[AArch64] auto-generate complete checks; NFC

llvm-svn: 323984

1 files changed, 319 insertions, 210 deletions

diff --git a/llvm/test/CodeGen/AArch64/sqrt-fastmath.ll b/llvm/test/CodeGen/AArch64/sqrt-fastmath.ll
index ade9e3d8df3..9b705fd4a6e 100644
--- a/llvm/test/CodeGen/AArch64/sqrt-fastmath.ll
+++ b/llvm/test/CodeGen/AArch64/sqrt-fastmath.ll
@@ -1,3 +1,4 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
 ; 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
 
@@ -10,289 +11,397 @@ 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)
-  ret float %1
-
 ; FAULT-LABEL: fsqrt:
-; FAULT-NEXT: %bb.0
-; FAULT-NEXT: fsqrt
-
+; FAULT:       // %bb.0:
+; FAULT-NEXT:    fsqrt s0, s0
+; FAULT-NEXT:    ret
+;
 ; CHECK-LABEL: fsqrt:
-; CHECK-NEXT: %bb.0
-; 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: frsqrts {{s[0-7]}}, {{s[0-7]}}, {{s[0-7]}}
-; CHECK-NOT: frsqrts {{s[0-7]}}, {{s[0-7]}}, {{s[0-7]}}
-; CHECK: fcmp {{s[0-7]}}, #0
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    frsqrte s1, s0
+; CHECK-NEXT:    fmul s2, s1, s1
+; CHECK-NEXT:    frsqrts s2, s0, s2
+; CHECK-NEXT:    fmul s1, s1, s2
+; CHECK-NEXT:    fmul s2, s1, s1
+; CHECK-NEXT:    frsqrts s2, s0, s2
+; CHECK-NEXT:    fmul s2, s2, s0
+; CHECK-NEXT:    fmul s1, s1, s2
+; CHECK-NEXT:    fcmp s0, #0.0
+; CHECK-NEXT:    fcsel s0, s0, s1, eq
+; CHECK-NEXT:    ret
+  %1 = tail call fast float @llvm.sqrt.f32(float %a)
+  ret float %1
 }
 
 define <2 x float> @f2sqrt(<2 x float> %a) #0 {
-  %1 = tail call fast <2 x float> @llvm.sqrt.v2f32(<2 x float> %a)
-  ret <2 x float> %1
-
 ; FAULT-LABEL: f2sqrt:
-; FAULT-NEXT: %bb.0
-; FAULT-NEXT: fsqrt
-
+; FAULT:       // %bb.0:
+; FAULT-NEXT:    fsqrt v0.2s, v0.2s
+; FAULT-NEXT:    ret
+;
 ; CHECK-LABEL: f2sqrt:
-; CHECK-NEXT: %bb.0
-; 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: frsqrts {{v[0-7]\.2s}}, {{v[0-7]\.2s}}, {{v[0-7]\.2s}}
-; CHECK-NOT: frsqrts {{v[0-7]\.2s}}, {{v[0-7]\.2s}}, {{v[0-7]\.2s}}
-; CHECK: fcmeq {{v[0-7]\.2s}}, {{v[0-7]\.2s}}, #0
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    frsqrte v1.2s, v0.2s
+; CHECK-NEXT:    fmul v2.2s, v1.2s, v1.2s
+; CHECK-NEXT:    frsqrts v2.2s, v0.2s, v2.2s
+; CHECK-NEXT:    fmul v1.2s, v1.2s, v2.2s
+; CHECK-NEXT:    fmul v2.2s, v1.2s, v1.2s
+; CHECK-NEXT:    frsqrts v2.2s, v0.2s, v2.2s
+; CHECK-NEXT:    fmul v2.2s, v2.2s, v0.2s
+; CHECK-NEXT:    fmul v2.2s, v1.2s, v2.2s
+; CHECK-NEXT:    fcmeq v1.2s, v0.2s, #0.0
+; CHECK-NEXT:    bsl v1.8b, v0.8b, v2.8b
+; CHECK-NEXT:    mov v0.16b, v1.16b
+; CHECK-NEXT:    ret
+  %1 = tail call fast <2 x float> @llvm.sqrt.v2f32(<2 x float> %a)
+  ret <2 x float> %1
 }
 
