[openblas] branch master updated (78004ed -> 12f4785)
Sébastien Villemot
sebastien at debian.org
Tue Jul 29 19:17:30 UTC 2014
This is an automated email from the git hooks/post-receive script.
sebastien pushed a change to branch master
in repository openblas.
from 78004ed Remove Sylvestre Ledru from Uploaders. Thanks Sylvestre for your work!
new 4df17b4 Imported Upstream version 0.2.10
new f6bedb2 debian/copyright: rewrite using machine-readable format.
new 6a6359b Use Files-Excluded from d/copyright to remove embedded LAPACK copy.
new 21dd820 Refresh patches.
new 652cd2f no-embedded-lapack.patch: new patch.
new 1d50f08 Rewrite using debhelper and upstream's 'make install' rule.
new 12f4785 Ship headers in /usr/include/openblas.
The 7 revisions listed above as "new" are entirely new to this
repository and will be described in separate emails. The revisions
listed as "adds" were already present in the repository and have only
been added to this reference.
Summary of changes:
.gitignore | 4 +
.travis.yml | 2 +-
CONTRIBUTORS.md | 8 +-
Changelog.txt | 90 +-
GotoBLAS_01Readme.txt | 2 +-
GotoBLAS_02QuickInstall.txt | 6 +-
GotoBLAS_03FAQ.txt | 2 +-
GotoBLAS_05LargePage.txt | 2 +-
GotoBLAS_06WeirdPerformance.txt | 4 +-
LICENSE | 22 +-
Makefile | 29 +-
Makefile.alpha | 2 +-
Makefile.ia64 | 2 +-
Makefile.install | 10 +-
Makefile.power | 8 +-
Makefile.rule | 37 +-
Makefile.sparc | 2 +-
Makefile.system | 117 +-
Makefile.tail | 14 +-
Makefile.x86 | 4 +-
Makefile.x86_64 | 2 +-
README.md | 14 +-
benchmark/Makefile | 714 ++++++-
benchmark/cholesky.c | 32 +-
benchmark/gemm.c | 210 ++
benchmark/hemm.c | 192 ++
benchmark/her2k.c | 191 ++
benchmark/herk.c | 189 ++
benchmark/linpack.c | 32 +-
benchmark/symm.c | 203 ++
benchmark/syr2k.c | 203 ++
benchmark/syrk.c | 199 ++
benchmark/trmm.c | 202 ++
benchmark/trsm.c | 202 ++
c_check | 18 +-
cblas.h | 19 +-
cblas_noconst.h | 17 +-
common.h | 29 +-
common_arm.h | 26 +-
common_arm64.h | 26 +-
common_c.h | 23 +
common_d.h | 12 +
common_ia64.h | 4 +-
common_interface.h | 141 +-
common_level1.h | 25 +-
common_level2.h | 16 +-
common_level3.h | 39 +-
common_linux.h | 6 +-
common_macro.h | 36 +
common_mips64.h | 46 +-
common_param.h | 113 +-
common_power.h | 2 +-
common_reference.h | 24 +-
common_s.h | 16 +
common_sparc.h | 26 +-
common_thread.h | 6 +-
common_x86.h | 12 +-
common_x86_64.h | 12 +-
common_z.h | 23 +
cpuid.S | 4 +-
cpuid_alpha.c | 8 +-
cpuid_arm.c | 8 +-
cpuid_ia64.c | 6 +-
cpuid_mips.c | 22 +-
cpuid_power.c | 2 +-
cpuid_x86.c | 86 +-
ctest/Makefile | 16 +-
ctest/c_c2chke.c | 292 +--
ctest/c_c3chke.c | 12 +-
ctest/c_cblas1.c | 6 +-
ctest/c_cblas2.c | 40 +-
ctest/c_cblas3.c | 60 +-
ctest/c_cblat2.f | 14 +-
ctest/c_cblat3.f | 78 +-
ctest/c_d2chke.c | 290 +--
ctest/c_d3chke.c | 14 +-
ctest/c_dblas1.c | 2 +-
ctest/c_dblas2.c | 58 +-
ctest/c_dblas3.c | 36 +-
ctest/c_dblat1.f | 4 +-
ctest/c_dblat2.f | 14 +-
ctest/c_dblat3.f | 64 +-
ctest/c_s2chke.c | 290 +--
ctest/c_s3chke.c | 14 +-
ctest/c_sblas1.c | 4 +-
ctest/c_sblas2.c | 58 +-
ctest/c_sblas3.c | 36 +-
ctest/c_sblat2.f | 14 +-
ctest/c_sblat3.f | 66 +-
ctest/c_xerbla.c | 20 +-
ctest/c_z2chke.c | 292 +--
ctest/c_z3chke.c | 12 +-
ctest/c_zblas1.c | 6 +-
ctest/c_zblas2.c | 40 +-
ctest/c_zblas3.c | 60 +-
ctest/c_zblat2.f | 26 +-
ctest/c_zblat3.f | 80 +-
debian/control | 2 +-
debian/copyright | 1188 ++++++-----
debian/libopenblas-base.install | 3 +-
debian/libopenblas-dev.install | 5 +-
debian/orig-tar.sh | 19 -
debian/patches/no-embedded-lapack.patch | 105 +
debian/patches/remove-openmp-warning.patch | 12 +-
debian/patches/series | 1 +
debian/patches/test-custom-package.patch | 4 +-
debian/rules | 35 +-
debian/watch | 2 +-
driver/level2/Makefile | 2130 ++++++++++----------
driver/level2/gbmv_k.c | 4 +-
driver/level2/gbmv_thread.c | 32 +-
driver/level2/gemv_thread.c | 22 +-
driver/level2/ger_thread.c | 28 +-
driver/level2/sbmv_k.c | 6 +-
driver/level2/sbmv_thread.c | 80 +-
driver/level2/spmv_k.c | 2 +-
driver/level2/spmv_thread.c | 78 +-
driver/level2/spr2_k.c | 2 +-
driver/level2/spr2_thread.c | 64 +-
driver/level2/spr_k.c | 2 +-
driver/level2/spr_thread.c | 56 +-
driver/level2/symv_thread.c | 76 +-
driver/level2/syr2_k.c | 2 +-
driver/level2/syr2_thread.c | 62 +-
driver/level2/syr_k.c | 2 +-
driver/level2/syr_thread.c | 56 +-
driver/level2/tbmv_L.c | 8 +-
driver/level2/tbmv_U.c | 6 +-
driver/level2/tbmv_thread.c | 96 +-
driver/level2/tbsv_L.c | 6 +-
driver/level2/tbsv_U.c | 8 +-
driver/level2/tpmv_L.c | 6 +-
driver/level2/tpmv_U.c | 6 +-
driver/level2/tpmv_thread.c | 88 +-
driver/level2/tpsv_L.c | 8 +-
driver/level2/tpsv_U.c | 6 +-
driver/level2/trmv_L.c | 10 +-
driver/level2/trmv_U.c | 8 +-
driver/level2/trmv_thread.c | 98 +-
driver/level2/trsv_L.c | 14 +-
driver/level2/trsv_U.c | 10 +-
driver/level2/zgbmv_k.c | 2 +-
driver/level2/zhbmv_k.c | 18 +-
driver/level2/zher2_k.c | 6 +-
driver/level2/zhpmv_k.c | 32 +-
driver/level2/zhpr2_k.c | 6 +-
driver/level2/zsbmv_k.c | 12 +-
driver/level2/zspmv_k.c | 16 +-
driver/level2/zspr2_k.c | 4 +-
driver/level2/zspr_k.c | 2 +-
driver/level2/zsyr2_k.c | 4 +-
driver/level2/zsyr_k.c | 2 +-
driver/level2/ztbmv_L.c | 6 +-
driver/level2/ztbmv_U.c | 2 +-
driver/level2/ztbsv_L.c | 10 +-
driver/level2/ztbsv_U.c | 12 +-
driver/level2/ztpmv_L.c | 8 +-
driver/level2/ztpmv_U.c | 4 +-
driver/level2/ztpsv_L.c | 12 +-
driver/level2/ztpsv_U.c | 14 +-
driver/level2/ztrmv_L.c | 2 +-
driver/level2/ztrmv_U.c | 6 +-
driver/level2/ztrsv_L.c | 8 +-
driver/level2/ztrsv_U.c | 6 +-
driver/level3/Makefile | 226 ++-
driver/level3/gemm3m_level3.c | 130 +-
driver/level3/gemm_thread_m.c | 8 +-
driver/level3/gemm_thread_mn.c | 12 +-
driver/level3/gemm_thread_n.c | 10 +-
driver/level3/gemm_thread_variable.c | 8 +-
driver/level3/level3.c | 48 +-
driver/level3/level3_gemm3m_thread.c | 280 +--
driver/level3/level3_syr2k.c | 114 +-
driver/level3/level3_syrk.c | 202 +-
driver/level3/level3_syrk_threaded.c | 142 +-
driver/level3/level3_thread.c | 132 +-
driver/level3/syr2k_k.c | 2 +-
driver/level3/syr2k_kernel.c | 42 +-
driver/level3/syrk_k.c | 2 +-
driver/level3/syrk_kernel.c | 24 +-
driver/level3/syrk_thread.c | 52 +-
driver/level3/trmm_L.c | 94 +-
driver/level3/trmm_R.c | 102 +-
driver/level3/trsm_L.c | 40 +-
driver/level3/trsm_R.c | 104 +-
driver/level3/zher2k_k.c | 2 +-
driver/level3/zher2k_kernel.c | 38 +-
driver/level3/zherk_k.c | 2 +-
driver/level3/zherk_kernel.c | 24 +-
driver/level3/zsyrk_beta.c | 2 +-
driver/mapper/mapper.c | 40 +-
driver/others/Makefile | 12 +-
driver/others/blas_l1_thread.c | 16 +-
driver/others/blas_server.c | 225 +--
driver/others/blas_server_omp.c | 36 +-
driver/others/blas_server_win32.c | 122 +-
driver/others/divtable.c | 36 +-
driver/others/dynamic.c | 123 +-
driver/others/init.c | 104 +-
driver/others/lamc3.c | 2 +-
driver/others/lamch.c | 2 +-
driver/others/memory.c | 236 +--
driver/others/memory_qalloc.c | 6 +-
