Re: [x265] [PATCH] asm: added 16bpp support for dct[4x4, 8x8], idct4x4, dst4x4 and idst4x4 primitives
Has this been fixed? Murugan - have you reproduced/fixed this issue? On Sat, Feb 15, 2014 at 12:13 AM, Steve Borho st...@borho.org wrote: On Fri, Feb 14, 2014 at 12:39 PM, Steve Borho st...@borho.org wrote: On Fri, Feb 14, 2014 at 4:41 AM, dnyanesh...@multicorewareinc.comwrote: # HG changeset patch # User Dnyaneshwar G dnyanesh...@multicorewareinc.com # Date 1392374441 -19800 # Fri Feb 14 16:10:41 2014 +0530 # Node ID 831536babdc08f1553a10754bf2a4f4af6aa1695 # Parent ed310b17ff6681f191c85341cf6efe7a50770143 asm: added 16bpp support for dct[4x4, 8x8], idct4x4, dst4x4 and idst4x4 primitives with this patch applied, if I fixup the elif problems, I get occasional dequant test failures on 8bpp mac. steve@zeppelin ./test/TestBench Using random seed 52FE6216 8bpp Testing primitives: SSE2 Testing primitives: SSE3 Testing primitives: SSSE3 Testing primitives: SSE4 dequant: Failed! Sorry, the dequant test failures appear to be caused by Murugan's testbench changes. I'm dequeuing those as well until we understand why the test is failing. -- Steve Borho ___ x265-devel mailing list x265-devel@videolan.org https://mailman.videolan.org/listinfo/x265-devel ___ x265-devel mailing list x265-devel@videolan.org https://mailman.videolan.org/listinfo/x265-devel
Re: [x265] [PATCH] asm: added 16bpp support for dct[4x4, 8x8], idct4x4, dst4x4 and idst4x4 primitives
I have also checked on Mac machine, I am not getting dequant failure. I will send patch again, as this will not apply on latest tip. --- Dnyaneshwar G On Wed, Feb 19, 2014 at 9:57 AM, Murugan Vairavel muru...@multicorewareinc.com wrote: Hi Deepthi, I tried to reproduce this , but it is working fine. On Wed, Feb 19, 2014 at 7:21 AM, Deepthi Nandakumar deep...@multicorewareinc.com wrote: Has this been fixed? Murugan - have you reproduced/fixed this issue? On Sat, Feb 15, 2014 at 12:13 AM, Steve Borho st...@borho.org wrote: On Fri, Feb 14, 2014 at 12:39 PM, Steve Borho st...@borho.org wrote: On Fri, Feb 14, 2014 at 4:41 AM, dnyanesh...@multicorewareinc.comwrote: # HG changeset patch # User Dnyaneshwar G dnyanesh...@multicorewareinc.com # Date 1392374441 -19800 # Fri Feb 14 16:10:41 2014 +0530 # Node ID 831536babdc08f1553a10754bf2a4f4af6aa1695 # Parent ed310b17ff6681f191c85341cf6efe7a50770143 asm: added 16bpp support for dct[4x4, 8x8], idct4x4, dst4x4 and idst4x4 primitives with this patch applied, if I fixup the elif problems, I get occasional dequant test failures on 8bpp mac. steve@zeppelin ./test/TestBench Using random seed 52FE6216 8bpp Testing primitives: SSE2 Testing primitives: SSE3 Testing primitives: SSSE3 Testing primitives: SSE4 dequant: Failed! Sorry, the dequant test failures appear to be caused by Murugan's testbench changes. I'm dequeuing those as well until we understand why the test is failing. -- Steve Borho ___ x265-devel mailing list x265-devel@videolan.org https://mailman.videolan.org/listinfo/x265-devel ___ x265-devel mailing list x265-devel@videolan.org https://mailman.videolan.org/listinfo/x265-devel -- With Regards, Murugan. V +919659287478 ___ x265-devel mailing list x265-devel@videolan.org https://mailman.videolan.org/listinfo/x265-devel ___ x265-devel mailing list x265-devel@videolan.org https://mailman.videolan.org/listinfo/x265-devel
Re: [x265] [PATCH] asm: added 16bpp support for dct[4x4, 8x8], idct4x4, dst4x4 and idst4x4 primitives
On Wed, Feb 19, 2014 at 1:04 AM, dnyanesh...@multicorewareinc.com wrote:
# HG changeset patch
# User Dnyaneshwar G dnyanesh...@multicorewareinc.com
# Date 1392792673 -19800
# Wed Feb 19 12:21:13 2014 +0530
# Node ID 6150985c3d535f0ea7a1dc0b8f3c69e65e30d25b
# Parent 1a0d5b456b19e8f187290c662425080cfc870492
asm: added 16bpp support for dct[4x4, 8x8], idct4x4, dst4x4 and idst4x4