 define <4 x float> @f4sqrt(<4 x float> %a) #0 {
-  %1 = tail call fast <4 x float> @llvm.sqrt.v4f32(<4 x float> %a)
-  ret <4 x float> %1
-
 ; FAULT-LABEL: f4sqrt:
-; FAULT-NEXT: %bb.0
-; FAULT-NEXT: fsqrt
-
+; FAULT:       // %bb.0:
+; FAULT-NEXT:    fsqrt v0.4s, v0.4s
+; FAULT-NEXT:    ret
+;
 ; CHECK-LABEL: f4sqrt:
-; CHECK-NEXT: %bb.0
-; 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: frsqrts {{v[0-7]\.4s}}, {{v[0-7]\.4s}}, {{v[0-7]\.4s}}
-; CHECK-NOT: frsqrts {{v[0-7]\.4s}}, {{v[0-7]\.4s}}, {{v[0-7]\.4s}}
-; CHECK: fcmeq {{v[0-7]\.4s}}, {{v[0-7]\.4s}}, #0
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    frsqrte v1.4s, v0.4s
+; CHECK-NEXT:    fmul v2.4s, v1.4s, v1.4s
+; CHECK-NEXT:    frsqrts v2.4s, v0.4s, v2.4s
+; CHECK-NEXT:    fmul v1.4s, v1.4s, v2.4s
+; CHECK-NEXT:    fmul v2.4s, v1.4s, v1.4s
+; CHECK-NEXT:    frsqrts v2.4s, v0.4s, v2.4s
+; CHECK-NEXT:    fmul v2.4s, v2.4s, v0.4s
+; CHECK-NEXT:    fmul v2.4s, v1.4s, v2.4s
+; CHECK-NEXT:    fcmeq v1.4s, v0.4s, #0.0
+; CHECK-NEXT:    bsl v1.16b, v0.16b, v2.16b
+; CHECK-NEXT:    mov v0.16b, v1.16b
+; CHECK-NEXT:    ret
+  %1 = tail call fast <4 x float> @llvm.sqrt.v4f32(<4 x float> %a)
+  ret <4 x float> %1
 }
 
 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
-
+; FAULT:       // %bb.0:
+; FAULT-NEXT:    fsqrt v0.4s, v0.4s
+; FAULT-NEXT:    fsqrt v1.4s, v1.4s
+; FAULT-NEXT:    ret
+;
 ; CHECK-LABEL: f8sqrt:
-; CHECK-NEXT: %bb.0
-; 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: frsqrts {{v[0-7]\.4s}}, {{v[0-7]\.4s}}, {{v[0-7]\.4s}}
-; CHECK: fcmeq {{v[0-7]\.4s}}, {{v[0-7]\.4s}}, #0
-; CHECK: frsqrte [[RC:v[0-7]\.4s]]
-; CHECK-NEXT: fmul [[RD:v[0-7]\.4s]], [[RC]], [[RC]]
-; CHECK-NEXT: frsqrts {{v[0-7]\.4s(, v[0-7]\.4s)?}}, [[RD]]
-; CHECK: frsqrts {{v[0-7]\.4s}}, {{v[0-7]\.4s}}, {{v[0-7]\.4s}}
-; CHECK-NOT: frsqrts {{v[0-7]\.4s}}, {{v[0-7]\.4s}}, {{v[0-7]\.4s}}
-; CHECK: fcmeq {{v[0-7]\.4s}}, {{v[0-7]\.4s}}, #0
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    frsqrte v2.4s, v0.4s
+; CHECK-NEXT:    fmul v3.4s, v2.4s, v2.4s
+; CHECK-NEXT:    frsqrts v3.4s, v0.4s, v3.4s
+; CHECK-NEXT:    fmul v2.4s, v2.4s, v3.4s
+; CHECK-NEXT:    fmul v3.4s, v2.4s, v2.4s
+; CHECK-NEXT:    frsqrts v3.4s, v0.4s, v3.4s
+; CHECK-NEXT:    fmul v3.4s, v3.4s, v0.4s
+; CHECK-NEXT:    fmul v3.4s, v2.4s, v3.4s
+; CHECK-NEXT:    fcmeq v2.4s, v0.4s, #0.0
+; CHECK-NEXT:    bsl v2.16b, v0.16b, v3.16b
+; CHECK-NEXT:    frsqrte v0.4s, v1.4s
+; CHECK-NEXT:    fmul v3.4s, v0.4s, v0.4s
+; CHECK-NEXT:    frsqrts v3.4s, v1.4s, v3.4s
+; CHECK-NEXT:    fmul v0.4s, v0.4s, v3.4s
+; CHECK-NEXT:    fmul v3.4s, v0.4s, v0.4s
+; CHECK-NEXT:    frsqrts v3.4s, v1.4s, v3.4s
+; CHECK-NEXT:    fmul v3.4s, v3.4s, v1.4s
+; CHECK-NEXT:    fmul v0.4s, v0.4s, v3.4s
+; CHECK-NEXT:    fcmeq v3.4s, v1.4s, #0.0
+; CHECK-NEXT:    bsl v3.16b, v1.16b, v0.16b
+; CHECK-NEXT:    mov v0.16b, v2.16b
+; CHECK-NEXT:    mov v1.16b, v3.16b
+; CHECK-NEXT:    ret
+  %1 = tail call fast <8 x float> @llvm.sqrt.v8f32(<8 x float> %a)
+  ret <8 x float> %1
 }
 
