diff options
Diffstat (limited to 'src/core/NEON/kernels/arm_gemm/mergeresults.cpp')
| -rw-r--r-- | src/core/NEON/kernels/arm_gemm/mergeresults.cpp | 6 |
1 files changed, 5 insertions, 1 deletions
diff --git a/src/core/NEON/kernels/arm_gemm/mergeresults.cpp b/src/core/NEON/kernels/arm_gemm/mergeresults.cpp index 17566db375..bbfe8f23d9 100644 --- a/src/core/NEON/kernels/arm_gemm/mergeresults.cpp +++ b/src/core/NEON/kernels/arm_gemm/mergeresults.cpp @@ -37,9 +37,13 @@ namespace arm_gemm { template<unsigned int twidth, unsigned int height, bool sve=false, typename Tin, typename Tout> void MergeResults(Tout * out, const Tin * in, int ldc, int y0, int ymax, int x0, int xmax, const Tout *bias, Activation act, bool append) { + // NOTE: The following code is disabled to avoid calling get_vector_length(), so templated MergeResults will not + // be correct for SVE cases. This is OK as we have specialisations for all needed SVE cases anyway. + // // For SVE cases, multiply the width up by the vector length. // Use the *input* type to determine this, since this will be what the kernel operated on. - const int width = twidth * (sve ? get_vector_length<Tin>() : 1); + // const int width = twidth * (sve ? get_vector_length<Tin>() : 1); + const int width = twidth; const int full_y_blocks = (ymax - y0) / height; const int y_remainder = (ymax - y0) % height; |