summaryrefslogtreecommitdiff
path: root/test/CodeGen/AArch64/sqrt-fastmath.ll
diff options
context:
space:
mode:
Diffstat (limited to 'test/CodeGen/AArch64/sqrt-fastmath.ll')
-rw-r--r--test/CodeGen/AArch64/sqrt-fastmath.ll163
1 files changed, 125 insertions, 38 deletions
diff --git a/test/CodeGen/AArch64/sqrt-fastmath.ll b/test/CodeGen/AArch64/sqrt-fastmath.ll
index 0d9533fd27fc..079562c05819 100644
--- a/test/CodeGen/AArch64/sqrt-fastmath.ll
+++ b/test/CodeGen/AArch64/sqrt-fastmath.ll
@@ -1,13 +1,13 @@
-; 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
-; RUN: llc < %s -mtriple=aarch64 -mattr=neon,-use-reverse-square-root | FileCheck %s --check-prefix=FAULT
-; RUN: llc < %s -mtriple=aarch64 -mattr=neon,+use-reverse-square-root | FileCheck %s
+; RUN: llc < %s -mtriple=aarch64-unknown-linux-gnu -mattr=+neon,-use-reciprocal-square-root | FileCheck %s --check-prefix=FAULT
+; RUN: llc < %s -mtriple=aarch64-unknown-linux-gnu -mattr=+neon,+use-reciprocal-square-root | 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
+declare float @llvm.sqrt.f32(float) #0
+declare <2 x float> @llvm.sqrt.v2f32(<2 x float>) #0
+declare <4 x float> @llvm.sqrt.v4f32(<4 x float>) #0
+declare <8 x float> @llvm.sqrt.v8f32(<8 x float>) #0
+declare double @llvm.sqrt.f64(double) #0
+declare <2 x double> @llvm.sqrt.v2f64(<2 x double>) #0
+declare <4 x double> @llvm.sqrt.v4f64(<4 x double>) #0
define float @fsqrt(float %a) #0 {
%1 = tail call fast float @llvm.sqrt.f32(float %a)
@@ -19,12 +19,14 @@ define float @fsqrt(float %a) #0 {
; CHECK-LABEL: fsqrt:
; CHECK-NEXT: BB#0
-; CHECK-NEXT: fmov
-; CHECK-NEXT: frsqrte
+; CHECK-NEXT: frsqrte [[RA:s[0-7]]]
+; CHECK-NEXT: fmul [[RB:s[0-7]]], [[RA]], [[RA]]
+; CHECK-NEXT: frsqrts {{s[0-7](, s[0-7])?}}, [[RB]]
+; CHECK: fcmp s0, #0
}
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
+ %1 = tail call fast <2 x float> @llvm.sqrt.v2f32(<2 x float> %a)
ret <2 x float> %1
; FAULT-LABEL: f2sqrt:
@@ -33,13 +35,14 @@ define <2 x float> @f2sqrt(<2 x float> %a) #0 {
; CHECK-LABEL: f2sqrt:
; CHECK-NEXT: BB#0
-; CHECK-NEXT: fmov
-; CHECK-NEXT: mov
-; CHECK-NEXT: frsqrte
+; CHECK-NEXT: frsqrte [[RA:v[0-7]\.2s]]
+; CHECK-NEXT: fmul [[RB:v[0-7]\.2s]], [[RA]], [[RA]]
+; CHECK-NEXT: frsqrts {{v[0-7]\.2s(, v[0-7]\.2s)?}}, [[RB]]
+; CHECK: fcmeq {{v[0-7]\.2s, v0\.2s}}, #0
}
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
+ %1 = tail call fast <4 x float> @llvm.sqrt.v4f32(<4 x float> %a)
ret <4 x float> %1
; FAULT-LABEL: f4sqrt:
@@ -48,9 +51,27 @@ define <4 x float> @f4sqrt(<4 x float> %a) #0 {
; CHECK-LABEL: f4sqrt:
; CHECK-NEXT: BB#0
-; CHECK-NEXT: fmov
-; CHECK-NEXT: mov
-; CHECK-NEXT: frsqrte
+; CHECK-NEXT: frsqrte [[RA:v[0-7]\.4s]]
+; CHECK-NEXT: fmul [[RB:v[0-7]\.4s]], [[RA]], [[RA]]
+; CHECK-NEXT: frsqrts {{v[0-7]\.4s(, v[0-7]\.4s)?}}, [[RB]]
