
+
+declare float @llvm.sqrt.f32(float) #1
+declare double @llvm.sqrt.f64(double) #1
+declare <2 x float> @llvm.sqrt.v2f32(<2 x float>) #1
+declare <4 x float> @llvm.sqrt.v4f32(<4 x float>) #1
+declare <2 x double> @llvm.sqrt.v2f64(<2 x double>) #1
+
+define float @fsqrt(float %a) #0 {
+  %1 = tail call fast float @llvm.sqrt.f32(float %a)
+  ret float %1
+
+; FAULT-LABEL: fsqrt:
+; FAULT-NEXT: BB#0
+; FAULT-NEXT: fsqrt
+
+; CHECK-LABEL: fsqrt:
+; CHECK-NEXT: BB#0
+; CHECK-NEXT: fmov
+; CHECK-NEXT: frsqrte
+}
+
+define <2 x float> @f2sqrt(<2 x float> %a) #0 {
+  %1 = tail call fast <2 x float> @llvm.sqrt.v2f32(<2 x float> %a) #2
+  ret <2 x float> %1
+
+; FAULT-LABEL: f2sqrt:
+; FAULT-NEXT: BB#0
+; FAULT-NEXT: fsqrt
+
+; CHECK-LABEL: f2sqrt:
+; CHECK-NEXT: BB#0
+; CHECK-NEXT: fmov
+; CHECK-NEXT: mov
+; CHECK-NEXT: frsqrte
+}
+
+define <4 x float> @f4sqrt(<4 x float> %a) #0 {
+  %1 = tail call fast <4 x float> @llvm.sqrt.v4f32(<4 x float> %a) #2
+  ret <4 x float> %1
+
+; FAULT-LABEL: f4sqrt:
+; FAULT-NEXT: BB#0
+; FAULT-NEXT: fsqrt
+
+; CHECK-LABEL: f4sqrt:
+; CHECK-NEXT: BB#0
+; CHECK-NEXT: fmov
+; CHECK-NEXT: mov
+; CHECK-NEXT: frsqrte
+}
+
+define double @dsqrt(double %a) #0 {
+  %1 = tail call fast double @llvm.sqrt.f64(double %a)
+  ret double %1
+
+; FAULT-LABEL: dsqrt:
+; FAULT-NEXT: BB#0
+; FAULT-NEXT: fsqrt
+
+; CHECK-LABEL: dsqrt:
+; CHECK-NEXT: BB#0
+; CHECK-NEXT: fmov
+; CHECK-NEXT: frsqrte
+}
+
+define <2 x double> @d2sqrt(<2 x double> %a) #0 {
+  %1 = tail call fast <2 x double> @llvm.sqrt.v2f64(<2 x double> %a) #2
+  ret <2 x double> %1
+
+; FAULT-LABEL: d2sqrt:
+; FAULT-NEXT: BB#0
+; FAULT-NEXT: fsqrt
+
+; CHECK-LABEL: d2sqrt:
+; CHECK-NEXT: BB#0
+; CHECK-NEXT: fmov
+; CHECK-NEXT: mov
+; CHECK-NEXT: frsqrte
+}
+
+define float @frsqrt(float %a) #0 {
+  %1 = tail call fast float @llvm.sqrt.f32(float %a)
+  %2 = fdiv fast float 1.000000e+00, %1
+  ret float %2
+
+; FAULT-LABEL: frsqrt:
+; FAULT-NEXT: BB#0
+; FAULT-NEXT: fsqrt
+
+; CHECK-LABEL: frsqrt:
+; CHECK-NEXT: BB#0
+; CHECK-NEXT: fmov
+; CHECK-NEXT: frsqrte
+}
+
+define <2 x float> @f2rsqrt(<2 x float> %a) #0 {
+  %1 = tail call fast <2 x float> @llvm.sqrt.v2f32(<2 x float> %a) #2
+  %2 = fdiv fast <2 x float> <float 1.000000e+00, float 1.000000e+00>, %1
+  ret <2 x float> %2
+
+; FAULT-LABEL: f2rsqrt:
+; FAULT-NEXT: BB#0
+; FAULT-NEXT: fsqrt
+
+; CHECK-LABEL: f2rsqrt:
+; CHECK-NEXT: BB#0
+; CHECK-NEXT: fmov
+; CHECK-NEXT: frsqrte
+}
+
+define <4 x float> @f4rsqrt(<4 x float> %a) #0 {
+  %1 = tail call fast <4 x float> @llvm.sqrt.v4f32(<4 x float> %a) #2
+  %2 = fdiv fast <4 x float> <float 1.000000e+00, float 1.000000e+00, float 1.000000e+00, float 1.000000e+00>, %1
+  ret <4 x float> %2
+
+; FAULT-LABEL: f4rsqrt:
+; FAULT-NEXT: BB#0
+; FAULT-NEXT: fsqrt
+
+; CHECK-LABEL: f4rsqrt:
+; CHECK-NEXT: BB#0
+; CHECK-NEXT: fmov
+; CHECK-NEXT: frsqrte
+}
+
+define double @drsqrt(double %a) #0 {
+  %1 = tail call fast double @llvm.sqrt.f64(double %a)
+  %2 = fdiv fast double 1.000000e+00, %1
+  ret double %2
+
+; FAULT-LABEL: drsqrt:
+; FAULT-NEXT: BB#0
+; FAULT-NEXT: fsqrt
+
+; CHECK-LABEL: drsqrt:
+; CHECK-NEXT: BB#0
+; CHECK-NEXT: fmov
+; CHECK-NEXT: frsqrte
+}
+
+define <2 x double> @d2rsqrt(<2 x double> %a) #0 {
+  %1 = tail call fast <2 x double> @llvm.sqrt.v2f64(<2 x double> %a) #2
+  %2 = fdiv fast <2 x double> <double 1.000000e+00, double 1.000000e+00>, %1
+  ret <2 x double> %2
+
+; FAULT-LABEL: d2rsqrt:
+; FAULT-NEXT: BB#0
+; FAULT-NEXT: fsqrt
+
+; CHECK-LABEL: d2rsqrt:
+; CHECK-NEXT: BB#0
+; CHECK-NEXT: fmov
+; CHECK-NEXT: frsqrte
+}
+
+attributes #0 = { nounwind "unsafe-fp-math"="true" }