 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
-
+; FAULT:       // %bb.0:
+; FAULT-NEXT:    fsqrt d0, d0
+; FAULT-NEXT:    ret
+;
 ; CHECK-LABEL: dsqrt:
-; CHECK-NEXT: %bb.0
-; 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: frsqrts {{d[0-7]}}, {{d[0-7]}}, {{d[0-7]}}
-; CHECK: frsqrts {{d[0-7]}}, {{d[0-7]}}, {{d[0-7]}}
-; CHECK-NOT: frsqrts {{d[0-7]}}, {{d[0-7]}}, {{d[0-7]}}
-; CHECK: fcmp {{d[0-7]}}, #0
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    frsqrte d1, d0
+; CHECK-NEXT:    fmul d2, d1, d1
+; CHECK-NEXT:    frsqrts d2, d0, d2
+; CHECK-NEXT:    fmul d1, d1, d2
+; CHECK-NEXT:    fmul d2, d1, d1
+; CHECK-NEXT:    frsqrts d2, d0, d2
+; CHECK-NEXT:    fmul d1, d1, d2
+; CHECK-NEXT:    fmul d2, d1, d1
+; CHECK-NEXT:    frsqrts d2, d0, d2
+; CHECK-NEXT:    fmul d2, d2, d0
+; CHECK-NEXT:    fmul d1, d1, d2
+; CHECK-NEXT:    fcmp d0, #0.0
+; CHECK-NEXT:    fcsel d0, d0, d1, eq
+; CHECK-NEXT:    ret
+  %1 = tail call fast double @llvm.sqrt.f64(double %a)
+  ret double %1
 }
 
