[<prev] [next>] [thread-next>] [day] [month] [year] [list]
Message-Id: <20180528060834.72DE86F377@po14934vm.idsi0.si.c-s.fr>
Date: Mon, 28 May 2018 06:08:34 +0000 (UTC)
From: Christophe Leroy <christophe.leroy@....fr>
To: Benjamin Herrenschmidt <benh@...nel.crashing.org>,
Paul Mackerras <paulus@...ba.org>,
Michael Ellerman <mpe@...erman.id.au>
Cc: linux-kernel@...r.kernel.org, linuxppc-dev@...ts.ozlabs.org
Subject: [PATCH] powerpc/Makefile: set -mcpu=860 flag for the 8xx
When compiled with GCC 8.1, vmlinux is significantly bigger than
with GCC 4.8.
When looking at the generated code with objdump, we notice that
all functions and loops when a 16 bytes alignment. This significantly
increases the size of the kernel. It is pointless and even
counterproductive as on the 8xx 'nop' also consumes one clock cycle.
Size of vmlinux with GCC 4.8:
text data bss dec hex filename
5801948 1626076 457796 7885820 7853fc vmlinux
Size of vmlinux with GCC 8.1:
text data bss dec hex filename
6764592 1630652 456476 8851720 871108 vmlinux
Size of vmlinux with GCC 8.1 and this patch:
text data bss dec hex filename
6331544 1631756 456476 8419776 8079c0 vmlinux
Signed-off-by: Christophe Leroy <christophe.leroy@....fr>
---
arch/powerpc/Makefile | 1 +
1 file changed, 1 insertion(+)
diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile
index 6a050b42a9f2..26ccd0b91512 100644
--- a/arch/powerpc/Makefile
+++ b/arch/powerpc/Makefile
@@ -178,6 +178,7 @@ CFLAGS-$(CONFIG_POWER6_CPU) += $(call cc-option,-mcpu=power6)
CFLAGS-$(CONFIG_POWER7_CPU) += $(call cc-option,-mcpu=power7)
CFLAGS-$(CONFIG_POWER8_CPU) += $(call cc-option,-mcpu=power8)
CFLAGS-$(CONFIG_POWER9_CPU) += $(call cc-option,-mcpu=power9)
+CFLAGS-$(CONFIG_PPC_8xx) += $(call cc-option,-mcpu=860)
# Altivec option not allowed with e500mc64 in GCC.
ifeq ($(CONFIG_ALTIVEC),y)
--
2.13.3
Powered by blists - more mailing lists