6502/llvm-6502
1
0
Fork 0
mirror of https://github.com/c64scene-ar/llvm-6502.git synced 2025-11-24 08:18:33 +00:00
Code Issues Projects Releases Wiki Activity

[NVPTX] Add (1.0 / sqrt(x)) => rsqrt(x) generation when allowable by FP flags

Browse Source 
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@185178 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Justin Holewinski
2013-06-28 17:58:13 +00:00
parent ac78a0645d
commit f51a22e815
2 changed files with 25 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
test/CodeGen/NVPTX/rsqrt.ll Normal file
View File

@@ -0,0 +1,13 @@
; RUN: llc < %s -march=nvptx -mcpu=sm_20 -nvptx-prec-divf32=1 -nvptx-prec-sqrtf32=0 | FileCheck %s
target datalayout = "e-p:32:32:32-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v16:16:16-v32:32:32-v64:64:64-v128:128:128-n16:32:64"
declare float @llvm.nvvm.sqrt.f(float)
define float @foo(float %a) {
; CHECK: rsqrt.approx.f32
%val = tail call float @llvm.nvvm.sqrt.f(float %a)
%ret = fdiv float 1.0, %val
ret float %ret
}