forked from OSchip/llvm-project
[llvm] [MatrixIntrinsics] Add row-major support for llvm.matrix.transpose
Summary: Only column-major was supported so far. This adds row-major support as well. Note that we probably also want very efficient SIMD implementations for the various target platforms. Bug: https://bugs.llvm.org/show_bug.cgi?id=46085 Reviewers: nicolasvasilache, reidtatge, bkramer, fhahn, ftynse, andydavis1, craig.topper, dcaballe, mehdi_amini, anemet Reviewed By: fhahn Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D80673
This commit is contained in:
aartbik
parent
47ffc81830
commit
f719e7d9e7
|
|
@ -1294,24 +1294,24 @@ public:
|
|||
VectorType *VectorTy = cast<VectorType>(InputVal->getType());
|
||||
ShapeInfo ArgShape(Inst->getArgOperand(1), Inst->getArgOperand(2));
|
||||
MatrixTy InputMatrix = getMatrix(InputVal, ArgShape, Builder);
|
||||
assert(InputMatrix.isColumnMajor() &&
|
||||
"Row-major code-gen not supported yet!");
|
||||
|
||||
for (unsigned Row = 0; Row < ArgShape.NumRows; ++Row) {
|
||||
// Build a single column vector for this row. First initialize it.
|
||||
Value *ResultColumn = UndefValue::get(
|
||||
VectorType::get(VectorTy->getElementType(), ArgShape.NumColumns));
|
||||
const unsigned NewNumVecs =
|
||||
InputMatrix.isColumnMajor() ? ArgShape.NumRows : ArgShape.NumColumns;
|
||||
const unsigned NewNumElts =
|
||||
InputMatrix.isColumnMajor() ? ArgShape.NumColumns : ArgShape.NumRows;
|
||||
|
||||
// Go through the elements of this row and insert it into the resulting
|
||||
// column vector.
|
||||
for (auto C : enumerate(InputMatrix.columns())) {
|
||||
Value *Elt = Builder.CreateExtractElement(C.value(), Row);
|
||||
// We insert at index Column since that is the row index after the
|
||||
// transpose.
|
||||
ResultColumn =
|
||||
Builder.CreateInsertElement(ResultColumn, Elt, C.index());
|
||||
for (unsigned I = 0; I < NewNumVecs; ++I) {
|
||||
// Build a single result vector. First initialize it.
|
||||
Value *ResultVector = UndefValue::get(
|
||||
VectorType::get(VectorTy->getElementType(), NewNumElts));
|
||||
// Go through the old elements and insert it into the resulting vector.
|
||||
for (auto J : enumerate(InputMatrix.vectors())) {
|
||||
Value *Elt = Builder.CreateExtractElement(J.value(), I);
|
||||
// Row and column indices are transposed.
|
||||
ResultVector =
|
||||
Builder.CreateInsertElement(ResultVector, Elt, J.index());
|
||||
}
|
||||
Result.addVector(ResultColumn);
|
||||
Result.addVector(ResultVector);
|
||||
}
|
||||
|
||||
// TODO: Improve estimate of operations needed for transposes. Currently we
|
||||
|
|
|
|||
|
|
@ -0,0 +1,111 @@
|
|||
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
|
||||
; RUN: opt -lower-matrix-intrinsics -matrix-default-layout=row-major -S < %s | FileCheck --check-prefix=RM %s
|
||||
|
||||
define <8 x double> @transpose(<8 x double> %a) {
|
||||
; RM-LABEL: @transpose(
|
||||
; RM-NEXT: entry:
|
||||
; RM-NEXT: [[SPLIT:%.*]] = shufflevector <8 x double> [[A:%.*]], <8 x double> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
|
||||
; RM-NEXT: [[SPLIT1:%.*]] = shufflevector <8 x double> [[A]], <8 x double> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
|
||||
; RM-NEXT: [[TMP0:%.*]] = extractelement <4 x double> [[SPLIT]], i64 0
|
||||
; RM-NEXT: [[TMP1:%.*]] = insertelement <2 x double> undef, double [[TMP0]], i64 0
|
||||
; RM-NEXT: [[TMP2:%.*]] = extractelement <4 x double> [[SPLIT1]], i64 0
|
||||
