mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-10-23 21:13:02 +02:00
160a5b1a73
When calculating a square root using Newton-Raphson with two constants, a naive implementation is to use five multiplications (four muls to calculate reciprocal square root and another one to calculate the square root itself). However, after some reassociation and CSE the same result can be obtained with only four multiplications. Unfortunately, there's no reliable way to do such a reassociation in the back-end. So, the patch modifies NR code itself so that it directly builds optimal code for SQRT and doesn't rely on any further reassociation. Patch by Nikolai Bozhenov! Differential Revision: http://reviews.llvm.org/D21127 llvm-svn: 272920
142 lines
4.8 KiB
LLVM
142 lines
4.8 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=sse2 -recip=!sqrtf,!vec-sqrtf,!divf,!vec-divf | FileCheck %s --check-prefix=NORECIP
|
|
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=avx -recip=sqrtf,vec-sqrtf | FileCheck %s --check-prefix=ESTIMATE
|
|
|
|
declare double @__sqrt_finite(double) #0
|
|
declare float @__sqrtf_finite(float) #0
|
|
declare x86_fp80 @__sqrtl_finite(x86_fp80) #0
|
|
declare float @llvm.sqrt.f32(float) #0
|
|
declare <4 x float> @llvm.sqrt.v4f32(<4 x float>) #0
|
|
declare <8 x float> @llvm.sqrt.v8f32(<8 x float>) #0
|
|
|
|
|
|
define double @fd(double %d) #0 {
|
|
; NORECIP-LABEL: fd:
|
|
; NORECIP: # BB#0:
|
|
; NORECIP-NEXT: sqrtsd %xmm0, %xmm0
|
|
; NORECIP-NEXT: retq
|
|
;
|
|
; ESTIMATE-LABEL: fd:
|
|
; ESTIMATE: # BB#0:
|
|
; ESTIMATE-NEXT: vsqrtsd %xmm0, %xmm0, %xmm0
|
|
; ESTIMATE-NEXT: retq
|
|
%call = tail call double @__sqrt_finite(double %d) #1
|
|
ret double %call
|
|
}
|
|
|
|
|
|
define float @ff(float %f) #0 {
|
|
; NORECIP-LABEL: ff:
|
|
; NORECIP: # BB#0:
|
|
; NORECIP-NEXT: sqrtss %xmm0, %xmm0
|
|
; NORECIP-NEXT: retq
|
|
;
|
|
; ESTIMATE-LABEL: ff:
|
|
; ESTIMATE: # BB#0:
|
|
; ESTIMATE-NEXT: vrsqrtss %xmm0, %xmm0, %xmm1
|
|
; ESTIMATE-NEXT: vmulss %xmm1, %xmm0, %xmm2
|
|
; ESTIMATE-NEXT: vmulss %xmm1, %xmm2, %xmm1
|
|
; ESTIMATE-NEXT: vaddss {{.*}}(%rip), %xmm1, %xmm1
|
|
; ESTIMATE-NEXT: vmulss {{.*}}(%rip), %xmm2, %xmm2
|
|
; ESTIMATE-NEXT: vmulss %xmm1, %xmm2, %xmm1
|
|
; ESTIMATE-NEXT: vxorps %xmm2, %xmm2, %xmm2
|
|
; ESTIMATE-NEXT: vcmpeqss %xmm2, %xmm0, %xmm0
|
|
; ESTIMATE-NEXT: vandnps %xmm1, %xmm0, %xmm0
|
|
; ESTIMATE-NEXT: retq
|
|
%call = tail call float @__sqrtf_finite(float %f) #1
|
|
ret float %call
|
|
}
|
|
|
|
|
|
define x86_fp80 @fld(x86_fp80 %ld) #0 {
|
|
; NORECIP-LABEL: fld:
|
|
; NORECIP: # BB#0:
|
|
; NORECIP-NEXT: fldt {{[0-9]+}}(%rsp)
|
|
; NORECIP-NEXT: fsqrt
|
|
; NORECIP-NEXT: retq
|
|
;
|
|
; ESTIMATE-LABEL: fld:
|
|
; ESTIMATE: # BB#0:
|
|
; ESTIMATE-NEXT: fldt {{[0-9]+}}(%rsp)
|
|
; ESTIMATE-NEXT: fsqrt
|
|
; ESTIMATE-NEXT: retq
|
|
%call = tail call x86_fp80 @__sqrtl_finite(x86_fp80 %ld) #1
|
|
ret x86_fp80 %call
|
|
}
|
|
|
|
|
|
|
|
