PACT-2022 Release

pact

Update README.md

BenchPress

• Introduced active search program generation.

• Added model evaluation.

• This is a submission checkpoint.

BenchPress

• Enabled compiler rewarded training to kick-in after a selected number of steps instead of always starting at the begginning.

BenchPress

A short summary of all changes and upgrades:

Models

• Implement Pytorch version of BERT
• Added iterative compilation training in BERT model
• Implement online data generator for training and sampling; Masks kernels on stream.
• Implement active data generator for sampling only; Creates generations of good candidates based on distance from target features.
• Add support for TPUs.
• Add support for data parallelism in multiple GPUs.
• Added compilation rate, sample features fields in samples DB.

Datasets

• Implement BigQuery module for querying large datasets, in C, C++, OpenCL, Java, Python and GO.
• Fetched a hybrid dataset (BigQuery + recursive miner) of 40,000 subject openCL files.
• Enabled official OpenCL 2.2 API and now CL types are supported in training and generation.
• Decreased overall rejection rate of corpuses; achieved 48% rejection rate in 40k kernel corpus.
• Sample set feature is added; original corpus is pickled and can be masked with new specs.
• Plot overall input features of encoded corpus.

System

• Removed Bazel as a build system and migrated to CMake.

• Upgraded full build to LLVM-9. Now both LLVM-6 and 9 are equally supported.

• Add memory management modules for RAM and GPU memory.

• Implement flask dashboard

• Implement interactive plotly plots.

• Bug fixes.

BERT 0.1.1

• Data generator into protobuf
• Fixes in sampler.

BERT 0.1.0

• CMake 3.13 in place of Bazel
• Database for Sampler storing samples
• Automated GPU stuff that had been wasting manual effort.

BERT 0.0.1

Checkpoint version of repo containing some flavours of BERT.