; RM-NEXT: [[TMP3:%.*]] = insertelement <2 x double> [[TMP1]], double [[TMP2]], i64 1
|
||||
; RM-NEXT: [[TMP4:%.*]] = extractelement <4 x double> [[SPLIT]], i64 1
|
||||
; RM-NEXT: [[TMP5:%.*]] = insertelement <2 x double> undef, double [[TMP4]], i64 0
|
||||
; RM-NEXT: [[TMP6:%.*]] = extractelement <4 x double> [[SPLIT1]], i64 1
|
||||
; RM-NEXT: [[TMP7:%.*]] = insertelement <2 x double> [[TMP5]], double [[TMP6]], i64 1
|
||||
; RM-NEXT: [[TMP8:%.*]] = extractelement <4 x double> [[SPLIT]], i64 2
|
||||
; RM-NEXT: [[TMP9:%.*]] = insertelement <2 x double> undef, double [[TMP8]], i64 0
|
||||
; RM-NEXT: [[TMP10:%.*]] = extractelement <4 x double> [[SPLIT1]], i64 2
|
||||
; RM-NEXT: [[TMP11:%.*]] = insertelement <2 x double> [[TMP9]], double [[TMP10]], i64 1
|
||||
; RM-NEXT: [[TMP12:%.*]] = extractelement <4 x double> [[SPLIT]], i64 3
|
||||
; RM-NEXT: [[TMP13:%.*]] = insertelement <2 x double> undef, double [[TMP12]], i64 0
|
||||
; RM-NEXT: [[TMP14:%.*]] = extractelement <4 x double> [[SPLIT1]], i64 3
|
||||
; RM-NEXT: [[TMP15:%.*]] = insertelement <2 x double> [[TMP13]], double [[TMP14]], i64 1
|
||||
; RM-NEXT: [[TMP16:%.*]] = shufflevector <2 x double> [[TMP3]], <2 x double> [[TMP7]], <4 x i32> <i32 0, i32 1, i32 2, i32 3>
|
||||
; RM-NEXT: [[TMP17:%.*]] = shufflevector <2 x double> [[TMP11]], <2 x double> [[TMP15]], <4 x i32> <i32 0, i32 1, i32 2, i32 3>
|
||||
; RM-NEXT: [[TMP18:%.*]] = shufflevector <4 x double> [[TMP16]], <4 x double> [[TMP17]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
|
||||
; RM-NEXT: ret <8 x double> [[TMP18]]
|
||||
;
|
||||
entry:
|
||||
%c = call <8 x double> @llvm.matrix.transpose(<8 x double> %a, i32 2, i32 4)
|
||||
ret <8 x double> %c
|
||||
}
|
||||
|
||||
declare <8 x double> @llvm.matrix.transpose(<8 x double>, i32, i32)
|
||||
|
||||
define <8 x double> @transpose_single_column(<8 x double> %a) {
|
||||
; RM-LABEL: @transpose_single_column(
|
||||
; RM-NEXT: entry:
|
||||
; RM-NEXT: [[SPLIT:%.*]] = shufflevector <8 x double> [[A:%.*]], <8 x double> undef, <1 x i32> zeroinitializer
|
||||
; RM-NEXT: [[SPLIT1:%.*]] = shufflevector <8 x double> [[A]], <8 x double> undef, <1 x i32> <i32 1>
|
||||
; RM-NEXT: [[SPLIT2:%.*]] = shufflevector <8 x double> [[A]], <8 x double> undef, <1 x i32> <i32 2>
|
||||
; RM-NEXT: [[SPLIT3:%.*]] = shufflevector <8 x double> [[A]], <8 x double> undef, <1 x i32> <i32 3>
|
||||
; RM-NEXT: [[SPLIT4:%.*]] = shufflevector <8 x double> [[A]], <8 x double> undef, <1 x i32> <i32 4>
|
||||
; RM-NEXT: [[SPLIT5:%.*]] = shufflevector <8 x double> [[A]], <8 x double> undef, <1 x i32> <i32 5>
|
||||
; RM-NEXT: [[SPLIT6:%.*]] = shufflevector <8 x double> [[A]], <8 x double> undef, <1 x i32> <i32 6>
|
||||
; RM-NEXT: [[SPLIT7:%.*]] = shufflevector <8 x double> [[A]], <8 x double> undef, <1 x i32> <i32 7>
|
||||
; RM-NEXT: [[TMP0:%.*]] = extractelement <1 x double> [[SPLIT]], i64 0
|
||||
; RM-NEXT: [[TMP1:%.*]] = insertelement <8 x double> undef, double [[TMP0]], i64 0
|
||||
; RM-NEXT: [[TMP2:%.*]] = extractelement <1 x double> [[SPLIT1]], i64 0
|
||||
; RM-NEXT: [[TMP3:%.*]] = insertelement <8 x double> [[TMP1]], double [[TMP2]], i64 1
|
||||
; RM-NEXT: [[TMP4:%.*]] = extractelement <1 x double> [[SPLIT2]], i64 0
|
||||
; RM-NEXT: [[TMP5:%.*]] = insertelement <8 x double> [[TMP3]], double [[TMP4]], i64 2
|
||||
; RM-NEXT: [[TMP6:%.*]] = extractelement <1 x double> [[SPLIT3]], i64 0
|
||||
; RM-NEXT: [[TMP7:%.*]] = insertelement <8 x double> [[TMP5]], double [[TMP6]], i64 3
|
||||
