OpenBLAS

5 years ago

caxpy_microk_haswell-2.c

5 years ago

caxpy_microk_sandy-2.c

5 years ago

caxpy_microk_steamroller-2.c

5 years ago

cdot.c

initial support for Sapphire Rapids platform

4 years ago

cdot_microk_bulldozer-2.c

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

6 years ago

cdot_microk_haswell-2.c

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

6 years ago

cdot_microk_sandy-2.c

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

6 years ago

cdot_microk_steamroller-2.c

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

6 years ago

cgemm3m_kernel_8x4_haswell.c

Update cgemm3m_kernel_8x4_haswell.c

5 years ago

cgemm_kernel_4x2_bulldozer.S

change line endings from CRLF to LF

2 years ago

cgemm_kernel_4x2_piledriver.S

change line endings from CRLF to LF

2 years ago

cgemm_kernel_4x8_sandy.S

Update organization info.

11 years ago

cgemm_kernel_8x2_haswell.S

modification for clang compiler

11 years ago

cgemm_kernel_8x2_haswell.c

Update cgemm_kernel_8x2_haswell.c

5 years ago

cgemm_kernel_8x2_sandy.S

change line endings from CRLF to LF

2 years ago

cgemm_kernel_8x2_skylakex.c

AVX512 CGEMM & ZGEMM kernels

5 years ago

cgemv_n.S

Remove all trailing whitespace except lapack-netlib

11 years ago

cgemv_n_4.c

Disable gcc's tree-vectorizer pass on all operating systems

2 years ago

cgemv_n_microk_bulldozer-4.c

7 years ago

cgemv_n_microk_haswell-4.c

Tag %1 and %2 as both input and output

7 years ago

cgemv_t.S

Remove all trailing whitespace except lapack-netlib

11 years ago

cgemv_t_4.c

Disable gcc's tree-vectorizer pass on all operating systems

2 years ago

cgemv_t_microk_bulldozer-4.c

7 years ago

cgemv_t_microk_haswell-4.c

Tag %1 and %2 as both input and output

7 years ago

copy.S

Remove all trailing whitespace except lapack-netlib

11 years ago

copy_sse.S

Import GotoBLAS2 1.13 BSD version codes.

14 years ago

copy_sse2.S

Convert aligned moves to unaligned

5 years ago

cscal.c

Add [cz]scal microkernels for SKYLAKEX

2 years ago

cscal_microk_bulldozer-2.c

Fix declaration of input arguments in the x86_64 SCAL microkernels (#1966)

6 years ago

cscal_microk_haswell-2.c

Fix declaration of input arguments in the x86_64 SCAL microkernels (#1966)

6 years ago

cscal_microk_skylakex-2.c

Enable use of AVX512 microkernels with NVIDIA HPC from version 22.3

2 years ago

cscal_microk_steamroller-2.c

Fix declaration of input arguments in the x86_64 SCAL microkernels (#1966)

6 years ago

csum.c

Add CSUM and ZSUM kernels (trivially derived from their existing ASUM counterparts)

1 year ago

csum_microk_skylakex-2.c

Add CSUM and ZSUM kernels (trivially derived from their existing ASUM counterparts)

1 year ago

ctrsm_kernel_LN_bulldozer.c

added optimized trsm_kernels

9 years ago

ctrsm_kernel_LT_bulldozer.c

added optimized trsm_kernels

9 years ago

ctrsm_kernel_RN_bulldozer.c

added optimized trsm_kernels

9 years ago

ctrsm_kernel_RT_bulldozer.c

added optimized trsm_kernels

9 years ago

dasum.c

Use SkylakeX ?ASUM microkernel for Cooperlake/Sapphirerapids as well

1 year ago

dasum_microk_haswell-2.c

Enable use of AVX512 microkernels with NVIDIA HPC from version 22.3

2 years ago

dasum_microk_skylakex-2.c

Enable use of AVX512 microkernels with NVIDIA HPC from version 22.3

2 years ago

daxpy.c

initial support for Sapphire Rapids platform

4 years ago

daxpy_bulldozer.S

Remove all trailing whitespace except lapack-netlib

11 years ago

daxpy_microk_bulldozer-2.c

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

6 years ago

daxpy_microk_haswell-2.c

5 years ago

daxpy_microk_nehalem-2.c

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

6 years ago

daxpy_microk_piledriver-2.c

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

6 years ago

daxpy_microk_sandy-2.c

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

6 years ago

daxpy_microk_skylakex-2.c

Enable use of AVX512 microkernels with NVIDIA HPC from version 22.3

2 years ago

daxpy_microk_steamroller-2.c

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

6 years ago

dcopy_bulldozer.S

added dcopy_bulldozer.S

12 years ago

ddot.c

fix improper function prototypes (empty parentheses)

