File: replace_unsupported_masked_mem_intrin.ll

package info (click to toggle)
llvm-toolchain-11 1%3A11.0.1-2
  • links: PTS, VCS
  • area: main
  • in suites: bullseye
  • size: 995,808 kB
  • sloc: cpp: 4,767,656; ansic: 760,916; asm: 477,436; python: 170,940; objc: 69,804; lisp: 29,914; sh: 23,855; f90: 18,173; pascal: 7,551; perl: 7,471; ml: 5,603; awk: 3,489; makefile: 2,573; xml: 915; cs: 573; fortran: 503; javascript: 452
file content (42 lines) | stat: -rw-r--r-- 1,724 bytes parent folder | download | duplicates (13)
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
; RUN: llc -O0 -mtriple=x86_64-unknown-linux-gnu -mattr=+sse,+sse2 < %s -o /dev/null
; pr33001 - Check that llc doesn't crash when running with O0 option.

; RUN: llc -O2 -opt-bisect-limit=0 -mtriple=x86_64-unknown-linux-gnu -mattr=+sse,+sse2 < %s -o /dev/null
; Check that llc doesn't crash due to ScalarizeMaskedMemIntring not being run
; because of opt-bisect-limit that in turn causes crash in instruction selection
; for unsupported gather/scatter.

target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-unknown-linux-gnu"

define <4 x i32> @test_masked_load(<4 x i32>* %base, <4 x i1> %mask) {
  %res = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %base, i32 4, <4 x i1> %mask, <4 x i32> zeroinitializer)
  ret <4 x i32> %res
}

declare <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>*, i32, <4 x i1>, <4 x i32>)


define void @test_masked_store(<4 x i32>* %base, <4 x i32> %value, <4 x i1> %mask) {
  call void @llvm.masked.store.v4i32.p0v4i32(<4 x i32> %value, <4 x i32>* %base, i32 4, <4 x i1> %mask)
  ret void
}

declare void @llvm.masked.store.v4i32.p0v4i32(<4 x i32>, <4 x i32>*, i32, <4 x i1>)


define <4 x i32> @llvm_masked_gather(<4 x i32*> %ptrs, <4 x i1> %mask) {
  %res = call <4 x i32> @llvm.masked.gather.v4i32(<4 x i32*> %ptrs, i32 4, <4 x i1> %mask, <4 x i32> undef)
  ret <4 x i32> %res
}

declare <4 x i32> @llvm.masked.gather.v4i32(<4 x i32*>, i32, <4 x i1>, <4 x i32>)


define void @llvm_masked_scatter(<4 x i32*> %ptrs, <4 x i32> %value, <4 x i1> %mask) {
  call void @llvm.masked.scatter.v4i32(<4 x i32> %value, <4 x i32*> %ptrs, i32 4, <4 x i1> %mask)
  ret void
}

declare void @llvm.masked.scatter.v4i32(<4 x i32>, <4 x i32*>, i32, <4 x i1>)