File: non-instr-bitcast.ll

package info (click to toggle)
llvm-toolchain-20 1%3A20.1.6-1~exp1
  • links: PTS, VCS
  • area: main
  • in suites: experimental
  • size: 2,111,304 kB
  • sloc: cpp: 7,438,677; ansic: 1,393,822; asm: 1,012,926; python: 241,650; f90: 86,635; objc: 75,479; lisp: 42,144; pascal: 17,286; sh: 10,027; ml: 5,082; perl: 4,730; awk: 3,523; makefile: 3,349; javascript: 2,251; xml: 892; fortran: 672
file content (14 lines) | stat: -rw-r--r-- 821 bytes parent folder | download | duplicates (14) 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
 
; RUN: opt -mtriple=nvptx64-nvidia-cuda -passes=load-store-vectorizer -S -o - %s | FileCheck %s

; Load from a constant.  This can be vectorized, but shouldn't crash us.

@global = internal addrspace(1) constant [4 x float] [float 0xBF71111120000000, float 0x3F70410420000000, float 0xBF81111120000000, float 0x3FB5555560000000], align 4

define void @foo() {
  ; CHECK: load <4 x float>
  %a = load float, ptr addrspace(1) @global, align 16
  %b = load float, ptr addrspace(1) getelementptr inbounds ([4 x float], ptr addrspace(1) @global, i64 0, i64 1), align 4
  %c = load float, ptr addrspace(1) getelementptr inbounds ([4 x float], ptr addrspace(1) @global, i64 0, i64 2), align 4
  %d = load float, ptr addrspace(1) getelementptr inbounds ([4 x float], ptr addrspace(1) @global, i64 0, i64 3), align 4
  ret void
}