-
### Here is a little example:
multiplications where one operand is a power of 2 and a constant integer, are optimized with a shift operation and the shift amount is calculated using the logBase2 of…
-
[0/1] Running the Dynamatic regression tests
FAIL: Dynamatic :: Dialect/Handshake/invalid.mlir (26 of 26)
******************** TEST 'Dynamatic :: Dialect/Handshake/invalid.mlir' FAILED *************…
-
The torch to linalg lowering for this op implicitly assumes the non-padded dimensions are 1 without checking this explicitly.
Some sample IR to reproduce the error:
```MLIR
module {
func.fu…
-
```
We currently use a minimal set of LLVM optimization passes [1]. We should
explore more passes and other pass orderings. Sources for these:
- LLVM's opt tool [2].
- MacRuby [3]. I notice that MacR…
-
### Description
Reopening https://github.com/swiftlang/swift/issues/77219 with some new information.
This compiler crash occurs when building the attached reproducer with a swift.org release toolc…
-
```
Version of flang : 20.0.0(590f451b60d434b26c634a07125fb05baf461fa0)/AArch64
```
Using `%VAL (which specifies that the actual argument should be passed by value)` for an `actual argument` results …
-
For context, I was trying to add PGO support to rustc, and I was adding a couple LLVM passes for profile info generation and usage, and the only thing I managed to do is crashing rustc under LLVM, or …
-
```
Assertion failed: (BitWidth == RHS.BitWidth && "Bit widths must be the same"), function operator+=, file APInt.cpp, line 199.
PLEASE submit a bug report to https://github.com/llvm/llvm-project/i…
-
Hello, triton experts.
I have a question about llvm.struct and vector
I think the element type of llvm.struct cannot be ensured the same, but, the each element type of vector must be the same with…
-
The following MLIR code is not able to compile anymore for the ROCm platform (6.2 used here), since this commit: https://github.com/openxla/xla/commit/6e9eefeec077f49c2b22bfeee8da537ed8517b22
```ml…