; RM-NEXT: [[TMP8:%.*]] = extractelement <1 x double> [[SPLIT4]], i64 0
|
||||
; RM-NEXT: [[TMP9:%.*]] = insertelement <8 x double> [[TMP7]], double [[TMP8]], i64 4
|
||||
; RM-NEXT: [[TMP10:%.*]] = extractelement <1 x double> [[SPLIT5]], i64 0
|
||||
; RM-NEXT: [[TMP11:%.*]] = insertelement <8 x double> [[TMP9]], double [[TMP10]], i64 5
|
||||
; RM-NEXT: [[TMP12:%.*]] = extractelement <1 x double> [[SPLIT6]], i64 0
|
||||
; RM-NEXT: [[TMP13:%.*]] = insertelement <8 x double> [[TMP11]], double [[TMP12]], i64 6
|
||||
; RM-NEXT: [[TMP14:%.*]] = extractelement <1 x double> [[SPLIT7]], i64 0
|
||||
; RM-NEXT: [[TMP15:%.*]] = insertelement <8 x double> [[TMP13]], double [[TMP14]], i64 7
|
||||
; RM-NEXT: ret <8 x double> [[TMP15]]
|
||||
;
|
||||
entry:
|
||||
%c = call <8 x double> @llvm.matrix.transpose(<8 x double> %a, i32 8, i32 1)
|
||||
ret <8 x double> %c
|
||||
}
|
||||
|
||||
declare <12 x double> @llvm.matrix.transpose.v12f64(<12 x double>, i32, i32)
|
||||
|
||||
define <12 x double> @transpose_double_3x4(<12 x double> %a) {
|
||||
; RM-LABEL: @transpose_double_3x4(
|
||||
; RM-NEXT: entry:
|
||||
; RM-NEXT: [[SPLIT:%.*]] = shufflevector <12 x double> [[A:%.*]], <12 x double> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
|
||||
; RM-NEXT: [[SPLIT1:%.*]] = shufflevector <12 x double> [[A]], <12 x double> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
|
||||
; RM-NEXT: [[SPLIT2:%.*]] = shufflevector <12 x double> [[A]], <12 x double> undef, <4 x i32> <i32 8, i32 9, i32 10, i32 11>
|
||||
; RM-NEXT: [[TMP0:%.*]] = extractelement <4 x double> [[SPLIT]], i64 0
|
||||
; RM-NEXT: [[TMP1:%.*]] = insertelement <3 x double> undef, double [[TMP0]], i64 0
|
||||
; RM-NEXT: [[TMP2:%.*]] = extractelement <4 x double> [[SPLIT1]], i64 0
|
||||
; RM-NEXT: [[TMP3:%.*]] = insertelement <3 x double> [[TMP1]], double [[TMP2]], i64 1
|
||||
; RM-NEXT: [[TMP4:%.*]] = extractelement <4 x double> [[SPLIT2]], i64 0
|
||||
; RM-NEXT: [[TMP5:%.*]] = insertelement <3 x double> [[TMP3]], double [[TMP4]], i64 2
|
||||
; RM-NEXT: [[TMP6:%.*]] = extractelement <4 x double> [[SPLIT]], i64 1
|
||||
; RM-NEXT: [[TMP7:%.*]] = insertelement <3 x double> undef, double [[TMP6]], i64 0
|
||||
; RM-NEXT: [[TMP8:%.*]] = extractelement <4 x double> [[SPLIT1]], i64 1
|
||||
; RM-NEXT: [[TMP9:%.*]] = insertelement <3 x double> [[TMP7]], double [[TMP8]], i64 1
|
||||
; RM-NEXT: [[TMP10:%.*]] = extractelement <4 x double> [[SPLIT2]], i64 1
|
||||
; RM-NEXT: [[TMP11:%.*]] = insertelement <3 x double> [[TMP9]], double [[TMP10]], i64 2
|
||||
; RM-NEXT: [[TMP12:%.*]] = extractelement <4 x double> [[SPLIT]], i64 2
|
||||
; RM-NEXT: [[TMP13:%.*]] = insertelement <3 x double> undef, double [[TMP12]], i64 0
|
||||
; RM-NEXT: [[TMP14:%.*]] = extractelement <4 x double> [[SPLIT1]], i64 2
|
||||
; RM-NEXT: [[TMP15:%.*]] = insertelement <3 x double> [[TMP13]], double [[TMP14]], i64 1
|
||||
; RM-NEXT: [[TMP16:%.*]] = extractelement <4 x double> [[SPLIT2]], i64 2
|
||||
; RM-NEXT: [[TMP17:%.*]] = insertelement <3 x double> [[TMP15]], double [[TMP16]], i64 2
|
||||
; RM-NEXT: [[TMP18:%.*]] = extractelement <4 x double> [[SPLIT]], i64 3
|
||||
; RM-NEXT: [[TMP19:%.*]] = insertelement <3 x double> undef, double [[TMP18]], i64 0
|
||||
; RM-NEXT: [[TMP20:%.*]] = extractelement <4 x double> [[SPLIT1]], i64 3
|
||||
; RM-NEXT: [[TMP21:%.*]] = insertelement <3 x double> [[TMP19]], double [[TMP20]], i64 1
|
||||
; RM-NEXT: [[TMP22:%.*]] = extractelement <4 x double> [[SPLIT2]], i64 3
