X-Git-Url: http://review.tizen.org/git/?a=blobdiff_plain;f=simd%2Fjdclrss2-64.asm;h=696a383bddf65b4daa38ed071ad8a888ed69703e;hb=HEAD;hp=fdb33a3627457238dbd9d65ff6237773ca2f845e;hpb=5f9f13097a33ee622c3fc7ddc194b3212485d8b0;p=external%2Flibjpeg-turbo.git

diff --git a/simd/jdclrss2-64.asm b/simd/jdclrss2-64.asm
index fdb33a3..696a383 100644
--- a/simd/jdclrss2-64.asm
+++ b/simd/jdclrss2-64.asm
@@ -290,6 +290,41 @@ EXTN(jsimd_ycc_rgb_convert_sse2):
 	movdqa	xmmA,xmmD
 	sub	rcx, 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	rcx, byte SIZEOF_MMWORD
+	jb	short .column_st7
+	movq	MMWORD [rdi], xmmA
+	add	rdi, byte SIZEOF_MMWORD
+	sub	rcx, 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	rcx, byte SIZEOF_DWORD
+	jb	short .column_st3
+	movd	DWORD [rdi], xmmA
+	add	rdi, byte SIZEOF_DWORD
+	sub	rcx, byte SIZEOF_DWORD
+	psrldq	xmmA, SIZEOF_DWORD
+.column_st3:
+	; Store the lower 2 bytes of rax to the output when it has enough
+	; space.
+	movd	eax, xmmA
+	cmp	rcx, byte SIZEOF_WORD
+	jb	short .column_st1
+	mov	WORD [rdi], ax
+	add	rdi, byte SIZEOF_WORD
+	sub	rcx, byte SIZEOF_WORD
+	shr	rax, 16
+.column_st1:
+	; Store the lower 1 byte of rax to the output when it has enough
+	; space.
+	test	rcx, rcx
+	jz	short .nextrow
+	mov	BYTE [rdi], al
+%else
 	mov	rax,rcx
 	xor	rcx, byte 0x0F
 	shl	rcx, 2
@@ -329,6 +364,7 @@ EXTN(jsimd_ycc_rgb_convert_sse2):
 	por	xmmE,xmmC
 .adj0:	; ----------------
 	maskmovdqu xmmA,xmmE			; movntdqu XMMWORD [rdi], xmmA
+%endif ; STRICT_MEMORY_ACCESS ; ---------------
 
 %else ; RGB_PIXELSIZE == 4 ; -----------
 
@@ -413,6 +449,22 @@ EXTN(jsimd_ycc_rgb_convert_sse2):
 	movdqa	xmmA,xmmD
 	sub	rcx, 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	rcx, byte SIZEOF_XMMWORD/8
+	jb	short .column_st7
+	movq	MMWORD [rdi], xmmA
+	add	rdi, byte SIZEOF_XMMWORD/8*4
+	sub	rcx, byte SIZEOF_XMMWORD/8
+	psrldq	xmmA, SIZEOF_XMMWORD/8*4
+.column_st7:
+	; Store one pixel (4 bytes) of xmmA to the output when it has enough
+	; space.
+	test	rcx, rcx
+	jz	short .nextrow
+	movd	DWORD [rdi], xmmA
+%else
 	cmp	rcx, byte SIZEOF_XMMWORD/16
 	jb	near .nextrow
 	mov	rax,rcx
@@ -452,6 +504,7 @@ EXTN(jsimd_ycc_rgb_convert_sse2):
 	por	xmmE,xmmG
 .adj0:	; ----------------
 	maskmovdqu xmmA,xmmE			; movntdqu XMMWORD [rdi], xmmA
+%endif ; STRICT_MEMORY_ACCESS ; ---------------
 
 %endif ; RGB_PIXELSIZE ; ---------------