mirror of https://gitee.com/openkylin/linux.git
arm64: crypto: increase AES interleave to 4x
This patch increases the interleave factor for parallel AES modes to 4x. This improves performance on Cortex-A57 by ~35%. This is due to the 3-cycle latency of AES instructions on the A57's relatively deep pipeline (compared to Cortex-A53 where the AES instruction latency is only 2 cycles). At the same time, disable inline expansion of the core AES functions, as the performance benefit of this feature is negligible. Measured on AMD Seattle (using tcrypt.ko mode=500 sec=1): Baseline (2x interleave, inline expansion) ------------------------------------------ testing speed of async cbc(aes) (cbc-aes-ce) decryption test 4 (128 bit key, 8192 byte blocks): 95545 operations in 1 seconds test 14 (256 bit key, 8192 byte blocks): 68496 operations in 1 seconds This patch (4x interleave, no inline expansion) ----------------------------------------------- testing speed of async cbc(aes) (cbc-aes-ce) decryption test 4 (128 bit key, 8192 byte blocks): 124735 operations in 1 seconds test 14 (256 bit key, 8192 byte blocks): 92328 operations in 1 seconds Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org> Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
This commit is contained in:
parent
6910fa16db
commit
0eee0fbd41
|
@ -29,7 +29,7 @@ aes-ce-blk-y := aes-glue-ce.o aes-ce.o
|
|||
obj-$(CONFIG_CRYPTO_AES_ARM64_NEON_BLK) += aes-neon-blk.o
|
||||
aes-neon-blk-y := aes-glue-neon.o aes-neon.o
|
||||
|
||||
AFLAGS_aes-ce.o := -DINTERLEAVE=2 -DINTERLEAVE_INLINE
|
||||
AFLAGS_aes-ce.o := -DINTERLEAVE=4
|
||||
AFLAGS_aes-neon.o := -DINTERLEAVE=4
|
||||
|
||||
CFLAGS_aes-glue-ce.o := -DUSE_V8_CRYPTO_EXTENSIONS
|
||||
|
|
Loading…
Reference in New Issue