[AArch64] auto-generate complete checks; NFC

llvm-svn: 323984
This commit is contained in:
Sanjay Patel 2018-02-01 17:44:50 +00:00
parent a8a24232ee
commit f42381fd7e
1 changed files with 319 additions and 210 deletions

View File

@ -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 {
; FAULT-LABEL: fsqrt:
; FAULT: // %bb.0:
; FAULT-NEXT: fsqrt s0, s0
; FAULT-NEXT: ret
;
; CHECK-LABEL: fsqrt:
; 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
; FAULT-LABEL: fsqrt:
; FAULT-NEXT: %bb.0
; FAULT-NEXT: fsqrt
; 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
}
define <2 x float> @f2sqrt(<2 x float> %a) #0 {
; FAULT-LABEL: f2sqrt:
; FAULT: // %bb.0:
; FAULT-NEXT: fsqrt v0.2s, v0.2s
; FAULT-NEXT: ret
;
; CHECK-LABEL: f2sqrt:
; 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
; FAULT-LABEL: f2sqrt:
; FAULT-NEXT: %bb.0
; FAULT-NEXT: fsqrt
; 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
}
define <4 x float> @f4sqrt(<4 x float> %a) #0 {
; FAULT-LABEL: f4sqrt:
; FAULT: // %bb.0:
; FAULT-NEXT: fsqrt v0.4s, v0.4s
; FAULT-NEXT: ret
;
; CHECK-LABEL: f4sqrt:
; 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
; FAULT-LABEL: f4sqrt:
; FAULT-NEXT: %bb.0
; FAULT-NEXT: fsqrt
; 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
}
define <8 x float> @f8sqrt(<8 x float> %a) #0 {
; FAULT-LABEL: f8sqrt:
; FAULT: // %bb.0:
; FAULT-NEXT: fsqrt v0.4s, v0.4s
; FAULT-NEXT: fsqrt v1.4s, v1.4s
; FAULT-NEXT: ret
;
; CHECK-LABEL: f8sqrt:
; 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
; 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-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
}
define double @dsqrt(double %a) #0 {
; FAULT-LABEL: dsqrt:
; FAULT: // %bb.0:
; FAULT-NEXT: fsqrt d0, d0
; FAULT-NEXT: ret
;
; CHECK-LABEL: dsqrt:
; 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
; FAULT-LABEL: dsqrt:
; FAULT-NEXT: %bb.0
; FAULT-NEXT: fsqrt
; 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
}
define <2 x double> @d2sqrt(<2 x double> %a) #0 {
; FAULT-LABEL: d2sqrt:
; FAULT: // %bb.0:
; FAULT-NEXT: fsqrt v0.2d, v0.2d
; FAULT-NEXT: ret
;
; CHECK-LABEL: d2sqrt:
; 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
; FAULT-LABEL: d2sqrt:
; FAULT-NEXT: %bb.0
; FAULT-NEXT: fsqrt
; 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
}
define <4 x double> @d4sqrt(<4 x double> %a) #0 {
; FAULT-LABEL: d4sqrt:
; FAULT: // %bb.0:
; FAULT-NEXT: fsqrt v0.2d, v0.2d
; FAULT-NEXT: fsqrt v1.2d, v1.2d
; FAULT-NEXT: ret
;
; CHECK-LABEL: d4sqrt:
; 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
; 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-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
}
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" }