|
||||
; RM-NEXT: [[TMP23:%.*]] = insertelement <3 x double> [[TMP21]], double [[TMP22]], i64 2
|
||||
; RM-NEXT: [[TMP24:%.*]] = shufflevector <3 x double> [[TMP5]], <3 x double> [[TMP11]], <6 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5>
|
||||
; RM-NEXT: [[TMP25:%.*]] = shufflevector <3 x double> [[TMP17]], <3 x double> [[TMP23]], <6 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5>
|
||||
; RM-NEXT: [[TMP26:%.*]] = shufflevector <6 x double> [[TMP24]], <6 x double> [[TMP25]], <12 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11>
|
||||
; RM-NEXT: ret <12 x double> [[TMP26]]
|
||||
;
|
||||
entry:
|
||||
%c = call <12 x double> @llvm.matrix.transpose.v12f64(<12 x double> %a, i32 3, i32 4)
|
||||
ret <12 x double> %c
|
||||
}
|
||||
|
|
@ -0,0 +1,111 @@
|
|||
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
|
||||
; RUN: opt -lower-matrix-intrinsics -matrix-default-layout=row-major -S < %s | FileCheck --check-prefix=RM %s
|
||||
|
||||
define <8 x float> @transpose(<8 x float> %a) {
|
||||
; RM-LABEL: @transpose(
|
||||
; RM-NEXT: entry:
|
||||
; RM-NEXT: [[SPLIT:%.*]] = shufflevector <8 x float> [[A:%.*]], <8 x float> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
|
||||
; RM-NEXT: [[SPLIT1:%.*]] = shufflevector <8 x float> [[A]], <8 x float> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
|
||||
; RM-NEXT: [[TMP0:%.*]] = extractelement <4 x float> [[SPLIT]], i64 0
|
||||
; RM-NEXT: [[TMP1:%.*]] = insertelement <2 x float> undef, float [[TMP0]], i64 0
|
||||
; RM-NEXT: [[TMP2:%.*]] = extractelement <4 x float> [[SPLIT1]], i64 0
|
||||
; RM-NEXT: [[TMP3:%.*]] = insertelement <2 x float> [[TMP1]], float [[TMP2]], i64 1
|
||||
; RM-NEXT: [[TMP4:%.*]] = extractelement <4 x float> [[SPLIT]], i64 1
|
||||
; RM-NEXT: [[TMP5:%.*]] = insertelement <2 x float> undef, float [[TMP4]], i64 0
|
||||
; RM-NEXT: [[TMP6:%.*]] = extractelement <4 x float> [[SPLIT1]], i64 1
|
||||
; RM-NEXT: [[TMP7:%.*]] = insertelement <2 x float> [[TMP5]], float [[TMP6]], i64 1
|
||||
; RM-NEXT: [[TMP8:%.*]] = extractelement <4 x float> [[SPLIT]], i64 2
|
||||
; RM-NEXT: [[TMP9:%.*]] = insertelement <2 x float> undef, float [[TMP8]], i64 0
|
||||
; RM-NEXT: [[TMP10:%.*]] = extractelement <4 x float> [[SPLIT1]], i64 2
|
||||
; RM-NEXT: [[TMP11:%.*]] = insertelement <2 x float> [[TMP9]], float [[TMP10]], i64 1
|
||||
; RM-NEXT: [[TMP12:%.*]] = extractelement <4 x float> [[SPLIT]], i64 3
|
||||
; RM-NEXT: [[TMP13:%.*]] = insertelement <2 x float> undef, float [[TMP12]], i64 0
|
||||
; RM-NEXT: [[TMP14:%.*]] = extractelement <4 x float> [[SPLIT1]], i64 3
|
||||
; RM-NEXT: [[TMP15:%.*]] = insertelement <2 x float> [[TMP13]], float [[TMP14]], i64 1
|
||||
; RM-NEXT: [[TMP16:%.*]] = shufflevector <2 x float> [[TMP3]], <2 x float> [[TMP7]], <4 x i32> <i32 0, i32 1, i32 2, i32 3>
|
||||
; RM-NEXT: [[TMP17:%.*]] = shufflevector <2 x float> [[TMP11]], <2 x float> [[TMP15]], <4 x i32> <i32 0, i32 1, i32 2, i32 3>
|
||||
; RM-NEXT: [[TMP18:%.*]] = shufflevector <4 x float> [[TMP16]], <4 x float> [[TMP17]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
|
||||
; RM-NEXT: ret <8 x float> [[TMP18]]
|
||||
;
|
||||
entry:
|
||||
%c = call <8 x float> @llvm.matrix.transpose(<8 x float> %a, i32 2, i32 4)
|
||||
ret <8 x float> %c
|
||||
}
|
||||
|
||||
declare <8 x float> @llvm.matrix.transpose(<8 x float>, i32, i32)
|
||||
|
||||
define <8 x float> @transpose_single_column(<8 x float> %a) {
|
||||
; RM-LABEL: @transpose_single_column(
