llvm-6502/test/CodeGen/PTX/fdiv-sm13.ll
Justin Holewinski 707fd44038 PTX: Adjust rounding modes
* rounding modes for fp add, mul, sub now use .rn
* float -> int rounding correctly uses .rzi not .rni
* 32bit fdiv for sm13 uses div.rn (instead of div.approx)
* 32bit fdiv for sm10 now uses div (instead of div.approx)

Approx is not IEEE 754 compatible (and should be optionally set by a flag to the backend instead). The .rn rounding modifier is the PTX default anyway, but it's better to be explicit.

All these modifiers should be available by using __fmul_rz functions for example, but support will need to be added for this in the backend.

Patch by Dan Bailey

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@133253 91177308-0d34-0410-b5e6-96231b3b80d8
2011-06-17 12:12:42 +00:00

16 lines
357 B
LLVM

; RUN: llc < %s -march=ptx32 -mattr=+sm13 | FileCheck %s
define ptx_device float @t1_f32(float %x, float %y) {
; CHECK: div.rn.f32 r0, r1, r2;
; CHECK-NEXT: ret;
%a = fdiv float %x, %y
ret float %a
}
define ptx_device double @t1_f64(double %x, double %y) {
; CHECK: div.rn.f64 rd0, rd1, rd2;
; CHECK-NEXT: ret;
%a = fdiv double %x, %y
ret double %a
}