2 years ago

ddot_bulldozer.S

Remove all trailing whitespace except lapack-netlib

11 years ago

ddot_microk_bulldozer-2.c

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

6 years ago

ddot_microk_haswell-2.c

5 years ago

ddot_microk_nehalem-2.c

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

6 years ago

ddot_microk_piledriver-2.c

5 years ago

ddot_microk_sandy-2.c

5 years ago

ddot_microk_skylakex-2.c

Enable use of AVX512 microkernels with NVIDIA HPC from version 22.3

2 years ago

ddot_microk_steamroller-2.c

5 years ago

dgemm_beta_skylakex.c

Fix thinko in skylake beta handling

6 years ago

dgemm_kernel_4x4_haswell.S

change line endings from CRLF to LF

2 years ago

dgemm_kernel_4x8_haswell.S

change line endings from CRLF to LF

2 years ago

dgemm_kernel_4x8_sandy.S

Change file comments to work around clang 3.9 assembler bug

9 years ago

dgemm_kernel_4x8_skylakex.c

Use p2align instead of align for OSX compatibility

6 years ago

dgemm_kernel_4x8_skylakex_2.c

change line endings from CRLF to LF

2 years ago

dgemm_kernel_6x4_piledriver.S

Remove all trailing whitespace except lapack-netlib

11 years ago

dgemm_kernel_8x2_bulldozer.S

change line endings from CRLF to LF

2 years ago

dgemm_kernel_8x2_piledriver.S

change line endings from CRLF to LF

2 years ago

dgemm_kernel_8x8_skylakex.c

Update dgemm_kernel_8x8_skylakex.c

6 years ago

dgemm_kernel_16x2_haswell.S

change line endings from CRLF to LF

2 years ago

dgemm_kernel_16x2_skylakex.S

Use AVX512 also for DGEMM

7 years ago

dgemm_kernel_16x2_skylakex.c

GEMM: skylake: improve the performance when m is small

4 years ago

dgemm_ncopy_2.S

Remove all trailing whitespace except lapack-netlib

11 years ago

dgemm_ncopy_4.S

Remove all trailing whitespace except lapack-netlib

11 years ago

dgemm_ncopy_8.S

Remove all trailing whitespace except lapack-netlib

11 years ago

dgemm_ncopy_8_bulldozer.S

Remove all trailing whitespace except lapack-netlib

11 years ago

dgemm_ncopy_8_skylakex.c

Fix warnings

3 years ago

dgemm_small_kernel_nn_skylakex.c

Enable use of AVX512 microkernels with NVIDIA HPC from version 22.3

2 years ago

dgemm_small_kernel_nt_skylakex.c

Small Matrix: use proper inline asm input constraint for AVX512 mask

3 years ago

dgemm_small_kernel_permit_skylakex.c

Small Matrix: skylakex: add DGEMM_SMALL_M_PERMIT and tune for TN kernel

4 years ago

dgemm_small_kernel_tn_skylakex.c

Enable use of AVX512 microkernels with NVIDIA HPC from version 22.3

2 years ago

dgemm_small_kernel_tt_skylakex.c

Small Matrix: skylakex: fix build error in old compiler

4 years ago

dgemm_tcopy_2.S

Remove all trailing whitespace except lapack-netlib

11 years ago

dgemm_tcopy_4.S

Remove all trailing whitespace except lapack-netlib

11 years ago

dgemm_tcopy_8.S

Remove all trailing whitespace except lapack-netlib

11 years ago

dgemm_tcopy_8_bulldozer.S

Remove all trailing whitespace except lapack-netlib

11 years ago

dgemm_tcopy_8_skylakex.c

Add optimized *copy versions for skylakex

7 years ago

dgemm_tcopy_16_skylakex.c

Fix build with -Werror=return-type

5 years ago

dgemv_n.S

Remove all trailing whitespace except lapack-netlib

11 years ago

dgemv_n_4.c

initial support for Sapphire Rapids platform

4 years ago

dgemv_n_atom.S

Remove all trailing whitespace except lapack-netlib

11 years ago

dgemv_n_bulldozer.S

Remove all trailing whitespace except lapack-netlib

11 years ago

dgemv_n_microk_haswell-4.c

5 years ago

dgemv_n_microk_nehalem-4.c

Replace .align with .p2align in the Nehalem microkernels

7 years ago

dgemv_n_microk_piledriver-4.c

5 years ago

dgemv_n_microk_skylakex-4.c

Enable use of AVX512 microkernels with NVIDIA HPC from version 22.3

2 years ago

dgemv_t.S

Remove all trailing whitespace except lapack-netlib

11 years ago

dgemv_t_4.c

initial support for Sapphire Rapids platform

4 years ago

dgemv_t_atom.S

Remove all trailing whitespace except lapack-netlib

11 years ago

dgemv_t_bulldozer.S

Remove all trailing whitespace except lapack-netlib

11 years ago

dgemv_t_microk_haswell-4.c

5 years ago

dger.c

optimized dger kernel for sandybridge

10 years ago

dger_microk_sandy-2.c

Fix declaration of input arguments in the Sandybridge GER microkernels (#1967)

6 years ago

dot.S

use emms instead, add WIN guards

5 years ago

dot_atom.S

Remove all trailing whitespace except lapack-netlib

11 years ago

dot_sse.S

Remove all trailing whitespace except lapack-netlib

11 years ago

dot_sse2.S

Remove all trailing whitespace except lapack-netlib

11 years ago

drot.c

fix improper function prototypes (empty parentheses)

