[x265] [PATCH] asm: removed duplicate and redundant constants
dnyaneshwar at multicorewareinc.com
dnyaneshwar at multicorewareinc.com
Tue May 19 14:39:34 CEST 2015
# HG changeset patch
# User Dnyaneshwar G <dnyaneshwar at multicorewareinc.com>
# Date 1432037856 -19800
# Tue May 19 17:47:36 2015 +0530
# Node ID e6fc4b6f16b32debf4a252b47ad6fc9c82364188
# Parent b44cdf8dc08c77e84b8707992cd0006bbf23d864
asm: removed duplicate and redundant constants
diff -r b44cdf8dc08c -r e6fc4b6f16b3 source/common/x86/const-a.asm
--- a/source/common/x86/const-a.asm Tue May 19 15:18:08 2015 +0530
+++ b/source/common/x86/const-a.asm Tue May 19 17:47:36 2015 +0530
@@ -92,7 +92,7 @@
const pw_0_15, times 2 dw 0, 1, 2, 3, 4, 5, 6, 7
const pw_ppppmmmm, times 1 dw 1, 1, 1, 1, -1, -1, -1, -1
const pw_ppmmppmm, times 1 dw 1, 1, -1, -1, 1, 1, -1, -1
-const pw_pmpmpmpm, times 1 dw 1, -1, 1, -1, 1, -1, 1, -1
+const pw_pmpmpmpm, times 16 dw 1, -1, 1, -1, 1, -1, 1, -1
const pw_pmmpzzzz, times 1 dw 1, -1, -1, 1, 0, 0, 0, 0
const multi_2Row, times 1 dw 1, 2, 3, 4, 1, 2, 3, 4
const multiH, times 1 dw 9, 10, 11, 12, 13, 14, 15, 16
@@ -102,7 +102,9 @@
const pw_planar16_mul, times 1 dw 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0
const pw_planar32_mul, times 1 dw 31, 30, 29, 28, 27, 26, 25, 24, 23, 22, 21, 20, 19, 18, 17, 16
const pw_FFFFFFFFFFFFFFF0, dw 0x00
- times 7 dw 0xff
+ times 7 dw 0xff
+const hmul_16p, times 16 db 1
+ times 8 db 1, -1
;; 32-bit constants
@@ -125,7 +127,6 @@
const pd_n32768, times 4 dd 0xffff8000
const trans8_shuf, times 1 dd 0, 4, 1, 5, 2, 6, 3, 7
-const deinterleave_shufd, times 1 dd 0, 4, 1, 5, 2, 6, 3, 7
const popcnt_table
%assign x 0
diff -r b44cdf8dc08c -r e6fc4b6f16b3 source/common/x86/mc-a.asm
--- a/source/common/x86/mc-a.asm Tue May 19 15:18:08 2015 +0530
+++ b/source/common/x86/mc-a.asm Tue May 19 17:47:36 2015 +0530
@@ -58,7 +58,6 @@
cextern pw_pixel_max
cextern sw_64
cextern pd_32
-cextern deinterleave_shufd
;====================================================================================================================
;void addAvg (int16_t* src0, int16_t* src1, pixel* dst, intptr_t src0Stride, intptr_t src1Stride, intptr_t dstStride)
diff -r b44cdf8dc08c -r e6fc4b6f16b3 source/common/x86/pixel-a.asm
--- a/source/common/x86/pixel-a.asm Tue May 19 15:18:08 2015 +0530
+++ b/source/common/x86/pixel-a.asm Tue May 19 17:47:36 2015 +0530
@@ -32,8 +32,6 @@
%include "x86util.asm"
SECTION_RODATA 32
-hmul_16p: times 16 db 1
- times 8 db 1, -1
hmul_8p: times 8 db 1
times 4 db 1, -1
times 8 db 1
@@ -45,8 +43,7 @@
