File: streaming-vectorization.ll

package info (click to toggle)
llvm-toolchain-21 1%3A21.1.6-3
  • links: PTS, VCS
  • area: main
  • in suites: sid
  • size: 2,245,028 kB
  • sloc: cpp: 7,619,726; ansic: 1,434,018; asm: 1,058,748; python: 252,740; f90: 94,671; objc: 70,685; lisp: 42,813; pascal: 18,401; sh: 8,601; ml: 5,111; perl: 4,720; makefile: 3,675; awk: 3,523; javascript: 2,409; xml: 892; fortran: 770
file content (56 lines) | stat: -rw-r--r-- 2,028 bytes parent folder | download | duplicates (3)
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
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
; REQUIRES: asserts
; RUN: opt -S -passes=loop-vectorize -debug-only=loop-vectorize --disable-output < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,NOVEC
; RUN: opt -S -passes=loop-vectorize -debug-only=loop-vectorize --disable-output -enable-scalable-autovec-in-streaming-mode < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,VEC

target triple = "aarch64-unknown-linux-gnu"

define void @normal_function(ptr %a, ptr %b, ptr %c) #0 {
; CHECK: LV: Checking a loop in 'normal_function'
; CHECK: LV: Scalable vectorization is available
entry:
  br label %loop

loop:
  %iv = phi i64 [ 0, %entry ], [ %iv.next, %loop ]
  %arrayidx = getelementptr inbounds i32, ptr %c, i64 %iv
  %0 = load i32, ptr %arrayidx, align 4
  %arrayidx2 = getelementptr inbounds i8, ptr %b, i64 %iv
  %1 = load i8, ptr %arrayidx2, align 4
  %zext = zext i8 %1 to i32
  %add = add nsw i32 %zext, %0
  %arrayidx5 = getelementptr inbounds i32, ptr %a, i64 %iv
  store i32 %add, ptr %arrayidx5, align 4
  %iv.next = add nuw nsw i64 %iv, 1
  %exitcond.not = icmp eq i64 %iv.next, 1024
  br i1 %exitcond.not, label %exit, label %loop

exit:
  ret void
}

define void @streaming_function(ptr %a, ptr %b, ptr %c) #0 "aarch64_pstate_sm_enabled" {
; CHECK: LV: Checking a loop in 'streaming_function'
; VEC: LV: Scalable vectorization is available
; NOVEC: LV: Scalable vectorization is explicitly disabled
entry:
  br label %loop

loop:
  %iv = phi i64 [ 0, %entry ], [ %iv.next, %loop ]
  %arrayidx = getelementptr inbounds i32, ptr %c, i64 %iv
  %0 = load i32, ptr %arrayidx, align 4
  %arrayidx2 = getelementptr inbounds i8, ptr %b, i64 %iv
  %1 = load i8, ptr %arrayidx2, align 4
  %zext = zext i8 %1 to i32
  %add = add nsw i32 %zext, %0
  %arrayidx5 = getelementptr inbounds i32, ptr %a, i64 %iv
  store i32 %add, ptr %arrayidx5, align 4
  %iv.next = add nuw nsw i64 %iv, 1
  %exitcond.not = icmp eq i64 %iv.next, 1024
  br i1 %exitcond.not, label %exit, label %loop

exit:
  ret void
}

attributes #0 = { vscale_range(1, 16) "target-features"="+sve,+sme" }