This patch updates code of avx512 support for xbzrle_encode_buffer function.
We mainly modified code in xbzrle-bench.c for addressing CI failure.
Signed-off-by: ling xu
Co-authored-by: Zhou Zhao
Co-authored-by: Jun Jin
ling xu (2):
Update AVX512 support for xbzrle_encode_buffer
Unit test
Unit test code is in test-xbzrle.c, and benchmark code is in xbzrle-bench.c
for performance benchmarking. we have modified xbzrle-bench.c to address
CI problem.
Signed-off-by: ling xu
Co-authored-by: Zhou Zhao
Co-authored-by: Jun Jin
---
tests/bench/meson.build| 4 +
tests/bench/xbzrle
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
Co-authored-by: Zhou Zhao
Co-authored-by: Jun Jin
---
meson.build| 16
Unit test code is in test-xbzrle.c, and benchmark code is in xbzrle-bench.c
for performance benchmarking.
Signed-off-by: ling xu
Co-authored-by: Zhou Zhao
Co-authored-by: Jun Jin
---
tests/bench/meson.build| 4 +
tests/bench/xbzrle-bench.c | 465
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
Co-authored-by: Zhou Zhao
Co-authored-by: Jun Jin
---
meson.build| 16 ++
meson_options.txt | 2 +
migration
This patch updates code of avx512 support for xbzrle_encode_buffer
function. We modified code of algorithm and check of avx512. Besides, we
provide benchmark in xbzrle-bench.c for performance comparison.
Signed-off-by: ling xu
Co-authored-by: Zhou Zhao
Co-authored-by: Jun Jin
ling xu (2
This patch updates code of avx512 support for xbzrle_encode_buffer
function. We modified runtime check of avx512 and simplified algorithm.
Besides, we provide benchmark in xbzrle-bench.c for performance
comparison.
Signed-off-by: ling xu
Co-authored-by: Zhou Zhao
Co-authored-by: Jun Jin
ling
Test code in test-xbzrle.c, benchmark code in xbzrle-bench.c for
performance benchmarking.
Signed-off-by: ling xu
Co-authored-by: Zhou Zhao
Co-authored-by: Jun Jin
---
tests/bench/meson.build| 4 +
tests/bench/xbzrle-bench.c | 468 +
tests/unit/test
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
Co-authored-by: Zhou Zhao
Co-authored-by: Jun Jin
---
meson.build| 16 ++
meson_options.txt | 2 +
migration/ram.c
Signed-off-by: ling xu
Co-authored-by: Zhou Zhao
Co-authored-by: Jun Jin
---
tests/unit/test-xbzrle.c | 458 ++-
1 file changed, 457 insertions(+), 1 deletion(-)
diff --git a/tests/unit/test-xbzrle.c b/tests/unit/test-xbzrle.c
index ef951b6e54..2676123ce3
updated in test-xbzrle.c.
Signed-off-by: ling xu
Co-authored-by: Zhou Zhao
Co-authored-by: Jun Jin
ling xu (2):
Update AVX512 support for xbzrle_encode_buffer function
Update test code of AVX512 support for xbzrle_encode
meson.build | 16 ++
meson_options.txt| 2
more unit test called
"test_encode_decode_random_avx512", in which dirty data are randomly
located in 4K page, and this case can achieve almost 140% performance
gain.
Signed-off-by: ling xu
Co-authored-by: Zhou Zhao
Co-authored-by: Jun Jin
---
meson.build| 16
meson_o
Signed-off-by: ling xu
Co-authored-by: Zhou Zhao
Co-authored-by: Jun Jin
---
tests/unit/test-xbzrle.c | 307 ---
1 file changed, 290 insertions(+), 17 deletions(-)
diff --git a/tests/unit/test-xbzrle.c b/tests/unit/test-xbzrle.c
index ef951b6e54..653016826f
is provided in test-xbzrle.c.
Previous discussion is refered below:
https://www.mail-archive.com/qemu-devel@nongnu.org/msg903520.html
ling xu (2):
Update AVX512 support for xbzrle_encode_buffer function
Test code for AVX512 support for xbzrle_encode_buffer
meson.build | 16
addition, we provide one more unit test called
"test_encode_decode_random", in which dirty data are randomly located in
4K page, and this case can achieve almost 140% performance gain.
Signed-off-by: ling xu
Co-authored-by: Zhou Zhao
Co-authored-by: Jun Jin
---
meson.build
Signed-off-by: ling xu
Co-authored-by: Zhou Zhao
Co-authored-by: Jun Jin
---
tests/unit/test-xbzrle.c | 307 ---
1 file changed, 290 insertions(+), 17 deletions(-)
diff --git a/tests/unit/test-xbzrle.c b/tests/unit/test-xbzrle.c
index ef951b6e54..653016826f
addition, we provide one more unit test called
"test_encode_decode_random", in which dirty data are randomly located in
4K page, and this case can achieve almost 140% performance gain.
Signed-off-by: ling xu
Co-authored-by: Zhou Zhao
Co-authored-by: Jun Jin
---
meson.build
is provided in test-xbzrle.c.
ling xu (2):
Update AVX512 support for xbzrle_encode_buffer function
Test code for AVX512 support for xbzrle_encode_buffer
meson.build | 16 ++
meson_options.txt| 2 +
migration/ram.c | 41 ++
migration/xbzrle.c | 181
.
The test code is provided in test-xbzrle.c.
Previous discussion is refered below:
https://lore.kernel.org/all/ytlshitevijwe...@redhat.com/
ling xu (2):
Update AVX512 support for xbzrle_encode_buffer function
Test code for AVX512 support for xbzrle_encode_buffer function
meson.build
Signed-off-by: ling xu
Co-authored-by: Zhou Zhao
Co-authored-by: Jun Jin
---
tests/unit/test-xbzrle.c | 307 ---
1 file changed, 290 insertions(+), 17 deletions(-)
diff --git a/tests/unit/test-xbzrle.c b/tests/unit/test-xbzrle.c
index ef951b6e54..653016826f
provided
by qemu. In addition, we provide one more unit test called
"test_encode_decode_random", in which dirty data are randomly located in
4K page, and this case can achieve almost 140% performance gain.
Signed-off-by: ling xu
Co-authored-by: Zhou Zhao
Co-authored-by: Jun Jin
---
m
"test_encode_decode_random" is provided in
qemu/tests/u nits/test-xbzrle.c.
ling xu (1):
Add AVX512 support for xbzrle_encode_buffer function
configure| 434 ++-
migration/ram.c | 6 +
migration/xbzrle.c
unit test called "test_encode_decode_random",
in which
dirty data are randomly located in 4K page, and this case can achieve almost
140% performance gain.
Signed-off-by: ling xu
Co-authored-by: Zhou Zhao
Co-authored-by: Jun Jin
---
configure
23 matches
Mail list logo