[PATCH] LoongArch: Select ARCH_HAS_FAST_MULTIPLIER

From: Xi Ruoyao
Date: Wed Mar 27 2024 - 13:19:30 EST


LA464 and LA664 can do 32-bit/64-bit integer multiplication with a
latency of 4 cycles and a throughput of 2 ops per cycle. It's
comparable to mainstream x86 and arm64 cores, so select
ARCH_HAS_FAST_MULTIPLIER like them.

It speeds up __sw_hweight32 in lib/hweight.c for about 14% on LA464 and
11% on LA664, and __sw_hweight64 for about 30% on LA464 and 33% on
LA664.

Signed-off-by: Xi Ruoyao <xry111@xxxxxxxxxxx>
---
arch/loongarch/Kconfig | 1 +
1 file changed, 1 insertion(+)

diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig
index 5a769bb92d7c..d52a95195e7f 100644
--- a/arch/loongarch/Kconfig
+++ b/arch/loongarch/Kconfig
@@ -16,6 +16,7 @@ config LOONGARCH
select ARCH_HAS_ACPI_TABLE_UPGRADE if ACPI
select ARCH_HAS_CPU_FINALIZE_INIT
select ARCH_HAS_CURRENT_STACK_POINTER
+ select ARCH_HAS_FAST_MULTIPLIER
select ARCH_HAS_FORTIFY_SOURCE
select ARCH_HAS_KCOV
select ARCH_HAS_NMI_SAFE_THIS_CPU_OPS
--
2.44.0