Searched full:convolutions (Results 1 – 14 of 14) sorted by relevance
1186 which is a special case for most depthwise convolutions.1207 which is a special case for most depthwise convolutions.1248 which is a special case for most depthwise convolutions.1269 which is a special case for most depthwise convolutions.1367 which is a special case for most depthwise convolutions.1402 which is a special case for most depthwise convolutions.
288 // Try to slice the targetted result size, cap to the convolutions width. in matchAndRewrite()
47 // Convolution proper. While Linalg has named operations for 2D convolutions,
4200 which is a special case for most depthwise convolutions.4283 which is a special case for most depthwise convolutions.4451 which is a special case for most depthwise convolutions.4544 which is a special case for most depthwise convolutions.4993 which is a special case for most depthwise convolutions.5092 which is a special case for most depthwise convolutions.
85 // Convolution proper. While Linalg has named operations for 2D convolutions,
312 // For 2D convolutions, we need to check if the target convolution op in matchAndRewrite()
990 return "unexpected input index map for convolutions"; in createFlatListOfOperandStaticDims()
1704 /// Linalg decompose convolutions patterns
160 Performs 2D convolutions separately over each channel of the given tensor
235 (depthwise) convolutions, into combinations of lower-dimensional equivalents
1176 // expected-error @+1 {{unexpected input index map for convolutions}}
3468 /// depthwise convolutions. This should lead to bette vectorization for in applyToOne()
120 // Extract rhs slice of size [{c, f} for channeled convolutions and {1} for in extractConvFilterSlices()
2357 // We go through some convolutions here to avoid copying results in LookupQualifiedNameInUsingDirectives()