driver/others/openblas_error_handle.c | 5 +-
driver/others/openblas_get_config.c | 47 +-
driver/others/openblas_get_parallel.c | 34 +-
driver/others/openblas_set_num_threads.c | 22 +-
driver/others/parameter.c | 50 +-
driver/others/profile.c | 12 +-
driver/others/xerbla.c | 4 +-
exports/Makefile | 8 +-
exports/dllinit.c | 2 +-
exports/gensymbol | 83 +-
f_check | 44 +-
ftest.f | 2 +-
ftest3.f | 2 +-
getarch.c | 39 +-
getarch_2nd.c | 6 +-
interface/Makefile | 134 +-
interface/asum.c | 4 +-
kernel/arm/swap.c => interface/axpby.c | 56 +-
interface/axpy.c | 14 +-
interface/copy.c | 6 +-
interface/dot.c | 4 +-
interface/dsdot.c | 8 +-
interface/gbmv.c | 10 +-
interface/gemm.c | 125 +-
interface/gemv.c | 20 +-
interface/ger.c | 21 +-
interface/imatcopy.c | 142 ++
interface/imax.c | 4 +-
interface/lapack/gesv.c | 8 +-
interface/lapack/getf2.c | 4 +-
interface/lapack/getrf.c | 4 +-
interface/lapack/getrs.c | 4 +-
interface/lapack/larf.c.obsolete | 4 +-
interface/lapack/laswp.c | 10 +-
interface/lapack/lauu2.c | 4 +-
interface/lapack/lauum.c | 6 +-
interface/lapack/potf2.c | 4 +-
interface/lapack/potrf.c | 4 +-
interface/lapack/potri.c | 8 +-
interface/lapack/trti2.c | 8 +-
interface/lapack/trtri.c | 10 +-
interface/lapack/zgetf2.c | 2 +-
interface/lapack/zgetrf.c | 2 +-
interface/lapack/zgetrs.c | 6 +-
interface/lapack/zlaswp.c | 4 +-
interface/lapack/zlauu2.c | 4 +-
interface/lapack/zlauum.c | 6 +-
interface/lapack/zpotf2.c | 4 +-
interface/lapack/zpotrf.c | 6 +-
interface/lapack/zpotri.c | 8 +-
interface/lapack/ztrti2.c | 8 +-
interface/lapack/ztrtri.c | 12 +-
interface/max.c | 4 +-
interface/nrm2.c | 4 +-
interface/omatcopy.c | 120 ++
interface/rot.c | 4 +-
interface/rotm.c | 6 +-
interface/rotmg.c | 14 +-
interface/sbmv.c | 26 +-
interface/scal.c | 15 +-
interface/sdsdot.c | 8 +-
interface/spmv.c | 6 +-
interface/spr.c | 8 +-
interface/spr2.c | 8 +-
interface/swap.c | 14 +-
interface/symm.c | 74 +-
interface/symv.c | 10 +-
interface/syr.c | 8 +-
interface/syr2.c | 8 +-
interface/syr2k.c | 44 +-
interface/syrk.c | 50 +-
interface/tbmv.c | 12 +-
interface/tbsv.c | 12 +-
interface/tpmv.c | 12 +-
interface/tpsv.c | 10 +-
interface/trmv.c | 16 +-
interface/trsm.c | 50 +-
interface/trsv.c | 10 +-
kernel/arm/zswap.c => interface/zaxpby.c | 66 +-
interface/zaxpy.c | 14 +-
interface/zgbmv.c | 6 +-
interface/zgemv.c | 22 +-
interface/zger.c | 21 +-
interface/zhbmv.c | 8 +-
interface/zhemv.c | 6 +-
interface/zher.c | 10 +-
interface/zher2.c | 8 +-
interface/zhpmv.c | 4 +-
interface/zhpr.c | 10 +-
interface/zhpr2.c | 10 +-
interface/zimatcopy.c | 185 ++
interface/zomatcopy.c | 154 ++
interface/zrot.c | 4 +-
interface/zsbmv.c | 24 +-
interface/zscal.c | 11 +-
interface/zspmv.c | 4 +-
interface/zspr.c | 10 +-
interface/zspr2.c | 12 +-
interface/zswap.c | 8 +-
interface/zsymv.c | 12 +-
interface/zsyr.c | 8 +-
interface/zsyr2.c | 6 +-
interface/ztbmv.c | 12 +-
interface/ztbsv.c | 12 +-
interface/ztpmv.c | 10 +-
interface/ztpsv.c | 10 +-
interface/ztrmv.c | 12 +-
interface/ztrsv.c | 12 +-
kernel/Makefile | 6 +-
kernel/Makefile.L1 | 240 ++-
kernel/Makefile.L2 | 142 +-
kernel/Makefile.L3 | 207 +-
kernel/alpha/KERNEL | 4 +-
kernel/alpha/cnrm2.S | 4 +-
kernel/alpha/dnrm2.S | 4 +-
kernel/alpha/gemm_kernel_4x4.S | 6 +-
kernel/alpha/gemv_n.S | 8 +-
kernel/alpha/iamax.S | 4 +-
kernel/alpha/imax.S | 2 +-
kernel/alpha/izamax.S | 2 +-
kernel/alpha/snrm2.S | 4 +-
kernel/alpha/trsm_kernel_4x4_LN.S | 120 +-
kernel/alpha/trsm_kernel_4x4_LT.S | 120 +-
kernel/alpha/trsm_kernel_4x4_RT.S | 120 +-
kernel/alpha/zamax.S | 2 +-
kernel/alpha/zaxpy.S | 30 +-
kernel/alpha/zgemm_kernel_2x2.S | 2 +-
kernel/alpha/znrm2.S | 4 +-
kernel/alpha/ztrsm_kernel_2x2_LN.S | 24 +-
kernel/alpha/ztrsm_kernel_2x2_LT.S | 24 +-
kernel/alpha/ztrsm_kernel_2x2_RT.S | 24 +-
kernel/arm/KERNEL.ARMV5 | 4 +-
kernel/arm/KERNEL.ARMV6 | 12 +-
kernel/arm/KERNEL.ARMV7 | 30 +-
kernel/arm/amax.c | 4 +-
kernel/arm/amin.c | 4 +-
kernel/arm/asum.c | 2 +-
kernel/arm/{axpy.c => axpby.c} | 66 +-
kernel/arm/axpy.c | 2 +-
kernel/arm/ccopy_vfp.S | 2 +-
kernel/arm/cdot_vfp.S | 10 +-
kernel/arm/cgemm_kernel_2x2_vfp.S | 28 +-
kernel/arm/cgemm_kernel_2x2_vfpv3.S | 28 +-
kernel/arm/cgemm_ncopy_2_vfp.S | 14 +-
kernel/arm/cgemv_n_vfp.S | 4 +-
kernel/arm/copy.c | 2 +-
kernel/arm/ctrmm_kernel_2x2_vfp.S | 28 +-
kernel/arm/ctrmm_kernel_2x2_vfpv3.S | 28 +-
kernel/arm/dcopy_vfp.S | 2 +-
kernel/arm/ddot_vfp.S | 2 +-
kernel/arm/dgemm_kernel_4x2_vfp.S | 50 +-
kernel/arm/dgemm_kernel_4x4_vfpv3.S | 74 +-
kernel/arm/dgemm_ncopy_2_vfp.S | 14 +-
kernel/arm/dgemm_ncopy_4_vfp.S | 20 +-
kernel/arm/dgemm_tcopy_4_vfp.S | 16 +-
kernel/arm/dot.c | 2 +-
kernel/arm/dtrmm_kernel_4x2_vfp.S | 42 +-
kernel/arm/dtrmm_kernel_4x4_vfpv3.S | 74 +-
kernel/arm/gemv_n.c | 4 +-
kernel/arm/gemv_n_vfp.S | 4 +-
kernel/arm/gemv_n_vfpv3.S | 4 +-
kernel/arm/gemv_t.c | 3 +-
kernel/arm/iamax.c | 4 +-
kernel/arm/iamax_vfp.S | 2 +-
kernel/arm/iamin.c | 4 +-
kernel/arm/imax.c | 4 +-
kernel/arm/imin.c | 8 +-
kernel/arm/izamax.c | 4 +-
kernel/arm/izamin.c | 4 +-
kernel/arm/max.c | 4 +-
kernel/arm/min.c | 4 +-
kernel/arm/nrm2.c | 6 +-
kernel/arm/nrm2_vfp.S | 62 +-
kernel/arm/nrm2_vfpv3.S | 56 +-
kernel/arm/{zswap.c => omatcopy_cn.c} | 78 +-
kernel/arm/{zswap.c => omatcopy_ct.c} | 77 +-
kernel/arm/{zswap.c => omatcopy_rn.c} | 78 +-
kernel/arm/{copy.c => omatcopy_rt.c} | 45 +-
kernel/arm/rot.c | 2 +-
kernel/arm/rot_vfp.S | 20 +-
kernel/arm/scal.c | 2 +-
kernel/arm/scal_vfp.S | 48 +-
kernel/arm/scopy_vfp.S | 2 +-
kernel/arm/sdot_vfp.S | 2 +-
kernel/arm/sgemm_kernel_4x2_vfp.S | 50 +-
kernel/arm/sgemm_kernel_4x4_vfpv3.S | 74 +-
kernel/arm/sgemm_ncopy_2_vfp.S | 14 +-
kernel/arm/sgemm_ncopy_4_vfp.S | 20 +-
kernel/arm/sgemm_tcopy_4_vfp.S | 18 +-
kernel/arm/strmm_kernel_4x2_vfp.S | 42 +-
kernel/arm/strmm_kernel_4x4_vfpv3.S | 68 +-
kernel/arm/swap.c | 2 +-
kernel/arm/zamax.c | 4 +-
kernel/arm/zamin.c | 4 +-
kernel/arm/zasum.c | 2 +-
kernel/arm/{zaxpy.c => zaxpby.c} | 89 +-
kernel/arm/zaxpy.c | 2 +-
kernel/arm/zcopy.c | 2 +-
kernel/arm/zcopy_vfp.S | 2 +-
kernel/arm/zdot.c | 4 +-
kernel/arm/zdot_vfp.S | 10 +-
kernel/arm/zgemm_kernel_2x2_vfp.S | 28 +-
kernel/arm/zgemm_kernel_2x2_vfpv3.S | 28 +-
kernel/arm/zgemm_ncopy_2_vfp.S | 14 +-
kernel/arm/zgemv_n.c | 4 +-
kernel/arm/zgemv_n_vfp.S | 4 +-
kernel/arm/zgemv_t.c | 2 +-
kernel/arm/znrm2.c | 10 +-
kernel/arm/{axpy.c => zomatcopy_cn.c} | 54 +-
kernel/arm/{axpy.c => zomatcopy_cnc.c} | 53 +-
kernel/arm/{axpy.c => zomatcopy_ct.c} | 55 +-
kernel/arm/{axpy.c => zomatcopy_ctc.c} | 55 +-
kernel/arm/{axpy.c => zomatcopy_rn.c} | 54 +-
kernel/arm/{axpy.c => zomatcopy_rnc.c} | 55 +-
kernel/arm/{axpy.c => zomatcopy_rt.c} | 56 +-
kernel/arm/{axpy.c => zomatcopy_rtc.c} | 56 +-
kernel/arm/zrot.c | 2 +-
kernel/arm/zscal.c | 2 +-
kernel/arm/zswap.c | 2 +-
kernel/arm/ztrmm_kernel_2x2_vfp.S | 28 +-
kernel/arm/ztrmm_kernel_2x2_vfpv3.S | 28 +-
