[x265] [PATCH] cleanup: remove unused asm calcrecon

Min Chen chenm003 at 163.com
Mon Nov 3 21:43:35 CET 2014


# HG changeset patch
# User Min Chen <chenm003 at 163.com>
# Date 1415047406 28800
# Node ID a7c7c1e849986dc7fa46cd213643b12c5f2866eb
# Parent  244d06de1b999315b5f006be5fc59b10481a2e33
cleanup: remove unused asm calcrecon

diff -r 244d06de1b99 -r a7c7c1e84998 source/common/primitives.h
--- a/source/common/primitives.h	Fri Oct 31 17:25:02 2014 -0500
+++ b/source/common/primitives.h	Mon Nov 03 12:43:26 2014 -0800
@@ -160,7 +160,6 @@
 typedef void (*denoiseDct_t)(int32_t* dctCoef, uint32_t* resSum, uint16_t* offset, int numCoeff);
 
 typedef void (*calcresidual_t)(pixel *fenc, pixel *pred, int16_t *residual, intptr_t stride);
-typedef void (*calcrecon_t)(pixel* pred, int16_t* residual, int16_t* reconqt, pixel *reconipred, int stride, int strideqt, int strideipred);
 typedef void (*transpose_t)(pixel* dst, pixel* src, intptr_t stride);
 typedef uint32_t (*quant_t)(int32_t *coef, int32_t *quantCoeff, int32_t *deltaU, int16_t *qCoef, int qBits, int add, int numCoeff);
 typedef uint32_t (*nquant_t)(int32_t *coef, int32_t *quantCoeff, int16_t *qCoef, int qBits, int add, int numCoeff);
diff -r 244d06de1b99 -r a7c7c1e84998 source/common/x86/pixel-util.h
--- a/source/common/x86/pixel-util.h	Fri Oct 31 17:25:02 2014 -0500
+++ b/source/common/x86/pixel-util.h	Mon Nov 03 12:43:26 2014 -0800
@@ -24,13 +24,6 @@
 #ifndef X265_PIXEL_UTIL_H
 #define X265_PIXEL_UTIL_H
 
-void x265_calcRecons4_sse2(pixel* pred, int16_t* residual, int16_t* reconqt, pixel *reconipred, int stride, int strideqt, int strideipred);
-void x265_calcRecons8_sse2(pixel* pred, int16_t* residual, int16_t* reconqt, pixel *reconipred, int stride, int strideqt, int strideipred);
-void x265_calcRecons16_sse2(pixel* pred, int16_t* residual, int16_t* reconqt, pixel *reconipred, int stride, int strideqt, int strideipred);
-void x265_calcRecons32_sse2(pixel* pred, int16_t* residual, int16_t* reconqt, pixel *reconipred, int stride, int strideqt, int strideipred);
-void x265_calcRecons16_sse4(pixel* pred, int16_t* residual, int16_t* reconqt, pixel *reconipred, int stride, int strideqt, int strideipred);
-void x265_calcRecons32_sse4(pixel* pred, int16_t* residual, int16_t* reconqt, pixel *reconipred, int stride, int strideqt, int strideipred);
-
 void x265_getResidual4_sse2(pixel *fenc, pixel *pred, int16_t *residual, intptr_t stride);
 void x265_getResidual8_sse2(pixel *fenc, pixel *pred, int16_t *residual, intptr_t stride);
 void x265_getResidual16_sse2(pixel *fenc, pixel *pred, int16_t *residual, intptr_t stride);
diff -r 244d06de1b99 -r a7c7c1e84998 source/common/x86/pixel-util8.asm
--- a/source/common/x86/pixel-util8.asm	Fri Oct 31 17:25:02 2014 -0500
+++ b/source/common/x86/pixel-util8.asm	Mon Nov 03 12:43:26 2014 -0800
@@ -61,447 +61,6 @@
 cextern pd_32767
 cextern pd_n32768
 
