1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-24 11:42:57 +01:00
llvm-mirror/test/CodeGen/NVPTX/bug22246.ll
Justin Holewinski a0a83cc9da [NVPTX] Generate a more optimal sequence for select of i1
Instead of creating a pattern like "(p && a) || ((!p) && b)",
just expand the i8 operands to i32 and perform the selp on them.

Fixes PR22246

llvm-svn: 227123
2015-01-26 19:52:20 +00:00

15 lines
500 B
LLVM

; RUN: llc < %s -march=nvptx -mcpu=sm_20 | FileCheck %s
target datalayout = "e-i64:64-v16:16-v32:32-n16:32:64"
target triple = "nvptx64-nvidia-cuda"
; CHECK-LABEL: _Z3foobbbPb
define void @_Z3foobbbPb(i1 zeroext %p1, i1 zeroext %p2, i1 zeroext %p3, i8* nocapture %output) {
entry:
; CHECK: selp.b32 %r{{[0-9]+}}, %r{{[0-9]+}}, %r{{[0-9]+}}, %p{{[0-9]+}}
%.sink.v = select i1 %p1, i1 %p2, i1 %p3
%frombool5 = zext i1 %.sink.v to i8
store i8 %frombool5, i8* %output, align 1
ret void
}