build: fix memcpy behaviour regression
PATCH 1/1 build: fix memcpy behaviour regression
When testing on some x86 platforms, code compiled with meson was observed running at a different power-license level to that compiled with make. This is due to the fact that meson auto-detects the instruction sets available on the system and enabled AVX512 rte_memcpy when AVX512 was available, while on make, a build time AVX-512 flag needed to be explicitly set to enable that AVX512 rte_memcpy code path.
In the absense of runtime path selection for rte_memcpy - which is complicated by it being a static inline function in a header file - we can fix this behaviour regression by similarly having a build-time option which must be set to enable the AVX-512 memcpy path.
---
NOTE: This patch is not suitable for backporting, as it will break the build support for make builds without addition makefile changes.
--- lib/librte_eal/include/generic/rte_memcpy.h | 4 ++++ lib/librte_eal/x86/include/rte_memcpy.h | 2 +- 2 files changed, 5 insertions(+), 1 deletion(-)
lib/librte_eal/include/generic/rte_memcpy.h +4 -0
@@ -95,6 +95,10 @@ rte_mov256(uint8_t *dst, const uint8_t *src);* @note This is implemented as a macro, so it's address should not be taken * and care is needed as parameter expressions may be evaluated multiple times. * +* @note For x86 platforms to enable the AVX-512 memcpy implementation, set +* -DRTE_MEMCPY_AVX512 macro in CFLAGS, or define the RTE_MEMCPY_AVX512 macro +* explicitly in the source file before including the rte_memcpy header file. +* * @param dst * Pointer to the destination of the data. * @param src
lib/librte_eal/x86/include/rte_memcpy.h +1 -1
@@ -45,7 +45,7 @@ extern "C" { static __rte_always_inline void *rte_memcpy (void *dst,const void *src,size_t n); -#ifdef __AVX512F__ +#if defined __AVX512F__ && definedRTE_MEMCPY_AVX512 #define ALIGNMENT_MASK 0x3F
Signature · 1 line
2.25.1
Best Regards,
Yingya
-----Original Message-----
From: Richardson, Bruce <[email protected]>
Sent: Monday, October 12, 2020 10:52 PM
To: [email protected]
Cc: Han, YingyaX <[email protected]>; Ananyev, Konstantin <[email protected]>; Tu, Lijuan <[email protected]>; Richardson, Bruce <[email protected]>
Subject: [PATCH] build: fix memcpy behaviour regression
When testing on some x86 platforms, code compiled with meson was observed running at a different power-license level to that compiled with make. This is due to the fact that meson auto-detects the instruction sets available on the system and enabled AVX512 rte_memcpy when AVX512 was available, while on make, a build time AVX-512 flag needed to be explicitly set to enable that AVX512 rte_memcpy code path.
In the absense of runtime path selection for rte_memcpy - which is complicated by it being a static inline function in a header file - we can fix this behaviour regression by similarly having a build-time option which must be set to enable the AVX-512 memcpy path.
Thomas Monjalon
AppliedQuoted 7 lines
From: Richardson, Bruce <[email protected]>
When testing on some x86 platforms, code compiled with meson was observed running at a different power-license level to that compiled with make. This is due to the fact that meson auto-detects the instruction sets available on the system and enabled AVX512
rte_memcpywhen AVX512 was available, while on make, a build time AVX-512 flag needed to be explicitly set to enable that AVX512rte_memcpycode path.In the absense of runtime path selection for
rte_memcpy- which is complicated by it being a static inline function in a header file - we can fix this behaviour regression by similarly having a build-time option which must be set to enable the AVX-512 memcpy path.Tested-by Han, Yingya <[email protected]>
Applied, thanks