 define <2 x double> @d2sqrt(<2 x double> %a) #0 {
-  %1 = tail call fast <2 x double> @llvm.sqrt.v2f64(<2 x double> %a)
-  ret <2 x double> %1
-
 ; FAULT-LABEL: d2sqrt:
-; FAULT-NEXT: %bb.0
-; FAULT-NEXT: fsqrt
-
+; FAULT:       // %bb.0:
+; FAULT-NEXT:    fsqrt v0.2d, v0.2d
+; FAULT-NEXT:    ret
+;
 ; CHECK-LABEL: d2sqrt:
-; CHECK-NEXT: %bb.0
-; 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: frsqrts {{v[0-7]\.2d}}, {{v[0-7]\.2d}}, {{v[0-7]\.2d}}
-; CHECK: frsqrts {{v[0-7]\.2d}}, {{v[0-7]\.2d}}, {{v[0-7]\.2d}}
-; CHECK-NOT: frsqrts {{v[0-7]\.2d}}, {{v[0-7]\.2d}}, {{v[0-7]\.2d}}
-; CHECK: fcmeq {{v[0-7]\.2d}}, {{v[0-7]\.2d}}, #0
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    frsqrte v1.2d, v0.2d
+; CHECK-NEXT:    fmul v2.2d, v1.2d, v1.2d
+; CHECK-NEXT:    frsqrts v2.2d, v0.2d, v2.2d
+; CHECK-NEXT:    fmul v1.2d, v1.2d, v2.2d
+; CHECK-NEXT:    fmul v2.2d, v1.2d, v1.2d
+; CHECK-NEXT:    frsqrts v2.2d, v0.2d, v2.2d
+; CHECK-NEXT:    fmul v1.2d, v1.2d, v2.2d
+; CHECK-NEXT:    fmul v2.2d, v1.2d, v1.2d
+; CHECK-NEXT:    frsqrts v2.2d, v0.2d, v2.2d
+; CHECK-NEXT:    fmul v2.2d, v2.2d, v0.2d
+; CHECK-NEXT:    fmul v2.2d, v1.2d, v2.2d
+; CHECK-NEXT:    fcmeq v1.2d, v0.2d, #0.0
+; CHECK-NEXT:    bsl v1.16b, v0.16b, v2.16b
+; CHECK-NEXT:    mov v0.16b, v1.16b
+; CHECK-NEXT:    ret
+  %1 = tail call fast <2 x double> @llvm.sqrt.v2f64(<2 x double> %a)
+  ret <2 x double> %1
 }
 
 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
-
+; FAULT:       // %bb.0:
+; FAULT-NEXT:    fsqrt v0.2d, v0.2d
+; FAULT-NEXT:    fsqrt v1.2d, v1.2d
+; FAULT-NEXT:    ret
+;
 ; CHECK-LABEL: d4sqrt:
-; CHECK-NEXT: %bb.0
-; 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: frsqrts {{v[0-7]\.2d}}, {{v[0-7]\.2d}}, {{v[0-7]\.2d}}
-; CHECK: frsqrts {{v[0-7]\.2d}}, {{v[0-7]\.2d}}, {{v[0-7]\.2d}}
-; CHECK-NOT: frsqrts {{v[0-7]\.2d}}, {{v[0-7]\.2d}}, {{v[0-7]\.2d}}
-; CHECK: fcmeq {{v[0-7]\.2d}}, {{v[0-7]\.2d}}, #0
-; CHECK: frsqrte [[RC:v[0-7]\.2d]]
-; CHECK-NEXT: fmul [[RD:v[0-7]\.2d]], [[RC]], [[RC]]
-; CHECK-NEXT: frsqrts {{v[0-7]\.2d(, v[0-7]\.2d)?}}, [[RD]]
-; CHECK: frsqrts {{v[0-7]\.2d}}, {{v[0-7]\.2d}}, {{v[0-7]\.2d}}
-; CHECK: frsqrts {{v[0-7]\.2d}}, {{v[0-7]\.2d}}, {{v[0-7]\.2d}}
-; CHECK-NOT: frsqrts {{v[0-7]\.2d}}, {{v[0-7]\.2d}}, {{v[0-7]\.2d}}
-; CHECK: fcmeq {{v[0-7]\.2d}}, {{v[0-7]\.2d}}, #0
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    frsqrte v2.2d, v0.2d
+; CHECK-NEXT:    fmul v3.2d, v2.2d, v2.2d
+; CHECK-NEXT:    frsqrts v3.2d, v0.2d, v3.2d
+; CHECK-NEXT:    fmul v2.2d, v2.2d, v3.2d
+; CHECK-NEXT:    fmul v3.2d, v2.2d, v2.2d
+; CHECK-NEXT:    frsqrts v3.2d, v0.2d, v3.2d
+; CHECK-NEXT:    fmul v2.2d, v2.2d, v3.2d
+; CHECK-NEXT:    fmul v3.2d, v2.2d, v2.2d
+; CHECK-NEXT:    frsqrts v3.2d, v0.2d, v3.2d
+; CHECK-NEXT:    fmul v3.2d, v3.2d, v0.2d
+; CHECK-NEXT:    fmul v3.2d, v2.2d, v3.2d
+; CHECK-NEXT:    fcmeq v2.2d, v0.2d, #0.0
+; CHECK-NEXT:    bsl v2.16b, v0.16b, v3.16b
+; CHECK-NEXT:    frsqrte v0.2d, v1.2d
+; CHECK-NEXT:    fmul v3.2d, v0.2d, v0.2d
+; CHECK-NEXT:    frsqrts v3.2d, v1.2d, v3.2d
+; CHECK-NEXT:    fmul v0.2d, v0.2d, v3.2d
+; CHECK-NEXT:    fmul v3.2d, v0.2d, v0.2d
+; CHECK-NEXT:    frsqrts v3.2d, v1.2d, v3.2d
+; CHECK-NEXT:    fmul v0.2d, v0.2d, v3.2d
+; CHECK-NEXT:    fmul v3.2d, v0.2d, v0.2d
+; CHECK-NEXT:    frsqrts v3.2d, v1.2d, v3.2d
+; CHECK-NEXT:    fmul v3.2d, v3.2d, v1.2d
+; CHECK-NEXT:    fmul v0.2d, v0.2d, v3.2d
+; CHECK-NEXT:    fcmeq v3.2d, v1.2d, #0.0
+; CHECK-NEXT:    bsl v3.16b, v1.16b, v0.16b
+; CHECK-NEXT:    mov v0.16b, v2.16b
+; CHECK-NEXT:    mov v1.16b, v3.16b
+; CHECK-NEXT:    ret
+  %1 = tail call fast <4 x double> @llvm.sqrt.v4f64(<4 x double> %a)
+  ret <4 x double> %1
 }
 
