diff options
Diffstat (limited to 'MdePkg/Library/BaseMemoryLibSse2/Ia32/SetMem.nasm')
| -rw-r--r-- | MdePkg/Library/BaseMemoryLibSse2/Ia32/SetMem.nasm | 11 |
1 files changed, 7 insertions, 4 deletions
diff --git a/MdePkg/Library/BaseMemoryLibSse2/Ia32/SetMem.nasm b/MdePkg/Library/BaseMemoryLibSse2/Ia32/SetMem.nasm index 24313cb4b3..a8744300c6 100644 --- a/MdePkg/Library/BaseMemoryLibSse2/Ia32/SetMem.nasm +++ b/MdePkg/Library/BaseMemoryLibSse2/Ia32/SetMem.nasm @@ -34,7 +34,7 @@ ASM_PFX(InternalMemSetMem): mov al, [esp + 16] ; al <- Value
xor ecx, ecx
sub ecx, edi
- and ecx, 15 ; ecx + edi aligns on 16-byte boundary
+ and ecx, 63 ; ecx + edi aligns on 16-byte boundary
jz .0
cmp ecx, edx
cmova ecx, edx
@@ -42,8 +42,8 @@ ASM_PFX(InternalMemSetMem): rep stosb
.0:
mov ecx, edx
- and edx, 15
- shr ecx, 4 ; ecx <- # of DQwords to set
+ and edx, 63
+ shr ecx, 6 ; ecx <- # of DQwords to set
jz @SetBytes
mov ah, al ; ax <- Value | (Value << 8)
add esp, -16
@@ -53,7 +53,10 @@ ASM_PFX(InternalMemSetMem): movlhps xmm0, xmm0 ; xmm0 <- Value repeats 16 times
.1:
movntdq [edi], xmm0 ; edi should be 16-byte aligned
- add edi, 16
+ movntdq [edi + 16], xmm0
+ movntdq [edi + 32], xmm0
+ movntdq [edi + 48], xmm0
+ add edi, 64
loop .1
mfence
movdqu xmm0, [esp] ; restore xmm0
|