llvm-project/mlir
Stephan Herhut 2c8afe1298 [mlir][gpu] Add support for f16 when lowering to nvvm intrinsics
Summary:
The NVVM target only provides implementations for tanh etc. on f32 and
f64 operands. To also support f16, we now insert operations to extend to f32
and truncate back to f16 around the intrinsic call.

Differential Revision: https://reviews.llvm.org/D81473
2020-06-09 19:33:45 +02:00
..
cmake/modules [mlir] Make translation libraries available through MLIRConfig.cmake 2020-05-28 17:39:07 +02:00
docs Revert "Revert "[MLIR] Lower shape.num_elements -> shape.reduce."" 2020-06-08 12:19:54 +02:00
examples [MLIR][Toy] Fix a few typos in the comments/docs. 2020-06-08 18:18:47 -04:00
include [mlir] Add number of operands verification for shape.assuming_all operation 2020-06-09 09:59:04 -07:00
lib [mlir][gpu] Add support for f16 when lowering to nvvm intrinsics 2020-06-09 19:33:45 +02:00
test [mlir][gpu] Add support for f16 when lowering to nvvm intrinsics 2020-06-09 19:33:45 +02:00
tools [mlir] Introduce allowMemrefFunctionResults for the helper operation converters of buffer placement 2020-06-08 09:25:41 +02:00
unittests [mlir] Fix representation of BF16 constants 2020-06-05 17:43:06 -07:00
utils [mlir] Change generate-test-checks.py to `%[[V:.*]]` style 2020-05-13 14:50:14 -07:00
.clang-format
.clang-tidy Fix MLIR clang-tidy: when tweaking it does not inherit from the parent 2020-03-07 17:44:21 +00:00
CMakeLists.txt [mlir][gpu] Introduce mlir-rocm-runner. 2020-06-05 09:46:39 -05:00
LICENSE.TXT Add the Apache2 with LLVM exceptions license to MLIR 2019-12-24 00:58:06 -08:00
README.md mlir README.md: Fix the syntax 2019-12-24 13:31:07 +01:00

README.md

Multi-Level Intermediate Representation

See https://mlir.llvm.org/ for more information.