-;-----------------------------------------------------------------------------
-; void calcrecon(pixel* pred, int16_t* residual, int16_t* reconqt, pixel *reconipred, int stride, int strideqt, int strideipred)
-;-----------------------------------------------------------------------------
-INIT_XMM sse2
-%if HIGH_BIT_DEPTH
-%if ARCH_X86_64 == 1
-cglobal calcRecons4, 5,8,4
-    %define t7b     r7b
-%else
-cglobal calcRecons4, 5,7,4,0-1
-    %define t7b     byte [rsp]
-%endif
-    mov         r4d, r4m
-    mov         r5d, r5m
-    mov         r6d, r6m
-    add         r4d, r4d
-    add         r5d, r5d
-    add         r6d, r6d
-
-    pxor        m4, m4
-    mova        m5, [pw_pixel_max]
-    mov         t7b, 4/2
-.loop:
-    movh        m0, [r0]
-    movh        m1, [r0 + r4]
-    punpcklqdq  m0, m1
-    movh        m2, [r1]
-    movh        m3, [r1 + r4]
-    punpcklqdq  m2, m3
-    paddw       m0, m2
-    CLIPW       m0, m4, m5
-
-    ; store recipred[]
-    movh        [r3], m0
-    movhps      [r3 + r6], m0
-
-    ; store recqt[]
-    movh        [r2], m0
-    movhps      [r2 + r5], m0
-
-    lea         r0, [r0 + r4 * 2]
-    lea         r1, [r1 + r4 * 2]
-    lea         r2, [r2 + r5 * 2]
-    lea         r3, [r3 + r6 * 2]
-
-    dec         t7b
-    jnz        .loop
-    RET
-%else          ;HIGH_BIT_DEPTH
-
-%if ARCH_X86_64 == 1
-cglobal calcRecons4, 5,8,4
-    %define t7b     r7b
-%else
-cglobal calcRecons4, 5,7,4,0-1
-    %define t7b     byte [rsp]
-%endif
-    mov         r4d, r4m
-    mov         r5d, r5m
-    mov         r6d, r6m
-    add         r5d, r5d
-
-    pxor        m0, m0
-    mov         t7b, 4/2
-.loop:
-    movd        m1, [r0]
-    movd        m2, [r0 + r4]
-    punpckldq   m1, m2
-    punpcklbw   m1, m0
-    movh        m2, [r1]
-    movh        m3, [r1 + r4 * 2]
-    punpcklqdq  m2, m3
-    paddw       m1, m2
-    packuswb    m1, m1
-
-    ; store recon[] and recipred[]
-    movd        [r3], m1
-    pshufd      m2, m1, 1
-    movd        [r3 + r6], m2
-
-    ; store recqt[]
-    punpcklbw   m1, m0
-    movh        [r2], m1
-    movhps      [r2 + r5], m1
-
-    lea         r0, [r0 + r4 * 2]
-    lea         r1, [r1 + r4 * 4]
-    lea         r2, [r2 + r5 * 2]
-    lea         r3, [r3 + r6 * 2]
-
-    dec         t7b
-    jnz        .loop
-    RET
-%endif          ;HIGH_BIT_DEPTH
-
-
-INIT_XMM sse2
-%if ARCH_X86_64 == 1
-cglobal calcRecons8, 5,8,4
-    %define t7b     r7b
-%else
-cglobal calcRecons8, 5,7,4,0-1
-    %define t7b     byte [rsp]
-%endif
-
-%if HIGH_BIT_DEPTH
-    mov         r4d, r4m
-    mov         r5d, r5m
-    mov         r6d, r6m
-    add         r4d, r4d
-    add         r5d, r5d
-    add         r6d, r6d
-
-    pxor        m4, m4
-    mova        m5, [pw_pixel_max]
-    mov         t7b, 8/2
-.loop:
-    movu        m0, [r0]
-    movu        m1, [r0 + r4]
-    movu        m2, [r1]
-    movu        m3, [r1 + r4]
-    paddw       m0, m2
-    paddw       m1, m3
-    CLIPW2      m0, m1, m4, m5
-
-    ; store recipred[]
-    movu        [r3], m0
-    movu        [r3 + r6], m1
-
-    ; store recqt[]
-    movu        [r2], m0
-    movu        [r2 + r5], m1
-
-    lea         r0, [r0 + r4 * 2]
-    lea         r1, [r1 + r4 * 2]
-    lea         r2, [r2 + r5 * 2]
-    lea         r3, [r3 + r6 * 2]
-
-    dec         t7b
-    jnz        .loop
-    RET
-%else          ;HIGH_BIT_DEPTH
-
-    mov         r4d, r4m
-    mov         r5d, r5m