kernel/arm64/KERNEL.ARMV8 | 4 +-
kernel/{arm => generic}/dot.c | 60 +-
kernel/generic/gemm_beta.c | 4 +-
kernel/generic/gemm_ncopy_1.c | 4 +-
kernel/generic/gemm_ncopy_16.c | 84 +-
kernel/generic/gemm_ncopy_2.c | 8 +-
kernel/generic/gemm_ncopy_4.c | 56 +-
kernel/generic/gemm_ncopy_6.c | 56 +-
kernel/generic/gemm_ncopy_8.c | 68 +-
kernel/generic/gemm_tcopy_1.c | 2 +-
kernel/generic/gemm_tcopy_16.c | 50 +-
kernel/generic/gemm_tcopy_2.c | 4 +-
kernel/generic/gemm_tcopy_4.c | 68 +-
kernel/generic/gemm_tcopy_6.c | 68 +-
kernel/generic/gemm_tcopy_8.c | 138 +-
kernel/generic/gemmkernel_2x2.c | 24 +-
kernel/generic/ger.c | 4 +-
kernel/generic/laswp_ncopy_1.c | 40 +-
kernel/generic/laswp_ncopy_2.c | 72 +-
kernel/generic/laswp_ncopy_4.c | 86 +-
kernel/generic/laswp_ncopy_8.c | 44 +-
kernel/generic/neg_tcopy_1.c | 2 +-
kernel/generic/neg_tcopy_16.c | 50 +-
kernel/generic/neg_tcopy_2.c | 4 +-
kernel/generic/neg_tcopy_4.c | 68 +-
kernel/generic/neg_tcopy_8.c | 138 +-
kernel/generic/symm_lcopy_1.c | 4 +-
kernel/generic/symm_lcopy_16.c | 20 +-
kernel/generic/symm_lcopy_2.c | 8 +-
kernel/generic/symm_lcopy_4.c | 12 +-
kernel/generic/symm_lcopy_6.c | 12 +-
kernel/generic/symm_lcopy_8.c | 16 +-
kernel/generic/symm_ucopy_1.c | 4 +-
kernel/generic/symm_ucopy_16.c | 22 +-
kernel/generic/symm_ucopy_2.c | 8 +-
kernel/generic/symm_ucopy_4.c | 14 +-
kernel/generic/symm_ucopy_6.c | 14 +-
kernel/generic/symm_ucopy_8.c | 18 +-
kernel/generic/symv_k.c | 18 +-
kernel/generic/trmm_lncopy_1.c | 2 +-
kernel/generic/trmm_lncopy_16.c | 64 +-
kernel/generic/trmm_lncopy_2.c | 16 +-
kernel/generic/trmm_lncopy_4.c | 68 +-
kernel/generic/trmm_lncopy_6.c | 68 +-
kernel/generic/trmm_lncopy_8.c | 178 +-
kernel/generic/trmm_ltcopy_1.c | 4 +-
kernel/generic/trmm_ltcopy_16.c | 94 +-
kernel/generic/trmm_ltcopy_2.c | 16 +-
kernel/generic/trmm_ltcopy_4.c | 72 +-
kernel/generic/trmm_ltcopy_6.c | 72 +-
kernel/generic/trmm_ltcopy_8.c | 140 +-
kernel/generic/trmm_uncopy_1.c | 8 +-
kernel/generic/trmm_uncopy_16.c | 76 +-
kernel/generic/trmm_uncopy_2.c | 22 +-
kernel/generic/trmm_uncopy_4.c | 74 +-
kernel/generic/trmm_uncopy_6.c | 12 +-
kernel/generic/trmm_uncopy_8.c | 182 +-
kernel/generic/trmm_utcopy_1.c | 6 +-
kernel/generic/trmm_utcopy_16.c | 94 +-
kernel/generic/trmm_utcopy_2.c | 26 +-
kernel/generic/trmm_utcopy_4.c | 64 +-
kernel/generic/trmm_utcopy_6.c | 64 +-
kernel/generic/trmm_utcopy_8.c | 160 +-
kernel/generic/trmmkernel_16x2.c | 94 +-
kernel/generic/trmmkernel_2x2.c | 52 +-
kernel/generic/trmmkernel_8x2.c | 76 +-
kernel/generic/trsm_kernel_LN.c | 74 +-
kernel/generic/trsm_kernel_LT.c | 58 +-
kernel/generic/trsm_kernel_RN.c | 62 +-
kernel/generic/trsm_kernel_RT.c | 60 +-
kernel/generic/trsm_lncopy_1.c | 2 +-
kernel/generic/trsm_lncopy_16.c | 22 +-
kernel/generic/trsm_lncopy_2.c | 4 +-
kernel/generic/trsm_lncopy_4.c | 8 +-
kernel/generic/trsm_lncopy_6.c | 8 +-
kernel/generic/trsm_lncopy_8.c | 52 +-
kernel/generic/trsm_ltcopy_16.c | 22 +-
kernel/generic/trsm_ltcopy_2.c | 6 +-
kernel/generic/trsm_ltcopy_4.c | 18 +-
kernel/generic/trsm_ltcopy_6.c | 18 +-
kernel/generic/trsm_ltcopy_8.c | 14 +-
kernel/generic/trsm_uncopy_1.c | 2 +-
kernel/generic/trsm_uncopy_16.c | 22 +-
kernel/generic/trsm_uncopy_2.c | 4 +-
kernel/generic/trsm_uncopy_4.c | 10 +-
kernel/generic/trsm_uncopy_6.c | 10 +-
kernel/generic/trsm_uncopy_8.c | 34 +-
kernel/generic/trsm_utcopy_1.c | 2 +-
kernel/generic/trsm_utcopy_16.c | 20 +-
kernel/generic/trsm_utcopy_2.c | 4 +-
kernel/generic/trsm_utcopy_4.c | 8 +-
kernel/generic/trsm_utcopy_6.c | 8 +-
kernel/generic/trsm_utcopy_8.c | 14 +-
kernel/generic/zgemm3m_ncopy_1.c | 12 +-
kernel/generic/zgemm3m_ncopy_2.c | 20 +-
kernel/generic/zgemm3m_ncopy_4.c | 24 +-
kernel/generic/zgemm3m_ncopy_8.c | 32 +-
kernel/generic/zgemm3m_tcopy_1.c | 14 +-
kernel/generic/zgemm3m_tcopy_2.c | 18 +-
kernel/generic/zgemm3m_tcopy_4.c | 54 +-
kernel/generic/zgemm3m_tcopy_8.c | 212 +-
kernel/generic/zgemm_beta.c | 16 +-
kernel/generic/zgemm_ncopy_1.c | 16 +-
kernel/generic/zgemm_ncopy_2.c | 32 +-
kernel/generic/zgemm_ncopy_4.c | 84 +-
kernel/generic/zgemm_ncopy_4_sandy.c | 48 +-
kernel/generic/zgemm_ncopy_8.c | 26 +-
kernel/generic/zgemm_ncopy_8_sandy.c | 56 +-
kernel/generic/zgemm_tcopy_1.c | 28 +-
kernel/generic/zgemm_tcopy_2.c | 52 +-
kernel/generic/zgemm_tcopy_4.c | 74 +-
kernel/generic/zgemm_tcopy_4_sandy.c | 48 +-
kernel/generic/zgemm_tcopy_8.c | 44 +-
kernel/generic/zgemm_tcopy_8_sandy.c | 54 +-
kernel/generic/zgemmkernel_2x2.c | 22 +-
kernel/generic/zger.c | 8 +-
kernel/generic/zhemm3m_lcopy_1.c | 18 +-
kernel/generic/zhemm3m_lcopy_2.c | 4 +-
kernel/generic/zhemm3m_lcopy_4.c | 6 +-
kernel/generic/zhemm3m_lcopy_8.c | 8 +-
kernel/generic/zhemm3m_ucopy_1.c | 18 +-
kernel/generic/zhemm3m_ucopy_2.c | 10 +-
kernel/generic/zhemm3m_ucopy_4.c | 14 +-
kernel/generic/zhemm3m_ucopy_8.c | 8 +-
kernel/generic/zhemm_ltcopy_1.c | 4 +-
kernel/generic/zhemm_ltcopy_2.c | 8 +-
kernel/generic/zhemm_ltcopy_4.c | 12 +-
kernel/generic/zhemm_ltcopy_8.c | 16 +-
kernel/generic/zhemm_utcopy_1.c | 4 +-
kernel/generic/zhemm_utcopy_2.c | 8 +-
kernel/generic/zhemm_utcopy_4.c | 14 +-
kernel/generic/zhemm_utcopy_8.c | 22 +-
kernel/generic/zhemv_k.c | 12 +-
kernel/generic/zlaswp_ncopy_1.c | 40 +-
kernel/generic/zlaswp_ncopy_2.c | 76 +-
kernel/generic/zlaswp_ncopy_4.c | 106 +-
kernel/generic/zneg_tcopy_1.c | 28 +-
kernel/generic/zneg_tcopy_2.c | 52 +-
kernel/generic/zneg_tcopy_4.c | 74 +-
kernel/generic/zneg_tcopy_8.c | 44 +-
kernel/generic/zsymm3m_lcopy_1.c | 20 +-
kernel/generic/zsymm3m_lcopy_2.c | 8 +-
kernel/generic/zsymm3m_lcopy_4.c | 10 +-
kernel/generic/zsymm3m_lcopy_8.c | 14 +-
kernel/generic/zsymm3m_ucopy_1.c | 20 +-
kernel/generic/zsymm3m_ucopy_2.c | 10 +-
kernel/generic/zsymm3m_ucopy_4.c | 14 +-
kernel/generic/zsymm3m_ucopy_8.c | 18 +-
kernel/generic/zsymm_lcopy_1.c | 4 +-
kernel/generic/zsymm_lcopy_2.c | 8 +-
kernel/generic/zsymm_lcopy_4.c | 12 +-
kernel/generic/zsymm_lcopy_8.c | 14 +-
kernel/generic/zsymm_ucopy_1.c | 2 +-
kernel/generic/zsymm_ucopy_2.c | 8 +-
kernel/generic/zsymm_ucopy_4.c | 12 +-
kernel/generic/zsymm_ucopy_8.c | 16 +-
kernel/generic/zsymv_k.c | 10 +-
kernel/generic/ztrmm_lncopy_1.c | 2 +-
kernel/generic/ztrmm_lncopy_2.c | 12 +-
kernel/generic/ztrmm_lncopy_4.c | 104 +-
kernel/generic/ztrmm_lncopy_8.c | 50 +-
kernel/generic/ztrmm_ltcopy_1.c | 6 +-
kernel/generic/ztrmm_ltcopy_2.c | 28 +-
kernel/generic/ztrmm_ltcopy_4.c | 116 +-
kernel/generic/ztrmm_ltcopy_8.c | 84 +-
kernel/generic/ztrmm_uncopy_1.c | 4 +-
kernel/generic/ztrmm_uncopy_2.c | 22 +-
kernel/generic/ztrmm_uncopy_4.c | 98 +-
kernel/generic/ztrmm_uncopy_8.c | 66 +-
kernel/generic/ztrmm_utcopy_1.c | 4 +-
kernel/generic/ztrmm_utcopy_2.c | 36 +-
kernel/generic/ztrmm_utcopy_4.c | 102 +-
kernel/generic/ztrmm_utcopy_8.c | 102 +-
kernel/generic/ztrmmkernel_2x2.c | 36 +-
kernel/generic/ztrsm_lncopy_1.c | 2 +-
