[Mlir-commits] [mlir] [MLIR][XeVM] Enable SPV_INTEL_bfloat16_arithmetic (PR #195727)
llvmlistbot at llvm.org
llvmlistbot at llvm.org
Mon May 4 13:02:10 PDT 2026
llvmorg-github-actions[bot] wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-mlir
Author: Sang Ik Lee (silee2)
<details>
<summary>Changes</summary>
---
Full diff: https://github.com/llvm/llvm-project/pull/195727.diff
1 Files Affected:
- (modified) mlir/lib/Target/LLVM/XeVM/Target.cpp (+6)
``````````diff
diff --git a/mlir/lib/Target/LLVM/XeVM/Target.cpp b/mlir/lib/Target/LLVM/XeVM/Target.cpp
index a160e81321511..18f6b7b3e67c8 100644
--- a/mlir/lib/Target/LLVM/XeVM/Target.cpp
+++ b/mlir/lib/Target/LLVM/XeVM/Target.cpp
@@ -460,12 +460,18 @@ void SPIRVSerializer::init() {
}
#if LLVM_HAS_SPIRV_TARGET
+// Enable default set of SPIR-V extensions.
+// Supported extensions vary based on chip. See,
+// https://github.com/intel/intel-graphics-compiler/blob/master/
+// documentation/igc/supported-spirv-extensions.md
+// for details.
static const std::vector<std::string> getDefaultSPIRVExtensions() {
return {
"SPV_KHR_bfloat16",
"SPV_EXT_relaxed_printf_string_address_space",
"SPV_INTEL_cache_controls",
"SPV_INTEL_variable_length_array",
+ "SPV_INTEL_bfloat16_arithmetic",
};
}
``````````
</details>
https://github.com/llvm/llvm-project/pull/195727
More information about the Mlir-commits
mailing list