bondhugula / polymage-benchmarksLinks
Base code and optimized code for the benchmarks used in the PolyMage paper published at ASPLOS 2015
☆19Updated 9 years ago
Alternatives and similar repositories for polymage-benchmarks
Users that are interested in polymage-benchmarks are comparing it to the libraries listed below
Sorting:
- Proof-of-Concept CNN in Halide☆22Updated 9 years ago
- A domain-specific language and compiler for image processing☆76Updated 4 years ago
- Reference workloads for modern deep learning methods.☆73Updated 2 years ago
- CNNs in Halide☆23Updated 9 years ago
- Optimized half precision gemm assembly kernels (deprecated due to ROCm)☆47Updated 8 years ago
- Greentea LibDNN - a universal convolution implementation supporting CUDA and OpenCL☆137Updated 8 years ago
- Fast matrix multiplication☆29Updated 4 years ago
- Boda: A C++ Framework for Efficient Experiments in Computer Vision☆63Updated 6 years ago
- a heterogeneous multiGPU level-3 BLAS library☆45Updated 5 years ago
- Kernel Fusion and Runtime Compilation Based on NNVM☆71Updated 8 years ago
- HLS branch of Halide☆78Updated 7 years ago
- An experimental ahead of time compiler for Relay.☆50Updated 5 years ago
- Code appendix to an OpenCL matrix-multiplication tutorial☆177Updated 8 years ago
- Communication-Minimizing 2D Convolution in GPU Registers☆30Updated 11 years ago
- High Efficiency Convolution Kernel for Maxwell GPU Architecture☆134Updated 8 years ago
- ☆39Updated 8 years ago
- Visualize TVM Relay program graph☆12Updated 5 years ago
- ☆74Updated 2 years ago
- A simple memory manager for CUDA designed to help Deep Learning frameworks manage memory☆298Updated 6 years ago
- TVM stack: exploring the incredible explosion of deep-learning frameworks and how to bring them together☆64Updated 7 years ago
- CaffePresso: An Optimized Library for Deep Learning on Embedded Accelerator-based platforms☆87Updated 10 months ago
- Symbolic Expression and Statement Module for new DSLs☆206Updated 4 years ago
- Generic system-wide modern C++ for heterogeneous platforms with SYCL from Khronos Group☆77Updated 4 years ago
- A portable high-level API with CUDA or OpenCL back-end☆54Updated 7 years ago
- implementation of winograd minimal convolution algorithm on Intel Architecture☆39Updated 7 years ago
- AMD OpenVX Core -- a sub-module of amdovx-modules:☆147Updated 6 years ago
- Python wrappers for the NVIDIA cuDNN libraries☆140Updated 8 years ago
- ☆12Updated 5 years ago
- Enabling on-the-fly manipulations with LLVM IR code of CUDA sources☆112Updated 4 months ago
- An exploration of log domain "alternative floating point" for hardware ML/AI accelerators.☆394Updated 2 years ago