 define float @frsqrt(float %a) #0 {
+; FAULT-LABEL: frsqrt:
+; FAULT:       // %bb.0:
+; FAULT-NEXT:    fsqrt s0, s0
+; FAULT-NEXT:    fmov s1, #1.00000000
+; FAULT-NEXT:    fdiv s0, s1, s0
+; FAULT-NEXT:    ret
+;
+; CHECK-LABEL: frsqrt:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    frsqrte s1, s0
+; CHECK-NEXT:    fmul s2, s1, s1
+; CHECK-NEXT:    frsqrts s2, s0, s2
+; CHECK-NEXT:    fmul s1, s1, s2
+; CHECK-NEXT:    fmul s2, s1, s1
+; CHECK-NEXT:    frsqrts s0, s0, s2
+; CHECK-NEXT:    fmul s0, s1, s0
+; CHECK-NEXT:    ret
   %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: 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: frsqrts {{s[0-7]}}, {{s[0-7]}}, {{s[0-7]}}
-; CHECK-NOT: frsqrts {{s[0-7]}}, {{s[0-7]}}, {{s[0-7]}}
-; CHECK-NOT: fcmp {{s[0-7]}}, #0
 }
 
 define <2 x float> @f2rsqrt(<2 x float> %a) #0 {
+; FAULT-LABEL: f2rsqrt:
+; FAULT:       // %bb.0:
+; FAULT-NEXT:    fsqrt v0.2s, v0.2s
+; FAULT-NEXT:    fmov v1.2s, #1.00000000
+; FAULT-NEXT:    fdiv v0.2s, v1.2s, v0.2s
+; FAULT-NEXT:    ret
+;
+; CHECK-LABEL: f2rsqrt:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    frsqrte v1.2s, v0.2s
+; CHECK-NEXT:    fmul v2.2s, v1.2s, v1.2s
+; CHECK-NEXT:    frsqrts v2.2s, v0.2s, v2.2s
+; CHECK-NEXT:    fmul v1.2s, v1.2s, v2.2s
+; CHECK-NEXT:    fmul v2.2s, v1.2s, v1.2s
+; CHECK-NEXT:    frsqrts v0.2s, v0.2s, v2.2s
+; CHECK-NEXT:    fmul v0.2s, v1.2s, v0.2s
+; CHECK-NEXT:    ret
   %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
-
-; FAULT-LABEL: f2rsqrt:
-; FAULT-NEXT: %bb.0
-; FAULT-NEXT: fsqrt
-
-; CHECK-LABEL: f2rsqrt:
-; CHECK-NEXT: %bb.0
-; 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: frsqrts {{v[0-7]\.2s}}, {{v[0-7]\.2s}}, {{v[0-7]\.2s}}
-; CHECK-NOT: frsqrts {{v[0-7]\.2s}}, {{v[0-7]\.2s}}, {{v[0-7]\.2s}}
-; CHECK-NOT: fcmeq {{v[0-7]\.2s}}, {{v[0-7]\.2s}}, #0
 }
 
