1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-26 04:32:44 +01:00
llvm-mirror/test/CodeGen/NVPTX/fma.ll
Justin Holewinski 3021ef095b [NVPTX] Improve handling of FP fusion
We now consider the FPOpFusion flag when determining whether
to fuse ops.  We also explicitly emit add.rn when fusion is
disabled to prevent ptxas from fusing the operations on its
own.

llvm-svn: 213287
2014-07-17 18:10:09 +00:00

18 lines
529 B
LLVM

; RUN: llc < %s -march=nvptx -mcpu=sm_20 -fp-contract=fast | FileCheck %s
define ptx_device float @t1_f32(float %x, float %y, float %z) {
; CHECK: fma.rn.f32 %f{{[0-9]+}}, %f{{[0-9]+}}, %f{{[0-9]+}}, %f{{[0-9]+}};
; CHECK: ret;
%a = fmul float %x, %y
%b = fadd float %a, %z
ret float %b
}
define ptx_device double @t1_f64(double %x, double %y, double %z) {
; CHECK: fma.rn.f64 %fd{{[0-9]+}}, %fd{{[0-9]+}}, %fd{{[0-9]+}}, %fd{{[0-9]+}};
; CHECK: ret;
%a = fmul double %x, %y
%b = fadd double %a, %z
ret double %b
}