kernel/generic/ztrsm_lncopy_2.c | 4 +-
kernel/generic/ztrsm_lncopy_4.c | 12 +-
kernel/generic/ztrsm_lncopy_8.c | 18 +-
kernel/generic/ztrsm_ltcopy_1.c | 2 +-
kernel/generic/ztrsm_ltcopy_2.c | 4 +-
kernel/generic/ztrsm_ltcopy_4.c | 12 +-
kernel/generic/ztrsm_ltcopy_8.c | 18 +-
kernel/generic/ztrsm_uncopy_1.c | 2 +-
kernel/generic/ztrsm_uncopy_2.c | 4 +-
kernel/generic/ztrsm_uncopy_4.c | 12 +-
kernel/generic/ztrsm_uncopy_8.c | 18 +-
kernel/generic/ztrsm_utcopy_1.c | 2 +-
kernel/generic/ztrsm_utcopy_2.c | 4 +-
kernel/generic/ztrsm_utcopy_4.c | 12 +-
kernel/generic/ztrsm_utcopy_8.c | 16 +-
kernel/ia64/amax.S | 8 +-
kernel/ia64/asum.S | 8 +-
kernel/ia64/caxpy.S | 4 +-
kernel/ia64/copy.S | 4 +-
kernel/ia64/daxpy.S | 2 +-
kernel/ia64/ddot.S | 10 +-
kernel/ia64/gemm_beta.S | 10 +-
kernel/ia64/gemm_kernel.S | 28 +-
kernel/ia64/gemm_ncopy.S | 4 +-
kernel/ia64/gemv_n.S | 16 +-
kernel/ia64/gemv_t.S | 12 +-
kernel/ia64/iamax.S | 2 +-
kernel/ia64/izamax.S | 8 +-
kernel/ia64/lsame.S | 2 +-
kernel/ia64/nrm2.S | 6 +-
kernel/ia64/qaxpy.S | 4 +-
kernel/ia64/qgemm_kernel.S | 28 +-
kernel/ia64/qgemv_n.S | 22 +-
kernel/ia64/qgemv_t.S | 114 +-
kernel/ia64/qscal.S | 2 +-
kernel/ia64/saxpy.S | 8 +-
kernel/ia64/scal.S | 2 +-
kernel/ia64/sdot.S | 10 +-
kernel/ia64/sgemv_n.S | 16 +-
kernel/ia64/symv_U.S | 16 +-
kernel/ia64/trsm_kernel_LN.S | 50 +-
kernel/ia64/trsm_kernel_LT.S | 24 +-
kernel/ia64/trsm_kernel_RT.S | 60 +-
kernel/ia64/xdot.S | 8 +-
kernel/ia64/zcopy.S | 2 +-
kernel/ia64/zdot.S | 8 +-
kernel/ia64/zgemm3m_kernel.S | 26 +-
kernel/ia64/zgemm_beta.S | 12 +-
kernel/ia64/zgemm_kernel.S | 22 +-
kernel/ia64/zgemm_ncopy.S | 4 +-
kernel/ia64/zgemv_n.S | 16 +-
kernel/ia64/zgemv_t.S | 14 +-
kernel/ia64/zscal.S | 2 +-
kernel/ia64/zswap.S | 6 +-
kernel/ia64/ztrsm_kernel_LN.S | 28 +-
kernel/ia64/ztrsm_kernel_LT.S | 28 +-
kernel/ia64/ztrsm_kernel_RT.S | 28 +-
kernel/mips64/KERNEL.LOONGSON3A | 2 +-
kernel/mips64/KERNEL.LOONGSON3B | 4 +-
kernel/mips64/amax.S | 4 +-
kernel/mips64/amin.S | 4 +-
kernel/mips64/asum.S | 4 +-
kernel/mips64/axpy.S | 2 +-
kernel/mips64/axpy_loongson3a.S | 46 +-
kernel/mips64/cgemm_kernel_loongson3a_2x2.S | 114 +-
kernel/mips64/cgemm_kernel_loongson3a_4x2_ps.S | 102 +-
kernel/mips64/cgemm_kernel_loongson3b_2x2.S | 114 +-
kernel/mips64/cnrm2.S | 10 +-
kernel/mips64/copy.S | 4 +-
kernel/mips64/daxpy_loongson3a_simd.S | 104 +-
kernel/mips64/dgemm_kernel_loongson3a_4x4.S | 484 ++---
kernel/mips64/dgemm_kernel_loongson3b_4x4.S | 414 ++--
kernel/mips64/dnrm2.S | 4 +-
kernel/mips64/dot.S | 6 +-
kernel/mips64/gemm_beta.S | 2 +-
kernel/mips64/gemm_kernel.S | 6 +-
kernel/mips64/gemv_n.S | 4 +-
kernel/mips64/gemv_n_loongson3a.c | 4 +-
kernel/mips64/gemv_t.S | 16 +-
kernel/mips64/gemv_t_loongson3a.c | 2 +-
kernel/mips64/iamax.S | 6 +-
kernel/mips64/iamin.S | 6 +-
kernel/mips64/imax.S | 6 +-
kernel/mips64/imin.S | 6 +-
kernel/mips64/izamax.S | 8 +-
kernel/mips64/izamin.S | 8 +-
kernel/mips64/max.S | 4 +-
kernel/mips64/min.S | 4 +-
kernel/mips64/rot.S | 4 +-
kernel/mips64/scal.S | 6 +-
kernel/mips64/sgemm_kernel_8x4_ps.S | 400 ++--
kernel/mips64/sgemm_kernel_loongson3a_4x4.S | 414 ++--
kernel/mips64/sgemm_kernel_loongson3b_4x4.S | 414 ++--
kernel/mips64/snrm2.S | 10 +-
kernel/mips64/swap.S | 2 +-
kernel/mips64/symv_L.S | 2 +-
kernel/mips64/symv_U.S | 2 +-
kernel/mips64/trsm_kernel_LN.S | 4 +-
kernel/mips64/trsm_kernel_LN_loongson3a.S | 270 +--
kernel/mips64/trsm_kernel_LT.S | 4 +-
kernel/mips64/trsm_kernel_LT_loongson3a.S | 244 +--
kernel/mips64/trsm_kernel_RN_loongson3a.S | 162 +-
kernel/mips64/trsm_kernel_RT.S | 4 +-
kernel/mips64/trsm_kernel_RT_loongson3a.S | 204 +-
kernel/mips64/zamax.S | 4 +-
kernel/mips64/zamin.S | 4 +-
kernel/mips64/zasum.S | 4 +-
kernel/mips64/zaxpy.S | 4 +-
kernel/mips64/zcopy.S | 4 +-
kernel/mips64/zdot.S | 6 +-
kernel/mips64/zgemm3m_kernel.S | 6 +-
kernel/mips64/zgemm_kernel.S | 4 +-
kernel/mips64/zgemm_kernel_loongson3a_2x2.S | 160 +-
kernel/mips64/zgemm_kernel_loongson3b_2x2.S | 114 +-
kernel/mips64/zgemv_n.S | 2 +-
kernel/mips64/zgemv_n_loongson3a.c | 2 +-
kernel/mips64/zgemv_t.S | 12 +-
kernel/mips64/zgemv_t_loongson3a.c | 2 +-
kernel/mips64/znrm2.S | 4 +-
kernel/mips64/zrot.S | 4 +-
kernel/mips64/zscal.S | 4 +-
kernel/mips64/zswap.S | 2 +-
kernel/mips64/zsymv_L.S | 2 +-
kernel/mips64/zsymv_U.S | 4 +-
kernel/mips64/ztrsm_kernel_LT.S | 4 +-
kernel/mips64/ztrsm_kernel_RT.S | 2 +-
kernel/power/KERNEL.CELL | 4 +-
kernel/power/KERNEL.POWER5 | 12 +-
kernel/power/KERNEL.POWER6 | 4 +-
kernel/power/KERNEL.PPC440 | 12 +-
kernel/power/KERNEL.PPC970 | 4 +-
kernel/power/KERNEL.PPCG4 | 4 +-
kernel/power/amax.S | 4 +-
kernel/power/amax_cell.S | 6 +-
kernel/power/amax_hummer.S | 6 +-
kernel/power/amax_ppc440.S | 4 +-
kernel/power/amin.S | 4 +-
kernel/power/amin_cell.S | 6 +-
kernel/power/amin_hummer.S | 6 +-
kernel/power/amin_ppc440.S | 4 +-
kernel/power/asum.S | 4 +-
kernel/power/asum_cell.S | 4 +-
kernel/power/asum_hummer.S | 6 +-
kernel/power/asum_ppc440.S | 4 +-
kernel/power/axpy.S | 16 +-
kernel/power/axpy_hummer.S | 6 +-
kernel/power/axpy_ppc440.S | 12 +-
kernel/power/cnrm2.S | 4 +-
kernel/power/cnrm2_hummer.S | 8 +-
kernel/power/cnrm2_ppc440.S | 8 +-
kernel/power/copy.S | 6 +-
kernel/power/copy_hummer.S | 18 +-
kernel/power/dnrm2_hummer.S | 10 +-
kernel/power/dnrm2_ppc440.S | 6 +-
kernel/power/dot.S | 4 +-
kernel/power/dot_cell.S | 2 +-
kernel/power/dot_hummer.S | 8 +-
kernel/power/dot_ppc440.S | 2 +-
kernel/power/exfunc.S | 2 +-
kernel/power/gemm_beta.S | 6 +-
kernel/power/gemm_kernel.S | 14 +-
kernel/power/gemm_kernel_altivec.S | 10 +-
kernel/power/gemm_kernel_altivec_cell.S | 10 +-
kernel/power/gemm_kernel_altivec_g4.S | 10 +-
kernel/power/gemm_kernel_cell.S | 12 +-
kernel/power/gemm_kernel_g4.S | 12 +-
kernel/power/gemm_kernel_hummer.S | 24 +-
kernel/power/gemm_kernel_power3.S | 10 +-
kernel/power/gemm_kernel_power6.S | 8 +-
kernel/power/gemm_kernel_ppc440.S | 10 +-
kernel/power/gemm_ncopy_4.S | 10 +-
kernel/power/gemm_ncopy_hummer_4.S | 16 +-
kernel/power/gemm_ncopy_hummer_8.S | 26 +-
kernel/power/gemm_tcopy_4.S | 12 +-
kernel/power/gemm_tcopy_hummer_4.S | 18 +-
kernel/power/gemm_tcopy_hummer_8.S | 22 +-
kernel/power/gemv_hummer_n.S | 6 +-
kernel/power/gemv_n.S | 2 +-
kernel/power/gemv_t.S | 12 +-
kernel/power/gemv_t_ppc440.S | 6 +-
kernel/power/ger.S | 4 +-
kernel/power/iamax.S | 8 +-
kernel/power/iamax_hummer.S | 6 +-
kernel/power/iamax_ppc440.S | 8 +-
kernel/power/iamin.S | 8 +-
kernel/power/iamin_hummer.S | 6 +-
kernel/power/iamin_ppc440.S | 8 +-
kernel/power/imax.S | 4 +-
kernel/power/imax_hummer.S | 6 +-
kernel/power/imax_ppc440.S | 4 +-
kernel/power/imin.S | 4 +-
kernel/power/imin_hummer.S | 6 +-
kernel/power/imin_ppc440.S | 6 +-
kernel/power/izamax.S | 8 +-
kernel/power/izamax_hummer.S | 6 +-
kernel/power/izamax_ppc440.S | 6 +-
kernel/power/izamin.S | 4 +-
kernel/power/izamin_hummer.S | 6 +-
