From d003ad630b1792f169373b8ab35c5ea7a6dfdccd Mon Sep 17 00:00:00 2001 From: Martin Kroeker Date: Tue, 31 Oct 2023 10:26:38 +0100 Subject: [PATCH 1/2] Increase the default GEMM buffer size on modern ARM server cpus --- common_arm64.h | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/common_arm64.h b/common_arm64.h index 436ccb8f59..1e593c66fc 100644 --- a/common_arm64.h +++ b/common_arm64.h @@ -162,7 +162,11 @@ static inline int blas_quickdivide(blasint x, blasint y){ #define HUGE_PAGESIZE ( 4 << 20) #ifndef BUFFERSIZE +if defined(NEOVERSEN1) || defined(NEOVERSEN2) || defined(NEOVERSEV1) || defined(A64FX) || defined(ARMV8SVE) +#define BUFFER_SIZE (32 << 22) +else #define BUFFER_SIZE (32 << 20) +#endif #else #define BUFFER_SIZE (32 << BUFFERSIZE) #endif From 728788f6676bb5e999cdf4fbcda9e2c7b8b9cd53 Mon Sep 17 00:00:00 2001 From: Martin Kroeker Date: Tue, 31 Oct 2023 11:08:22 +0100 Subject: [PATCH 2/2] typo fix --- common_arm64.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/common_arm64.h b/common_arm64.h index 1e593c66fc..6ae6a35a30 100644 --- a/common_arm64.h +++ b/common_arm64.h @@ -162,9 +162,9 @@ static inline int blas_quickdivide(blasint x, blasint y){ #define HUGE_PAGESIZE ( 4 << 20) #ifndef BUFFERSIZE -if defined(NEOVERSEN1) || defined(NEOVERSEN2) || defined(NEOVERSEV1) || defined(A64FX) || defined(ARMV8SVE) +#if defined(NEOVERSEN1) || defined(NEOVERSEN2) || defined(NEOVERSEV1) || defined(A64FX) || defined(ARMV8SVE) #define BUFFER_SIZE (32 << 22) -else +#else #define BUFFER_SIZE (32 << 20) #endif #else