enp1s0

Emulation is all you need

@NVIDIATokyo/Japan

Pinned Repositories

CULiP
Library for profiling the execution time of CUDA official library functions
Language:Cuda7 3 00
cuMpSGEMM
Fast SGEMM emulation on Tensor Cores
Language:Cuda7 3 00
cutf
CUDA Template Functions
Language:C++19 4 01
cutlass
CUDA Templates for Linear Algebra Subroutines
Language:C++6 2 02
gpu_monitor
Records GPU temperature, power consumption, memory usage while executing programs on GPUs
Language:C++51
ozIMMU
FP64 equivalent GEMM via Int8 Tensor Cores using the Ozaki scheme
Language:Cuda49 4 12
shgemm
Fast multiplication of single-precision and half-precision matrices on Tensor Cores
Language:Cuda7 2 00
tsqr-gpu
Implementation of TSQR, an efficient QR factorization algorithm for tall skinny matrices, on TensorCores
Language:Cuda60
tsqr-tc
TSQR on TensorCores
Language:Cuda41
wmma_extension
An extension library of WMMA API (Tensor Core API)
Language:Cuda87 8 414

enp1s0's Repositories

enp1s0/ozIMMU
FP64 equivalent GEMM via Int8 Tensor Cores using the Ozaki scheme
Language:Cuda49 4 12
enp1s0/cutf
CUDA Template Functions
Language:C++19 4 01
enp1s0/CULiP
Library for profiling the execution time of CUDA official library functions
Language:Cuda7 3 00
enp1s0/cuMpSGEMM
Fast SGEMM emulation on Tensor Cores
Language:Cuda7 3 00
enp1s0/gpu_monitor
Records GPU temperature, power consumption, memory usage while executing programs on GPUs
Language:C++51
enp1s0/anns_dataset
Language:C++2 2 0
enp1s0/mateval
Language:Cuda2
enp1s0/cublas-imma-test
Language:Cuda1
enp1s0/culina
Language:Cuda1 2 0
enp1s0/enp1s0.github.io
Language:HTML1 3 00
enp1s0/matfile
Language:C++11
enp1s0/mk_graph
Language:Python1 3 0
enp1s0/simple_fp8
Language:C++1
enp1s0/single-shot-cublas-test
Language:Cuda1 2 0
enp1s0/blog
Language:Ruby2 01
enp1s0/cfigout
Language:C++2 0
enp1s0/cublas-performance
Language:Cuda
enp1s0/cublaslt-test
Language:Cuda2 0
enp1s0/cuda-redux
Language:Cuda2 0
enp1s0/cuda-streamed-gemv-bench
Language:Cuda2 0
enp1s0/cudaMemcpy2DAsync.example
Language:Cuda2 0
enp1s0/cuvs
cuVS - a library for vector search and clustering on the GPU
Language:Cuda0 0
enp1s0/fphistogram
Language:C++3 0
enp1s0/gres_config_gen
Language:Shell3 02
enp1s0/histo
Language:C++2 0
enp1s0/jobscheduler2slack
Language:Shell3 0
enp1s0/mpitf
Language:C++
enp1s0/parallel-rand-test
Language:C++
enp1s0/raft
RAFT contains fundamental widely-used algorithms and primitives for data science, graph and machine learning.
Language:Cuda1 0
enp1s0/sycl-test
Language:C++2 0