kernel/power/izamin_ppc440.S | 6 +-
kernel/power/max.S | 4 +-
kernel/power/max_hummer.S | 6 +-
kernel/power/max_ppc440.S | 4 +-
kernel/power/min.S | 4 +-
kernel/power/min_hummer.S | 6 +-
kernel/power/min_ppc440.S | 4 +-
kernel/power/nrm2.S | 4 +-
kernel/power/rot.S | 4 +-
kernel/power/rot_ppc440.S | 4 +-
kernel/power/scal.S | 4 +-
kernel/power/scal_hummer.S | 6 +-
kernel/power/scal_ppc440.S | 4 +-
kernel/power/snrm2.S | 4 +-
kernel/power/snrm2_hummer.S | 4 +-
kernel/power/snrm2_ppc440.S | 6 +-
kernel/power/swap.S | 12 +-
kernel/power/swap_hummer.S | 12 +-
kernel/power/symv_L.S | 12 +-
kernel/power/symv_U.S | 18 +-
kernel/power/trsm_kernel_LN.S | 18 +-
kernel/power/trsm_kernel_LT.S | 20 +-
kernel/power/trsm_kernel_RT.S | 20 +-
kernel/power/trsm_kernel_cell_LN.S | 20 +-
kernel/power/trsm_kernel_cell_LT.S | 22 +-
kernel/power/trsm_kernel_cell_RT.S | 20 +-
kernel/power/trsm_kernel_hummer_LN.S | 16 +-
kernel/power/trsm_kernel_hummer_LT.S | 16 +-
kernel/power/trsm_kernel_hummer_RT.S | 16 +-
kernel/power/trsm_kernel_power6_LN.S | 16 +-
kernel/power/trsm_kernel_power6_LT.S | 18 +-
kernel/power/trsm_kernel_power6_RT.S | 18 +-
kernel/power/trsm_kernel_ppc440_LN.S | 16 +-
kernel/power/trsm_kernel_ppc440_LT.S | 18 +-
kernel/power/trsm_kernel_ppc440_RT.S | 18 +-
kernel/power/zamax.S | 4 +-
kernel/power/zamax_cell.S | 4 +-
kernel/power/zamax_hummer.S | 6 +-
kernel/power/zamax_ppc440.S | 6 +-
kernel/power/zamin.S | 4 +-
kernel/power/zamin_cell.S | 4 +-
kernel/power/zamin_hummer.S | 6 +-
kernel/power/zamin_ppc440.S | 4 +-
kernel/power/zasum.S | 4 +-
kernel/power/zasum_cell.S | 4 +-
kernel/power/zasum_hummer.S | 6 +-
kernel/power/zasum_ppc440.S | 4 +-
kernel/power/zaxpy.S | 8 +-
kernel/power/zaxpy_hummer.S | 6 +-
kernel/power/zaxpy_ppc440.S | 6 +-
kernel/power/zcopy.S | 6 +-
kernel/power/zcopy_hummer.S | 14 +-
kernel/power/zdot.S | 8 +-
kernel/power/zdot_cell.S | 8 +-
kernel/power/zdot_hummer.S | 8 +-
kernel/power/zdot_ppc440.S | 6 +-
kernel/power/zgemm_beta.S | 10 +-
kernel/power/zgemm_kernel.S | 10 +-
kernel/power/zgemm_kernel_altivec.S | 4 +-
kernel/power/zgemm_kernel_altivec_cell.S | 4 +-
kernel/power/zgemm_kernel_altivec_g4.S | 4 +-
kernel/power/zgemm_kernel_cell.S | 6 +-
kernel/power/zgemm_kernel_g4.S | 4 +-
kernel/power/zgemm_kernel_hummer.S | 16 +-
kernel/power/zgemm_kernel_power3.S | 8 +-
kernel/power/zgemm_kernel_power6.S | 16 +-
kernel/power/zgemm_kernel_ppc440.S | 4 +-
kernel/power/zgemm_ncopy_hummer_2.S | 12 +-
kernel/power/zgemm_ncopy_hummer_4.S | 16 +-
kernel/power/zgemm_tcopy_hummer_2.S | 12 +-
kernel/power/zgemm_tcopy_hummer_4.S | 16 +-
kernel/power/zgemv_n.S | 4 +-
kernel/power/zgemv_n_ppc440.S | 4 +-
kernel/power/zgemv_t.S | 12 +-
kernel/power/zgemv_t_ppc440.S | 8 +-
kernel/power/zger.S | 4 +-
kernel/power/znrm2.S | 4 +-
kernel/power/znrm2_hummer.S | 10 +-
kernel/power/znrm2_ppc440.S | 6 +-
kernel/power/zrot.S | 6 +-
kernel/power/zrot_ppc440.S | 4 +-
kernel/power/zscal.S | 6 +-
kernel/power/zscal_hummer.S | 6 +-
kernel/power/zscal_ppc440.S | 6 +-
kernel/power/zswap.S | 14 +-
kernel/power/zswap_hummer.S | 12 +-
kernel/power/zsymv_L.S | 6 +-
kernel/power/zsymv_U.S | 6 +-
kernel/power/ztrsm_kernel_LN.S | 10 +-
kernel/power/ztrsm_kernel_LT.S | 10 +-
kernel/power/ztrsm_kernel_RT.S | 12 +-
kernel/power/ztrsm_kernel_cell_LN.S | 10 +-
kernel/power/ztrsm_kernel_cell_LT.S | 10 +-
kernel/power/ztrsm_kernel_cell_RT.S | 12 +-
kernel/power/ztrsm_kernel_hummer_LN.S | 12 +-
kernel/power/ztrsm_kernel_hummer_LT.S | 8 +-
kernel/power/ztrsm_kernel_hummer_RT.S | 10 +-
kernel/power/ztrsm_kernel_power6_LN.S | 24 +-
kernel/power/ztrsm_kernel_power6_LT.S | 24 +-
kernel/power/ztrsm_kernel_power6_RT.S | 24 +-
kernel/power/ztrsm_kernel_ppc440_LN.S | 8 +-
kernel/power/ztrsm_kernel_ppc440_LT.S | 8 +-
kernel/power/ztrsm_kernel_ppc440_RT.S | 10 +-
kernel/setparam-ref.c | 197 +-
kernel/sparc/KERNEL.sparc | 4 +-
kernel/sparc/axpy.S | 2 +-
kernel/sparc/cabs.S | 2 +-
kernel/sparc/dnrm2.S | 2 +-
kernel/sparc/dot.S | 6 +-
kernel/sparc/gemm_kernel_2x8.S | 4 +-
kernel/sparc/gemv_n.S | 12 +-
kernel/sparc/gemv_t.S | 8 +-
kernel/sparc/ger.S | 6 +-
kernel/sparc/imax.S | 2 +-
kernel/sparc/lsame.S | 2 +-
kernel/sparc/max.S | 2 +-
kernel/sparc/rot.S | 4 +-
kernel/sparc/scal.S | 2 +-
kernel/sparc/swap.S | 2 +-
kernel/sparc/trsm_kernel_LN_2x8.S | 2 +-
kernel/sparc/trsm_kernel_LT_2x8.S | 2 +-
kernel/sparc/trsm_kernel_RT.S | 2 +-
kernel/sparc/trsm_kernel_RT_2x8.S | 2 +-
kernel/sparc/zamax.S | 2 +-
kernel/sparc/zasum.S | 2 +-
kernel/sparc/zgemm_kernel.S | 4 +-
kernel/sparc/zgemm_kernel_1x4.S | 6 +-
kernel/sparc/zgemv_n.S | 6 +-
kernel/sparc/zgemv_t.S | 6 +-
kernel/sparc/znrm2.S | 2 +-
kernel/sparc/zrot.S | 4 +-
kernel/sparc/zscal.S | 2 +-
kernel/sparc/zswap.S | 2 +-
kernel/sparc/ztrsm_kernel_LN.S | 6 +-
kernel/sparc/ztrsm_kernel_LT.S | 6 +-
kernel/sparc/ztrsm_kernel_LT_1x4.S | 8 +-
kernel/sparc/ztrsm_kernel_RT.S | 6 +-
kernel/sparc/ztrsm_kernel_RT_1x4.S | 6 +-
kernel/x86/KERNEL | 310 +--
kernel/x86/KERNEL.ATOM | 8 +-
kernel/x86/KERNEL.BARCELONA | 14 +-
kernel/x86/KERNEL.BOBCAT | 14 +-
kernel/x86/KERNEL.BULLDOZER | 14 +-
kernel/x86/KERNEL.DUNNINGTON | 8 +-
kernel/x86/KERNEL.OPTERON | 14 +-
kernel/x86/KERNEL.PENRYN | 8 +-
kernel/x86/KERNEL.PILEDRIVER | 14 +-
kernel/x86/KERNEL.PRESCOTT | 14 +-
kernel/x86/KERNEL.YONAH | 14 +-
kernel/x86/amax.S | 46 +-
kernel/x86/amax_sse.S | 20 +-
kernel/x86/amax_sse2.S | 20 +-
kernel/x86/asum.S | 10 +-
kernel/x86/asum_sse.S | 8 +-
kernel/x86/asum_sse2.S | 10 +-
kernel/x86/axpy.S | 4 +-
kernel/x86/axpy_sse.S | 6 +-
kernel/x86/axpy_sse2.S | 6 +-
kernel/x86/axpy_sse2_opteron.S | 4 +-
kernel/x86/copy.S | 20 +-
kernel/x86/copy_sse.S | 2 +-
kernel/x86/copy_sse2.S | 2 +-
kernel/x86/cpuid.S | 2 +-
kernel/x86/dot.S | 6 +-
kernel/x86/dot_amd.S | 6 +-
kernel/x86/dot_sse.S | 10 +-
kernel/x86/dot_sse2.S | 6 +-
kernel/x86/dot_sse2_opteron.S | 6 +-
kernel/x86/dot_sse_opteron.S | 8 +-
kernel/x86/gemm_beta.S | 4 +-
kernel/x86/gemm_kernel_1x4.S | 20 +-
kernel/x86/gemm_kernel_2x2.S | 34 +-
kernel/x86/gemm_kernel_2x2_atom.S | 24 +-
kernel/x86/gemm_kernel_2x4_3dnow.S | 34 +-
kernel/x86/gemm_kernel_2x4_barcelona.S | 34 +-
kernel/x86/gemm_kernel_2x4_core2.S | 28 +-
kernel/x86/gemm_kernel_2x4_penryn.S | 28 +-
kernel/x86/gemm_kernel_2x4_sse2.S | 50 +-
kernel/x86/gemm_kernel_2x4_sse3.S | 36 +-
kernel/x86/gemm_kernel_4x2_core2.S | 30 +-
kernel/x86/gemm_kernel_4x2_sse2.S | 68 +-
kernel/x86/gemm_kernel_4x4_barcelona.S | 64 +-
kernel/x86/gemm_kernel_4x4_penryn.S | 28 +-
kernel/x86/gemm_kernel_4x4_sse.S | 66 +-
kernel/x86/gemm_kernel_4x4_sse3.S | 62 +-
kernel/x86/gemm_kernel_8x1_sse2.S | 20 +-
kernel/x86/gemm_kernel_8x2_core2.S | 34 +-
kernel/x86/gemm_kernel_8x2_sse.S | 104 +-
kernel/x86/gemm_ncopy_2.S | 2 +-
kernel/x86/gemm_ncopy_2_sse.S | 4 +-
kernel/x86/gemm_ncopy_4_sse.S | 4 +-
kernel/x86/gemm_tcopy_2.S | 4 +-
kernel/x86/gemm_tcopy_2_sse.S | 4 +-
kernel/x86/gemm_tcopy_4_sse.S | 4 +-
