From f2091321044d9fbcadb93dfc1c9cf23e563ea40c Mon Sep 17 00:00:00 2001 From: WANG Xuerui Date: Wed, 6 Sep 2023 22:53:55 +0800 Subject: raid6: Add LoongArch SIMD recovery implementation Similar to the syndrome calculation, the recovery algorithms also work on 64 bytes at a time to align with the L1 cache line size of current and future LoongArch cores (that we care about). Which means unrolled-by-4 LSX and unrolled-by-2 LASX code. The assembly is originally based on the x86 SSSE3/AVX2 ports, but register allocation has been redone to take advantage of LSX/LASX's 32 vector registers, and instruction sequence has been optimized to suit (e.g. LoongArch can perform per-byte srl and andi on vectors, but x86 cannot). Performance numbers measured by instrumenting the raid6test code, on a 3A5000 system clocked at 2.5GHz: > lasx 2data: 354.987 MiB/s > lasx datap: 350.430 MiB/s > lsx 2data: 340.026 MiB/s > lsx datap: 337.318 MiB/s > intx1 2data: 164.280 MiB/s > intx1 datap: 187.966 MiB/s Because recovery algorithms are chosen solely based on priority and availability, lasx is marked as priority 2 and lsx priority 1. At least for the current generation of LoongArch micro-architectures, LASX should always be faster than LSX whenever supported, and have similar power consumption characteristics (because the only known LASX-capable uarch, the LA464, always compute the full 256-bit result for vector ops). Acked-by: Song Liu Signed-off-by: WANG Xuerui Signed-off-by: Huacai Chen --- lib/raid6/algos.c | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'lib/raid6/algos.c') diff --git a/lib/raid6/algos.c b/lib/raid6/algos.c index 739c7ebcae1a..0ec534faf019 100644 --- a/lib/raid6/algos.c +++ b/lib/raid6/algos.c @@ -111,6 +111,14 @@ const struct raid6_recov_calls *const raid6_recov_algos[] = { #endif #if defined(CONFIG_KERNEL_MODE_NEON) &raid6_recov_neon, +#endif +#ifdef CONFIG_LOONGARCH +#ifdef CONFIG_CPU_HAS_LASX + &raid6_recov_lasx, +#endif +#ifdef CONFIG_CPU_HAS_LSX + &raid6_recov_lsx, +#endif #endif &raid6_recov_intx1, NULL -- cgit v1.2.3