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
|
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -passes='lower-matrix-intrinsics' -S < %s | FileCheck %s
; Currently we only lower stores with shape information, but need to embed the
; matrix in a flat vector for function calls and returns.
define <8 x double> @strided_load_4x4(<8 x double> %in, ptr %Ptr) {
; CHECK-LABEL: @strided_load_4x4(
; CHECK-NEXT: [[SPLIT:%.*]] = shufflevector <8 x double> [[IN:%.*]], <8 x double> poison, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
; CHECK-NEXT: [[SPLIT1:%.*]] = shufflevector <8 x double> [[IN]], <8 x double> poison, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
; CHECK-NEXT: [[TMP1:%.*]] = extractelement <4 x double> [[SPLIT]], i64 0
; CHECK-NEXT: [[TMP2:%.*]] = insertelement <2 x double> poison, double [[TMP1]], i64 0
; CHECK-NEXT: [[TMP3:%.*]] = extractelement <4 x double> [[SPLIT1]], i64 0
; CHECK-NEXT: [[TMP4:%.*]] = insertelement <2 x double> [[TMP2]], double [[TMP3]], i64 1
; CHECK-NEXT: [[TMP5:%.*]] = extractelement <4 x double> [[SPLIT]], i64 1
; CHECK-NEXT: [[TMP6:%.*]] = insertelement <2 x double> poison, double [[TMP5]], i64 0
; CHECK-NEXT: [[TMP7:%.*]] = extractelement <4 x double> [[SPLIT1]], i64 1
; CHECK-NEXT: [[TMP8:%.*]] = insertelement <2 x double> [[TMP6]], double [[TMP7]], i64 1
; CHECK-NEXT: [[TMP9:%.*]] = extractelement <4 x double> [[SPLIT]], i64 2
; CHECK-NEXT: [[TMP10:%.*]] = insertelement <2 x double> poison, double [[TMP9]], i64 0
; CHECK-NEXT: [[TMP11:%.*]] = extractelement <4 x double> [[SPLIT1]], i64 2
; CHECK-NEXT: [[TMP12:%.*]] = insertelement <2 x double> [[TMP10]], double [[TMP11]], i64 1
; CHECK-NEXT: [[TMP13:%.*]] = extractelement <4 x double> [[SPLIT]], i64 3
; CHECK-NEXT: [[TMP14:%.*]] = insertelement <2 x double> poison, double [[TMP13]], i64 0
; CHECK-NEXT: [[TMP15:%.*]] = extractelement <4 x double> [[SPLIT1]], i64 3
; CHECK-NEXT: [[TMP16:%.*]] = insertelement <2 x double> [[TMP14]], double [[TMP15]], i64 1
; CHECK-NEXT: [[TMP17:%.*]] = shufflevector <2 x double> [[TMP4]], <2 x double> [[TMP8]], <4 x i32> <i32 0, i32 1, i32 2, i32 3>
; CHECK-NEXT: [[TMP18:%.*]] = shufflevector <2 x double> [[TMP12]], <2 x double> [[TMP16]], <4 x i32> <i32 0, i32 1, i32 2, i32 3>
; CHECK-NEXT: [[TMP19:%.*]] = shufflevector <4 x double> [[TMP17]], <4 x double> [[TMP18]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
; CHECK-NEXT: store <2 x double> [[TMP4]], ptr [[PTR:%.*]], align 8
; CHECK-NEXT: [[VEC_GEP:%.*]] = getelementptr double, ptr [[PTR]], i64 2
; CHECK-NEXT: store <2 x double> [[TMP8]], ptr [[VEC_GEP]], align 8
; CHECK-NEXT: [[VEC_GEP2:%.*]] = getelementptr double, ptr [[PTR]], i64 4
; CHECK-NEXT: store <2 x double> [[TMP12]], ptr [[VEC_GEP2]], align 8
; CHECK-NEXT: [[VEC_GEP3:%.*]] = getelementptr double, ptr [[PTR]], i64 6
; CHECK-NEXT: store <2 x double> [[TMP16]], ptr [[VEC_GEP3]], align 8
; CHECK-NEXT: call void @foo(<8 x double> [[TMP19]])
; CHECK-NEXT: ret <8 x double> [[TMP19]]
;
%transposed = call <8 x double> @llvm.matrix.transpose(<8 x double> %in, i32 4, i32 2)
store <8 x double> %transposed, ptr %Ptr, align 8
call void @foo(<8 x double> %transposed)
ret <8 x double> %transposed
}
declare <8 x double> @llvm.matrix.transpose(<8 x double>, i32, i32)
declare void @foo(<8 x double>)
|
