OpenBLAS

9527 Commits

51 Branches

78 MB

305 Download

Branch: develop

Commit Graph

Author	SHA1	Message	Date
Bart Oldeman	b073d759d0	x86_64: clobber all xmm registers after vzeroupper As observed using GCC 10 using -march=native -ftree-vectorize on Knights Landing, it is now smart enough to find clobbers inside non-inlined static functions. In particular, sgemv counted on a kernel to preserve the whole %ymm2 register (since it was not in the clobber list), but the top part was destroyed by vzeroupper. This caused many tests to fail. This patch makes sure all xmm (and ymm/zmm by extension) registers are listed as clobbered to avoid this happening, as most kernels already did correctly in fact.	5 years ago
Martin Kroeker	d5e6940253	Fix declaration of input arguments in the x86_64 microkernels for DOT and AXPY (#1965 ) * Tag operands 0 and 1 as both input and output For #1964 (basically a continuation of coding problems first seen in #1292)	7 years ago
Werner Saar	baa0363ea2	add optimized ddot-kernel for piledriver	10 years ago

Author

SHA1

Message

Date

Bart Oldeman

b073d759d0

x86_64: clobber all xmm registers after vzeroupper

As observed using GCC 10 using -march=native -ftree-vectorize
on Knights Landing, it is now smart enough to find clobbers inside
non-inlined static functions.

In particular, sgemv counted on a kernel to preserve the whole
%ymm2 register (since it was not in the clobber list), but the top
part was destroyed by vzeroupper. This caused many tests to fail.

This patch makes sure all xmm (and ymm/zmm by extension) registers
are listed as clobbered to avoid this happening, as most kernels
already did correctly in fact.

5 years ago

Martin Kroeker

d5e6940253

Fix declaration of input arguments in the x86_64 microkernels for DOT and AXPY (#1965 )

* Tag operands 0 and 1 as both input and output

For #1964 (basically a continuation of coding problems first seen in #1292)

7 years ago

Werner Saar

baa0363ea2

add optimized ddot-kernel for piledriver

10 years ago

3 Commits (develop)