[Mlir-commits] [llvm] [mlir] [SPIR-V] Add support for the SPIR-V extension SPV_INTEL_tensor_float32_conversion (PR #150090)

[llvmlistbot at llvm.org]

================
@@ -110,6 +111,59 @@ def SPIRV_INTELConvertBF16ToFOp : SPIRV_IntelVendorOp<"ConvertBF16ToF", []> {
   let hasVerifier = 1;
 }
 
+// -----
+
+def SPIRV_INTELRoundFToTF32Op : SPIRV_IntelVendorOp<"RoundFToTF32", []> {
+  let summary = "See extension SPV_INTEL_tensor_float32_conversion";
+
+  let description = [{
+    Convert value numerically from a 32-bit floating point type to tensor float32,
+    with rounding to the nearest even.
+
+    Result Type must be a scalar or vector of 32-bit floating-point type.
+    The component width must be 32 bits. Bit pattern in the Result represents a tensor float32 value.
+
+    Float Value must be a scalar or vector of floating-point type.
+    It must have the same number of components as Result Type. The component width must be 32 bits.
+
+    Results are computed per component.
+  
+
+    ```
+    convert-f-to-tf32-op ::= ssa-id `=` `spirv.INTEL.RoundFToTF32` ssa-use
----------------
YixingZhang007 wrote:

Thanks for the suggestion! I have made the modification (The MLIR part of this PR have been moved to a new PR https://github.com/llvm/llvm-project/pull/151337 and changes are made there)

https://github.com/llvm/llvm-project/pull/150090