Unclaimed project
Are you a maintainer of BladeDISC? Claim this project to take control of your public changelog and roadmap.
Changelog
BladeDISC is an end-to-end DynamIc Shape Compiler project for machine learning workloads.
For CUDA platform, we have supported fusion of GEMM and its following element-wise ops (e.g. GELU, transpose), and then do codegen based on CUTLASS. Experiments show that this feature achieves up to 1.1x speedup for BERT model.
Please set DISC_ENABLE_COMPUTE_INTENSIVE_FUSE=true if you want to try this feature.
We introduced MLIR Transf...
We released GPU AStitch optimization mainly last time in v0.2.0. Now we are proud to announce the release of BladeDISC v0.3.0.
We have done the following things in the latest 6 months:
Make use of GPU shared memory to fuse reduce operator with its consumers into one kernel. It helps to accommodate complex memory-intensive computations (e.g., LayerNorm, SoftMax) into one kernel, reducing off-chip memory traffics and overhead of kernel scheduling and launching. It implements partial functions described in pap...