|
||||
; RM-NEXT: entry:
|
||||
; RM-NEXT: [[SPLIT:%.*]] = shufflevector <8 x float> [[A:%.*]], <8 x float> undef, <1 x i32> zeroinitializer
|
||||
; RM-NEXT: [[SPLIT1:%.*]] = shufflevector <8 x float> [[A]], <8 x float> undef, <1 x i32> <i32 1>
|
||||
; RM-NEXT: [[SPLIT2:%.*]] = shufflevector <8 x float> [[A]], <8 x float> undef, <1 x i32> <i32 2>
|
||||
; RM-NEXT: [[SPLIT3:%.*]] = shufflevector <8 x float> [[A]], <8 x float> undef, <1 x i32> <i32 3>
|
||||
; RM-NEXT: [[SPLIT4:%.*]] = shufflevector <8 x float> [[A]], <8 x float> undef, <1 x i32> <i32 4>
|
||||
; RM-NEXT: [[SPLIT5:%.*]] = shufflevector <8 x float> [[A]], <8 x float> undef, <1 x i32> <i32 5>
|
||||
; RM-NEXT: [[SPLIT6:%.*]] = shufflevector <8 x float> [[A]], <8 x float> undef, <1 x i32> <i32 6>
|
||||
; RM-NEXT: [[SPLIT7:%.*]] = shufflevector <8 x float> [[A]], <8 x float> undef, <1 x i32> <i32 7>
|
||||
; RM-NEXT: [[TMP0:%.*]] = extractelement <1 x float> [[SPLIT]], i64 0
|
||||
; RM-NEXT: [[TMP1:%.*]] = insertelement <8 x float> undef, float [[TMP0]], i64 0
|
||||
; RM-NEXT: [[TMP2:%.*]] = extractelement <1 x float> [[SPLIT1]], i64 0
|
||||
; RM-NEXT: [[TMP3:%.*]] = insertelement <8 x float> [[TMP1]], float [[TMP2]], i64 1
|
||||
; RM-NEXT: [[TMP4:%.*]] = extractelement <1 x float> [[SPLIT2]], i64 0
|
||||
; RM-NEXT: [[TMP5:%.*]] = insertelement <8 x float> [[TMP3]], float [[TMP4]], i64 2
|
||||
; RM-NEXT: [[TMP6:%.*]] = extractelement <1 x float> [[SPLIT3]], i64 0
|
||||
; RM-NEXT: [[TMP7:%.*]] = insertelement <8 x float> [[TMP5]], float [[TMP6]], i64 3
|
||||
; RM-NEXT: [[TMP8:%.*]] = extractelement <1 x float> [[SPLIT4]], i64 0
|
||||
; RM-NEXT: [[TMP9:%.*]] = insertelement <8 x float> [[TMP7]], float [[TMP8]], i64 4
|
||||
; RM-NEXT: [[TMP10:%.*]] = extractelement <1 x float> [[SPLIT5]], i64 0
|
||||
; RM-NEXT: [[TMP11:%.*]] = insertelement <8 x float> [[TMP9]], float [[TMP10]], i64 5
|
||||
; RM-NEXT: [[TMP12:%.*]] = extractelement <1 x float> [[SPLIT6]], i64 0
|
||||
; RM-NEXT: [[TMP13:%.*]] = insertelement <8 x float> [[TMP11]], float [[TMP12]], i64 6
|
||||
; RM-NEXT: [[TMP14:%.*]] = extractelement <1 x float> [[SPLIT7]], i64 0
|
||||
; RM-NEXT: [[TMP15:%.*]] = insertelement <8 x float> [[TMP13]], float [[TMP14]], i64 7
|
||||
; RM-NEXT: ret <8 x float> [[TMP15]]
|
||||
;
|
||||
entry:
|
||||
%c = call <8 x float> @llvm.matrix.transpose(<8 x float> %a, i32 8, i32 1)
|
||||
ret <8 x float> %c
|
||||
}
|
||||
|
||||
declare <12 x float> @llvm.matrix.transpose.v12f32(<12 x float>, i32, i32)
|
||||
|
||||
define <12 x float> @transpose_float_3x4(<12 x float> %a) {
|
||||
; RM-LABEL: @transpose_float_3x4(
|
||||
; RM-NEXT: entry:
|
||||
; RM-NEXT: [[SPLIT:%.*]] = shufflevector <12 x float> [[A:%.*]], <12 x float> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
|
||||
; RM-NEXT: [[SPLIT1:%.*]] = shufflevector <12 x float> [[A]], <12 x float> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
|
||||
; RM-NEXT: [[SPLIT2:%.*]] = shufflevector <12 x float> [[A]], <12 x float> undef, <4 x i32> <i32 8, i32 9, i32 10, i32 11>
|
||||
; RM-NEXT: [[TMP0:%.*]] = extractelement <4 x float> [[SPLIT]], i64 0
|
||||
; RM-NEXT: [[TMP1:%.*]] = insertelement <3 x float> undef, float [[TMP0]], i64 0
|
||||
; RM-NEXT: [[TMP2:%.*]] = extractelement <4 x float> [[SPLIT1]], i64 0
|
||||
; RM-NEXT: [[TMP3:%.*]] = insertelement <3 x float> [[TMP1]], float [[TMP2]], i64 1
|
||||
; RM-NEXT: [[TMP4:%.*]] = extractelement <4 x float> [[SPLIT2]], i64 0
|
||||