 define <4 x float> @f4rsqrt(<4 x float> %a) #0 {
+; FAULT-LABEL: f4rsqrt:
+; FAULT:       // %bb.0:
+; FAULT-NEXT:    fsqrt v0.4s, v0.4s
+; FAULT-NEXT:    fmov v1.4s, #1.00000000
+; FAULT-NEXT:    fdiv v0.4s, v1.4s, v0.4s
+; FAULT-NEXT:    ret
+;
+; CHECK-LABEL: f4rsqrt:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    frsqrte v1.4s, v0.4s
+; CHECK-NEXT:    fmul v2.4s, v1.4s, v1.4s
+; CHECK-NEXT:    frsqrts v2.4s, v0.4s, v2.4s
+; CHECK-NEXT:    fmul v1.4s, v1.4s, v2.4s
+; CHECK-NEXT:    fmul v2.4s, v1.4s, v1.4s
+; CHECK-NEXT:    frsqrts v0.4s, v0.4s, v2.4s
+; CHECK-NEXT:    fmul v0.4s, v1.4s, v0.4s
+; CHECK-NEXT:    ret
   %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
-
-; FAULT-LABEL: f4rsqrt:
-; FAULT-NEXT: %bb.0
-; FAULT-NEXT: fsqrt
-
-; CHECK-LABEL: f4rsqrt:
-; CHECK-NEXT: %bb.0
-; 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: frsqrts {{v[0-7]\.4s}}, {{v[0-7]\.4s}}, {{v[0-7]\.4s}}
-; CHECK-NOT: frsqrts {{v[0-7]\.4s}}, {{v[0-7]\.4s}}, {{v[0-7]\.4s}}
-; CHECK-NOT: fcmeq {{v[0-7]\.4s}}, {{v[0-7]\.4s}}, #0
 }
 
 define <8 x float> @f8rsqrt(<8 x float> %a) #0 {
+; FAULT-LABEL: f8rsqrt:
+; FAULT:       // %bb.0:
+; FAULT-NEXT:    fsqrt v1.4s, v1.4s
+; FAULT-NEXT:    fsqrt v0.4s, v0.4s
+; FAULT-NEXT:    fmov v2.4s, #1.00000000
+; FAULT-NEXT:    fdiv v0.4s, v2.4s, v0.4s
+; FAULT-NEXT:    fdiv v1.4s, v2.4s, v1.4s
+; FAULT-NEXT:    ret
+;
+; CHECK-LABEL: f8rsqrt:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    frsqrte v2.4s, v0.4s
+; CHECK-NEXT:    fmul v4.4s, v2.4s, v2.4s
+; CHECK-NEXT:    frsqrte v3.4s, v1.4s
+; CHECK-NEXT:    frsqrts v4.4s, v0.4s, v4.4s
+; CHECK-NEXT:    fmul v2.4s, v2.4s, v4.4s
+; CHECK-NEXT:    fmul v4.4s, v3.4s, v3.4s
+; CHECK-NEXT:    frsqrts v4.4s, v1.4s, v4.4s
+; CHECK-NEXT:    fmul v3.4s, v3.4s, v4.4s
+; CHECK-NEXT:    fmul v4.4s, v2.4s, v2.4s
+; CHECK-NEXT:    frsqrts v0.4s, v0.4s, v4.4s
+; CHECK-NEXT:    fmul v4.4s, v3.4s, v3.4s
+; CHECK-NEXT:    frsqrts v1.4s, v1.4s, v4.4s
+; CHECK-NEXT:    fmul v0.4s, v2.4s, v0.4s
+; CHECK-NEXT:    fmul v1.4s, v3.4s, v1.4s
+; CHECK-NEXT:    ret
   %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: frsqrts {{v[0-7]\.4s}}, {{v[0-7]\.4s}}, {{v[0-7]\.4s}}
-; CHECK: frsqrts {{v[0-7]\.4s}}, {{v[0-7]\.4s}}, {{v[0-7]\.4s}}
-; CHECK: frsqrts {{v[0-7]\.4s}}, {{v[0-7]\.4s}}, {{v[0-7]\.4s}}
-; CHECK-NOT: frsqrts {{v[0-7]\.4s}}, {{v[0-7]\.4s}}, {{v[0-7]\.4s}}
-; CHECK-NOT: fcmeq {{v[0-7]\.4s}}, {{v[0-7]\.4s}}, #0
 }
 
