diff options
author | Victorien Le Couviour--Tuffet <victorien@videolan.org> | 2019-12-12 02:24:02 +0300 |
---|---|---|
committer | Ronald S. Bultje <rsbultje@gmail.com> | 2020-01-09 16:56:42 +0300 |
commit | 5462c2a80de6f7f6c0b1b0d20cbe571b09510a19 (patch) | |
tree | c6709713e932148b38a7636b9b39501f759d7622 /meson.build | |
parent | 40891aab9bc2f60bdbef16d1a499f36944e1738d (diff) |
x86: add prep_bilin AVX512 asm
------------------------------------------
mct_bilinear_w4_0_8bpc_avx2: 3.8
mct_bilinear_w4_0_8bpc_avx512icl: 3.7
---------------------
mct_bilinear_w8_0_8bpc_avx2: 5.0
mct_bilinear_w8_0_8bpc_avx512icl: 4.8
---------------------
mct_bilinear_w16_0_8bpc_avx2: 8.5
mct_bilinear_w16_0_8bpc_avx512icl: 7.1
---------------------
mct_bilinear_w32_0_8bpc_avx2: 29.5
mct_bilinear_w32_0_8bpc_avx512icl: 17.1
---------------------
mct_bilinear_w64_0_8bpc_avx2: 68.1
mct_bilinear_w64_0_8bpc_avx512icl: 34.7
---------------------
mct_bilinear_w128_0_8bpc_avx2: 180.5
mct_bilinear_w128_0_8bpc_avx512icl: 138.0
------------------------------------------
mct_bilinear_w4_h_8bpc_avx2: 4.0
mct_bilinear_w4_h_8bpc_avx512icl: 3.9
---------------------
mct_bilinear_w8_h_8bpc_avx2: 5.3
mct_bilinear_w8_h_8bpc_avx512icl: 5.0
---------------------
mct_bilinear_w16_h_8bpc_avx2: 11.7
mct_bilinear_w16_h_8bpc_avx512icl: 7.5
---------------------
mct_bilinear_w32_h_8bpc_avx2: 41.8
mct_bilinear_w32_h_8bpc_avx512icl: 20.3
---------------------
mct_bilinear_w64_h_8bpc_avx2: 94.9
mct_bilinear_w64_h_8bpc_avx512icl: 35.0
---------------------
mct_bilinear_w128_h_8bpc_avx2: 240.1
mct_bilinear_w128_h_8bpc_avx512icl: 143.8
------------------------------------------
mct_bilinear_w4_v_8bpc_avx2: 4.1
mct_bilinear_w4_v_8bpc_avx512icl: 4.0
---------------------
mct_bilinear_w8_v_8bpc_avx2: 6.0
mct_bilinear_w8_v_8bpc_avx512icl: 5.4
---------------------
mct_bilinear_w16_v_8bpc_avx2: 10.3
mct_bilinear_w16_v_8bpc_avx512icl: 8.9
---------------------
mct_bilinear_w32_v_8bpc_avx2: 29.5
mct_bilinear_w32_v_8bpc_avx512icl: 25.9
---------------------
mct_bilinear_w64_v_8bpc_avx2: 64.3
mct_bilinear_w64_v_8bpc_avx512icl: 41.3
---------------------
mct_bilinear_w128_v_8bpc_avx2: 198.2
mct_bilinear_w128_v_8bpc_avx512icl: 139.6
------------------------------------------
mct_bilinear_w4_hv_8bpc_avx2: 5.6
mct_bilinear_w4_hv_8bpc_avx512icl: 5.2
---------------------
mct_bilinear_w8_hv_8bpc_avx2: 8.3
mct_bilinear_w8_hv_8bpc_avx512icl: 7.0
---------------------
mct_bilinear_w16_hv_8bpc_avx2: 19.4
mct_bilinear_w16_hv_8bpc_avx512icl: 12.1
---------------------
mct_bilinear_w32_hv_8bpc_avx2: 69.1
mct_bilinear_w32_hv_8bpc_avx512icl: 32.5
---------------------
mct_bilinear_w64_hv_8bpc_avx2: 164.4
mct_bilinear_w64_hv_8bpc_avx512icl: 71.1
---------------------
mct_bilinear_w128_hv_8bpc_avx2: 405.2
mct_bilinear_w128_hv_8bpc_avx512icl: 193.1
------------------------------------------
Diffstat (limited to 'meson.build')
-rw-r--r-- | meson.build | 8 |
1 files changed, 4 insertions, 4 deletions
diff --git a/meson.build b/meson.build index e323030..d867631 100644 --- a/meson.build +++ b/meson.build @@ -268,12 +268,12 @@ if host_machine.cpu_family().startswith('x86') if get_option('stack_alignment') > 0 stack_alignment = get_option('stack_alignment') elif host_machine.cpu_family() == 'x86_64' - if cc.has_argument('-mpreferred-stack-boundary=5') - stackalign_flag = ['-mpreferred-stack-boundary=5'] + if cc.has_argument('-mpreferred-stack-boundary=6') + stackalign_flag = ['-mpreferred-stack-boundary=6'] stackrealign_flag = ['-mincoming-stack-boundary=4'] stack_alignment = 32 - elif cc.has_argument('-mstack-alignment=32') - stackalign_flag = ['-mstack-alignment=32'] + elif cc.has_argument('-mstack-alignment=64') + stackalign_flag = ['-mstack-alignment=64'] stackrealign_flag = ['-mstackrealign'] stack_alignment = 32 else |