mirror_zfs/include/zfs_fletcher.h

101 lines
3.1 KiB
C
Raw Normal View History

/*
* CDDL HEADER START
*
* The contents of this file are subject to the terms of the
* Common Development and Distribution License (the "License").
* You may not use this file except in compliance with the License.
*
* You can obtain a copy of the license at usr/src/OPENSOLARIS.LICENSE
* or http://www.opensolaris.org/os/licensing.
* See the License for the specific language governing permissions
* and limitations under the License.
*
* When distributing Covered Code, include this CDDL HEADER in each
* file and include the License file at usr/src/OPENSOLARIS.LICENSE.
* If applicable, add the following below this CDDL HEADER, with the
* fields enclosed by brackets "[]" replaced with your own identifying
* information: Portions Copyright [yyyy] [name of copyright owner]
*
* CDDL HEADER END
*/
/*
* Copyright 2009 Sun Microsystems, Inc. All rights reserved.
* Use is subject to license terms.
*/
#ifndef _ZFS_FLETCHER_H
#define _ZFS_FLETCHER_H
#include <sys/types.h>
#include <sys/spa_checksum.h>
#ifdef __cplusplus
extern "C" {
#endif
/*
* fletcher checksum functions
Rework of fletcher_4 module - Benchmark memory block is increased to 128kiB to reflect real block sizes more accurately. Measurements include all three stages needed for checksum generation, i.e. `init()/compute()/fini()`. The inner loop is repeated multiple times to offset overhead of time function. - Fastest implementation selects native and byteswap methods independently in benchmark. To support this new function pointers `init_byteswap()/fini_byteswap()` are introduced. - Implementation mutex lock is replaced by atomic variable. - To save time, benchmark is not executed in userspace. Instead, highest supported implementation is used for fastest. Default userspace selector is still 'cycle'. - `fletcher_4_native/byteswap()` methods use incremental methods to finish calculation if data size is not multiple of vector stride (currently 64B). - Added `fletcher_4_native_varsize()` special purpose method for use when buffer size is not known in advance. The method does not enforce 4B alignment on buffer size, and will ignore last (size % 4) bytes of the data buffer. - Benchmark `kstat` is changed to match the one of vdev_raidz. It now shows throughput for all supported implementations (in B/s), native and byteswap, as well as the code [fastest] is running. Example of `fletcher_4_bench` running on `Intel(R) Xeon(R) CPU E5-2660 v3 @ 2.60GHz`: implementation native byteswap scalar 4768120823 3426105750 sse2 7947841777 4318964249 ssse3 7951922722 6112191941 avx2 13269714358 11043200912 fastest avx2 avx2 Example of `fletcher_4_bench` running on `Intel(R) Xeon Phi(TM) CPU 7210 @ 1.30GHz`: implementation native byteswap scalar 1291115967 1031555336 sse2 2539571138 1280970926 ssse3 2537778746 1080016762 avx2 4950749767 1078493449 avx512f 9581379998 4010029046 fastest avx512f avx512f Signed-off-by: Gvozden Neskovic <neskovic@gmail.com> Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> Closes #4952
2016-07-12 18:50:54 +03:00
*
* Note: Fletcher checksum methods expect buffer size to be 4B aligned. This
* limitation stems from the algorithm design. Performing incremental checksum
* without said alignment would yield different results. Therefore, the code
* includes assertions for the size alignment.
* For compatibility, it is required that some code paths calculate checksum of
* non-aligned buffer sizes. For this purpose, `fletcher_4_native_varsize()`
* checksum method is added. This method will ignore last (size % 4) bytes of
* the data buffer.
