Nallani Bhaskar 1d31386c02 Fixed few out of bound memory reads in sgemmsup kernels ...

Details:
 Fixed memory access bugs in the bli_sgemmsup_rd_zen_asm_s1x16()
  kernel. The bugs were caused by loading four
  single-precision elements of C, via instructions such as:

	vfmadd231ps(mem(rcx, 0*32), ymm3, ymm4)

        or

        vfmadd231ps(mem(rcx, 0*32), xmm3, xmm4)

  in situations where only two elements are guaranteed to exist. (These
  bugs may not have manifested in earlier tests due to the leading
  dimension alignment that BLIS employs by default.) The issue was fixed
  by replacing lines like the one above with:

	vmovsd(mem(rcx), xmm0)
	vfmadd231ps(xmm0, xmm3, xmm4)

  Thus, we use vmovsd to explicitly load only two elements of C into
  registers, and then operate on those values using register addressing.

  AMD_CPUPLID: CPUPL-2279

Change-Id: Ic39290d651f5218b2e548351a87ac5e4b5b79c68

2022-07-29 09:09:12 -04:00

..

sup

Fixed few out of bound memory reads in sgemmsup kernels

2022-07-29 09:09:12 -04:00

bli_dgemm_ref_k1.c

Fixed high impact static analysis issues

2022-06-27 08:19:26 +00:00

bli_gemm_small.c

Changes to enable zgemm small from BLAS Layer

2022-05-17 18:10:38 +05:30

bli_gemm_sqp_kernels.c

Induced method turned off, fix for beta=0 & C = NAN

2021-11-12 08:58:50 +05:30

bli_gemm_sqp_kernels.h

3m_sqp conjugate support added

2021-07-05 18:44:55 +05:30

bli_gemm_sqp.c

3m_sqp conjugate support added

2021-07-05 18:44:55 +05:30

bli_trsm_small.c

BugFix of AOCL_DYNAMIC in TRSM multithreaded small.

2022-06-14 15:46:17 +05:30

bli_zgemm_ref_k1.c

Implemented efficient ZGEMM algorithm when k=1

2022-07-28 02:09:45 -04:00

CMakeLists.txt

ZGEMM kernel performance improvement for k=1 sizes:

2022-06-30 07:19:52 -04:00