6502/llvm-6502
1
0
Fork 0
mirror of https://github.com/c64scene-ar/llvm-6502.git synced 2025-11-02 22:23:10 +00:00
Code Issues Projects Releases Wiki Activity

Use rsqrt (X86) to speed up reciprocal square root calcs

Browse Source 
This is a first step for generating SSE rsqrt instructions for
reciprocal square root calcs when fast-math is allowed.

For now, be conservative and only enable this for AMD btver2
where performance improves significantly - for example, 29%
on llvm/projects/test-suite/SingleSource/Benchmarks/BenchmarkGame/n-body.c
(if we convert the data type to single-precision float).

This patch adds a two constant version of the Newton-Raphson
refinement algorithm to DAGCombiner that can be selected by any target
via a parameter returned by getRsqrtEstimate()..

See PR20900 for more details:
http://llvm.org/bugs/show_bug.cgi?id=20900

Differential Revision: http://reviews.llvm.org/D5658



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@220570 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Sanjay Patel
2014-10-24 17:02:16 +00:00
parent 2992ea0cb5
commit a46f06efe2
10 changed files with 185 additions and 46 deletions
Download Patch File Download Diff File Expand all files Collapse all files

55
test/CodeGen/X86/sqrt-fastmath.ll
View File

@@ -1,4 +1,5 @@
; RUN: llc < %s -mcpu=core2 | FileCheck %s
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=core2 | FileCheck %s
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=btver2 | FileCheck %s --check-prefix=BTVER2
; generated using "clang -S -O2 -ffast-math -emit-llvm sqrt.c" from
; #include <math.h>
@@ -52,9 +53,59 @@ entry:
ret x86_fp80 %call
}
; Function Attrs: nounwind readnone
declare x86_fp80 @__sqrtl_finite(x86_fp80) #1
; If the target's sqrtss and divss instructions are substantially
; slower than rsqrtss with a Newton-Raphson refinement, we should
; generate the estimate sequence.
define float @reciprocal_square_root(float %x) #0 {
%sqrt = tail call float @llvm.sqrt.f32(float %x)
%div = fdiv fast float 1.0, %sqrt
ret float %div
; CHECK-LABEL: reciprocal_square_root:
; CHECK: sqrtss
; CHECK-NEXT: movss
; CHECK-NEXT: divss
; CHECK-NEXT: retq
; BTVER2-LABEL: reciprocal_square_root:
; BTVER2: vrsqrtss
; BTVER2-NEXT: vmulss
; BTVER2-NEXT: vmulss
; BTVER2-NEXT: vmulss
; BTVER2-NEXT: vaddss
; BTVER2-NEXT: vmulss
; BTVER2-NEXT: retq
}
declare float @llvm.sqrt.f32(float) #1
; If the target's sqrtps and divps instructions are substantially
; slower than rsqrtps with a Newton-Raphson refinement, we should
; generate the estimate sequence.
define <4 x float> @reciprocal_square_root_v4f32(<4 x float> %x) #0 {
%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
; CHECK-LABEL: reciprocal_square_root_v4f32:
; CHECK: sqrtps
; CHECK-NEXT: movaps
; CHECK-NEXT: divps
; CHECK-NEXT: retq
; BTVER2-LABEL: reciprocal_square_root_v4f32:
; BTVER2: vrsqrtps
; BTVER2-NEXT: vmulps
; BTVER2-NEXT: vmulps
; BTVER2-NEXT: vmulps
; BTVER2-NEXT: vaddps
; BTVER2-NEXT: vmulps
; BTVER2-NEXT: retq
}
declare <4 x float> @llvm.sqrt.v4f32(<4 x float>) #1
attributes #0 = { nounwind readnone uwtable "less-precise-fpmad"="false" "no-frame-pointer-elim"="false" "no-infs-fp-math"="true" "no-nans-fp-math"="true" "unsafe-fp-math"="true" "use-soft-float"="false" }
attributes #1 = { nounwind readnone "less-precise-fpmad"="false" "no-frame-pointer-elim"="false" "no-infs-fp-math"="true" "no-nans-fp-math"="true" "unsafe-fp-math"="true" "use-soft-float"="false" }
attributes #2 = { nounwind readnone }