; RM-NEXT: [[TMP5:%.*]] = insertelement <3 x float> [[TMP3]], float [[TMP4]], i64 2
|
||||
; RM-NEXT: [[TMP6:%.*]] = extractelement <4 x float> [[SPLIT]], i64 1
|
||||
; RM-NEXT: [[TMP7:%.*]] = insertelement <3 x float> undef, float [[TMP6]], i64 0
|
||||
; RM-NEXT: [[TMP8:%.*]] = extractelement <4 x float> [[SPLIT1]], i64 1
|
||||
; RM-NEXT: [[TMP9:%.*]] = insertelement <3 x float> [[TMP7]], float [[TMP8]], i64 1
|
||||
; RM-NEXT: [[TMP10:%.*]] = extractelement <4 x float> [[SPLIT2]], i64 1
|
||||
; RM-NEXT: [[TMP11:%.*]] = insertelement <3 x float> [[TMP9]], float [[TMP10]], i64 2
|
||||
; RM-NEXT: [[TMP12:%.*]] = extractelement <4 x float> [[SPLIT]], i64 2
|
||||
; RM-NEXT: [[TMP13:%.*]] = insertelement <3 x float> undef, float [[TMP12]], i64 0
|
||||
; RM-NEXT: [[TMP14:%.*]] = extractelement <4 x float> [[SPLIT1]], i64 2
|
||||
; RM-NEXT: [[TMP15:%.*]] = insertelement <3 x float> [[TMP13]], float [[TMP14]], i64 1
|
||||
; RM-NEXT: [[TMP16:%.*]] = extractelement <4 x float> [[SPLIT2]], i64 2
|
||||
; RM-NEXT: [[TMP17:%.*]] = insertelement <3 x float> [[TMP15]], float [[TMP16]], i64 2
|
||||
; RM-NEXT: [[TMP18:%.*]] = extractelement <4 x float> [[SPLIT]], i64 3
|
||||
; RM-NEXT: [[TMP19:%.*]] = insertelement <3 x float> undef, float [[TMP18]], i64 0
|
||||
; RM-NEXT: [[TMP20:%.*]] = extractelement <4 x float> [[SPLIT1]], i64 3
|
||||
; RM-NEXT: [[TMP21:%.*]] = insertelement <3 x float> [[TMP19]], float [[TMP20]], i64 1
|
||||
; RM-NEXT: [[TMP22:%.*]] = extractelement <4 x float> [[SPLIT2]], i64 3
|
||||
; RM-NEXT: [[TMP23:%.*]] = insertelement <3 x float> [[TMP21]], float [[TMP22]], i64 2
|
||||
; RM-NEXT: [[TMP24:%.*]] = shufflevector <3 x float> [[TMP5]], <3 x float> [[TMP11]], <6 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5>
|
||||
; RM-NEXT: [[TMP25:%.*]] = shufflevector <3 x float> [[TMP17]], <3 x float> [[TMP23]], <6 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5>
|
||||
; RM-NEXT: [[TMP26:%.*]] = shufflevector <6 x float> [[TMP24]], <6 x float> [[TMP25]], <12 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11>
|
||||
; RM-NEXT: ret <12 x float> [[TMP26]]
|
||||
;
|
||||
entry:
|
||||
%c = call <12 x float> @llvm.matrix.transpose.v12f32(<12 x float> %a, i32 3, i32 4)
|
||||
ret <12 x float> %c
|
||||
}
|
||||
|
|
@ -0,0 +1,111 @@
|
|||
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
|
||||
; RUN: opt -lower-matrix-intrinsics -matrix-default-layout=row-major -S < %s | FileCheck --check-prefix=RM %s
|
||||
|
||||
define <8 x i32> @transpose(<8 x i32> %a) {
|
||||
; RM-LABEL: @transpose(
|
||||
; RM-NEXT: entry:
|
||||
; RM-NEXT: [[SPLIT:%.*]] = shufflevector <8 x i32> [[A:%.*]], <8 x i32> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
|
||||
; RM-NEXT: [[SPLIT1:%.*]] = shufflevector <8 x i32> [[A]], <8 x i32> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
|
||||
; RM-NEXT: [[TMP0:%.*]] = extractelement <4 x i32> [[SPLIT]], i64 0
|
||||
; RM-NEXT: [[TMP1:%.*]] = insertelement <2 x i32> undef, i32 [[TMP0]], i64 0
|
||||
; RM-NEXT: [[TMP2:%.*]] = extractelement <4 x i32> [[SPLIT1]], i64 0
|
||||
; RM-NEXT: [[TMP3:%.*]] = insertelement <2 x i32> [[TMP1]], i32 [[TMP2]], i64 1
|
||||
; RM-NEXT: [[TMP4:%.*]] = extractelement <4 x i32> [[SPLIT]], i64 1
|
||||
; RM-NEXT: [[TMP5:%.*]] = insertelement <2 x i32> undef, i32 [[TMP4]], i64 0
|
||||
; RM-NEXT: [[TMP6:%.*]] = extractelement <4 x i32> [[SPLIT1]], i64 1
|
||||
; RM-NEXT: [[TMP7:%.*]] = insertelement <2 x i32> [[TMP5]], i32 [[TMP6]], i64 1
|
||||
