File: load-scalarization-cost-1.ll

package info (click to toggle)
llvm-toolchain-13 1%3A13.0.1-6~deb11u1
  • links: PTS, VCS
  • area: main
  • in suites: bullseye
  • size: 1,418,812 kB
  • sloc: cpp: 5,290,827; ansic: 996,570; asm: 544,593; python: 188,212; objc: 72,027; lisp: 30,291; f90: 25,395; sh: 24,900; javascript: 9,780; pascal: 9,398; perl: 7,484; ml: 5,432; awk: 3,523; makefile: 2,892; xml: 953; cs: 573; fortran: 539
file content (28 lines) | stat: -rw-r--r-- 972 bytes parent folder | download | duplicates (11) 
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 -mtriple=s390x-unknown-linux -mcpu=z13 -loop-vectorize \
; RUN:   -force-vector-width=4 -debug-only=loop-vectorize \
; RUN:   -enable-interleaved-mem-accesses=false -disable-output < %s 2>&1 \
; RUN:   | FileCheck %s
; REQUIRES: asserts
;
; Check that a scalarized load does not get a zero cost in a vectorized
; loop. It can only be folded into the add operand in the scalar loop.

define i32 @fun(i64* %data, i64 %n, i64 %s, i32* %Src) {
entry:
  br label %for.body

for.body:
  %iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
  %acc = phi i32 [ 0, %entry ], [ %acc_next, %for.body ]
  %gep = getelementptr inbounds i32, i32* %Src, i64 %iv
  %ld = load i32, i32* %gep
  %acc_next = add i32 %acc, %ld
  %iv.next = add nuw nsw i64 %iv, 2
  %cmp110.us = icmp slt i64 %iv.next, %n
  br i1 %cmp110.us, label %for.body, label %for.end

for.end:
  ret i32 %acc_next

; CHECK: Found an estimated cost of 4 for VF 4 For instruction:   %ld = load i32, i32* %gep
}