2 years ago

drot_microk_haswell-2.c

replace spurious avx512 requirement with fma check

4 years ago

drot_microk_skylakex-2.c

Enable use of AVX512 microkernels with NVIDIA HPC from version 22.3

2 years ago

dscal.c

initial support for Sapphire Rapids platform

4 years ago

dscal_microk_bulldozer-2.c

Fix declaration of input arguments in the x86_64 SCAL microkernels (#1966)

6 years ago

dscal_microk_haswell-2.c

dscal: use ymm registers in Haswell microkernel

2 years ago

dscal_microk_sandy-2.c

Fix declaration of input arguments in the x86_64 SCAL microkernels (#1966)

6 years ago

dscal_microk_skylakex-2.c

Enable use of AVX512 microkernels with NVIDIA HPC from version 22.3

2 years ago

dsymv_L.c

initial support for Sapphire Rapids platform

4 years ago

dsymv_L_microk_bulldozer-2.c

6 years ago

dsymv_L_microk_haswell-2.c

6 years ago

dsymv_L_microk_nehalem-2.c

6 years ago

dsymv_L_microk_sandy-2.c

6 years ago

dsymv_L_microk_skylakex-2.c

Enable use of AVX512 microkernels with NVIDIA HPC from version 22.3

2 years ago

dsymv_U.c

initial support for Sapphire Rapids platform

4 years ago

dsymv_U_microk_bulldozer-2.c

Fix declaration of assembly arguments in SSYMV and DSYMV microkernels

6 years ago

dsymv_U_microk_haswell-2.c

Fix declaration of assembly arguments in SSYMV and DSYMV microkernels

6 years ago

dsymv_U_microk_nehalem-2.c

Fix declaration of assembly arguments in SSYMV and DSYMV microkernels

6 years ago

dsymv_U_microk_sandy-2.c

Fix declaration of assembly arguments in SSYMV and DSYMV microkernels

6 years ago

dtobf16_microk_cooperlake.c

Enable use of AVX512 microkernels with NVIDIA HPC from version 22.3

2 years ago

dtrmm_kernel_4x8_haswell.c

Replace vpermpd with vpermilpd in the Haswell DTRMM kernel

6 years ago

dtrsm_kernel_LN_bulldozer.c

Remove unused variables from Haswell dtrmm and Bulldozer dtrsm

7 years ago

dtrsm_kernel_LT_8x2_bulldozer.S

Remove all trailing whitespace except lapack-netlib

11 years ago

dtrsm_kernel_RN_8x2_bulldozer.S

Remove all trailing whitespace except lapack-netlib

11 years ago

dtrsm_kernel_RN_haswell.c

Replace most vpermpd calls in the Haswell DTRSM_RN kernel

6 years ago

dtrsm_kernel_RT_bulldozer.c

Fix inline assembly constraints in Bulldozer TRSM kernels

6 years ago

gemm_beta.S

Remove all trailing whitespace except lapack-netlib

11 years ago

gemm_kernel_2x8_nehalem.S

Remove all trailing whitespace except lapack-netlib

11 years ago

gemm_kernel_4x2_atom.S

Remove all trailing whitespace except lapack-netlib

11 years ago

gemm_kernel_4x4_barcelona.S

Remove all trailing whitespace except lapack-netlib

11 years ago

gemm_kernel_4x4_core2.S

Remove all trailing whitespace except lapack-netlib

11 years ago

gemm_kernel_4x4_penryn.S

Remove all trailing whitespace except lapack-netlib

11 years ago

gemm_kernel_4x4_sse2.S

Remove all trailing whitespace except lapack-netlib

11 years ago

gemm_kernel_4x4_sse3.S

Remove all trailing whitespace except lapack-netlib

11 years ago

gemm_kernel_4x8_nano.S

Fix crash in sgemm SSE/nano kernel on x86_64

6 years ago

gemm_kernel_4x8_nehalem.S

Remove all trailing whitespace except lapack-netlib

11 years ago

gemm_kernel_8x4_barcelona.S

Remove all trailing whitespace except lapack-netlib

11 years ago

gemm_kernel_8x4_core2.S

Remove all trailing whitespace except lapack-netlib

11 years ago

gemm_kernel_8x4_penryn.S

Remove all trailing whitespace except lapack-netlib

11 years ago

gemm_kernel_8x4_sse.S

Fix crash in sgemm SSE/nano kernel on x86_64

6 years ago

gemm_kernel_8x4_sse3.S

Remove all trailing whitespace except lapack-netlib

11 years ago

gemm_ncopy_2.S

Remove all trailing whitespace except lapack-netlib

11 years ago

gemm_ncopy_2_bulldozer.S

Remove all trailing whitespace except lapack-netlib

11 years ago

gemm_ncopy_4.S

Add forgotten conditional uses of PREFETCH

1 year ago

gemm_ncopy_4_opteron.S

Remove all trailing whitespace except lapack-netlib

11 years ago

gemm_tcopy_2.S

Remove all trailing whitespace except lapack-netlib

11 years ago

gemm_tcopy_2_bulldozer.S

Remove all trailing whitespace except lapack-netlib

11 years ago

gemm_tcopy_4.S

Add forgotten conditional uses of PREFETCH

1 year ago

gemm_tcopy_4_opteron.S

Remove all trailing whitespace except lapack-netlib

11 years ago

iamax.S

use emms instead, add WIN guards

5 years ago

iamax_sse.S

Silence a redefinition warning

5 years ago

iamax_sse2.S

Remove all trailing whitespace except lapack-netlib

11 years ago

izamax.S

use emms instead, add WIN guards

5 years ago

izamax_sse.S

Remove all trailing whitespace except lapack-netlib

11 years ago

izamax_sse2.S

Remove all trailing whitespace except lapack-netlib

11 years ago

lsame.S

Import GotoBLAS2 1.13 BSD version codes.