+; CHECK: fcmeq {{v[0-7]\.4s, v0\.4s}}, #0
+}
+
+define <8 x float> @f8sqrt(<8 x float> %a) #0 {
+ %1 = tail call fast <8 x float> @llvm.sqrt.v8f32(<8 x float> %a)
+ ret <8 x float> %1
+
+; FAULT-LABEL: f8sqrt:
+; FAULT-NEXT: BB#0
+; FAULT-NEXT: fsqrt
+; FAULT-NEXT: fsqrt
+
+; CHECK-LABEL: f8sqrt:
+; CHECK-NEXT: BB#0
+; CHECK-NEXT: frsqrte [[RA:v[0-7]\.4s]]
+; CHECK: fmul [[RB:v[0-7]\.4s]], [[RA]], [[RA]]
+; CHECK: frsqrts {{v[0-7]\.4s(, v[0-7]\.4s)?}}, [[RB]]
+; CHECK: fcmeq {{v[0-7]\.4s, v[0-1]\.4s}}, #0
}
define double @dsqrt(double %a) #0 {
@@ -63,12 +84,14 @@ define double @dsqrt(double %a) #0 {
; CHECK-LABEL: dsqrt:
; CHECK-NEXT: BB#0
-; CHECK-NEXT: fmov
-; CHECK-NEXT: frsqrte
+; CHECK-NEXT: frsqrte [[RA:d[0-7]]]
+; CHECK-NEXT: fmul [[RB:d[0-7]]], [[RA]], [[RA]]
+; CHECK-NEXT: frsqrts {{d[0-7](, d[0-7])?}}, [[RB]]
+; CHECK: fcmp d0, #0
}
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
+ %1 = tail call fast <2 x double> @llvm.sqrt.v2f64(<2 x double> %a)
ret <2 x double> %1
; FAULT-LABEL: d2sqrt:
@@ -77,9 +100,27 @@ define <2 x double> @d2sqrt(<2 x double> %a) #0 {
; CHECK-LABEL: d2sqrt:
; CHECK-NEXT: BB#0
-; CHECK-NEXT: fmov
-; CHECK-NEXT: mov
-; CHECK-NEXT: frsqrte
+; CHECK-NEXT: frsqrte [[RA:v[0-7]\.2d]]
+; CHECK-NEXT: fmul [[RB:v[0-7]\.2d]], [[RA]], [[RA]]
+; CHECK-NEXT: frsqrts {{v[0-7]\.2d(, v[0-7]\.2d)?}}, [[RB]]
+; CHECK: fcmeq {{v[0-7]\.2d, v0\.2d}}, #0
+}
+
+define <4 x double> @d4sqrt(<4 x double> %a) #0 {
+ %1 = tail call fast <4 x double> @llvm.sqrt.v4f64(<4 x double> %a)
+ ret <4 x double> %1
+
+; FAULT-LABEL: d4sqrt:
+; FAULT-NEXT: BB#0
+; FAULT-NEXT: fsqrt
+; FAULT-NEXT: fsqrt
+
+; CHECK-LABEL: d4sqrt:
+; CHECK-NEXT: BB#0
+; CHECK-NEXT: frsqrte [[RA:v[0-7]\.2d]]
+; CHECK: fmul [[RB:v[0-7]\.2d]], [[RA]], [[RA]]
+; CHECK: frsqrts {{v[0-7]\.2d(, v[0-7]\.2d)?}}, [[RB]]
+; CHECK: fcmeq {{v[0-7]\.2d, v[0-1]\.2d}}, #0
}
define float @frsqrt(float %a) #0 {
@@ -93,12 +134,14 @@ define float @frsqrt(float %a) #0 {
; CHECK-LABEL: frsqrt:
; CHECK-NEXT: BB#0
-; CHECK-NEXT: fmov
-; CHECK-NEXT: frsqrte
+; CHECK-NEXT: frsqrte [[RA:s[0-7]]]
+; CHECK-NEXT: fmul [[RB:s[0-7]]], [[RA]], [[RA]]
+; CHECK-NEXT: frsqrts {{s[0-7](, s[0-7])?}}, [[RB]]
+; CHECK-NOT: fcmp {{s[0-7]}}, #0
}
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
+ %1 = tail call fast <2 x float> @llvm.sqrt.v2f32(<2 x float> %a)
%2 = fdiv fast <2 x float> <float 1.000000e+00, float 1.000000e+00>, %1
ret <2 x float> %2
@@ -108,12 +151,14 @@ define <2 x float> @f2rsqrt(<2 x float> %a) #0 {
; CHECK-LABEL: f2rsqrt:
; CHECK-NEXT: BB#0
-; CHECK-NEXT: fmov
-; CHECK-NEXT: frsqrte
+; CHECK-NEXT: frsqrte [[RA:v[0-7]\.2s]]
+; CHECK-NEXT: fmul [[RB:v[0-7]\.2s]], [[RA]], [[RA]]
+; CHECK-NEXT: frsqrts {{v[0-7]\.2s(, v[0-7]\.2s)?}}, [[RB]]
+; CHECK-NOT: fcmeq {{v[0-7]\.2s, v0\.2s}}, #0
}
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
