File: load-store-scalarization-cost.ll

package info (click to toggle)
llvm-toolchain-19 1%3A19.1.7-3~deb12u1
  • links: PTS, VCS
  • area: main
  • in suites: bookworm-proposed-updates
  • size: 1,998,492 kB
  • sloc: cpp: 6,951,680; ansic: 1,486,157; asm: 913,598; python: 232,024; f90: 80,126; objc: 75,281; lisp: 37,276; pascal: 16,990; sh: 10,009; ml: 5,058; perl: 4,724; awk: 3,523; makefile: 3,167; javascript: 2,504; xml: 892; fortran: 664; cs: 573
file content (33 lines) | stat: -rw-r--r-- 1,152 bytes parent folder | download | duplicates (12) 
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
29
30
31
32
33
 
; REQUIRES: asserts
; RUN: opt -mtriple=s390x-unknown-linux -mcpu=z13 -passes=loop-vectorize \
; RUN:   -force-vector-width=4 -debug-only=loop-vectorize \
; RUN:   -disable-output -enable-interleaved-mem-accesses=false < %s 2>&1 | \
; RUN:   FileCheck %s
;
; Check that a scalarized load/store does not get a cost for insterts/
; extracts, since z13 supports element load/store.

define void @fun(ptr %data, i64 %n) {
entry:
  br label %for.body

for.body:
  %i = phi i64 [ 0, %entry ], [ %i.next, %for.body ]
  %tmp0 = getelementptr inbounds i32, ptr %data, i64 %i
  %tmp1 = load i32, ptr %tmp0, align 4
  %tmp2 = add i32 %tmp1, 1
  store i32 %tmp2, ptr %tmp0, align 4
  %i.next = add nuw nsw i64 %i, 2
  %cond = icmp slt i64 %i.next, %n
  br i1 %cond, label %for.body, label %for.end

for.end:
  ret void

; CHECK: LV: Scalarizing:  %tmp1 = load i32, ptr %tmp0, align 4
; CHECK: LV: Scalarizing:  store i32 %tmp2, ptr %tmp0, align 4

; CHECK: LV: Found an estimated cost of 4 for VF 4 For instruction:   %tmp1 = load i32, ptr %tmp0, align 4
; CHECK: LV: Found an estimated cost of 4 for VF 4 For instruction:   store i32 %tmp2, ptr %tmp0, align 4
}