File: strided-load-i32.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 (65 lines) | stat: -rw-r--r-- 3,739 bytes parent folder | download | duplicates (6)
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
57
58
59
60
61
62
63
64
65
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -lower-matrix-intrinsics -S < %s | FileCheck %s
; RUN: opt -passes='lower-matrix-intrinsics' -S < %s | FileCheck %s

define <9 x i32> @strided_load_3x3(i32* %in, i64 %stride) {
; CHECK-LABEL: @strided_load_3x3(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[VEC_START:%.*]] = mul i64 0, [[STRIDE:%.*]]
; CHECK-NEXT:    [[VEC_GEP:%.*]] = getelementptr i32, i32* [[IN:%.*]], i64 [[VEC_START]]
; CHECK-NEXT:    [[VEC_CAST:%.*]] = bitcast i32* [[VEC_GEP]] to <3 x i32>*
; CHECK-NEXT:    [[COL_LOAD:%.*]] = load <3 x i32>, <3 x i32>* [[VEC_CAST]], align 4
; CHECK-NEXT:    [[VEC_START1:%.*]] = mul i64 1, [[STRIDE]]
; CHECK-NEXT:    [[VEC_GEP2:%.*]] = getelementptr i32, i32* [[IN]], i64 [[VEC_START1]]
; CHECK-NEXT:    [[VEC_CAST3:%.*]] = bitcast i32* [[VEC_GEP2]] to <3 x i32>*
; CHECK-NEXT:    [[COL_LOAD4:%.*]] = load <3 x i32>, <3 x i32>* [[VEC_CAST3]], align 4
; CHECK-NEXT:    [[VEC_START5:%.*]] = mul i64 2, [[STRIDE]]
; CHECK-NEXT:    [[VEC_GEP6:%.*]] = getelementptr i32, i32* [[IN]], i64 [[VEC_START5]]
; CHECK-NEXT:    [[VEC_CAST7:%.*]] = bitcast i32* [[VEC_GEP6]] to <3 x i32>*
; CHECK-NEXT:    [[COL_LOAD8:%.*]] = load <3 x i32>, <3 x i32>* [[VEC_CAST7]], align 4
; CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <3 x i32> [[COL_LOAD]], <3 x i32> [[COL_LOAD4]], <6 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5>
; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <3 x i32> [[COL_LOAD8]], <3 x i32> poison, <6 x i32> <i32 0, i32 1, i32 2, i32 undef, i32 undef, i32 undef>
; CHECK-NEXT:    [[TMP2:%.*]] = shufflevector <6 x i32> [[TMP0]], <6 x i32> [[TMP1]], <9 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8>
; CHECK-NEXT:    ret <9 x i32> [[TMP2]]
;
entry:
  %load = call <9 x i32> @llvm.matrix.column.major.load(i32* %in, i64 %stride, i1 false, i32 3, i32 3)
  ret <9 x i32> %load
}

declare <9 x i32> @llvm.matrix.column.major.load(i32*, i64, i1, i32, i32)

define <9 x i32> @strided_load_9x1(i32* %in, i64 %stride) {
; CHECK-LABEL: @strided_load_9x1(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[VEC_START:%.*]] = mul i64 0, [[STRIDE:%.*]]
; CHECK-NEXT:    [[VEC_GEP:%.*]] = getelementptr i32, i32* [[IN:%.*]], i64 [[VEC_START]]
; CHECK-NEXT:    [[VEC_CAST:%.*]] = bitcast i32* [[VEC_GEP]] to <9 x i32>*
; CHECK-NEXT:    [[COL_LOAD:%.*]] = load <9 x i32>, <9 x i32>* [[VEC_CAST]], align 4
; CHECK-NEXT:    ret <9 x i32> [[COL_LOAD]]
;
entry:
  %load = call <9 x i32> @llvm.matrix.column.major.load(i32* %in, i64 %stride, i1 false, i32 9, i32 1)
  ret <9 x i32> %load
}

declare <8 x i32> @llvm.matrix.column.major.load.v8i32(i32*, i64, i1, i32, i32)

define <8 x i32> @strided_load_4x2(i32* %in, i64 %stride) {
; CHECK-LABEL: @strided_load_4x2(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[VEC_START:%.*]] = mul i64 0, [[STRIDE:%.*]]
; CHECK-NEXT:    [[VEC_GEP:%.*]] = getelementptr i32, i32* [[IN:%.*]], i64 [[VEC_START]]
; CHECK-NEXT:    [[VEC_CAST:%.*]] = bitcast i32* [[VEC_GEP]] to <4 x i32>*
; CHECK-NEXT:    [[COL_LOAD:%.*]] = load <4 x i32>, <4 x i32>* [[VEC_CAST]], align 4
; CHECK-NEXT:    [[VEC_START1:%.*]] = mul i64 1, [[STRIDE]]
; CHECK-NEXT:    [[VEC_GEP2:%.*]] = getelementptr i32, i32* [[IN]], i64 [[VEC_START1]]
; CHECK-NEXT:    [[VEC_CAST3:%.*]] = bitcast i32* [[VEC_GEP2]] to <4 x i32>*
; CHECK-NEXT:    [[COL_LOAD4:%.*]] = load <4 x i32>, <4 x i32>* [[VEC_CAST3]], align 4
; CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <4 x i32> [[COL_LOAD]], <4 x i32> [[COL_LOAD4]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
; CHECK-NEXT:    ret <8 x i32> [[TMP0]]
;
entry:
  %load = call <8 x i32> @llvm.matrix.column.major.load.v8i32(i32* %in, i64 %stride, i1 false, i32 4, i32 2)
  ret <8 x i32> %load
}