*/
void fletcher_2_native(const void *, uint64_t, zio_cksum_t *);
void fletcher_2_byteswap(const void *, uint64_t, zio_cksum_t *);
void fletcher_4_native(const void *, uint64_t, zio_cksum_t *);
Rework of fletcher_4 module - Benchmark memory block is increased to 128kiB to reflect real block sizes more accurately. Measurements include all three stages needed for checksum generation, i.e. `init()/compute()/fini()`. The inner loop is repeated multiple times to offset overhead of time function. - Fastest implementation selects native and byteswap methods independently in benchmark. To support this new function pointers `init_byteswap()/fini_byteswap()` are introduced. - Implementation mutex lock is replaced by atomic variable. - To save time, benchmark is not executed in userspace. Instead, highest supported implementation is used for fastest. Default userspace selector is still 'cycle'. - `fletcher_4_native/byteswap()` methods use incremental methods to finish calculation if data size is not multiple of vector stride (currently 64B). - Added `fletcher_4_native_varsize()` special purpose method for use when buffer size is not known in advance. The method does not enforce 4B alignment on buffer size, and will ignore last (size % 4) bytes of the data buffer. - Benchmark `kstat` is changed to match the one of vdev_raidz. It now shows throughput for all supported implementations (in B/s), native and byteswap, as well as the code [fastest] is running. Example of `fletcher_4_bench` running on `Intel(R) Xeon(R) CPU E5-2660 v3 @ 2.60GHz`: implementation native byteswap scalar 4768120823 3426105750 sse2 7947841777 4318964249 ssse3 7951922722 6112191941 avx2 13269714358 11043200912 fastest avx2 avx2 Example of `fletcher_4_bench` running on `Intel(R) Xeon Phi(TM) CPU 7210 @ 1.30GHz`: implementation native byteswap scalar 1291115967 1031555336 sse2 2539571138 1280970926 ssse3 2537778746 1080016762 avx2 4950749767 1078493449 avx512f 9581379998 4010029046 fastest avx512f avx512f Signed-off-by: Gvozden Neskovic <neskovic@gmail.com> Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> Closes #4952
2016-07-12 18:50:54 +03:00
void fletcher_4_native_varsize(const void *, uint64_t, zio_cksum_t *);
void fletcher_4_byteswap(const void *, uint64_t, zio_cksum_t *);
void fletcher_4_incremental_native(const void *, uint64_t,
zio_cksum_t *);
void fletcher_4_incremental_byteswap(const void *, uint64_t,
zio_cksum_t *);
int fletcher_4_impl_set(const char *selector);
void fletcher_4_init(void);
void fletcher_4_fini(void);
Rework of fletcher_4 module - Benchmark memory block is increased to 128kiB to reflect real block sizes more accurately. Measurements include all three stages needed for checksum generation, i.e. `init()/compute()/fini()`. The inner loop is repeated multiple times to offset overhead of time function. - Fastest implementation selects native and byteswap methods independently in benchmark. To support this new function pointers `init_byteswap()/fini_byteswap()` are introduced. - Implementation mutex lock is replaced by atomic variable. - To save time, benchmark is not executed in userspace. Instead, highest supported implementation is used for fastest. Default userspace selector is still 'cycle'. - `fletcher_4_native/byteswap()` methods use incremental methods to finish calculation if data size is not multiple of vector stride (currently 64B). - Added `fletcher_4_native_varsize()` special purpose method for use when buffer size is not known in advance. The method does not enforce 4B alignment on buffer size, and will ignore last (size % 4) bytes of the data buffer. - Benchmark `kstat` is changed to match the one of vdev_raidz. It now shows throughput for all supported implementations (in B/s), native and byteswap, as well as the code [fastest] is running. Example of `fletcher_4_bench` running on `Intel(R) Xeon(R) CPU E5-2660 v3 @ 2.60GHz`: implementation native byteswap scalar 4768120823 3426105750 sse2 7947841777 4318964249 ssse3 7951922722 6112191941 avx2 13269714358 11043200912 fastest avx2 avx2 Example of `fletcher_4_bench` running on `Intel(R) Xeon Phi(TM) CPU 7210 @ 1.30GHz`: implementation native byteswap scalar 1291115967 1031555336 sse2 2539571138 1280970926 ssse3 2537778746 1080016762 avx2 4950749767 1078493449 avx512f 9581379998 4010029046 fastest avx512f avx512f Signed-off-by: Gvozden Neskovic <neskovic@gmail.com> Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> Closes #4952
2016-07-12 18:50:54 +03:00
/*
* fletcher checksum struct
*/