14 years ago

mcount.S

Import GotoBLAS2 1.13 BSD version codes.

14 years ago

nrm2.S

Allow negative INCX (API change from version 3.10 of the reference implementation)

2 years ago

nrm2_sse.S

Allow negative INCX (API change from version 3.10 of the reference implementation)

2 years ago

omatcopy_rt.c

Fix warnings

3 years ago

qconjg.S

use emms instead, add WIN guards

5 years ago

qdot.S

use emms instead, add WIN guards

5 years ago

qgemm_kernel_2x2.S

use emms instead, add WIN guards

5 years ago

qgemv_n.S

use emms instead, add WIN guards

5 years ago

qgemv_t.S

use emms instead, add WIN guards

5 years ago

qtrsm_kernel_LN_2x2.S

use emms instead, add WIN guards

5 years ago

qtrsm_kernel_LT_2x2.S

use emms instead, add WIN guards

5 years ago

qtrsm_kernel_RT_2x2.S

use emms instead, add WIN guards

5 years ago

rot.S

Remove all trailing whitespace except lapack-netlib

11 years ago

rot_sse.S

Remove all trailing whitespace except lapack-netlib

11 years ago

rot_sse2.S

Remove all trailing whitespace except lapack-netlib

11 years ago

sasum.c

Use SkylakeX ?ASUM microkernel for Cooperlake/Sapphirerapids as well

1 year ago

sasum_microk_haswell-2.c

Enable use of AVX512 microkernels with NVIDIA HPC from version 22.3

2 years ago

sasum_microk_skylakex-2.c

Enable use of AVX512 microkernels with NVIDIA HPC from version 22.3

2 years ago

saxpy.c

initial support for Sapphire Rapids platform

4 years ago

saxpy_microk_haswell-2.c

5 years ago

saxpy_microk_nehalem-2.c

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

6 years ago

saxpy_microk_piledriver-2.c

5 years ago

saxpy_microk_sandy-2.c

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

6 years ago

saxpy_microk_skylakex-2.c

Enable use of AVX512 microkernels with NVIDIA HPC from version 22.3

2 years ago

sbdot.c

initial support for Sapphire Rapids platform

4 years ago

sbdot_microk_cooperlake.c

Enable use of AVX512 microkernels with NVIDIA HPC from version 22.3

2 years ago

sbgemm_block_microk_cooperlake.c

x86_64: BFLOAT16: fix build warning

4 years ago

sbgemm_kernel_16x4_cooperlake.c

Prevent compiler attempts to use k0 as mask register

3 years ago

sbgemm_kernel_16x16_spr.c

sbgemm: spr: kernel handle alpha != 1.0

4 years ago

sbgemm_kernel_16x16_spr_tmpl.c

Fix spr sbgemm error

2 years ago

sbgemm_microk_cooperlake_template.c

really fix definition of SHUFFLE_MAGIC_NO

3 years ago

sbgemm_ncopy_4_cooperlake.c

sbgemm: cooperlake: kernel works for NN

4 years ago

sbgemm_ncopy_16_cooperlake.c

Fix non-portable u_int64_t

3 years ago

sbgemm_oncopy_16_spr.c

sbgemm: spr: oncopy: use tile load/store instead

4 years ago

sbgemm_otcopy_16_spr.c

sbgemm: spr: implement otcopy_16

4 years ago

sbgemm_small_kernel_nn_cooperlake.c

sbgemm: cooperlake: enable SBGEMM by small matrix path

4 years ago

sbgemm_small_kernel_nt_cooperlake.c

sbgemm: cooperlake: enable SBGEMM by small matrix path

4 years ago

sbgemm_small_kernel_permit_cooperlake.c

sbgemm: cooperlake: tuning for small matrix

4 years ago

sbgemm_small_kernel_permit_spr.c

sbgemm: spr: disable small matrix path by default

4 years ago

sbgemm_small_kernel_template_cooperlake.c

sbgemm: cooperlake: make sure hot buffer aligned to 64

4 years ago

sbgemm_small_kernel_tn_cooperlake.c

sbgemm: cooperlake: enable SBGEMM by small matrix path

4 years ago

sbgemm_small_kernel_tt_cooperlake.c

sbgemm: cooperlake: enable SBGEMM by small matrix path

4 years ago

sbgemm_tcopy_4_cooperlake.c

sbgemm: cooperlake: add n24 kernel for tcopy_4

4 years ago

sbgemm_tcopy_16_cooperlake.c

sbgemm: cooperlake: implement tcopy_4

4 years ago

sbgemv_n.c

initial support for Sapphire Rapids platform

4 years ago

sbgemv_n_microk_cooperlake.c

Enable use of AVX512 microkernels with NVIDIA HPC from version 22.3

2 years ago

sbgemv_n_microk_cooperlake_template.c

x86_64: BFLOAT16: fix build warning

4 years ago

sbgemv_t.c

initial support for Sapphire Rapids platform

4 years ago

sbgemv_t_microk_cooperlake.c

Enable use of AVX512 microkernels with NVIDIA HPC from version 22.3

2 years ago

sbgemv_t_microk_cooperlake_template.c

x86_64: BFLOAT16: fix build warning

4 years ago

scal.S

Import GotoBLAS2 1.13 BSD version codes.

