spcl / DNN-cpp-proxies
C++/MPI proxies for distributed training of deep neural networks.
☆12Updated 2 years ago
Related projects ⓘ
Alternatives and complementary repositories for DNN-cpp-proxies
- A LogGOPS (LogP, LogGP, LogGPS) Simulator and Simulation Framework☆11Updated 3 months ago
- This serves as a repository for reproducibility of the SC21 paper "In-Depth Analyses of Unified Virtual Memory System for GPU Accelerated…☆27Updated last year
- ☆23Updated 2 years ago
- ☆25Updated 4 years ago
- ☆66Updated 4 years ago
- Persistent Collectives X- A collective communication library for high performance, low cost persistent collectives over RDMA devices.☆14Updated 5 years ago
- A hierarchical collective communications library with portable optimizations☆23Updated 4 months ago
- Tartan: Evaluating Modern GPU Interconnect via a Multi-GPU Benchmark Suite☆60Updated 6 years ago
- ☆13Updated last year
- ROC_SHMEM intra-kernel networking runtime for AMD dGPUs on the ROCm platform.☆39Updated last year
- ☆41Updated 4 years ago
- ☆24Updated 3 years ago
- Repository for MLCommons Chakra schema and tools☆39Updated 10 months ago
- A benchmarking suite for heterogeneous systems. The primary goal of this project is to improve and update aspects of existing benchmarkin…☆40Updated 8 months ago
- The Artifact of NeoMem: Hardware/Software Co-Design for CXL-Native Memory Tiering☆28Updated 3 months ago
- Ok-Topk is a scheme for distributed training with sparse gradients. Ok-Topk integrates a novel sparse allreduce algorithm (less than 6k c…☆23Updated last year
- The Splash-3 benchmark suite☆42Updated last year
- A PIM instrumentation, compilation, execution, simulation, and evaluation repository for BLIMP-style architectures.☆16Updated 2 years ago
- HeteroSync is a benchmark suite for performing fine-grained synchronization on tightly coupled GPUs☆27Updated 2 months ago
- CUDA Flux is a profiler for GPU applications which reports the basic block executions frequencies of compute kernels☆31Updated 3 years ago
- Benchmark Suite for RDMA Performance Isolation☆36Updated last year
- A repository where GPU applications are aggregated using a common build flow that supports multiple CUDA versions.☆45Updated last month
- A Micro-benchmarking Tool for HPC Networks☆22Updated 3 weeks ago
- An infrastructure for inline acceleration of network applications☆30Updated 3 years ago
- SparseP is the first open-source Sparse Matrix Vector Multiplication (SpMV) software package for real-world Processing-In-Memory (PIM) ar…☆70Updated 2 years ago
- ☆36Updated 5 months ago
- ☆31Updated 5 months ago
- Modifications to GEM5 for running kernel bypass networking. (DPDK)☆15Updated last year
- ☆20Updated 7 years ago
- Instanciate the Cache Aware Roofline Model on single socket and multisocket systems.☆27Updated 5 years ago