diff options
| author | ling xu <ling1.xu@intel.com> | 2022-11-16 23:29:22 +0800 |
|---|---|---|
| committer | Juan Quintela <quintela@redhat.com> | 2023-02-11 16:51:09 +0100 |
| commit | 04ffce137b6d85ab4e7687e54e4dffcef0a9ab99 (patch) | |
| tree | 857d2986fa10dc683585f56c742038b413f9ae5e /meson.build | |
| parent | e26470501271adf22e4f37d218c2164884ae96fb (diff) | |
AVX512 support for xbzrle_encode_buffer
This commit is the same with [PATCH v6 1/2], and provides avx512 support for xbzrle_encode_buffer
function to accelerate xbzrle encoding speed. Runtime check of avx512
support and benchmark for this feature are added. Compared with C
version of xbzrle_encode_buffer function, avx512 version can achieve
50%-70% performance improvement on benchmarking. In addition, if dirty
data is randomly located in 4K page, the avx512 version can achieve
almost 140% performance gain.
Signed-off-by: ling xu <ling1.xu@intel.com>
Co-authored-by: Zhou Zhao <zhou.zhao@intel.com>
Co-authored-by: Jun Jin <jun.i.jin@intel.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
Diffstat (limited to 'meson.build')
| -rw-r--r-- | meson.build | 17 |
1 files changed, 17 insertions, 0 deletions
diff --git a/meson.build b/meson.build index 4ba3bf3431..c626ccfa82 100644 --- a/meson.build +++ b/meson.build @@ -2351,6 +2351,22 @@ config_host_data.set('CONFIG_AVX512F_OPT', get_option('avx512f') \ int main(int argc, char *argv[]) { return bar(argv[argc - 1]); } '''), error_message: 'AVX512F not available').allowed()) +config_host_data.set('CONFIG_AVX512BW_OPT', get_option('avx512bw') \ + .require(have_cpuid_h, error_message: 'cpuid.h not available, cannot enable AVX512BW') \ + .require(cc.links(''' + #pragma GCC push_options + #pragma GCC target("avx512bw") + #include <cpuid.h> + #include <immintrin.h> + static int bar(void *a) { + + __m512i *x = a; + __m512i res= _mm512_abs_epi8(*x); + return res[1]; + } + int main(int argc, char *argv[]) { return bar(argv[0]); } + '''), error_message: 'AVX512BW not available').allowed()) + have_pvrdma = get_option('pvrdma') \ .require(rdma.found(), error_message: 'PVRDMA requires OpenFabrics libraries') \ .require(cc.compiles(gnu_source_prefix + ''' @@ -3783,6 +3799,7 @@ summary_info += {'debug stack usage': get_option('debug_stack_usage')} summary_info += {'mutex debugging': get_option('debug_mutex')} summary_info += {'memory allocator': get_option('malloc')} summary_info += {'avx2 optimization': config_host_data.get('CONFIG_AVX2_OPT')} +summary_info += {'avx512bw optimization': config_host_data.get('CONFIG_AVX512BW_OPT')} summary_info += {'avx512f optimization': config_host_data.get('CONFIG_AVX512F_OPT')} summary_info += {'gprof enabled': get_option('gprof')} summary_info += {'gcov': get_option('b_coverage')} |