kernel/x86/gemv_n.S | 10 +-
kernel/x86/gemv_n_atom.S | 6 +-
kernel/x86/gemv_n_sse.S | 6 +-
kernel/x86/gemv_n_sse2.S | 6 +-
kernel/x86/gemv_t.S | 4 +-
kernel/x86/gemv_t_atom.S | 12 +-
kernel/x86/gemv_t_sse.S | 20 +-
kernel/x86/gemv_t_sse2.S | 14 +-
kernel/x86/iamax.S | 46 +-
kernel/x86/iamax_sse.S | 42 +-
kernel/x86/iamax_sse2.S | 44 +-
kernel/x86/izamax.S | 52 +-
kernel/x86/izamax_sse.S | 26 +-
kernel/x86/izamax_sse2.S | 16 +-
kernel/x86/nrm2.S | 10 +-
kernel/x86/nrm2_sse.S | 12 +-
kernel/x86/qaxpy.S | 4 +-
kernel/x86/qdot.S | 2 +-
kernel/x86/qgemm_kernel_2x2.S | 38 +-
kernel/x86/qgemv_n.S | 10 +-
kernel/x86/qgemv_t.S | 4 +-
kernel/x86/qtrsm_kernel_LN_2x2.S | 28 +-
kernel/x86/qtrsm_kernel_LT_2x2.S | 28 +-
kernel/x86/qtrsm_kernel_RT_2x2.S | 28 +-
kernel/x86/rot.S | 8 +-
kernel/x86/rot_sse.S | 6 +-
kernel/x86/rot_sse2.S | 4 +-
kernel/x86/scal_sse.S | 6 +-
kernel/x86/scal_sse2.S | 6 +-
kernel/x86/swap.S | 2 +-
kernel/x86/swap_sse.S | 10 +-
kernel/x86/swap_sse2.S | 4 +-
kernel/x86/trsm_kernel_LN_2x2.S | 24 +-
kernel/x86/trsm_kernel_LN_2x2_atom.S | 16 +-
kernel/x86/trsm_kernel_LN_2x4_penryn.S | 24 +-
kernel/x86/trsm_kernel_LN_2x4_sse2.S | 44 +-
kernel/x86/trsm_kernel_LN_2x4_sse3.S | 22 +-
kernel/x86/trsm_kernel_LN_4x2_core2.S | 54 +-
kernel/x86/trsm_kernel_LN_4x2_sse2.S | 62 +-
kernel/x86/trsm_kernel_LN_4x4_penryn.S | 28 +-
kernel/x86/trsm_kernel_LN_4x4_sse.S | 46 +-
kernel/x86/trsm_kernel_LN_8x2_sse.S | 78 +-
kernel/x86/trsm_kernel_LT_1x4.S | 22 +-
kernel/x86/trsm_kernel_LT_2x2.S | 24 +-
kernel/x86/trsm_kernel_LT_2x2_atom.S | 16 +-
kernel/x86/trsm_kernel_LT_2x4_penryn.S | 22 +-
kernel/x86/trsm_kernel_LT_2x4_sse2.S | 44 +-
kernel/x86/trsm_kernel_LT_2x4_sse3.S | 22 +-
kernel/x86/trsm_kernel_LT_4x2_core2.S | 54 +-
kernel/x86/trsm_kernel_LT_4x2_sse2.S | 60 +-
kernel/x86/trsm_kernel_LT_4x4_penryn.S | 28 +-
kernel/x86/trsm_kernel_LT_4x4_sse.S | 46 +-
kernel/x86/trsm_kernel_LT_8x2_sse.S | 78 +-
kernel/x86/trsm_kernel_RT_1x4.S | 22 +-
kernel/x86/trsm_kernel_RT_2x2.S | 24 +-
kernel/x86/trsm_kernel_RT_2x2_atom.S | 16 +-
kernel/x86/trsm_kernel_RT_2x4_penryn.S | 24 +-
kernel/x86/trsm_kernel_RT_2x4_sse2.S | 44 +-
kernel/x86/trsm_kernel_RT_2x4_sse3.S | 22 +-
kernel/x86/trsm_kernel_RT_4x2_core2.S | 54 +-
kernel/x86/trsm_kernel_RT_4x2_sse2.S | 60 +-
kernel/x86/trsm_kernel_RT_4x4_penryn.S | 28 +-
kernel/x86/trsm_kernel_RT_4x4_sse.S | 46 +-
kernel/x86/trsm_kernel_RT_8x2_sse.S | 78 +-
kernel/x86/xaxpy.S | 4 +-
kernel/x86/xdot.S | 2 +-
kernel/x86/xgemm3m_kernel_2x2.S | 38 +-
kernel/x86/xgemm_kernel_1x1.S | 26 +-
kernel/x86/xgemv_n.S | 2 +-
kernel/x86/xgemv_t.S | 2 +-
kernel/x86/xtrsm_kernel_LT_1x1.S | 26 +-
kernel/x86/zamax.S | 52 +-
kernel/x86/zamax_sse.S | 18 +-
kernel/x86/zamax_sse2.S | 12 +-
kernel/x86/zasum.S | 10 +-
kernel/x86/zasum_sse.S | 16 +-
kernel/x86/zasum_sse2.S | 10 +-
kernel/x86/zaxpy.S | 2 +-
kernel/x86/zaxpy_sse.S | 6 +-
kernel/x86/zaxpy_sse2.S | 8 +-
kernel/x86/zcopy.S | 30 +-
kernel/x86/zcopy_sse.S | 4 +-
kernel/x86/zcopy_sse2.S | 2 +-
kernel/x86/zdot.S | 6 +-
kernel/x86/zdot_amd.S | 6 +-
kernel/x86/zdot_sse.S | 2 +-
kernel/x86/zdot_sse2.S | 234 +--
kernel/x86/zgemm3m_kernel_1x4_athlon.S | 30 +-
kernel/x86/zgemm3m_kernel_2x2_atom.S | 24 +-
kernel/x86/zgemm3m_kernel_2x2_coppermine.S | 32 +-
kernel/x86/zgemm3m_kernel_2x4_barcelona.S | 34 +-
kernel/x86/zgemm3m_kernel_2x4_opteron.S | 50 +-
kernel/x86/zgemm3m_kernel_2x4_penryn.S | 28 +-
kernel/x86/zgemm3m_kernel_2x4_prescott.S | 36 +-
kernel/x86/zgemm3m_kernel_4x2_core2.S | 28 +-
kernel/x86/zgemm3m_kernel_4x2_northwood.S | 66 +-
kernel/x86/zgemm3m_kernel_4x4_barcelona.S | 64 +-
kernel/x86/zgemm3m_kernel_4x4_opteron.S | 64 +-
kernel/x86/zgemm3m_kernel_4x4_penryn.S | 30 +-
kernel/x86/zgemm3m_kernel_4x4_prescott.S | 62 +-
kernel/x86/zgemm3m_kernel_8x2_core2.S | 34 +-
kernel/x86/zgemm3m_kernel_8x2_sse.S | 102 +-
kernel/x86/zgemm_beta.S | 2 +-
kernel/x86/zgemm_kernel_1x1.S | 8 +-
kernel/x86/zgemm_kernel_1x1_atom.S | 14 +-
kernel/x86/zgemm_kernel_1x2.S | 20 +-
kernel/x86/zgemm_kernel_1x2_3dnow.S | 16 +-
kernel/x86/zgemm_kernel_1x2_barcelona.S | 20 +-
kernel/x86/zgemm_kernel_1x2_penryn.S | 22 +-
kernel/x86/zgemm_kernel_1x2_sse2.S | 32 +-
kernel/x86/zgemm_kernel_1x2_sse3.S | 28 +-
kernel/x86/zgemm_kernel_2x1_core2.S | 20 +-
kernel/x86/zgemm_kernel_2x1_sse2.S | 28 +-
kernel/x86/zgemm_kernel_2x2_barcelona.S | 46 +-
kernel/x86/zgemm_kernel_2x2_penryn.S | 46 +-
kernel/x86/zgemm_kernel_2x2_sse.S | 48 +-
kernel/x86/zgemm_kernel_2x2_sse3.S | 46 +-
kernel/x86/zgemm_kernel_4x1_core2.S | 28 +-
kernel/x86/zgemm_kernel_4x1_sse.S | 48 +-
kernel/x86/zgemm_ncopy_2.S | 2 +-
kernel/x86/zgemm_tcopy_2.S | 4 +-
kernel/x86/zgemv_n.S | 4 +-
kernel/x86/zgemv_n_atom.S | 6 +-
kernel/x86/zgemv_n_sse.S | 8 +-
kernel/x86/zgemv_n_sse2.S | 8 +-
kernel/x86/zgemv_t.S | 2 +-
kernel/x86/zgemv_t_atom.S | 10 +-
kernel/x86/zgemv_t_sse.S | 16 +-
kernel/x86/zgemv_t_sse2.S | 10 +-
kernel/x86/znrm2.S | 10 +-
kernel/x86/znrm2_sse.S | 12 +-
kernel/x86/zrot.S | 8 +-
kernel/x86/zrot_sse.S | 4 +-
kernel/x86/zrot_sse2.S | 2 +-
kernel/x86/zscal.S | 2 +-
kernel/x86/zscal_sse.S | 2 +-
kernel/x86/zscal_sse2.S | 16 +-
kernel/x86/zswap.S | 2 +-
kernel/x86/zswap_sse.S | 8 +-
kernel/x86/zswap_sse2.S | 2 +-
kernel/x86/ztrsm_kernel_LN_2x1_core2.S | 14 +-
kernel/x86/ztrsm_kernel_LN_2x1_sse2.S | 18 +-
kernel/x86/ztrsm_kernel_LN_2x2_penryn.S | 42 +-
kernel/x86/ztrsm_kernel_LN_2x2_sse.S | 30 +-
kernel/x86/ztrsm_kernel_LN_4x1_sse.S | 24 +-
kernel/x86/ztrsm_kernel_LT_1x1.S | 8 +-
kernel/x86/ztrsm_kernel_LT_1x1_atom.S | 12 +-
kernel/x86/ztrsm_kernel_LT_1x2_penryn.S | 20 +-
kernel/x86/ztrsm_kernel_LT_1x2_sse2.S | 28 +-
kernel/x86/ztrsm_kernel_LT_1x2_sse3.S | 20 +-
kernel/x86/ztrsm_kernel_LT_2x1_core2.S | 16 +-
kernel/x86/ztrsm_kernel_LT_2x1_sse2.S | 18 +-
kernel/x86/ztrsm_kernel_LT_2x2_penryn.S | 42 +-
kernel/x86/ztrsm_kernel_LT_2x2_sse.S | 28 +-
kernel/x86/ztrsm_kernel_LT_4x1_sse.S | 24 +-
kernel/x86/ztrsm_kernel_RT_1x2_penryn.S | 20 +-
kernel/x86/ztrsm_kernel_RT_1x2_sse2.S | 24 +-
kernel/x86/ztrsm_kernel_RT_1x2_sse3.S | 20 +-
kernel/x86/ztrsm_kernel_RT_2x2_penryn.S | 42 +-
kernel/x86/ztrsm_kernel_RT_2x2_sse.S | 28 +-
kernel/x86_64/KERNEL | 6 +-
kernel/x86_64/KERNEL.ATOM | 4 +-
kernel/x86_64/KERNEL.BARCELONA | 6 +-
kernel/x86_64/KERNEL.BOBCAT | 6 +-
kernel/x86_64/KERNEL.BULLDOZER | 8 +-
kernel/x86_64/KERNEL.CORE2 | 4 +-
kernel/x86_64/KERNEL.DUNNINGTON | 4 +-
kernel/x86_64/KERNEL.HASWELL | 9 +-
kernel/x86_64/KERNEL.NANO | 4 +-
kernel/x86_64/KERNEL.NEHALEM | 28 +-
kernel/x86_64/KERNEL.OPTERON | 4 +-
kernel/x86_64/KERNEL.OPTERON_SSE3 | 6 +-
kernel/x86_64/KERNEL.PENRYN | 4 +-
kernel/x86_64/KERNEL.PILEDRIVER | 8 +-
kernel/x86_64/KERNEL.PRESCOTT | 8 +-
kernel/x86_64/KERNEL.SANDYBRIDGE | 30 +-
kernel/x86_64/amax.S | 44 +-
kernel/x86_64/amax_atom.S | 16 +-
kernel/x86_64/amax_sse.S | 18 +-
kernel/x86_64/amax_sse2.S | 18 +-
