-
While working at this, I noticed that LLVM IR dialect GlobalOp does not yet support `alias`, so we cannot yet lower this information down. Let me file another issue for that.
For now, I'm going to …
-
https://blog.gopheracademy.com/advent-2018/llvm-ir-and-go/
-
LLVM IR dialect lacks support for `ptr elementtype(i32)` on `LLVM_CallIntrinsicOp`. This is necessary to properly lower `clang::AArch64::BI__builtin_arm_ldrex`. Whenever
_Originally posted by @bca…
-
I tried to add new test `IotaF8E4M3FN` based on `IotaF8E4FNUZ` code ([xla/service/elemental_ir_emitter_test.cc](https://github.com/openxla/xla/blob/main/xla/service/elemental_ir_emitter_test.cc#L540))…
-
With the latest LLVM integration from https://github.com/openxla/stablehlo/pull/2635, building llvm-project for stablehlo leads to the following compilation error:
```
$ MLIR_ENABLE_BINDINGS_PYTHON=…
pearu updated
20 hours ago
-
For example with the ClangIR of the day https://github.com/llvm/clangir/commit/bae7bd9e68764afb586040f6d63b3759e0b6d856 on https://github.com/llvm/clangir/blob/main/clang/test/CIR/Lowering/ThroughMLIR…
-
Step1: Change this [line](https://github.com/nod-ai/iree-amd-aie/blob/c15a45a016a504f032b0f5c02d64c9916da91521/build_tools/build_test_cpp.ps1#L61) from
"-DCMAKE_BUILD_TYPE=Release"
to
"-DCMAKE_BUIL…
-
jank currently generates C++, which it then gives to clang to JIT compile. There are some serious benefits to this:
1. Super easy codegen
2. Full access to jank's runtime API, including templates,…
jeaye updated
1 month ago
-
I couldn't find the corresponding conversion method in `iree-opt` and` iree-translate` tools.
-
### Describe the bug
When I use python/triton/compiler/compiler.py::compile to compile a llvm IR, I got a RuntimeError:
```
loc("/workspace/triton/python/test/single_dot.llir":1:1): error: unexpect…