-    mov         r6d, r6m
-    add         r5d, r5d
-
-    pxor        m0, m0
-    mov         t7b, 8/2
-.loop:
-    movh        m1, [r0]
-    movh        m2, [r0 + r4]
-    punpcklbw   m1, m0
-    punpcklbw   m2, m0
-    movu        m3, [r1]
-    movu        m4, [r1 + r4 * 2]
-    paddw       m1, m3
-    paddw       m2, m4
-    packuswb    m1, m2
-
-    ; store recon[] and recipred[]
-    movh        [r3], m1
-    movhps      [r3 + r6], m1
-
-    ; store recqt[]
-    punpcklbw   m2, m1, m0
-    punpckhbw   m1, m0
-    movu        [r2], m2
-    movu        [r2 + r5], m1
-
-    lea         r0, [r0 + r4 * 2]
-    lea         r1, [r1 + r4 * 4]
-    lea         r2, [r2 + r5 * 2]
-    lea         r3, [r3 + r6 * 2]
-
-    dec         t7b
-    jnz        .loop
-    RET
-%endif          ;HIGH_BIT_DEPTH
-
-
-
-%if HIGH_BIT_DEPTH
-INIT_XMM sse2
-%if ARCH_X86_64 == 1
-cglobal calcRecons16, 5,8,4
-    %define t7b     r7b
-%else
-cglobal calcRecons16, 5,7,4,0-1
-    %define t7b     byte [rsp]
-%endif
-
-    mov         r4d, r4m
-    mov         r5d, r5m
-    mov         r6d, r6m
-    add         r4d, r4d
-    add         r5d, r5d
-    add         r6d, r6d
-
-    pxor        m4, m4
-    mova        m5, [pw_pixel_max]
-    mov         t7b, 16/2
-.loop:
-    movu        m0, [r0]
-    movu        m1, [r0 + 16]
-    movu        m2, [r1]
-    movu        m3, [r1 + 16]
-    paddw       m0, m2
-    paddw       m1, m3
-    CLIPW2      m0, m1, m4, m5
-
-    ; store recipred[]
-    movu        [r3], m0
-    movu        [r3 + 16], m1
-
-    ; store recqt[]
-    movu        [r2], m0
-    movu        [r2 + 16], m1
-
-    movu        m0, [r0 + r4]
-    movu        m1, [r0 + r4 + 16]
-    movu        m2, [r1 + r4]
-    movu        m3, [r1 + r4 + 16]
-    paddw       m0, m2
-    paddw       m1, m3
-    CLIPW2      m0, m1, m4, m5
-
-    ; store recon[] and recipred[]
-    movu        [r3 + r6], m0
-    movu        [r3 + r6 + 16], m1
-
-    ; store recqt[]
-    movu        [r2 + r5], m0
-    movu        [r2 + r5 + 16], m1
-
-    lea         r0, [r0 + r4 * 2]
-    lea         r1, [r1 + r4 * 2]
-    lea         r2, [r2 + r5 * 2]
-    lea         r3, [r3 + r6 * 2]
-
-    dec         t7b
-    jnz        .loop
-    RET
-%else          ;HIGH_BIT_DEPTH
-
-INIT_XMM sse4
-%if ARCH_X86_64 == 1
-cglobal calcRecons16, 5,8,4
-    %define t7b     r7b
-%else
-cglobal calcRecons16, 5,7,4,0-1
-    %define t7b     byte [rsp]
-%endif
-
-    mov         r4d, r4m
-    mov         r5d, r5m
-    mov         r6d, r6m
-    add         r5d, r5d
-
-    pxor        m0, m0
-    mov         t7b, 16
-.loop:
-    movu        m2, [r0]
-    pmovzxbw    m1, m2
-    punpckhbw   m2, m0
-    paddw       m1, [r1]
-    paddw       m2, [r1 + 16]
-    packuswb    m1, m2
-
-    ; store recon[] and recipred[]
-    movu        [r3], m1
-
-    ; store recqt[]
-    pmovzxbw    m2, m1
-    punpckhbw   m1, m0
-    movu        [r2], m2
-    movu        [r2 + 16], m1
-
-    add         r2, r5
-    add         r3, r6
-    add         r0, r4
-    lea         r1, [r1 + r4 * 2]
-
-    dec         t7b
-    jnz        .loop
-    RET
-%endif          ;HIGH_BIT_DEPTH
-
-%if HIGH_BIT_DEPTH
-INIT_XMM sse2
-%if ARCH_X86_64 == 1
-cglobal calcRecons32, 5,8,4
-    %define t7b     r7b
-%else
-cglobal calcRecons32, 5,7,4,0-1
-    %define t7b     byte [rsp]
-%endif
-
-    mov         r4d, r4m
-    mov         r5d, r5m
-    mov         r6d, r6m
