diff options
| author | Andi Kleen <ak@suse.de> | 2005-11-05 17:25:54 +0100 |
|---|---|---|
| committer | Linus Torvalds <torvalds@g5.osdl.org> | 2005-11-14 19:55:17 -0800 |
| commit | a5b250a428aabc619ace872f8220a7d0b8f7d557 (patch) | |
| tree | 11cabf07982ae37f94bc929f9a605cbbd20e35ab /arch/x86_64/lib/clear_page.S | |
| parent | a6f5deb2be4c82f24fefadcbf7e448f540c05ae6 (diff) | |
[PATCH] x86_64: Remove optimization for B stepping AMD K8
B stepping were the first shipping Opterons. memcpy/memset/copy_page/
clear_page had special optimized version for them. These are really
old and in the minority now and the difference to the generic versions
(using rep microcode) is not that big anyways. So just remove them.
TODO: figure out optimized versions for Intel Netburst based EM64T
Signed-off-by: Andi Kleen <ak@suse.de>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Diffstat (limited to 'arch/x86_64/lib/clear_page.S')
| -rw-r--r-- | arch/x86_64/lib/clear_page.S | 38 |
1 files changed, 0 insertions, 38 deletions
diff --git a/arch/x86_64/lib/clear_page.S b/arch/x86_64/lib/clear_page.S index 30a9da458c15..43d9fa136180 100644 --- a/arch/x86_64/lib/clear_page.S +++ b/arch/x86_64/lib/clear_page.S @@ -5,46 +5,8 @@ .globl clear_page .p2align 4 clear_page: - xorl %eax,%eax - movl $4096/64,%ecx - .p2align 4 -.Lloop: - decl %ecx -#define PUT(x) movq %rax,x*8(%rdi) - movq %rax,(%rdi) - PUT(1) - PUT(2) - PUT(3) - PUT(4) - PUT(5) - PUT(6) - PUT(7) - leaq 64(%rdi),%rdi - jnz .Lloop - nop - ret -clear_page_end: - - /* C stepping K8 run faster using the string instructions. - It is also a lot simpler. Use this when possible */ - -#include <asm/cpufeature.h> - - .section .altinstructions,"a" - .align 8 - .quad clear_page - .quad clear_page_c - .byte X86_FEATURE_K8_C - .byte clear_page_end-clear_page - .byte clear_page_c_end-clear_page_c - .previous - - .section .altinstr_replacement,"ax" -clear_page_c: movl $4096/8,%ecx xorl %eax,%eax rep stosq ret -clear_page_c_end: - .previous |