OpenBLAS

78 MB

Tree: 94de62e8be

Author	SHA1	Message	Date
Martin Kroeker	701ea88347	Use p2align instead of align for OSX compatibility fixes #1902	7 years ago
Arjan van de Ven	582c589727	dgemm/skylakex: replace discrete mul/add with fma very minor gains since it's not super hot code, but general principles	7 years ago
Arjan van de Ven	20c5d668fe	dgemm/avx512 simplify and speed up the 4x4 kernel	7 years ago
Arjan van de Ven	6d43c51ccf	undo slow dgemm/skylake microoptimization the compare is more costly than the work	7 years ago
Arjan van de Ven	66b43affbc	Add a 24x8 kernel to the skylakex dgemm implementation Minor gains for small matrixes, but at 512x512 and above the gain gets more significant.	7 years ago
Arjan van de Ven	1938819c25	skylake dgemm: Add a 16x8 kernel The next step for the avx512 dgemm code is adding a 16x8 kernel. In the 8x8 kernel, each FMA has a matching load (the broadcast); in the 16x8 kernel we can reuse this load for 2 FMAs, which in turn reduces pressure on the load ports of the CPU and gives a nice performance boost (in the 25% range).	7 years ago
Martin Kroeker	b7496c3638	Function name needs to be CNAME, set from outside to allow suffixing for dynamic_arch	7 years ago
Arjan van de Ven	45fe8cb0c5	Create a AVX512 enabled version of DGEMM This patch adds dgemm_kernel_4x8_skylakex.c which is * dgemm_kernel_4x8_haswell.s converted to C + intrinsics * 8x8 support added * 8x8 kernel implemented using AVX512 Performance is a work in progress, but already shows a 10% - 20% increase for a wide range of matrix sizes.	7 years ago

8 Commits (94de62e8be1d63d2668d2aa71ce266e630c90b17)