The tiled kernel uses 16x16 output tiles backed by an 18x18 shared-memory tile so that each block can reuse neighboring pixels while computing the convolution. The test covers 1x1, 1x17, 17x1, 2x3, ...
Implicit GEMM is the formulation of a convolution operation as a GEMM (generalized matrix-matrix product). Convolution takes an activation tensor and applies a sliding filter on it to produce an ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results