14 years ago

scal_atom.S

Remove all trailing whitespace except lapack-netlib

11 years ago

scal_sse.S

Remove all trailing whitespace except lapack-netlib

11 years ago

scal_sse2.S

Remove all trailing whitespace except lapack-netlib

11 years ago

sdot.c

initial support for Sapphire Rapids platform

4 years ago

sdot_microk_bulldozer-2.c

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

6 years ago

sdot_microk_haswell-2.c

5 years ago

sdot_microk_nehalem-2.c

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

6 years ago

sdot_microk_sandy-2.c

5 years ago

sdot_microk_skylakex-2.c

Enable use of AVX512 microkernels with NVIDIA HPC from version 22.3

2 years ago

sdot_microk_steamroller-2.c

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

6 years ago

sgemm_beta_skylakex.c

sbgemm: cooperlake: add dummy source files

4 years ago

sgemm_direct_performant.c

[WIP] Refactor the driver code for direct SGEMM (#2782)

5 years ago

sgemm_direct_skylakex.c

initial support for Sapphire Rapids platform

4 years ago

sgemm_kernel_8x4_bulldozer.S

Remove all trailing whitespace except lapack-netlib

11 years ago

sgemm_kernel_8x4_haswell.c

Update sgemm_kernel_8x4_haswell.c

5 years ago

sgemm_kernel_8x4_haswell_2.c

Strip UTF8 byte order marker from source

5 years ago

sgemm_kernel_8x8_sandy.S

Update organization info.

11 years ago

sgemm_kernel_16x2_bulldozer.S

change line endings from CRLF to LF

2 years ago

sgemm_kernel_16x2_piledriver.S

change line endings from CRLF to LF

2 years ago

sgemm_kernel_16x4_haswell.S

change line endings from CRLF to LF

2 years ago

sgemm_kernel_16x4_sandy.S

change line endings from CRLF to LF

2 years ago

sgemm_kernel_16x4_skylakex.S

Use AVX512 also for DGEMM

7 years ago

sgemm_kernel_16x4_skylakex.c

make skylakex sgemm code more friendly for readers

5 years ago

sgemm_kernel_16x4_skylakex_2.c

AVX512 STRMM kernel

5 years ago

sgemm_kernel_16x4_skylakex_3.c

Use "old" compute(24) function with clang due to register limitations

4 years ago

sgemm_ncopy_4_skylakex.c

Use sgemm_ncopy_4_skylakex.c also for Haswell

6 years ago

sgemm_small_kernel_nn_skylakex.c

Enable use of AVX512 microkernels with NVIDIA HPC from version 22.3

2 years ago

sgemm_small_kernel_nt_skylakex.c

Small Matrix: use proper inline asm input constraint for AVX512 mask

3 years ago

sgemm_small_kernel_permit_skylakex.c

Small Matrix: skylakex: add sgemm tt kernel

4 years ago

sgemm_small_kernel_tn_skylakex.c

Enable use of AVX512 microkernels with NVIDIA HPC from version 22.3

2 years ago

sgemm_small_kernel_tt_skylakex.c

Small Matrix: skylakex: fix build error in old compiler

4 years ago

sgemm_tcopy_16_skylakex.c

Add a C+intrinsics version of the SGEMM/skylakex kernel

7 years ago

sgemv_n.S

Remove all trailing whitespace except lapack-netlib

11 years ago

sgemv_n.c

removed obsolete gemv kernel files

11 years ago

sgemv_n_4.c

Disable gcc's tree-vectorizer pass on all operating systems

2 years ago

sgemv_n_microk_bulldozer-4.c

Fix inline assembly constraints

6 years ago

sgemv_n_microk_haswell-4.c

5 years ago

sgemv_n_microk_nehalem-4.c

Fix inline assembly constraints

6 years ago

sgemv_n_microk_sandy-4.c

Fix inline assembly constraints

6 years ago

sgemv_n_microk_skylakex-8.c

Enable use of AVX512 microkernels with NVIDIA HPC from version 22.3

2 years ago

sgemv_t.S

Remove all trailing whitespace except lapack-netlib

11 years ago

sgemv_t.c

removed obsolete gemv kernel files

11 years ago

sgemv_t_4.c

Disable gcc's tree-vectorizer pass on all operating systems

2 years ago

sgemv_t_microk_bulldozer-4.c

7 years ago

sgemv_t_microk_haswell-4.c

5 years ago

sgemv_t_microk_nehalem-4.c

Replace .align with .p2align in the Nehalem microkernels

7 years ago

sgemv_t_microk_sandy-4.c

Use .p2align instead of .align for compatibility on Sandybridge as well

7 years ago

sgemv_t_microk_skylakex.c

Enable use of AVX512 microkernels with NVIDIA HPC from version 22.3

2 years ago

sgemv_t_microk_skylakex_template.c

sgemv: skylakex: fix build warning

4 years ago

sger.c

added optimized sger kernel for sandybridge

10 years ago

sger_microk_sandy-2.c

Fix declaration of input arguments in the Sandybridge GER microkernels (#1967)

