amirjalili

CUDA_Data_Parallel_Reduction

Implementation of a work-efficient parallel reduction algorithm on the GPU with accumulation using atomic additions

CUDA_Parallel_Scan_prefix_sum

Implementation of a work-efficient parallel prefix-sum algorithm on the GPU.

CUDA_Tiled_2D_Convolution

Tiled implementation of a 2D matrix convolution by utilizing the shared and global constant memory within GPU thread blocks to minimize the memory bandwidth bottleneck and achieve a higher performance speedup.

CUDA_Tiled_Matrix_Multiplication

TILED Matrix Multiplication in CUDA by utilizing the lower latency, higher bandwidth shared memory within GPU thread blocks.

oberan

webflow-cost-calculator-CDN

amirjalili/CUDA_Parallel_Scan_prefix_sum

Implementation of a work-efficient parallel prefix-sum algorithm on the GPU.

amirjalili/CUDA_Tiled_2D_Convolution

Tiled implementation of a 2D matrix convolution by utilizing the shared and global constant memory within GPU thread blocks to minimize the memory bandwidth bottleneck and achieve a higher performance speedup.

amirjalili/CUDA_Data_Parallel_Reduction

Implementation of a work-efficient parallel reduction algorithm on the GPU with accumulation using atomic additions

amirjalili/CUDA_Tiled_Matrix_Multiplication

TILED Matrix Multiplication in CUDA by utilizing the lower latency, higher bandwidth shared memory within GPU thread blocks.

amirjalili/oberan

amirjalili/webflow-cost-calculator-CDN