kernel/x86_64/asum.S | 6 +-
kernel/x86_64/asum_atom.S | 22 +-
kernel/x86_64/asum_sse.S | 14 +-
kernel/x86_64/asum_sse2.S | 16 +-
kernel/x86_64/axpy.S | 6 +-
kernel/x86_64/axpy_atom.S | 2 +-
kernel/x86_64/axpy_sse.S | 8 +-
kernel/x86_64/axpy_sse2.S | 6 +-
kernel/x86_64/builtin_stinit.S | 2 +-
kernel/x86_64/cabs.S | 6 +-
kernel/x86_64/cgemm_kernel_4x2_bulldozer.S | 50 +-
kernel/x86_64/cgemm_kernel_4x2_piledriver.S | 49 +-
kernel/x86_64/cgemm_kernel_4x8_sandy.S | 108 +-
kernel/x86_64/cgemm_kernel_8x2_haswell.S | 49 +-
...rnel_8x2_haswell.S => cgemm_kernel_8x2_sandy.S} | 177 +-
kernel/x86_64/cgemv_n.S | 74 +-
kernel/x86_64/cgemv_t.S | 28 +-
kernel/x86_64/copy.S | 10 +-
kernel/x86_64/daxpy_bulldozer.S | 6 +-
kernel/x86_64/ddot_bulldozer.S | 4 +-
kernel/x86_64/dgemm_kernel_4x4_haswell.S | 2 +-
kernel/x86_64/dgemm_kernel_4x8_sandy.S | 154 +-
kernel/x86_64/dgemm_kernel_6x4_piledriver.S | 30 +-
kernel/x86_64/dgemm_kernel_8x2_bulldozer.S | 4 +-
kernel/x86_64/dgemm_kernel_8x2_piledriver.S | 4 +-
kernel/x86_64/dgemm_ncopy_2.S | 2 +-
kernel/x86_64/dgemm_ncopy_4.S | 2 +-
kernel/x86_64/dgemm_ncopy_8.S | 2 +-
kernel/x86_64/dgemm_ncopy_8_bulldozer.S | 2 +-
kernel/x86_64/dgemm_tcopy_2.S | 4 +-
kernel/x86_64/dgemm_tcopy_4.S | 4 +-
kernel/x86_64/dgemm_tcopy_8.S | 4 +-
kernel/x86_64/dgemm_tcopy_8_bulldozer.S | 4 +-
kernel/x86_64/dgemv_n.S | 26 +-
kernel/x86_64/dgemv_n_atom.S | 8 +-
kernel/x86_64/dgemv_n_bulldozer.S | 22 +-
kernel/x86_64/dgemv_t.S | 8 +-
kernel/x86_64/dgemv_t_atom.S | 10 +-
kernel/x86_64/dgemv_t_bulldozer.S | 10 +-
kernel/x86_64/dot_atom.S | 4 +-
kernel/x86_64/dot_sse.S | 6 +-
kernel/x86_64/dot_sse2.S | 4 +-
kernel/x86_64/dtrsm_kernel_LT_8x2_bulldozer.S | 96 +-
kernel/x86_64/dtrsm_kernel_RN_8x2_bulldozer.S | 46 +-
kernel/x86_64/gemm_beta.S | 2 +-
kernel/x86_64/gemm_kernel_2x8_nehalem.S | 72 +-
kernel/x86_64/gemm_kernel_4x2_atom.S | 48 +-
kernel/x86_64/gemm_kernel_4x4_barcelona.S | 80 +-
kernel/x86_64/gemm_kernel_4x4_core2.S | 102 +-
kernel/x86_64/gemm_kernel_4x4_penryn.S | 88 +-
kernel/x86_64/gemm_kernel_4x4_sse2.S | 90 +-
kernel/x86_64/gemm_kernel_4x4_sse3.S | 80 +-
kernel/x86_64/gemm_kernel_4x8_nano.S | 106 +-
kernel/x86_64/gemm_kernel_4x8_nehalem.S | 114 +-
kernel/x86_64/gemm_kernel_8x4_barcelona.S | 116 +-
kernel/x86_64/gemm_kernel_8x4_core2.S | 118 +-
kernel/x86_64/gemm_kernel_8x4_penryn.S | 100 +-
kernel/x86_64/gemm_kernel_8x4_sse.S | 120 +-
kernel/x86_64/gemm_kernel_8x4_sse3.S | 114 +-
kernel/x86_64/gemm_ncopy_2.S | 2 +-
kernel/x86_64/gemm_ncopy_2_bulldozer.S | 2 +-
kernel/x86_64/gemm_ncopy_4.S | 2 +-
kernel/x86_64/gemm_ncopy_4_opteron.S | 4 +-
kernel/x86_64/gemm_tcopy_2.S | 4 +-
kernel/x86_64/gemm_tcopy_2_bulldozer.S | 10 +-
kernel/x86_64/gemm_tcopy_4.S | 2 +-
kernel/x86_64/gemm_tcopy_4_opteron.S | 2 +-
kernel/x86_64/iamax.S | 44 +-
kernel/x86_64/iamax_sse.S | 42 +-
kernel/x86_64/iamax_sse2.S | 40 +-
kernel/x86_64/izamax.S | 50 +-
kernel/x86_64/izamax_sse.S | 24 +-
kernel/x86_64/izamax_sse2.S | 14 +-
kernel/x86_64/nrm2.S | 8 +-
kernel/x86_64/nrm2_sse.S | 10 +-
kernel/x86_64/qdot.S | 2 +-
kernel/x86_64/qgemm_kernel_2x2.S | 40 +-
kernel/x86_64/qgemv_n.S | 10 +-
kernel/x86_64/qgemv_t.S | 4 +-
kernel/x86_64/qtrsm_kernel_LN_2x2.S | 34 +-
kernel/x86_64/qtrsm_kernel_LT_2x2.S | 34 +-
kernel/x86_64/qtrsm_kernel_RT_2x2.S | 34 +-
kernel/x86_64/rot.S | 6 +-
kernel/x86_64/rot_sse.S | 6 +-
kernel/x86_64/rot_sse2.S | 6 +-
kernel/x86_64/scal_atom.S | 6 +-
kernel/x86_64/scal_sse.S | 12 +-
kernel/x86_64/scal_sse2.S | 10 +-
kernel/x86_64/sgemm_kernel_16x2_bulldozer.S | 4 +-
kernel/x86_64/sgemm_kernel_16x2_piledriver.S | 4 +-
kernel/x86_64/sgemm_kernel_16x4_haswell.S | 4 +-
...el_16x4_haswell.S => sgemm_kernel_16x4_sandy.S} | 190 +-
kernel/x86_64/sgemm_kernel_8x4_bulldozer.S | 126 +-
kernel/x86_64/sgemm_kernel_8x8_sandy.S | 150 +-
kernel/x86_64/sgemv_n.S | 44 +-
kernel/x86_64/sgemv_t.S | 236 +--
kernel/x86_64/swap.S | 2 +-
kernel/x86_64/swap_sse.S | 6 +-
kernel/x86_64/swap_sse2.S | 2 +-
kernel/x86_64/symv_L_sse.S | 8 +-
kernel/x86_64/symv_L_sse2.S | 8 +-
kernel/x86_64/symv_U_sse.S | 8 +-
kernel/x86_64/symv_U_sse2.S | 10 +-
kernel/x86_64/trsm_kernel_LN_2x8_nehalem.S | 68 +-
kernel/x86_64/trsm_kernel_LN_4x2_atom.S | 42 +-
kernel/x86_64/trsm_kernel_LN_4x4_barcelona.S | 58 +-
kernel/x86_64/trsm_kernel_LN_4x4_core2.S | 82 +-
kernel/x86_64/trsm_kernel_LN_4x4_penryn.S | 76 +-
kernel/x86_64/trsm_kernel_LN_4x4_sse2.S | 74 +-
kernel/x86_64/trsm_kernel_LN_4x4_sse3.S | 64 +-
kernel/x86_64/trsm_kernel_LN_4x8_nehalem.S | 102 +-
kernel/x86_64/trsm_kernel_LN_8x4_sse.S | 86 +-
kernel/x86_64/trsm_kernel_LT_2x8_nehalem.S | 70 +-
kernel/x86_64/trsm_kernel_LT_4x2_atom.S | 44 +-
kernel/x86_64/trsm_kernel_LT_4x4_barcelona.S | 60 +-
kernel/x86_64/trsm_kernel_LT_4x4_core2.S | 82 +-
kernel/x86_64/trsm_kernel_LT_4x4_penryn.S | 76 +-
kernel/x86_64/trsm_kernel_LT_4x4_sse2.S | 82 +-
kernel/x86_64/trsm_kernel_LT_4x4_sse3.S | 62 +-
kernel/x86_64/trsm_kernel_LT_4x8_nehalem.S | 106 +-
kernel/x86_64/trsm_kernel_LT_8x4_sse.S | 92 +-
kernel/x86_64/trsm_kernel_RT_2x8_nehalem.S | 68 +-
kernel/x86_64/trsm_kernel_RT_4x2_atom.S | 42 +-
kernel/x86_64/trsm_kernel_RT_4x4_barcelona.S | 60 +-
kernel/x86_64/trsm_kernel_RT_4x4_core2.S | 80 +-
kernel/x86_64/trsm_kernel_RT_4x4_penryn.S | 76 +-
kernel/x86_64/trsm_kernel_RT_4x4_sse2.S | 78 +-
kernel/x86_64/trsm_kernel_RT_4x4_sse3.S | 62 +-
kernel/x86_64/trsm_kernel_RT_4x8_nehalem.S | 106 +-
kernel/x86_64/trsm_kernel_RT_8x4_sse.S | 90 +-
kernel/x86_64/xdot.S | 2 +-
kernel/x86_64/xgemm3m_kernel_2x2.S | 40 +-
kernel/x86_64/xgemm_kernel_1x1.S | 28 +-
kernel/x86_64/xgemv_n.S | 6 +-
kernel/x86_64/xgemv_t.S | 4 +-
kernel/x86_64/xtrsm_kernel_LT_1x1.S | 30 +-
kernel/x86_64/zamax.S | 50 +-
kernel/x86_64/zamax_atom.S | 12 +-
kernel/x86_64/zamax_sse.S | 16 +-
kernel/x86_64/zamax_sse2.S | 10 +-
kernel/x86_64/zasum.S | 6 +-
kernel/x86_64/zasum_atom.S | 20 +-
kernel/x86_64/zasum_sse.S | 16 +-
kernel/x86_64/zasum_sse2.S | 14 +-
kernel/x86_64/zaxpy.S | 6 +-
kernel/x86_64/zaxpy_atom.S | 6 +-
kernel/x86_64/zaxpy_sse.S | 12 +-
kernel/x86_64/zaxpy_sse2.S | 18 +-
kernel/x86_64/zcopy.S | 2 +-
kernel/x86_64/zcopy_sse.S | 4 +-
kernel/x86_64/zdot.S | 2 +-
kernel/x86_64/zdot_sse.S | 488 ++---
kernel/x86_64/zdot_sse2.S | 236 +--
kernel/x86_64/zgemm3m_kernel_2x8_nehalem.S | 72 +-
kernel/x86_64/zgemm3m_kernel_4x2_atom.S | 16 +-
kernel/x86_64/zgemm3m_kernel_4x4_barcelona.S | 108 +-
kernel/x86_64/zgemm3m_kernel_4x4_core2.S | 116 +-
kernel/x86_64/zgemm3m_kernel_4x4_penryn.S | 82 +-
kernel/x86_64/zgemm3m_kernel_4x4_sse2.S | 108 +-
kernel/x86_64/zgemm3m_kernel_4x4_sse3.S | 86 +-
kernel/x86_64/zgemm3m_kernel_4x8_nehalem.S | 112 +-
kernel/x86_64/zgemm3m_kernel_8x4_barcelona.S | 118 +-
kernel/x86_64/zgemm3m_kernel_8x4_core2.S | 128 +-
kernel/x86_64/zgemm3m_kernel_8x4_penryn.S | 106 +-
kernel/x86_64/zgemm3m_kernel_8x4_sse.S | 124 +-
kernel/x86_64/zgemm3m_kernel_8x4_sse3.S | 116 +-
