66 lines
3.7 KiB
LLVM
66 lines
3.7 KiB
LLVM
; 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
|
|
}
|