From e128749be88278768c50907ca87270b9d5e96eb5 Mon Sep 17 00:00:00 2001 From: Archana R Date: Sun, 19 Sep 2021 23:50:02 -0500 Subject: [PATCH] hash/crc32: improve performance of ppc64SlicingUpdateBy8 on ppc64le MIME-Version: 1.0 Content-Type: text/plain; charset=utf8 Content-Transfer-Encoding: 8bit Reduce the number of instructions in the short loop of ppc64SlicingUpdateBy8 function by combining MOVWZ and SRD into a SRD with appropriate parameters performing the same operation and remove MOVWZ R7,R7 from the loop This change produces the following improvements on POWER9. None of the other tests regress. Improvments on other POWERPC platforms similar. name old time/op new time/op delta CRC32/poly=IEEE/size=15/align=0 80.5ns ± 0% 70.6ns ± 0% -12% CRC32/poly=IEEE/size=15/align=1 80.5ns ± 0% 70.6ns ± 0% -12% CRC32/poly=IEEE/size=512/align=1 151ns ± 0% 139ns ± 0% -7% CRC32/poly=IEEE/size=1kB/align=1 167ns ± 0% 155ns ± 0% -7% CRC32/poly=Castagnoli/size=15/align=0 80.2ns ± 0% 70.5ns ± 0% -12% CRC32/poly=Castagnoli/size=15/align=1 80.2ns ± 0% 70.5ns ± 0% -12% CRC32/poly=Castagnoli/size=512/align=1 150ns ± 0% 139ns ± 0% -7% CRC32/poly=Castagnoli/size=1kB/align=1 166ns ± 0% 155ns ± 0% -6% Change-Id: I424709041c30d1c637b595d0845e3ae78dc3e0a0 Reviewed-on: https://go-review.googlesource.com/c/go/+/350989 Reviewed-by: Lynn Boger Reviewed-by: Cherry Mui Run-TryBot: Lynn Boger TryBot-Result: Go Bot --- src/hash/crc32/crc32_ppc64le.s | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/src/hash/crc32/crc32_ppc64le.s b/src/hash/crc32/crc32_ppc64le.s index 10d5dd61db..763d3270f3 100644 --- a/src/hash/crc32/crc32_ppc64le.s +++ b/src/hash/crc32/crc32_ppc64le.s @@ -112,19 +112,17 @@ loop: ANDCC $7,R6,R8 // any leftover bytes BEQ done // none --> done MOVD R8,CTR // byte count - + PCALIGN $16 // align short loop short: MOVBZ 0(R5),R8 // get v MOVBZ R7,R9 // byte(crc) -> R8 BE vs LE? - MOVWZ R7,R14 - SRD $8,R14,R14 // crc>>8 + SRD $8,R7,R14 // crc>>8 XOR R8,R9,R8 // byte(crc)^v -> R8 ADD $1,R5 // ptr to next v SLD $2,R8 // convert index-> bytes ADD R8,R4,R9 // &tab[byte(crc)^v] MOVWZ 0(R9),R10 // tab[byte(crc)^v] XOR R10,R14,R7 // loop crc in R7 - MOVWZ R7,R7 // 32 bits BC 16,0,short done: NOR R7,R7,R7 // ^crc -- 2.50.0