EmulateMulFInBF16Pattern Struct Reference

Pattern to emulate an f32 multiply with bf16 inputs. More...

Inheritance diagram for EmulateMulFInBF16Pattern:

Collaboration diagram for EmulateMulFInBF16Pattern:

Public Member Functions
LogicalResult	matchAndRewrite (arith::MulFOp op, PatternRewriter &rewriter) const override

Detailed Description

Pattern to emulate an f32 multiply with bf16 inputs.

The product of two bf16 values fits in f32 except at the ends of the exponent range, so only the inputs are rounded: r = arith.mulf a, b : vector<16xf32> becomes r = arith.mulf (extf (truncf a)), (extf (truncf b)) : vector<16xf32>

Definition at line 873 of file VectorToVectorConversions.cpp.

Member Function Documentation

matchAndRewrite()

LogicalResult EmulateMulFInBF16Pattern::matchAndRewrite ( arith::MulFOp op, PatternRewriter & rewriter ) const

inlineoverride

Definition at line 876 of file VectorToVectorConversions.cpp.

---

The documentation for this struct was generated from the following file:

• lib/Dialect/AIEVec/Transforms/VectorToVectorConversions.cpp