Rework of fletcher_4 module - Benchmark memory block is increased to 128kiB to reflect real block sizes more accurately. Measurements include all three stages needed for checksum generation, i.e. `init()/compute()/fini()`. The inner loop is repeated multiple times to offset overhead of time function. - Fastest implementation selects native and byteswap methods independently in benchmark. To support this new function pointers `init_byteswap()/fini_byteswap()` are introduced. - Implementation mutex lock is replaced by atomic variable. - To save time, benchmark is not executed in userspace. Instead, highest supported implementation is used for fastest. Default userspace selector is still 'cycle'. - `fletcher_4_native/byteswap()` methods use incremental methods to finish calculation if data size is not multiple of vector stride (currently 64B). - Added `fletcher_4_native_varsize()` special purpose method for use when buffer size is not known in advance. The method does not enforce 4B alignment on buffer size, and will ignore last (size % 4) bytes of the data buffer. - Benchmark `kstat` is changed to match the one of vdev_raidz. It now shows throughput for all supported implementations (in B/s), native and byteswap, as well as the code [fastest] is running. Example of `fletcher_4_bench` running on `Intel(R) Xeon(R) CPU E5-2660 v3 @ 2.60GHz`: implementation native byteswap scalar 4768120823 3426105750 sse2 7947841777 4318964249 ssse3 7951922722 6112191941 avx2 13269714358 11043200912 fastest avx2 avx2 Example of `fletcher_4_bench` running on `Intel(R) Xeon Phi(TM) CPU 7210 @ 1.30GHz`: implementation native byteswap scalar 1291115967 1031555336 sse2 2539571138 1280970926 ssse3 2537778746 1080016762 avx2 4950749767 1078493449 avx512f 9581379998 4010029046 fastest avx512f avx512f Signed-off-by: Gvozden Neskovic <neskovic@gmail.com> Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> Closes #4952
2016-07-12 18:50:54 +03:00
typedef void (*fletcher_4_init_f)(zio_cksum_t *);
typedef void (*fletcher_4_fini_f)(zio_cksum_t *);
typedef void (*fletcher_4_compute_f)(const void *, uint64_t, zio_cksum_t *);
typedef struct fletcher_4_func {
Rework of fletcher_4 module - Benchmark memory block is increased to 128kiB to reflect real block sizes more accurately. Measurements include all three stages needed for checksum generation, i.e. `init()/compute()/fini()`. The inner loop is repeated multiple times to offset overhead of time function. - Fastest implementation selects native and byteswap methods independently in benchmark. To support this new function pointers `init_byteswap()/fini_byteswap()` are introduced. - Implementation mutex lock is replaced by atomic variable. - To save time, benchmark is not executed in userspace. Instead, highest supported implementation is used for fastest. Default userspace selector is still 'cycle'. - `fletcher_4_native/byteswap()` methods use incremental methods to finish calculation if data size is not multiple of vector stride (currently 64B). - Added `fletcher_4_native_varsize()` special purpose method for use when buffer size is not known in advance. The method does not enforce 4B alignment on buffer size, and will ignore last (size % 4) bytes of the data buffer. - Benchmark `kstat` is changed to match the one of vdev_raidz. It now shows throughput for all supported implementations (in B/s), native and byteswap, as well as the code [fastest] is running. Example of `fletcher_4_bench` running on `Intel(R) Xeon(R) CPU E5-2660 v3 @ 2.60GHz`: implementation native byteswap scalar 4768120823 3426105750 sse2 7947841777 4318964249 ssse3 7951922722 6112191941 avx2 13269714358 11043200912 fastest avx2 avx2 Example of `fletcher_4_bench` running on `Intel(R) Xeon Phi(TM) CPU 7210 @ 1.30GHz`: implementation native byteswap scalar 1291115967 1031555336 sse2 2539571138 1280970926 ssse3 2537778746 1080016762 avx2 4950749767 1078493449 avx512f 9581379998 4010029046 fastest avx512f avx512f Signed-off-by: Gvozden Neskovic <neskovic@gmail.com> Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> Closes #4952
2016-07-12 18:50:54 +03:00
fletcher_4_init_f init_native;
fletcher_4_fini_f fini_native;
fletcher_4_compute_f compute_native;
fletcher_4_init_f init_byteswap;
fletcher_4_fini_f fini_byteswap;
fletcher_4_compute_f compute_byteswap;
boolean_t (*valid)(void);
const char *name;
} fletcher_4_ops_t;
#if defined(HAVE_SSE2)
extern const fletcher_4_ops_t fletcher_4_sse2_ops;
#endif
#if defined(HAVE_SSE2) && defined(HAVE_SSSE3)
extern const fletcher_4_ops_t fletcher_4_ssse3_ops;
#endif
#if defined(HAVE_AVX) && defined(HAVE_AVX2)
extern const fletcher_4_ops_t fletcher_4_avx2_ops;
#endif
#if defined(__x86_64) && defined(HAVE_AVX512F)
extern const fletcher_4_ops_t fletcher_4_avx512f_ops;
#endif
#ifdef __cplusplus
}
#endif
#endif /* _ZFS_FLETCHER_H */