-    add         r4d, r4d
-    add         r5d, r5d
-    add         r6d, r6d
-
-    pxor        m4, m4
-    mova        m5, [pw_pixel_max]
-    mov         t7b, 32/2
-.loop:
-
-    movu        m0, [r0]
-    movu        m1, [r0 + 16]
-    movu        m2, [r1]
-    movu        m3, [r1 + 16]
-    paddw       m0, m2
-    paddw       m1, m3
-    CLIPW2      m0, m1, m4, m5
-
-    ; store recipred[]
-    movu        [r3], m0
-    movu        [r3 + 16], m1
-
-    ; store recqt[]
-    movu        [r2], m0
-    movu        [r2 + 16], m1
-
-    movu        m0, [r0 + 32]
-    movu        m1, [r0 + 48]
-    movu        m2, [r1 + 32]
-    movu        m3, [r1 + 48]
-    paddw       m0, m2
-    paddw       m1, m3
-    CLIPW2      m0, m1, m4, m5
-
-    ; store recon[] and recipred[]
-    movu        [r3 + 32], m0
-    movu        [r3 + 48], m1
-
-    ; store recqt[]
-    movu        [r2 + 32], m0
-    movu        [r2 + 48], m1
-    add         r2, r5
-
-    movu        m0, [r0 + r4]
-    movu        m1, [r0 + r4 + 16]
-    movu        m2, [r1 + r4]
-    movu        m3, [r1 + r4 + 16]
-    paddw       m0, m2
-    paddw       m1, m3
-    CLIPW2      m0, m1, m4, m5
-
-    ; store recon[] and recipred[]
-    movu        [r3 + r6], m0
-    movu        [r3 + r6 + 16], m1
-
-    ; store recqt[]
-    movu        [r2], m0
-    movu        [r2 + 16], m1
-
-    movu        m0, [r0 + r4 + 32]
-    movu        m1, [r0 + r4 + 48]
-    movu        m2, [r1 + r4 + 32]
-    movu        m3, [r1 + r4 + 48]
-    paddw       m0, m2
-    paddw       m1, m3
-    CLIPW2      m0, m1, m4, m5
-
-    ; store recon[] and recipred[]
-    movu        [r3 + r6 + 32], m0
-    movu        [r3 + r6 + 48], m1
-    lea         r3, [r3 + r6 * 2]
-
-    ; store recqt[]
-    movu        [r2 + 32], m0
-    movu        [r2 + 48], m1
-    add         r2, r5
-
-    lea         r0, [r0 + r4 * 2]
-    lea         r1, [r1 + r4 * 2]
-
-    dec         t7b
-    jnz        .loop
-    RET
-%else          ;HIGH_BIT_DEPTH
-INIT_XMM sse4
-%if ARCH_X86_64 == 1
-cglobal calcRecons32, 5,8,4
-    %define t7b     r7b
-%else
-cglobal calcRecons32, 5,7,4,0-1
-    %define t7b     byte [rsp]
-%endif
-
-    mov         r4d, r4m
-    mov         r5d, r5m
-    mov         r6d, r6m
-    add         r5d, r5d
-
-    pxor        m0, m0
-    mov         t7b, 32
-.loop:
-    movu        m2, [r0]
-    movu        m4, [r0 + 16]
-    pmovzxbw    m1, m2
-    punpckhbw   m2, m0
-    pmovzxbw    m3, m4
-    punpckhbw   m4, m0
-
-    paddw       m1, [r1 + 0 * 16]
-    paddw       m2, [r1 + 1 * 16]
-    packuswb    m1, m2
-
-    paddw       m3, [r1 + 2 * 16]
-    paddw       m4, [r1 + 3 * 16]
-    packuswb    m3, m4
-
-    ; store recon[] and recipred[]
-    movu        [r3], m1
-    movu        [r3 + 16], m3
-
-    ; store recqt[]
-    pmovzxbw    m2, m1
-    punpckhbw   m1, m0
-    movu        [r2 + 0 * 16], m2
-    movu        [r2 + 1 * 16], m1
-    pmovzxbw    m4, m3
-    punpckhbw   m3, m0
-    movu        [r2 + 2 * 16], m4
-    movu        [r2 + 3 * 16], m3
-
-    add         r2, r5
-    add         r3, r6
-    add         r0, r4
-    lea         r1, [r1 + r4 * 2]
-
-    dec         t7b
-    jnz        .loop
-    RET
-%endif          ;HIGH_BIT_DEPTH
-
 
 ;-----------------------------------------------------------------------------
 ; void getResidual(pixel *fenc, pixel *pred, int16_t *residual, intptr_t stride)



More information about the x265-devel mailing list