[clang-tools-extra] [clang] [mlir] [llvm] [MLIR][Linalg] Support dynamic sizes in `lower_unpack` (PR #75494)

https://github.com/chelini commented: Thanks! https://github.com/llvm/llvm-project/pull/75494 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[llvm] [clang] [clang-tools-extra] [mlir] [MLIR][Linalg] Support dynamic sizes in `lower_unpack` (PR #75494)

https://github.com/chelini edited https://github.com/llvm/llvm-project/pull/75494 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[clang] [llvm] [clang-tools-extra] [mlir] [MLIR][Linalg] Support dynamic sizes in `lower_unpack` (PR #75494)

@@ -434,8 +429,21 @@ FailureOr linalg::lowerUnPack(RewriterBase &rewriter, RankedTensorType::Builder(packedTensorType).setShape(stripMinedShape); RankedTensorType collapsedType = tensor::CollapseShapeOp::inferCollapsedType( stripMinedTensorType, packingMetadata.r

[clang-tools-extra] [clang] [mlir] [llvm] [MLIR][Linalg] Support dynamic sizes in `lower_unpack` (PR #75494)

@@ -434,8 +429,21 @@ FailureOr linalg::lowerUnPack(RewriterBase &rewriter, RankedTensorType::Builder(packedTensorType).setShape(stripMinedShape); RankedTensorType collapsedType = tensor::CollapseShapeOp::inferCollapsedType( stripMinedTensorType, packingMetadata.r

[mlir] [clang-tools-extra] [llvm] [clang] [MLIR][Linalg] Support dynamic sizes in `lower_unpack` (PR #75494)

@@ -381,11 +381,6 @@ FailureOr linalg::lowerUnPack(RewriterBase &rewriter, return rewriter.notifyMatchFailure(unPackOp, "outer dims perm NYI"); RankedTensorType packedTensorType = unPackOp.getSourceType(); chelini wrote: nit: I would move this line aft

[clang] [llvm] [clang-tools-extra] [mlir] [MLIR][Linalg] Support dynamic sizes in `lower_unpack` (PR #75494)

@@ -434,8 +428,14 @@ FailureOr linalg::lowerUnPack(RewriterBase &rewriter, RankedTensorType::Builder(packedTensorType).setShape(stripMinedShape); RankedTensorType collapsedType = tensor::CollapseShapeOp::inferCollapsedType( stripMinedTensorType, packingMetadata.r

[mlir] [llvm] [clang-tools-extra] [clang] [MLIR][Linalg] Support dynamic sizes in `lower_unpack` (PR #75494)

https://github.com/chelini edited https://github.com/llvm/llvm-project/pull/75494 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[clang] [clang-tools-extra] [llvm] [mlir] [MLIR][Linalg] Support dynamic sizes in `lower_unpack` (PR #75494)

@@ -464,6 +464,129 @@ module attributes {transform.with_named_sequence} { // - +// Check that we can lower unpack with dynamic dimensions in the input and destination. +// CHECK-LABEL: func.func @unpack_with_dynamic_input_dest( +// CHECK-SAME: %[[ARG0:.*]]: tensor, %[[AR

[mlir] [clang-tools-extra] [clang] [llvm] [MLIR][Linalg] Support dynamic sizes in `lower_unpack` (PR #75494)

https://github.com/chelini approved this pull request. Thanks, it looks good to me. https://github.com/llvm/llvm-project/pull/75494 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[clang] [clang-tools-extra] [llvm] [mlir] [MLIR][Linalg] Support dynamic sizes in `lower_unpack` (PR #75494)

https://github.com/chelini closed https://github.com/llvm/llvm-project/pull/75494 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

[libcxx] [clang-tools-extra] [clang] [libc] [compiler-rt] [flang] [mlir] [llvm] [mlir][Linalg] Support dynamic tiles in `lower_pack` transform (PR #76003)

chelini wrote: > It was suggested to me by @chelini to only have the `reshape` op to handle > all cases and get rid of the `expand_shape` op. We can then implement a > canonicalizer to convert when valid. I'm all for this, however want to make > sure this is the direction we want to go before

[mlir] [clang] [llvm] [libcxx] [lld] [clang-tools-extra] [lldb] [mlir][transform] Add elementwise criteria to `match.structured.body` (PR #79626)

chelini wrote: Is it ready for review? Is marked as "draft". https://github.com/llvm/llvm-project/pull/79626 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits