Zhang Xianyi
229ce2ccd1
Add cortex-a9 and cortex-a15 targets.
11 years ago
Zhang Xianyi
41aad0407f
Merge pull request #482 from jeromerobert/develop
Allow to do gemv and ger buffer allocation on the stack
11 years ago
Werner Saar
ddf983d643
added optimizations for steamroller
11 years ago
Werner Saar
4319769b79
added target processor STEAMROLLER
11 years ago
Jerome Robert
e9d9a8eae3
Allow to do gemv and ger buffer allocation on the stack
ger and gemv call blas_memory_alloc/free which in their turn
call blas_lock. blas_lock create thread contention when matrices
are small and the number of thread is high enough. We avoid
call blas_memory_alloc by replacing it with stack allocation.
This can be enabled with:
make -DMAX_STACK_ALLOC=2048
The given size (in byte) must be high enough to avoid thread contention
and small enough to avoid stack overflow.
Fix #478
11 years ago
Werner Saar
587e16fba3
Ref #458 : Backport, sandybrigde uses nehalem zgemm kernel
11 years ago
Werner Saar
6261342de3
small optimization on dgemm_kernel for N=1
11 years ago
Werner Saar
bc5fff7085
changed inline assembler labels to short form
11 years ago
Zhang Xianyi
0cf29ba6d2
Fixed a bug of sgemm sandy bridge kernel.
Reported by Julia project. JuliaLang/julia#9084
11 years ago
Zhang Xianyi
2fb02626da
Update organization info.
11 years ago
Zhang Xianyi
a85c2785ae
Refs #467 . Added generic kernel file for x86_64.
11 years ago
Benedikt Huber
58c90d5937
# The first commit's message is:
Optimizations for APM's xgene-1 (aarch64).
1) general system updates to support armv8 better. Make all did not work, one needed to supply TARGET=ARMV8.
2) sgem 4x4 kernel in assembler using SIMD, and configuration changes to use it.
3) strmm 4x4 kernel in C. Since the sgem kernel does 4x4, the trmm kernel must also do 4xN.
Added Dave Nuechterlein to the contributors list.
11 years ago
wernsaar
7aae4a62e7
enabled use of GEMM3M functions
11 years ago
wernsaar
b7c9566eea
removed obsolete gemv kernel files
11 years ago
wernsaar
6df1b0be81
optimized zgemv_n_microk_sandy-4.c
11 years ago
wernsaar
2ac1e076c1
added optimized zgemv_n kernel for sandybridge
11 years ago
wernsaar
9908b6031c
bugfix in KERNEL.PILEDRIVER
11 years ago
wernsaar
8f100a14f2
optimized cgemv_t kernel for haswell
11 years ago
wernsaar
53b5726b04
added optimized cgemv_t kernel for haswell
11 years ago
wernsaar
1a352b24e6
updated KERNEL.HASWELL
11 years ago
wernsaar
5194818d4b
updated zgemv_t_4.c
11 years ago
wernsaar
8a39cdb1c1
added optimized zgemv_t kernel for haswell
11 years ago
wernsaar
0a1390f2d8
enabled optimized zgemv_t kernel for bulldozer
11 years ago
wernsaar
a8b0812feb
optimized zgemv_t for bulldozer
11 years ago
wernsaar
a0fb68ab42
added optimized zgemv_t kernel for bulldozer
11 years ago
wernsaar
44c11165d5
bugfix in cgemv_t_4.c
11 years ago
wernsaar
564be4eb72
added optimized cgemv_t kernel
11 years ago
wernsaar
107c3ea7d5
added optimized zgemv_t routine
11 years ago
wernsaar
bb8d698335
optimized zgemv_n_microk_haswell-4.c for small size
11 years ago
wernsaar
e0192a6914
bugfix in zgemv_n_4.c
11 years ago
wernsaar
bced4594bb
added optimized zgemv_n kernel
11 years ago
wernsaar
cafba99b6b
bufix in cgemv_n_microk_haswell-4.c
11 years ago
wernsaar
ac8f232b2a
more optimizations
11 years ago
wernsaar
f98e1244c4
optimized cgemv_n_4.c
11 years ago
wernsaar
be95700b30
added optimized cgemv_kernel for haswell
11 years ago
wernsaar
4aa534ae93
added cgemv_n kernel, optimized for small sizes
11 years ago
wernsaar
baa46e4fba
added and tested optimized dgemv_n kernel for haswell
11 years ago
wernsaar
faab7a181d
added optimized dgemv_n kernel for haswell
11 years ago
wernsaar
8109d8232c
optimized dgemv_t kernel for haswell
11 years ago
wernsaar
debc6d1a05
bugfix in KERNEL.HASWELL
11 years ago
wernsaar
e73a0113ec
added optimized gemv kernels
11 years ago
wernsaar
44f2bf9bae
added optimized dgemv_t kernel for haswell
11 years ago
wernsaar
cd34e9701b
removed obsolete files
11 years ago
wernsaar
658939faaa
optimized dgemv_n kernel for small sizes
11 years ago
wernsaar
c4d9d4e5f8
added haswell optimized kernel
11 years ago
wernsaar
7c0a94ff47
bugfix in sgemv_n_microk_haswell-4.c
11 years ago
wernsaar
cbbc80aad3
added optimized sgemv_t kernel for haswell
11 years ago
wernsaar
2be5c7a640
bugfix for windows
11 years ago
wernsaar
80f7786875
enabled optimized sgemv kernels for piledriver
11 years ago
wernsaar
553e275407
optimized sgemv_n kernel for sandybridge
11 years ago