+ %1 = tail call fast <4 x float> @llvm.sqrt.v4f32(<4 x float> %a)
%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
@@ -123,8 +168,28 @@ define <4 x float> @f4rsqrt(<4 x float> %a) #0 {
; CHECK-LABEL: f4rsqrt:
; CHECK-NEXT: BB#0
-; CHECK-NEXT: fmov
-; CHECK-NEXT: frsqrte
+; CHECK-NEXT: frsqrte [[RA:v[0-7]\.4s]]
+; CHECK-NEXT: fmul [[RB:v[0-7]\.4s]], [[RA]], [[RA]]
+; CHECK-NEXT: frsqrts {{v[0-7]\.4s(, v[0-7]\.4s)?}}, [[RB]]
+; CHECK-NOT: fcmeq {{v[0-7]\.4s, v0\.4s}}, #0
+}
+
+define <8 x float> @f8rsqrt(<8 x float> %a) #0 {
+ %1 = tail call fast <8 x float> @llvm.sqrt.v8f32(<8 x float> %a)
+ %2 = fdiv fast <8 x float> <float 1.000000e+00, float 1.000000e+00, float 1.000000e+00, float 1.000000e+00, float 1.000000e+00, float 1.000000e+00, float 1.000000e+00, float 1.000000e+00>, %1
+ ret <8 x float> %2
+
+; FAULT-LABEL: f8rsqrt:
+; FAULT-NEXT: BB#0
+; FAULT-NEXT: fsqrt
+; FAULT-NEXT: fsqrt
+
+; CHECK-LABEL: f8rsqrt:
+; CHECK-NEXT: BB#0
+; CHECK-NEXT: frsqrte [[RA:v[0-7]\.4s]]
+; CHECK: fmul [[RB:v[0-7]\.4s]], [[RA]], [[RA]]
+; CHECK: frsqrts {{v[0-7]\.4s(, v[0-7]\.4s)?}}, [[RB]]
+; CHECK-NOT: fcmeq {{v[0-7]\.4s, v0\.4s}}, #0
}
define double @drsqrt(double %a) #0 {
@@ -138,12 +203,14 @@ define double @drsqrt(double %a) #0 {
; CHECK-LABEL: drsqrt:
; CHECK-NEXT: BB#0
-; CHECK-NEXT: fmov
-; CHECK-NEXT: frsqrte
+; CHECK-NEXT: frsqrte [[RA:d[0-7]]]
+; CHECK-NEXT: fmul [[RB:d[0-7]]], [[RA]], [[RA]]
+; CHECK-NEXT: frsqrts {{d[0-7](, d[0-7])?}}, [[RB]]
+; CHECK-NOT: fcmp d0, #0
}
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
+ %1 = tail call fast <2 x double> @llvm.sqrt.v2f64(<2 x double> %a)
%2 = fdiv fast <2 x double> <double 1.000000e+00, double 1.000000e+00>, %1
ret <2 x double> %2
@@ -153,8 +220,28 @@ define <2 x double> @d2rsqrt(<2 x double> %a) #0 {
; CHECK-LABEL: d2rsqrt:
; CHECK-NEXT: BB#0
-; CHECK-NEXT: fmov
-; CHECK-NEXT: frsqrte
+; CHECK-NEXT: frsqrte [[RA:v[0-7]\.2d]]
+; CHECK-NEXT: fmul [[RB:v[0-7]\.2d]], [[RA]], [[RA]]
+; CHECK-NEXT: frsqrts {{v[0-7]\.2d(, v[0-7]\.2d)?}}, [[RB]]
+; CHECK-NOT: fcmeq {{v[0-7]\.2d, v0\.2d}}, #0
+}
+
+define <4 x double> @d4rsqrt(<4 x double> %a) #0 {
+ %1 = tail call fast <4 x double> @llvm.sqrt.v4f64(<4 x double> %a)
+ %2 = fdiv fast <4 x double> <double 1.000000e+00, double 1.000000e+00, double 1.000000e+00, double 1.000000e+00>, %1
+ ret <4 x double> %2
+
+; FAULT-LABEL: d4rsqrt:
+; FAULT-NEXT: BB#0
+; FAULT-NEXT: fsqrt
+; FAULT-NEXT: fsqrt
+
+; CHECK-LABEL: d4rsqrt:
+; CHECK-NEXT: BB#0
+; CHECK-NEXT: frsqrte [[RA:v[0-7]\.2d]]
+; CHECK: fmul [[RB:v[0-7]\.2d]], [[RA]], [[RA]]
+; CHECK: frsqrts {{v[0-7]\.2d(, v[0-7]\.2d)?}}, [[RB]]
+; CHECK-NOT: fcmeq {{v[0-7]\.2d, v0\.2d}}, #0
}
attributes #0 = { nounwind "unsafe-fp-math"="true" }
generated by cgit v1.3 (git 2.53.0) at 2026-05-02 23:06:38 +0000