; RM-NEXT: [[TMP8:%.*]] = extractelement <4 x i32> [[SPLIT]], i64 2
|
||||
; RM-NEXT: [[TMP9:%.*]] = insertelement <2 x i32> undef, i32 [[TMP8]], i64 0
|
||||
; RM-NEXT: [[TMP10:%.*]] = extractelement <4 x i32> [[SPLIT1]], i64 2
|
||||
; RM-NEXT: [[TMP11:%.*]] = insertelement <2 x i32> [[TMP9]], i32 [[TMP10]], i64 1
|
||||
; RM-NEXT: [[TMP12:%.*]] = extractelement <4 x i32> [[SPLIT]], i64 3
|
||||
; RM-NEXT: [[TMP13:%.*]] = insertelement <2 x i32> undef, i32 [[TMP12]], i64 0
|
||||
; RM-NEXT: [[TMP14:%.*]] = extractelement <4 x i32> [[SPLIT1]], i64 3
|
||||
; RM-NEXT: [[TMP15:%.*]] = insertelement <2 x i32> [[TMP13]], i32 [[TMP14]], i64 1
|
||||
; RM-NEXT: [[TMP16:%.*]] = shufflevector <2 x i32> [[TMP3]], <2 x i32> [[TMP7]], <4 x i32> <i32 0, i32 1, i32 2, i32 3>
|
||||
; RM-NEXT: [[TMP17:%.*]] = shufflevector <2 x i32> [[TMP11]], <2 x i32> [[TMP15]], <4 x i32> <i32 0, i32 1, i32 2, i32 3>
|
||||
; RM-NEXT: [[TMP18:%.*]] = shufflevector <4 x i32> [[TMP16]], <4 x i32> [[TMP17]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
|
||||
; RM-NEXT: ret <8 x i32> [[TMP18]]
|
||||
;
|
||||
entry:
|
||||
%c = call <8 x i32> @llvm.matrix.transpose(<8 x i32> %a, i32 2, i32 4)
|
||||
ret <8 x i32> %c
|
||||
}
|
||||
|
||||
declare <8 x i32> @llvm.matrix.transpose(<8 x i32>, i32, i32)
|
||||
|
||||
define <8 x i32> @transpose_single_column(<8 x i32> %a) {
|
||||
; RM-LABEL: @transpose_single_column(
|
||||
; RM-NEXT: entry:
|
||||
; RM-NEXT: [[SPLIT:%.*]] = shufflevector <8 x i32> [[A:%.*]], <8 x i32> undef, <1 x i32> zeroinitializer
|
||||
; RM-NEXT: [[SPLIT1:%.*]] = shufflevector <8 x i32> [[A]], <8 x i32> undef, <1 x i32> <i32 1>
|
||||
; RM-NEXT: [[SPLIT2:%.*]] = shufflevector <8 x i32> [[A]], <8 x i32> undef, <1 x i32> <i32 2>
|
||||
; RM-NEXT: [[SPLIT3:%.*]] = shufflevector <8 x i32> [[A]], <8 x i32> undef, <1 x i32> <i32 3>
|
||||
; RM-NEXT: [[SPLIT4:%.*]] = shufflevector <8 x i32> [[A]], <8 x i32> undef, <1 x i32> <i32 4>
|
||||
; RM-NEXT: [[SPLIT5:%.*]] = shufflevector <8 x i32> [[A]], <8 x i32> undef, <1 x i32> <i32 5>
|
||||
; RM-NEXT: [[SPLIT6:%.*]] = shufflevector <8 x i32> [[A]], <8 x i32> undef, <1 x i32> <i32 6>
|
||||
; RM-NEXT: [[SPLIT7:%.*]] = shufflevector <8 x i32> [[A]], <8 x i32> undef, <1 x i32> <i32 7>
|
||||
; RM-NEXT: [[TMP0:%.*]] = extractelement <1 x i32> [[SPLIT]], i64 0
|
||||
; RM-NEXT: [[TMP1:%.*]] = insertelement <8 x i32> undef, i32 [[TMP0]], i64 0
|
||||
; RM-NEXT: [[TMP2:%.*]] = extractelement <1 x i32> [[SPLIT1]], i64 0
|
||||
; RM-NEXT: [[TMP3:%.*]] = insertelement <8 x i32> [[TMP1]], i32 [[TMP2]], i64 1
|
||||
; RM-NEXT: [[TMP4:%.*]] = extractelement <1 x i32> [[SPLIT2]], i64 0
|
||||
; RM-NEXT: [[TMP5:%.*]] = insertelement <8 x i32> [[TMP3]], i32 [[TMP4]], i64 2
|
||||
; RM-NEXT: [[TMP6:%.*]] = extractelement <1 x i32> [[SPLIT3]], i64 0
|
||||
; RM-NEXT: [[TMP7:%.*]] = insertelement <8 x i32> [[TMP5]], i32 [[TMP6]], i64 3
|
||||
; RM-NEXT: [[TMP8:%.*]] = extractelement <1 x i32> [[SPLIT4]], i64 0
|
||||
; RM-NEXT: [[TMP9:%.*]] = insertelement <8 x i32> [[TMP7]], i32 [[TMP8]], i64 4
|
||||
; RM-NEXT: [[TMP10:%.*]] = extractelement <1 x i32> [[SPLIT5]], i64 0
|
||||
; RM-NEXT: [[TMP11:%.*]] = insertelement <8 x i32> [[TMP9]], i32 [[TMP10]], i64 5
|
||||
; RM-NEXT: [[TMP12:%.*]] = extractelement <1 x i32> [[SPLIT6]], i64 0
|
||||
; RM-NEXT: [[TMP13:%.*]] = insertelement <8 x i32> [[TMP11]], i32 [[TMP12]], i64 6
|
||||
; RM-NEXT: [[TMP14:%.*]] = extractelement <1 x i32> [[SPLIT7]], i64 0
|
||||