 define double @drsqrt(double %a) #0 {
+; FAULT-LABEL: drsqrt:
+; FAULT:       // %bb.0:
+; FAULT-NEXT:    fsqrt d0, d0
+; FAULT-NEXT:    fmov d1, #1.00000000
+; FAULT-NEXT:    fdiv d0, d1, d0
+; FAULT-NEXT:    ret
+;
+; CHECK-LABEL: drsqrt:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    frsqrte d1, d0
+; CHECK-NEXT:    fmul d2, d1, d1
+; CHECK-NEXT:    frsqrts d2, d0, d2
+; CHECK-NEXT:    fmul d1, d1, d2
+; CHECK-NEXT:    fmul d2, d1, d1
+; CHECK-NEXT:    frsqrts d2, d0, d2
+; CHECK-NEXT:    fmul d1, d1, d2
+; CHECK-NEXT:    fmul d2, d1, d1
+; CHECK-NEXT:    frsqrts d0, d0, d2
+; CHECK-NEXT:    fmul d0, d1, d0
+; CHECK-NEXT:    ret
   %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: 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: frsqrts {{d[0-7]}}, {{d[0-7]}}, {{d[0-7]}}
-; CHECK: frsqrts {{d[0-7]}}, {{d[0-7]}}, {{d[0-7]}}
-; CHECK-NOT: frsqrts {{d[0-7]}}, {{d[0-7]}}, {{d[0-7]}}
-; CHECK-NOT: fcmp d0, #0
 }
 
 define <2 x double> @d2rsqrt(<2 x double> %a) #0 {
+; FAULT-LABEL: d2rsqrt:
+; FAULT:       // %bb.0:
+; FAULT-NEXT:    fsqrt v0.2d, v0.2d
+; FAULT-NEXT:    fmov v1.2d, #1.00000000
+; FAULT-NEXT:    fdiv v0.2d, v1.2d, v0.2d
+; FAULT-NEXT:    ret
+;
+; CHECK-LABEL: d2rsqrt:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    frsqrte v1.2d, v0.2d
+; CHECK-NEXT:    fmul v2.2d, v1.2d, v1.2d
+; CHECK-NEXT:    frsqrts v2.2d, v0.2d, v2.2d
+; CHECK-NEXT:    fmul v1.2d, v1.2d, v2.2d
+; CHECK-NEXT:    fmul v2.2d, v1.2d, v1.2d
+; CHECK-NEXT:    frsqrts v2.2d, v0.2d, v2.2d
+; CHECK-NEXT:    fmul v1.2d, v1.2d, v2.2d
+; CHECK-NEXT:    fmul v2.2d, v1.2d, v1.2d
+; CHECK-NEXT:    frsqrts v0.2d, v0.2d, v2.2d
+; CHECK-NEXT:    fmul v0.2d, v1.2d, v0.2d
+; CHECK-NEXT:    ret
   %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
-
-; FAULT-LABEL: d2rsqrt:
-; FAULT-NEXT: %bb.0
-; FAULT-NEXT: fsqrt
-
-; CHECK-LABEL: d2rsqrt:
-; CHECK-NEXT: %bb.0
-; 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: frsqrts {{v[0-7]\.2d}}, {{v[0-7]\.2d}}, {{v[0-7]\.2d}}
-; CHECK: frsqrts {{v[0-7]\.2d}}, {{v[0-7]\.2d}}, {{v[0-7]\.2d}}
-; CHECK-NOT: frsqrts {{v[0-7]\.2d}}, {{v[0-7]\.2d}}, {{v[0-7]\.2d}}
-; CHECK-NOT: fcmeq {{v[0-7]\.2d}}, {{v[0-7]\.2d}}, #0
 }
 