define float @reciprocal_square_root(float %x) #0 {
|
|
; NORECIP-LABEL: reciprocal_square_root:
|
|
; NORECIP: # BB#0:
|
|
; NORECIP-NEXT: sqrtss %xmm0, %xmm1
|
|
; NORECIP-NEXT: movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
|
|
; NORECIP-NEXT: divss %xmm1, %xmm0
|
|
; NORECIP-NEXT: retq
|
|
;
|
|
; ESTIMATE-LABEL: reciprocal_square_root:
|
|
; ESTIMATE: # BB#0:
|
|
; ESTIMATE-NEXT: vrsqrtss %xmm0, %xmm0, %xmm1
|
|
; ESTIMATE-NEXT: vmulss %xmm1, %xmm1, %xmm2
|
|
; ESTIMATE-NEXT: vmulss %xmm2, %xmm0, %xmm0
|
|
; ESTIMATE-NEXT: vaddss {{.*}}(%rip), %xmm0, %xmm0
|
|
; ESTIMATE-NEXT: vmulss {{.*}}(%rip), %xmm1, %xmm1
|
|
; ESTIMATE-NEXT: vmulss %xmm0, %xmm1, %xmm0
|
|
; ESTIMATE-NEXT: retq
|
|
%sqrt = tail call float @llvm.sqrt.f32(float %x)
|
|
%div = fdiv fast float 1.0, %sqrt
|
|
ret float %div
|
|
}
|
|
|
|
define <4 x float> @reciprocal_square_root_v4f32(<4 x float> %x) #0 {
|
|
; NORECIP-LABEL: reciprocal_square_root_v4f32:
|
|
; NORECIP: # BB#0:
|
|
; NORECIP-NEXT: sqrtps %xmm0, %xmm1
|
|
; NORECIP-NEXT: movaps {{.*#+}} xmm0 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
|
|
; NORECIP-NEXT: divps %xmm1, %xmm0
|
|
; NORECIP-NEXT: retq
|
|
;
|
|
; ESTIMATE-LABEL: reciprocal_square_root_v4f32:
|
|
; ESTIMATE: # BB#0:
|
|
; ESTIMATE-NEXT: vrsqrtps %xmm0, %xmm1
|
|
; ESTIMATE-NEXT: vmulps %xmm1, %xmm1, %xmm2
|
|
; ESTIMATE-NEXT: vmulps %xmm2, %xmm0, %xmm0
|
|
; ESTIMATE-NEXT: vaddps {{.*}}(%rip), %xmm0, %xmm0
|
|
; ESTIMATE-NEXT: vmulps {{.*}}(%rip), %xmm1, %xmm1
|
|
; ESTIMATE-NEXT: vmulps %xmm0, %xmm1, %xmm0
|
|
; ESTIMATE-NEXT: retq
|
|
%sqrt = tail call <4 x float> @llvm.sqrt.v4f32(<4 x float> %x)
|
|
%div = fdiv fast <4 x float> <float 1.0, float 1.0, float 1.0, float 1.0>, %sqrt
|
|
ret <4 x float> %div
|
|
}
|
|
|
|
define <8 x float> @reciprocal_square_root_v8f32(<8 x float> %x) #0 {
|
|
; NORECIP-LABEL: reciprocal_square_root_v8f32:
|
|
; NORECIP: # BB#0:
|
|
; NORECIP-NEXT: sqrtps %xmm1, %xmm2
|
|
; NORECIP-NEXT: sqrtps %xmm0, %xmm3
|
|
; NORECIP-NEXT: movaps {{.*#+}} xmm1 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
|
|
; NORECIP-NEXT: movaps %xmm1, %xmm0
|
|
; NORECIP-NEXT: divps %xmm3, %xmm0
|
|
; NORECIP-NEXT: divps %xmm2, %xmm1
|
|
; NORECIP-NEXT: retq
|
|
;
|
|
; ESTIMATE-LABEL: reciprocal_square_root_v8f32:
|
|
; ESTIMATE: # BB#0:
|
|
; ESTIMATE-NEXT: vrsqrtps %ymm0, %ymm1
|
|
; ESTIMATE-NEXT: vmulps %ymm1, %ymm1, %ymm2
|
|
; ESTIMATE-NEXT: vmulps %ymm2, %ymm0, %ymm0
|
|
; ESTIMATE-NEXT: vaddps {{.*}}(%rip), %ymm0, %ymm0
|
|
; ESTIMATE-NEXT: vmulps {{.*}}(%rip), %ymm1, %ymm1
|
|
; ESTIMATE-NEXT: vmulps %ymm0, %ymm1, %ymm0
|
|
; ESTIMATE-NEXT: retq
|
|
%sqrt = tail call <8 x float> @llvm.sqrt.v8f32(<8 x float> %x)
|
|
%div = fdiv fast <8 x float> <float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0>, %sqrt
|
|
ret <8 x float> %div
|
|
}
|
|
|
|
|
|
attributes #0 = { "unsafe-fp-math"="true" }
|
|
attributes #1 = { nounwind readnone }
|
|
|