Efficient out-of-core GEMM solvers for GPUs

The package contains efficient out-of-core solvers performing the following Matrix-Matrix multiplication on one or more GPUs.

C = alpha * op(A) * op(B) + beta * C

where A, B, C are dense matrices of sizes m*k, k*n, and m*n respectively.

Original Authors

Ziming Zhong
Vladimir Rychkov
Alexey Lastovetsky

Current Developers
Ravi Reddy Manumachu
Hamidreza Khaleghzadeh

Downloads