OpenBLAS

78 MB

Tree: 2c3cdaf74e

Author	SHA1	Message	Date
Chris Sidebottom	2c3cdaf74e	Optimized BGEMV for NEOVERSEV1 target - Adds bgemv T based off of sbgemv T kernel - Adds bgemv N which is slightly alterated to not use Y as an accumulator due to the output being bf16 which results in loss of precision - Enables BGEMM_GEMV_FORWARD to proxy BGEMM to BGEMV with new kernels	2 months ago
Annop Wongwathanarat	edef2e4441	Fix bug in ARM64 sbgemv_t	6 months ago
Annop Wongwathanarat	a085b6c9ec	Fix aarch64 sbgemv_t compilation error for GCC < 13	6 months ago
Annop Wongwathanarat	edaf51dd99	Add sbgemv_t_bfdot kernel for ARM64 This improves performance for sbgemv_t by up to 100x on NEOVERSEV1. The geometric mean speedup is ~61x for M=N=[2,512].	7 months ago