6 years ago

srot.c

fix improper function prototypes (empty parentheses)

2 years ago

srot_microk_haswell-2.c

Remove spurious AVX512 requirement and add AVX2/FMA3 guard

4 years ago

srot_microk_skylakex-2.c

Enable use of AVX512 microkernels with NVIDIA HPC from version 22.3

2 years ago

sscal.c

Add sscal.c + microkernels for Haswell, Zen, Skylake and newer.

2 years ago

sscal_microk_haswell-2.c

Fix typo in clobber list, should be xmm14 instead of ymm14.

2 years ago

sscal_microk_skylakex-2.c

Enable use of AVX512 microkernels with NVIDIA HPC from version 22.3

2 years ago

ssymv_L.c

Disable gcc's tree-vectorizer pass on all operating systems

2 years ago

ssymv_L_microk_bulldozer-2.c

6 years ago

ssymv_L_microk_haswell-2.c

6 years ago

ssymv_L_microk_nehalem-2.c

6 years ago

ssymv_L_microk_sandy-2.c

6 years ago

ssymv_U.c

Disable gcc's tree-vectorizer pass on all operating systems

2 years ago

ssymv_U_microk_bulldozer-2.c

Fix declaration of assembly arguments in SSYMV and DSYMV microkernels

6 years ago

ssymv_U_microk_haswell-2.c

Fix declaration of assembly arguments in SSYMV and DSYMV microkernels

6 years ago

ssymv_U_microk_nehalem-2.c

Fix declaration of assembly arguments in SSYMV and DSYMV microkernels

6 years ago

ssymv_U_microk_sandy-2.c

Fix declaration of assembly arguments in SSYMV and DSYMV microkernels

6 years ago

staticbuffer.S

Import GotoBLAS2 1.13 BSD version codes.