times 2 dw 1, -1
times 4 dw 1
times 2 dw 1, -1
-ALIGN 32
-hmul_w: times 2 dw 1, -1, 1, -1, 1, -1, 1, -1
+
ALIGN 32
transd_shuf1: SHUFFLE_MASK_W 0, 8, 2, 10, 4, 12, 6, 14
transd_shuf2: SHUFFLE_MASK_W 1, 9, 3, 11, 5, 13, 7, 15
@@ -54,8 +51,6 @@
sw_f0: dq 0xfff0, 0
pd_f0: times 4 dd 0xffff0000
-pw_76543210: dw 0, 1, 2, 3, 4, 5, 6, 7
-
SECTION .text
cextern pb_0
@@ -72,6 +67,7 @@
cextern pd_1
cextern popcnt_table
cextern pd_2
+cextern hmul_16p
;=============================================================================
; SATD
@@ -9070,7 +9066,7 @@
INIT_XMM sse4
cglobal psyCost_ss_8x8, 4, 6, 15
- mova m13, [hmul_w]
+ mova m13, [pw_pmpmpmpm]
mova m14, [pw_1]
add r1, r1
add r3, r3
@@ -10220,7 +10216,7 @@
INIT_XMM sse4
cglobal psyCost_ss_16x16, 4, 9, 16
- mova m13, [hmul_w]
+ mova m13, [pw_pmpmpmpm]
mova m14, [pw_1]
add r1, r1
add r3, r3
@@ -10248,7 +10244,7 @@
INIT_XMM sse4
cglobal psyCost_ss_32x32, 4, 9, 16
- mova m13, [hmul_w]
+ mova m13, [pw_pmpmpmpm]
mova m14, [pw_1]
add r1, r1
add r3, r3
@@ -10276,7 +10272,7 @@
INIT_XMM sse4
cglobal psyCost_ss_64x64, 4, 9, 16
- mova m13, [hmul_w]
+ mova m13, [pw_pmpmpmpm]
mova m14, [pw_1]
add r1, r1
add r3, r3
@@ -10717,7 +10713,7 @@
and rsp, ~63
mova m12, [pw_1]
- mova m13, [hmul_w]
+ mova m13, [pw_pmpmpmpm]
add r1, r1
add r3, r3
@@ -10737,7 +10733,7 @@
and rsp, ~63
mova m12, [pw_1]
- mova m13, [hmul_w]
+ mova m13, [pw_pmpmpmpm]
add r1, r1
add r3, r3
pxor m14, m14
@@ -10771,7 +10767,7 @@
and rsp, ~63
mova m12, [pw_1]
- mova m13, [hmul_w]
+ mova m13, [pw_pmpmpmpm]
add r1, r1
add r3, r3
pxor m14, m14
@@ -10805,7 +10801,7 @@
and rsp, ~63
mova m12, [pw_1]
- mova m13, [hmul_w]
+ mova m13, [pw_pmpmpmpm]
add r1, r1
add r3, r3
pxor m14, m14
diff -r b44cdf8dc08c -r e6fc4b6f16b3 source/common/x86/pixel-util8.asm
--- a/source/common/x86/pixel-util8.asm Tue May 19 15:18:08 2015 +0530
+++ b/source/common/x86/pixel-util8.asm Tue May 19 17:47:36 2015 +0530
@@ -45,13 +45,9 @@
times 16 db 0
deinterleave_shuf: times 2 db 0, 2, 4, 6, 8, 10, 12, 14, 1, 3, 5, 7, 9, 11, 13, 15
deinterleave_word_shuf: times 2 db 0, 1, 4, 5, 8, 9, 12, 13, 2, 3, 6, 7, 10, 11, 14, 15
-hmul_16p: times 16 db 1
- times 8 db 1, -1
hmulw_16p: times 8 dw 1
times 4 dw 1, -1
-trans8_shuf: dd 0, 4, 1, 5, 2, 6, 3, 7
-
SECTION .text
cextern pw_1
@@ -72,6 +68,8 @@
cextern pb_16
cextern pb_32
cextern pb_64
+cextern hmul_16p
+cextern trans8_shuf
;-----------------------------------------------------------------------------
; void getResidual(pixel *fenc, pixel *pred, int16_t *residual, intptr_t stride)
More information about the x265-devel
mailing list