kernel/x86_64/zgemm_beta.S | 2 +-
kernel/x86_64/zgemm_kernel_1x4_nehalem.S | 30 +-
kernel/x86_64/zgemm_kernel_2x1_atom.S | 28 +-
kernel/x86_64/zgemm_kernel_2x2_barcelona.S | 42 +-
kernel/x86_64/zgemm_kernel_2x2_bulldozer.S | 51 +-
kernel/x86_64/zgemm_kernel_2x2_core2.S | 56 +-
kernel/x86_64/zgemm_kernel_2x2_penryn.S | 44 +-
kernel/x86_64/zgemm_kernel_2x2_piledriver.S | 53 +-
kernel/x86_64/zgemm_kernel_2x2_sse2.S | 68 +-
kernel/x86_64/zgemm_kernel_2x2_sse3.S | 48 +-
kernel/x86_64/zgemm_kernel_2x4_nehalem.S | 66 +-
kernel/x86_64/zgemm_kernel_4x2_barcelona.S | 78 +-
kernel/x86_64/zgemm_kernel_4x2_core2.S | 72 +-
kernel/x86_64/zgemm_kernel_4x2_haswell.S | 49 +-
kernel/x86_64/zgemm_kernel_4x2_penryn.S | 64 +-
kernel/x86_64/zgemm_kernel_4x2_sse.S | 80 +-
kernel/x86_64/zgemm_kernel_4x2_sse3.S | 84 +-
kernel/x86_64/zgemm_kernel_4x4_sandy.S | 92 +-
kernel/x86_64/zgemm_ncopy_1.S | 2 +-
kernel/x86_64/zgemm_ncopy_2.S | 2 +-
kernel/x86_64/zgemm_tcopy_1.S | 4 +-
kernel/x86_64/zgemm_tcopy_2.S | 2 +-
kernel/x86_64/zgemv_n.S | 22 +-
kernel/x86_64/zgemv_n_atom.S | 8 +-
kernel/x86_64/zgemv_n_dup.S | 8 +-
kernel/x86_64/zgemv_t.S | 22 +-
kernel/x86_64/zgemv_t_atom.S | 10 +-
kernel/x86_64/zgemv_t_dup.S | 16 +-
kernel/x86_64/znrm2.S | 8 +-
kernel/x86_64/znrm2_sse.S | 10 +-
kernel/x86_64/zrot.S | 6 +-
kernel/x86_64/zrot_sse.S | 6 +-
kernel/x86_64/zrot_sse2.S | 4 +-
kernel/x86_64/zscal_atom.S | 6 +-
kernel/x86_64/zscal_sse.S | 6 +-
kernel/x86_64/zscal_sse2.S | 18 +-
kernel/x86_64/zswap.S | 2 +-
kernel/x86_64/zswap_sse.S | 6 +-
kernel/x86_64/zsymv_L_sse.S | 8 +-
kernel/x86_64/zsymv_L_sse2.S | 8 +-
kernel/x86_64/zsymv_U_sse.S | 10 +-
kernel/x86_64/zsymv_U_sse2.S | 8 +-
kernel/x86_64/ztrsm_kernel_LN_2x1_atom.S | 24 +-
kernel/x86_64/ztrsm_kernel_LN_2x2_core2.S | 46 +-
kernel/x86_64/ztrsm_kernel_LN_2x2_penryn.S | 40 +-
kernel/x86_64/ztrsm_kernel_LN_2x2_sse2.S | 50 +-
kernel/x86_64/ztrsm_kernel_LN_2x2_sse3.S | 38 +-
kernel/x86_64/ztrsm_kernel_LN_2x4_nehalem.S | 56 +-
kernel/x86_64/ztrsm_kernel_LN_4x2_sse.S | 52 +-
kernel/x86_64/ztrsm_kernel_LT_1x4_nehalem.S | 32 +-
kernel/x86_64/ztrsm_kernel_LT_2x1_atom.S | 26 +-
kernel/x86_64/ztrsm_kernel_LT_2x2_core2.S | 50 +-
kernel/x86_64/ztrsm_kernel_LT_2x2_penryn.S | 40 +-
kernel/x86_64/ztrsm_kernel_LT_2x2_sse2.S | 48 +-
kernel/x86_64/ztrsm_kernel_LT_2x2_sse3.S | 40 +-
kernel/x86_64/ztrsm_kernel_LT_2x4_nehalem.S | 62 +-
kernel/x86_64/ztrsm_kernel_LT_4x2_sse.S | 56 +-
kernel/x86_64/ztrsm_kernel_RT_1x4_nehalem.S | 32 +-
kernel/x86_64/ztrsm_kernel_RT_2x2_core2.S | 48 +-
kernel/x86_64/ztrsm_kernel_RT_2x2_penryn.S | 40 +-
kernel/x86_64/ztrsm_kernel_RT_2x2_sse2.S | 50 +-
kernel/x86_64/ztrsm_kernel_RT_2x2_sse3.S | 40 +-
kernel/x86_64/ztrsm_kernel_RT_2x4_nehalem.S | 62 +-
kernel/x86_64/ztrsm_kernel_RT_4x2_sse.S | 56 +-
lapack-devel.log | 14 +-
lapack-netlib/Makefile | 1 -
lapack-netlib/TESTING/Makefile | 1 -
lapack/getf2/getf2_k.c | 8 +-
lapack/getf2/zgetf2_k.c | 10 +-
lapack/getrf/getrf_parallel.c | 190 +-
lapack/getrf/getrf_parallel_omp.c | 36 +-
lapack/getrf/getrf_single.c | 38 +-
lapack/getrs/getrs_parallel.c | 8 +-
lapack/getrs/zgetrs_parallel.c | 2 +-
lapack/getrs/zgetrs_single.c | 4 +-
lapack/laswp/generic/Makefile | 2 +-
lapack/laswp/generic/laswp_k_1.c | 48 +-
lapack/laswp/generic/laswp_k_2.c | 98 +-
lapack/laswp/generic/laswp_k_4.c | 132 +-
lapack/laswp/generic/laswp_k_8.c | 180 +-
lapack/laswp/generic/zlaswp_k_1.c | 52 +-
lapack/laswp/generic/zlaswp_k_2.c | 90 +-
lapack/laswp/generic/zlaswp_k_4.c | 140 +-
lapack/lauu2/lauu2_L.c | 10 +-
lapack/lauu2/lauu2_U.c | 10 +-
lapack/lauu2/zlauu2_L.c | 8 +-
lapack/lauu2/zlauu2_U.c | 10 +-
lapack/lauum/lauum_L_parallel.c | 12 +-
lapack/lauum/lauum_L_single.c | 80 +-
lapack/lauum/lauum_U_parallel.c | 10 +-
lapack/lauum/lauum_U_single.c | 76 +-
lapack/potf2/potf2_L.c | 6 +-
lapack/potf2/potf2_U.c | 6 +-
lapack/potf2/zpotf2_L.c | 4 +-
lapack/potf2/zpotf2_U.c | 6 +-
lapack/potrf/potrf_L_parallel.c | 14 +-
lapack/potrf/potrf_L_single.c | 24 +-
lapack/potrf/potrf_U_parallel.c | 14 +-
lapack/potrf/potrf_U_single.c | 42 +-
lapack/potrf/potrf_parallel.c | 114 +-
lapack/trti2/trti2_L.c | 4 +-
lapack/trti2/trti2_U.c | 8 +-
lapack/trti2/ztrti2_L.c | 6 +-
lapack/trti2/ztrti2_U.c | 10 +-
lapack/trtri/trtri_L_parallel.c | 8 +-
lapack/trtri/trtri_U_parallel.c | 8 +-
make.inc | 1 -
param.h | 71 +-
reference/Makefile | 8 +-
reference/cspmvf.f | 2 +-
reference/ctpmvf.f | 2 +-
reference/sgetrff.f | 2 +-
reference/sgetrsf.f | 2 +-
reference/spotrff.f | 2 +-
reference/strtrif.f | 2 +-
reference/ztpmvf.f | 2 +-
reference/ztrmvf.f | 2 +-
segfaults.patch | 2 +-
symcopy.h | 352 ++--
test/Makefile | 2 +-
test/get_threading_model.c | 24 +-
test/sblat2.f | 2 +-
utest/Makefile | 10 +-
utest/common_utest.h | 22 +-
utest/main.c | 42 +-
utest/test_amax.c | 24 +-
utest/test_axpy.c | 22 +-
utest/test_dotu.c | 26 +-
utest/test_dsdot.c | 26 +-
utest/test_fork.c | 8 +-
utest/test_rot.c | 22 +-
utest/test_rotmg.c | 24 +-
version.h | 22 +-
1470 files changed, 27070 insertions(+), 23014 deletions(-)
create mode 100644 benchmark/gemm.c
create mode 100644 benchmark/hemm.c
create mode 100644 benchmark/her2k.c
create mode 100644 benchmark/herk.c
create mode 100644 benchmark/symm.c
create mode 100644 benchmark/syr2k.c
create mode 100644 benchmark/syrk.c
create mode 100644 benchmark/trmm.c
create mode 100644 benchmark/trsm.c
delete mode 100755 debian/orig-tar.sh
create mode 100644 debian/patches/no-embedded-lapack.patch
copy kernel/arm/swap.c => interface/axpby.c (73%)
create mode 100644 interface/imatcopy.c
create mode 100644 interface/omatcopy.c
copy kernel/arm/zswap.c => interface/zaxpby.c (70%)
create mode 100644 interface/zimatcopy.c
create mode 100644 interface/zomatcopy.c
copy kernel/arm/{axpy.c => axpby.c} (74%)
copy kernel/arm/{zswap.c => omatcopy_cn.c} (67%)
copy kernel/arm/{zswap.c => omatcopy_ct.c} (67%)
copy kernel/arm/{zswap.c => omatcopy_rn.c} (67%)
copy kernel/arm/{copy.c => omatcopy_rt.c} (77%)
copy kernel/arm/{zaxpy.c => zaxpby.c} (63%)
copy kernel/arm/{axpy.c => zomatcopy_cn.c} (71%)
copy kernel/arm/{axpy.c => zomatcopy_cnc.c} (71%)
copy kernel/arm/{axpy.c => zomatcopy_ct.c} (71%)
copy kernel/arm/{axpy.c => zomatcopy_ctc.c} (70%)
copy kernel/arm/{axpy.c => zomatcopy_rn.c} (71%)
copy kernel/arm/{axpy.c => zomatcopy_rnc.c} (71%)
copy kernel/arm/{axpy.c => zomatcopy_rt.c} (71%)
copy kernel/arm/{axpy.c => zomatcopy_rtc.c} (70%)
copy kernel/{arm => generic}/dot.c (73%)
copy kernel/x86_64/{cgemm_kernel_8x2_haswell.S => cgemm_kernel_8x2_sandy.S} (89%)
copy kernel/x86_64/{sgemm_kernel_16x4_haswell.S => sgemm_kernel_16x4_sandy.S} (90%)
delete mode 100644 lapack-netlib/Makefile
delete mode 100644 lapack-netlib/TESTING/Makefile
--
Alioth's /usr/local/bin/git-commit-notice on /srv/git.debian.org/git/debian-science/packages/openblas.git
More information about the debian-science-commits
mailing list