14 years ago

stobf16_microk_cooperlake.c

Enable use of AVX512 microkernels with NVIDIA HPC from version 22.3

2 years ago

strsm_kernel_8x4_haswell_LN.c

Strip UTF8 byte order marker from source

5 years ago

strsm_kernel_8x4_haswell_LT.c

AVX2 STRSM kernel

5 years ago

strsm_kernel_8x4_haswell_L_common.h

Strip UTF8 byte order marker from source

5 years ago

strsm_kernel_8x4_haswell_RN.c

change line endings from CRLF to LF

2 years ago

strsm_kernel_8x4_haswell_RT.c

change line endings from CRLF to LF

2 years ago

strsm_kernel_8x4_haswell_R_common.h

change line endings from CRLF to LF

2 years ago

strsm_kernel_LN_bulldozer.c

Fix inline assembly constraints in Bulldozer TRSM kernels

6 years ago

strsm_kernel_LT_bulldozer.c

Fix inline assembly constraints in Bulldozer TRSM kernels

6 years ago

strsm_kernel_RN_bulldozer.c

Fix inline assembly constraints in Bulldozer TRSM kernels

6 years ago

strsm_kernel_RT_bulldozer.c

Fix inline assembly constraints in Bulldozer TRSM kernels

6 years ago

sum.S

use emms instead, add WIN guards

5 years ago

swap.S

Remove all trailing whitespace except lapack-netlib

11 years ago

swap_sse.S

Remove all trailing whitespace except lapack-netlib

11 years ago

swap_sse2.S

Remove all trailing whitespace except lapack-netlib

11 years ago

symv_L_sse.S

initial support for Sapphire Rapids platform

4 years ago

symv_L_sse2.S

initial support for Sapphire Rapids platform

4 years ago

symv_U_sse.S

initial support for Sapphire Rapids platform

4 years ago

symv_U_sse2.S

initial support for Sapphire Rapids platform

4 years ago

tobf16.c

initial support for Sapphire Rapids platform

4 years ago

trsm_kernel_LN_2x8_nehalem.S

Remove all trailing whitespace except lapack-netlib

11 years ago

trsm_kernel_LN_4x2_atom.S

Remove all trailing whitespace except lapack-netlib

11 years ago

trsm_kernel_LN_4x4_barcelona.S

Remove all trailing whitespace except lapack-netlib

11 years ago

trsm_kernel_LN_4x4_core2.S

Remove all trailing whitespace except lapack-netlib

11 years ago

trsm_kernel_LN_4x4_penryn.S

Remove all trailing whitespace except lapack-netlib

11 years ago

trsm_kernel_LN_4x4_sse2.S

Remove all trailing whitespace except lapack-netlib

11 years ago

trsm_kernel_LN_4x4_sse3.S

Remove all trailing whitespace except lapack-netlib

11 years ago

trsm_kernel_LN_4x8_nehalem.S

Remove all trailing whitespace except lapack-netlib

11 years ago

trsm_kernel_LN_8x4_sse.S

Remove all trailing whitespace except lapack-netlib

11 years ago

trsm_kernel_LT_2x8_nehalem.S

Remove all trailing whitespace except lapack-netlib

11 years ago

trsm_kernel_LT_4x2_atom.S

Remove all trailing whitespace except lapack-netlib

11 years ago

trsm_kernel_LT_4x4_barcelona.S

Remove all trailing whitespace except lapack-netlib

11 years ago

trsm_kernel_LT_4x4_core2.S

Remove all trailing whitespace except lapack-netlib

11 years ago

trsm_kernel_LT_4x4_penryn.S

Remove all trailing whitespace except lapack-netlib

11 years ago

trsm_kernel_LT_4x4_sse2.S

Remove all trailing whitespace except lapack-netlib

11 years ago

trsm_kernel_LT_4x4_sse3.S

Remove all trailing whitespace except lapack-netlib

11 years ago

trsm_kernel_LT_4x8_nehalem.S

Remove all trailing whitespace except lapack-netlib

11 years ago

trsm_kernel_LT_8x4_sse.S

Remove all trailing whitespace except lapack-netlib

11 years ago

trsm_kernel_RT_2x8_nehalem.S

Remove all trailing whitespace except lapack-netlib

11 years ago

trsm_kernel_RT_4x2_atom.S

Remove all trailing whitespace except lapack-netlib

11 years ago

trsm_kernel_RT_4x4_barcelona.S

Remove all trailing whitespace except lapack-netlib

11 years ago

trsm_kernel_RT_4x4_core2.S

Remove all trailing whitespace except lapack-netlib

11 years ago

trsm_kernel_RT_4x4_penryn.S

Remove all trailing whitespace except lapack-netlib

11 years ago

trsm_kernel_RT_4x4_sse2.S

Remove all trailing whitespace except lapack-netlib

11 years ago

trsm_kernel_RT_4x4_sse3.S

Remove all trailing whitespace except lapack-netlib

11 years ago

trsm_kernel_RT_4x8_nehalem.S

Remove all trailing whitespace except lapack-netlib

11 years ago

trsm_kernel_RT_8x4_sse.S

Remove all trailing whitespace except lapack-netlib

11 years ago

xdot.S

use emms instead, add WIN guards

5 years ago

xgemm3m_kernel_2x2.S

use emms instead, add WIN guards

5 years ago

xgemm_kernel_1x1.S

use emms instead, add WIN guards

5 years ago

xgemv_n.S

use emms instead, add WIN guards

5 years ago

xgemv_t.S

use emms instead, add WIN guards

5 years ago

xtrsm_kernel_LT_1x1.S

use emms instead, add WIN guards

5 years ago

zamax.S

use emms instead, add WIN guards

5 years ago

zamax_atom.S

Remove all trailing whitespace except lapack-netlib

11 years ago

zamax_sse.S

Remove all trailing whitespace except lapack-netlib

11 years ago

zamax_sse2.S

Remove all trailing whitespace except lapack-netlib

11 years ago

zasum.S

use emms instead, add WIN guards

5 years ago

zasum.c

Use SkylakeX ?ASUM microkernel for Cooperlake/Sapphirerapids as well

1 year ago

zasum_atom.S

Remove all trailing whitespace except lapack-netlib

11 years ago

zasum_microk_skylakex-2.c

Use _mm_set1_epi{32,64x} to init mask in x86-64 [cz]asum

1 year ago

zasum_sse.S

Remove all trailing whitespace except lapack-netlib

11 years ago

zasum_sse2.S

Remove all trailing whitespace except lapack-netlib

11 years ago

zaxpy.S

Remove all trailing whitespace except lapack-netlib

11 years ago

zaxpy.c

initial support for Sapphire Rapids platform

4 years ago

zaxpy_atom.S

Remove all trailing whitespace except lapack-netlib

11 years ago

zaxpy_microk_bulldozer-2.c

5 years ago

zaxpy_microk_haswell-2.c

5 years ago

zaxpy_microk_sandy-2.c

5 years ago

zaxpy_microk_steamroller-2.c

5 years ago

zaxpy_sse.S

Remove all trailing whitespace except lapack-netlib

11 years ago

zaxpy_sse2.S

use shortcut only when both incx and incy are zero

2 years ago

zcopy.S

Remove all trailing whitespace except lapack-netlib

11 years ago

zcopy_sse.S

Remove all trailing whitespace except lapack-netlib

11 years ago

zcopy_sse2.S

Import GotoBLAS2 1.13 BSD version codes.

14 years ago

zdot.S

use emms instead, add WIN guards

5 years ago

zdot.c

fix improper function prototypes (empty parentheses)

2 years ago

zdot_atom.S

Import GotoBLAS2 1.13 BSD version codes.