 define <4 x double> @d4rsqrt(<4 x double> %a) #0 {
+; FAULT-LABEL: d4rsqrt:
+; FAULT:       // %bb.0:
+; FAULT-NEXT:    fsqrt v1.2d, v1.2d
+; FAULT-NEXT:    fsqrt v0.2d, v0.2d
+; FAULT-NEXT:    fmov v2.2d, #1.00000000
+; FAULT-NEXT:    fdiv v0.2d, v2.2d, v0.2d
+; FAULT-NEXT:    fdiv v1.2d, v2.2d, v1.2d
+; FAULT-NEXT:    ret
+;
+; CHECK-LABEL: d4rsqrt:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    frsqrte v2.2d, v0.2d
+; CHECK-NEXT:    fmul v4.2d, v2.2d, v2.2d
+; CHECK-NEXT:    frsqrte v3.2d, v1.2d
+; CHECK-NEXT:    frsqrts v4.2d, v0.2d, v4.2d
+; CHECK-NEXT:    fmul v2.2d, v2.2d, v4.2d
+; CHECK-NEXT:    fmul v4.2d, v3.2d, v3.2d
+; CHECK-NEXT:    frsqrts v4.2d, v1.2d, v4.2d
+; CHECK-NEXT:    fmul v3.2d, v3.2d, v4.2d
+; CHECK-NEXT:    fmul v4.2d, v2.2d, v2.2d
+; CHECK-NEXT:    frsqrts v4.2d, v0.2d, v4.2d
+; CHECK-NEXT:    fmul v2.2d, v2.2d, v4.2d
+; CHECK-NEXT:    fmul v4.2d, v3.2d, v3.2d
+; CHECK-NEXT:    frsqrts v4.2d, v1.2d, v4.2d
+; CHECK-NEXT:    fmul v3.2d, v3.2d, v4.2d
+; CHECK-NEXT:    fmul v4.2d, v2.2d, v2.2d
+; CHECK-NEXT:    frsqrts v0.2d, v0.2d, v4.2d
+; CHECK-NEXT:    fmul v4.2d, v3.2d, v3.2d
+; CHECK-NEXT:    frsqrts v1.2d, v1.2d, v4.2d
+; CHECK-NEXT:    fmul v0.2d, v2.2d, v0.2d
+; CHECK-NEXT:    fmul v1.2d, v3.2d, v1.2d
+; CHECK-NEXT:    ret
   %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: frsqrts {{v[0-7]\.2d}}, {{v[0-7]\.2d}}, {{v[0-7]\.2d}}
-; CHECK: frsqrts {{v[0-7]\.2d}}, {{v[0-7]\.2d}}, {{v[0-7]\.2d}}
-; CHECK: frsqrts {{v[0-7]\.2d}}, {{v[0-7]\.2d}}, {{v[0-7]\.2d}}
-; CHECK: frsqrts {{v[0-7]\.2d}}, {{v[0-7]\.2d}}, {{v[0-7]\.2d}}
-; CHECK: frsqrts {{v[0-7]\.2d}}, {{v[0-7]\.2d}}, {{v[0-7]\.2d}}
-; CHECK-NOT: frsqrts {{v[0-7]\.2d}}, {{v[0-7]\.2d}}, {{v[0-7]\.2d}}
-; CHECK-NOT: fcmeq {{v[0-7]\.2d}}, {{v[0-7]\.2d}}, #0
 }
 
-attributes #0 = { nounwind "unsafe-fp-math"="true" }
+attributes #0 = { "unsafe-fp-math"="true" }
+