update latest

[external/libjpeg-turbo.git] / simd / jdmrgss2.asm

diff --git a/simd/jdmrgss2.asm b/simd/jdmrgss2.asm
index 368ac3c..04089aa 100644 (file)
--- a/simd/jdmrgss2.asm
+++ b/simd/jdmrgss2.asm
@@ -307,6 +307,41 @@ EXTN(jsimd_h2v1_merged_upsample_sse2):
        movdqa  xmmA,xmmD
        sub     ecx, byte SIZEOF_XMMWORD
 .column_st15:
+%ifdef STRICT_MEMORY_ACCESS
+       ; Store the lower 8 bytes of xmmA to the output when it has enough
+       ; space.
+       cmp     ecx, byte SIZEOF_MMWORD
+       jb      short .column_st7
+       movq    MMWORD [edi], xmmA
+       add     edi, byte SIZEOF_MMWORD
+       sub     ecx, byte SIZEOF_MMWORD
+       psrldq  xmmA, SIZEOF_MMWORD
+.column_st7:
+       ; Store the lower 4 bytes of xmmA to the output when it has enough
+       ; space.
+       cmp     ecx, byte SIZEOF_DWORD
+       jb      short .column_st3
+       movd    DWORD [edi], xmmA
+       add     edi, byte SIZEOF_DWORD
+       sub     ecx, byte SIZEOF_DWORD
+       psrldq  xmmA, SIZEOF_DWORD
+.column_st3:
+       ; Store the lower 2 bytes of eax to the output when it has enough
+       ; space.
+       movd    eax, xmmA
+       cmp     ecx, byte SIZEOF_WORD
+       jb      short .column_st1
+       mov     WORD [edi], ax
+       add     edi, byte SIZEOF_WORD
+       sub     ecx, byte SIZEOF_WORD
+       shr     eax, 16
+.column_st1:
+       ; Store the lower 1 byte of eax to the output when it has enough
+       ; space.
+       test    ecx, ecx
+       jz      short .endcolumn
+       mov     BYTE [edi], al
+%else
        mov     eax,ecx
        xor     ecx, byte 0x0F
        shl     ecx, 2
@@ -346,6 +381,7 @@ EXTN(jsimd_h2v1_merged_upsample_sse2):
        por     xmmE,xmmC
 .adj0: ; ----------------
        maskmovdqu xmmA,xmmE                    ; movntdqu XMMWORD [edi], xmmA
+%endif ; STRICT_MEMORY_ACCESS ; ---------------
 
 %else ; RGB_PIXELSIZE == 4 ; -----------
 
@@ -434,6 +470,22 @@ EXTN(jsimd_h2v1_merged_upsample_sse2):
        movdqa  xmmA,xmmD
        sub     ecx, byte SIZEOF_XMMWORD/4
 .column_st15:
+%ifdef STRICT_MEMORY_ACCESS
+       ; Store two pixels (8 bytes) of xmmA to the output when it has enough
+       ; space.
+       cmp     ecx, byte SIZEOF_XMMWORD/8
+       jb      short .column_st7
+       movq    MMWORD [edi], xmmA
+       add     edi, byte SIZEOF_XMMWORD/2
+       sub     ecx, byte SIZEOF_XMMWORD/8
+       psrldq  xmmA, 64
+.column_st7:
+       ; Store one pixel (4 bytes) of xmmA to the output when it has enough
+       ; space.
+       test    ecx, ecx
+       jz      short .endcolumn
+       movd    DWORD [edi], xmmA
+%else
        cmp     ecx, byte SIZEOF_XMMWORD/16
        jb      short .endcolumn
        mov     eax,ecx
@@ -473,6 +525,7 @@ EXTN(jsimd_h2v1_merged_upsample_sse2):
        por     xmmE,xmmG
 .adj0: ; ----------------
        maskmovdqu xmmA,xmmE                    ; movntdqu XMMWORD [edi], xmmA
+%endif ; STRICT_MEMORY_ACCESS ; ---------------
 
 %endif ; RGB_PIXELSIZE ; ---------------