14 years ago

zdot_microk_bulldozer-2.c

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

6 years ago

zdot_microk_haswell-2.c

Replace vpermpd with vpermilpd

6 years ago

zdot_microk_sandy-2.c

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

6 years ago

zdot_microk_steamroller-2.c

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

6 years ago

zdot_sse.S

Remove all trailing whitespace except lapack-netlib

11 years ago

zdot_sse2.S

Remove all trailing whitespace except lapack-netlib

11 years ago

zgemm3m_kernel_2x8_nehalem.S

Remove all trailing whitespace except lapack-netlib

11 years ago

zgemm3m_kernel_4x2_atom.S

Remove all trailing whitespace except lapack-netlib

11 years ago

zgemm3m_kernel_4x4_barcelona.S

Remove all trailing whitespace except lapack-netlib

11 years ago

zgemm3m_kernel_4x4_core2.S

Remove all trailing whitespace except lapack-netlib

11 years ago

zgemm3m_kernel_4x4_haswell.c

Update zgemm3m_kernel_4x4_haswell.c

5 years ago

zgemm3m_kernel_4x4_penryn.S

Remove all trailing whitespace except lapack-netlib

11 years ago

zgemm3m_kernel_4x4_sse2.S

Remove all trailing whitespace except lapack-netlib

11 years ago

zgemm3m_kernel_4x4_sse3.S

Remove all trailing whitespace except lapack-netlib

11 years ago

zgemm3m_kernel_4x8_nehalem.S

Remove all trailing whitespace except lapack-netlib

11 years ago

zgemm3m_kernel_8x4_barcelona.S

Remove all trailing whitespace except lapack-netlib

11 years ago

zgemm3m_kernel_8x4_core2.S

Remove all trailing whitespace except lapack-netlib

11 years ago

zgemm3m_kernel_8x4_penryn.S

Remove all trailing whitespace except lapack-netlib

11 years ago

zgemm3m_kernel_8x4_sse.S

Remove all trailing whitespace except lapack-netlib

11 years ago

zgemm3m_kernel_8x4_sse3.S

Remove all trailing whitespace except lapack-netlib

11 years ago

zgemm_beta.S

Remove all trailing whitespace except lapack-netlib

11 years ago

zgemm_kernel_1x4_nehalem.S

Remove all trailing whitespace except lapack-netlib

11 years ago

zgemm_kernel_2x1_atom.S

Remove all trailing whitespace except lapack-netlib

11 years ago

zgemm_kernel_2x2_barcelona.S

Remove all trailing whitespace except lapack-netlib

11 years ago

zgemm_kernel_2x2_bulldozer.S

change line endings from CRLF to LF

2 years ago

zgemm_kernel_2x2_core2.S

Remove all trailing whitespace except lapack-netlib

11 years ago

zgemm_kernel_2x2_penryn.S

Remove all trailing whitespace except lapack-netlib

11 years ago

zgemm_kernel_2x2_piledriver.S

change line endings from CRLF to LF

2 years ago

zgemm_kernel_2x2_sse2.S

Remove all trailing whitespace except lapack-netlib

11 years ago

zgemm_kernel_2x2_sse3.S

Remove all trailing whitespace except lapack-netlib

11 years ago

zgemm_kernel_2x4_nehalem.S

Remove all trailing whitespace except lapack-netlib

11 years ago

zgemm_kernel_4x2_barcelona.S

Remove all trailing whitespace except lapack-netlib

11 years ago

zgemm_kernel_4x2_core2.S

Remove all trailing whitespace except lapack-netlib

11 years ago

zgemm_kernel_4x2_haswell.S

change line endings from CRLF to LF

2 years ago

zgemm_kernel_4x2_haswell.c

Update zgemm_kernel_4x2_haswell.c

5 years ago

zgemm_kernel_4x2_penryn.S

Remove all trailing whitespace except lapack-netlib

11 years ago

zgemm_kernel_4x2_skylakex.c

AVX512 CGEMM & ZGEMM kernels

5 years ago

zgemm_kernel_4x2_sse.S

Add forgotten conditional uses of PREFETCH

1 year ago

zgemm_kernel_4x2_sse3.S

Remove all trailing whitespace except lapack-netlib

11 years ago

zgemm_kernel_4x4_sandy.S

Update organization info.

11 years ago

zgemm_ncopy_1.S

Remove all trailing whitespace except lapack-netlib

11 years ago

zgemm_ncopy_2.S

Remove all trailing whitespace except lapack-netlib

11 years ago

zgemm_tcopy_1.S

Remove all trailing whitespace except lapack-netlib

11 years ago

zgemm_tcopy_2.S

Remove all trailing whitespace except lapack-netlib

11 years ago

zgemv_n.S

Remove all trailing whitespace except lapack-netlib

11 years ago

zgemv_n_4.c

Disable gcc's tree-vectorizer pass on all operating systems

2 years ago

zgemv_n_atom.S

Remove all trailing whitespace except lapack-netlib

11 years ago

zgemv_n_dup.S

Remove all trailing whitespace except lapack-netlib

11 years ago

zgemv_n_microk_bulldozer-4.c

7 years ago

zgemv_n_microk_haswell-4.c

Tag %1 and %2 as both input and output

7 years ago

zgemv_n_microk_sandy-4.c

Use .p2align instead of .align for compatibility on Sandybridge as well

7 years ago

zgemv_t.S

Remove all trailing whitespace except lapack-netlib

11 years ago

zgemv_t_4.c

Disable gcc's tree-vectorizer pass on all operating systems

2 years ago

zgemv_t_atom.S

Remove all trailing whitespace except lapack-netlib

11 years ago

zgemv_t_dup.S

Remove all trailing whitespace except lapack-netlib

11 years ago

zgemv_t_microk_bulldozer-4.c