File: unroll-in-loop-vectorizer.ll

package info (click to toggle)
llvm-toolchain-14 1%3A14.0.6-12
  • links: PTS, VCS
  • area: main
  • in suites: bookworm
  • size: 1,496,180 kB
  • sloc: cpp: 5,593,972; ansic: 986,872; asm: 585,869; python: 184,223; objc: 72,530; lisp: 31,119; f90: 27,793; javascript: 9,780; pascal: 9,762; sh: 9,482; perl: 7,468; ml: 5,432; awk: 3,523; makefile: 2,538; xml: 953; cs: 573; fortran: 567
file content (28 lines) | stat: -rw-r--r-- 909 bytes parent folder | download | duplicates (15) 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
 
; RUN: opt -S -mtriple=amdgcn-unknown-amdhsa -mcpu=fiji -loop-vectorize < %s | FileCheck %s


; For AMDGPU, loop unroll in loop vectorizer is disabled when VF==1.
;
; CHECK-LABEL: @small_loop(
; CHECK: store i32
; CHECK-NOT: store i32
; CHECK: ret
define amdgpu_kernel void @small_loop(i32* nocapture %inArray, i32 %size) nounwind {
entry:
  %0 = icmp sgt i32 %size, 0
  br i1 %0, label %loop, label %exit

loop:                                          ; preds = %entry, %loop
  %iv = phi i32 [ %iv1, %loop ], [ 0, %entry ]
  %1 = getelementptr inbounds i32, i32* %inArray, i32 %iv
  %2 = load i32, i32* %1, align 4
  %3 = add nsw i32 %2, 6
  store i32 %3, i32* %1, align 4
  %iv1 = add i32 %iv, 1
;  %lftr.wideiv = trunc i64 %indvars.iv.next to i32
  %cond = icmp eq i32 %iv1, %size
  br i1 %cond, label %exit, label %loop

exit:                                         ; preds = %loop, %entry
  ret void
}