; RM-NEXT: [[TMP15:%.*]] = insertelement <8 x i32> [[TMP13]], i32 [[TMP14]], i64 7
|
||||
; RM-NEXT: ret <8 x i32> [[TMP15]]
|
||||
;
|
||||
entry:
|
||||
%c = call <8 x i32> @llvm.matrix.transpose(<8 x i32> %a, i32 8, i32 1)
|
||||
ret <8 x i32> %c
|
||||
}
|
||||
|
||||
declare <12 x i32> @llvm.matrix.transpose.v12i32(<12 x i32>, i32, i32)
|
||||
|
||||
define <12 x i32> @transpose_i32_3x4(<12 x i32> %a) {
|
||||
; RM-LABEL: @transpose_i32_3x4(
|
||||
; RM-NEXT: entry:
|
||||
; RM-NEXT: [[SPLIT:%.*]] = shufflevector <12 x i32> [[A:%.*]], <12 x i32> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
|
||||
; RM-NEXT: [[SPLIT1:%.*]] = shufflevector <12 x i32> [[A]], <12 x i32> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
|
||||
; RM-NEXT: [[SPLIT2:%.*]] = shufflevector <12 x i32> [[A]], <12 x i32> undef, <4 x i32> <i32 8, i32 9, i32 10, i32 11>
|
||||
; RM-NEXT: [[TMP0:%.*]] = extractelement <4 x i32> [[SPLIT]], i64 0
|
||||
; RM-NEXT: [[TMP1:%.*]] = insertelement <3 x i32> undef, i32 [[TMP0]], i64 0
|
||||
; RM-NEXT: [[TMP2:%.*]] = extractelement <4 x i32> [[SPLIT1]], i64 0
|
||||
; RM-NEXT: [[TMP3:%.*]] = insertelement <3 x i32> [[TMP1]], i32 [[TMP2]], i64 1
|
||||
; RM-NEXT: [[TMP4:%.*]] = extractelement <4 x i32> [[SPLIT2]], i64 0
|
||||
; RM-NEXT: [[TMP5:%.*]] = insertelement <3 x i32> [[TMP3]], i32 [[TMP4]], i64 2
|
||||
; RM-NEXT: [[TMP6:%.*]] = extractelement <4 x i32> [[SPLIT]], i64 1
|
||||
; RM-NEXT: [[TMP7:%.*]] = insertelement <3 x i32> undef, i32 [[TMP6]], i64 0
|
||||
; RM-NEXT: [[TMP8:%.*]] = extractelement <4 x i32> [[SPLIT1]], i64 1
|
||||
; RM-NEXT: [[TMP9:%.*]] = insertelement <3 x i32> [[TMP7]], i32 [[TMP8]], i64 1
|
||||
; RM-NEXT: [[TMP10:%.*]] = extractelement <4 x i32> [[SPLIT2]], i64 1
|
||||
; RM-NEXT: [[TMP11:%.*]] = insertelement <3 x i32> [[TMP9]], i32 [[TMP10]], i64 2
|
||||
; RM-NEXT: [[TMP12:%.*]] = extractelement <4 x i32> [[SPLIT]], i64 2
|
||||
; RM-NEXT: [[TMP13:%.*]] = insertelement <3 x i32> undef, i32 [[TMP12]], i64 0
|
||||
; RM-NEXT: [[TMP14:%.*]] = extractelement <4 x i32> [[SPLIT1]], i64 2
|
||||
; RM-NEXT: [[TMP15:%.*]] = insertelement <3 x i32> [[TMP13]], i32 [[TMP14]], i64 1
|
||||
; RM-NEXT: [[TMP16:%.*]] = extractelement <4 x i32> [[SPLIT2]], i64 2
|
||||
; RM-NEXT: [[TMP17:%.*]] = insertelement <3 x i32> [[TMP15]], i32 [[TMP16]], i64 2
|
||||
; RM-NEXT: [[TMP18:%.*]] = extractelement <4 x i32> [[SPLIT]], i64 3
|
||||
; RM-NEXT: [[TMP19:%.*]] = insertelement <3 x i32> undef, i32 [[TMP18]], i64 0
|
||||
; RM-NEXT: [[TMP20:%.*]] = extractelement <4 x i32> [[SPLIT1]], i64 3
|
||||
; RM-NEXT: [[TMP21:%.*]] = insertelement <3 x i32> [[TMP19]], i32 [[TMP20]], i64 1
|
||||
; RM-NEXT: [[TMP22:%.*]] = extractelement <4 x i32> [[SPLIT2]], i64 3
|
||||
; RM-NEXT: [[TMP23:%.*]] = insertelement <3 x i32> [[TMP21]], i32 [[TMP22]], i64 2
|
||||
; RM-NEXT: [[TMP24:%.*]] = shufflevector <3 x i32> [[TMP5]], <3 x i32> [[TMP11]], <6 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5>
|
||||
; RM-NEXT: [[TMP25:%.*]] = shufflevector <3 x i32> [[TMP17]], <3 x i32> [[TMP23]], <6 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5>
|
||||
; RM-NEXT: [[TMP26:%.*]] = shufflevector <6 x i32> [[TMP24]], <6 x i32> [[TMP25]], <12 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11>
|
||||
; RM-NEXT: ret <12 x i32> [[TMP26]]
|
||||
;
|
||||
entry:
|
||||
%c = call <12 x i32> @llvm.matrix.transpose.v12i32(<12 x i32> %a, i32 3, i32 4)
|
||||
ret <12 x i32> %c
|
||||
}
|
||||
Loading…
Reference in New Issue