primitives
pushed
diff -r 1a0d5b456b19 -r 6150985c3d53 source/common/x86/asm-primitives.cpp
--- a/source/common/x86/asm-primitives.cpp Tue Feb 18 14:46:51 2014
-0600
+++ b/source/common/x86/asm-primitives.cpp Wed Feb 19 12:21:13 2014
+0530
@@ -808,6 +808,10 @@
p.calcrecon[BLOCK_8x8] = x265_calcRecons8_sse2;
p.calcrecon[BLOCK_16x16] = x265_calcRecons16_sse2;
p.calcrecon[BLOCK_32x32] = x265_calcRecons32_sse2;
+
+p.dct[DCT_4x4] = x265_dct4_sse2;
+p.idct[IDCT_4x4] = x265_idct4_sse2;
+p.idct[IDST_4x4] = x265_idst4_sse2;
}
if (cpuMask X265_CPU_SSSE3)
{
@@ -822,10 +826,12 @@
SETUP_INTRA_ANG32(2, 2, ssse3);
SETUP_INTRA_ANG32(34, 2, ssse3);
+
+p.dct[DST_4x4] = x265_dst4_ssse3;
}
if (cpuMask X265_CPU_SSE4)
{
-
+p.dct[DCT_8x8] = x265_dct8_sse4;
p.quant = x265_quant_sse4;
p.dequant_normal = x265_dequant_normal_sse4;
p.cvt16to32_shl = x265_cvt16to32_shl_sse4;
diff -r 1a0d5b456b19 -r 6150985c3d53 source/common/x86/const-a.asm
--- a/source/common/x86/const-a.asm Tue Feb 18 14:46:51 2014 -0600
+++ b/source/common/x86/const-a.asm Wed Feb 19 12:21:13 2014 +0530
@@ -69,9 +69,10 @@
const pw_ppmmppmm, dw 1,1,-1,-1,1,1,-1,-1
const pw_pmpmpmpm, dw 1,-1,1,-1,1,-1,1,-1
const pw_pmmp, dw 1,-1,-1,1,0,0,0,0
-
const pd_1,times 4 dd 1
const pd_2,times 4 dd 2
+const pd_4,times 4 dd 4
+const pd_8,times 4 dd 8
const pd_16, times 4 dd 16
const pd_32, times 4 dd 32
const pd_64, times 4 dd 64
diff -r 1a0d5b456b19 -r 6150985c3d53 source/common/x86/dct8.asm
--- a/source/common/x86/dct8.asmTue Feb 18 14:46:51 2014 -0600
+++ b/source/common/x86/dct8.asmWed Feb 19 12:21:13 2014 +0530
@@ -64,9 +64,12 @@
pb_unpackhlw1: db 0,1,8,9,2,3,10,11,4,5,12,13,6,7,14,15
SECTION .text
-
cextern pd_1
cextern pd_2
+cextern pd_4
+cextern pd_8
+cextern pd_16
+cextern pd_32
cextern pd_64
cextern pd_128
cextern pd_256
@@ -79,16 +82,21 @@
;--
INIT_XMM sse2
cglobal dct4, 3, 4, 8
-
+%if BIT_DEPTH == 10
+ %define DCT_SHIFT 3
+ mova m7, [pd_4]
+%elif BIT_DEPTH == 8
+ %define DCT_SHIFT 1
+ mova m7, [pd_1]
+%else
+ %error Unsupported BIT_DEPTH!
+%endif
add r2d, r2d
lea r3, [tab_dct4]
movam4, [r3 + 0 * 16]
movam5, [r3 + 1 * 16]
movam6, [r3 + 2 * 16]
-
-movam7, [pd_1]
-
movhm0, [r0 + 0 * r2]
movhm1, [r0 + 1 * r2]
punpcklqdq m0, m1
@@ -107,27 +115,21 @@
paddw m1, m2, m0
psubw m2, m0
-
pmaddwd m0, m1, m4
paddd m0, m7
-psrad m0, 1
-
+psrad m0, DCT_SHIFT
pmaddwd m3, m2, m5
paddd m3, m7
-psrad m3, 1
-
+psrad m3, DCT_SHIFT
packssdwm0, m3
pshufd m0, m0, 0xD8
pshufhw m0, m0, 0xB1
-
pmaddwd m1, m6
paddd m1, m7
-psrad m1, 1
-
+psrad m1, DCT_SHIFT
pmaddwd m2, [r3 + 3 * 16]
paddd m2, m7
-psrad m2, 1
-
+psrad m2, DCT_SHIFT
packssdwm1, m2
pshufd m1, m1, 0xD8
pshufhw m1, m1, 0xB1
@@ -179,7 +181,7 @@
%define IDCT4_OFFSET [pd_512]
%define IDCT4_SHIFT 10
%else
- %error Unsupport BIT_DEPTH!
+ %error Unsupported BIT_DEPTH!
%endif
add r2d, r2d
lea r3, [tab_dct4]
@@ -268,67 +270,60 @@
INIT_XMM ssse3
%if ARCH_X86_64
cglobal dst4, 3, 4, 8+2
+ %define coef2 m8
+ %define coef3 m9
%else ; ARCH_X86_64 = 0
cglobal dst4, 3, 4, 8
+ %define coef2 [r3 + 2 * 16]
+ %define coef3 [r3 + 3 * 16]
%endif ; ARCH_X86_64
+%define coef0 m6
+%define coef1 m7
-%define coef0 m6
-%define coef1 m7
-%if ARCH_X86_64
-%define coef2 m8
-%define coef3 m9
-%else
-%define coef2 [r3 + 2 * 16]
-%define coef3 [r3 + 3 * 16]
+%if BIT_DEPTH == 8
+ %define DST_SHIFT 1
+ mova m5, [pd_1]
+%elif BIT_DEPTH == 10
+ %define DST_SHIFT 3
+ mova m5, [pd_4]
%endif
-
add r2d, r2d
lea r3, [tab_dst4]
-
-movam5, [pd_1]
-
movacoef0, [r3 + 0 * 16]
movacoef1, [r3 + 1 * 16]
%if ARCH_X86_64
Re: [x265] [PATCH] asm: added 16bpp support for dct[4x4, 8x8], idct4x4, dst4x4 and idst4x4 primitives
right At 2014-02-14 18:41:34,dnyanesh...@multicorewareinc.com wrote: # HG changeset patch # User Dnyaneshwar G dnyanesh...@multicorewareinc.com # Date 1392374441 -19800 # Fri Feb 14 16:10:41 2014 +0530 # Node ID 831536babdc08f1553a10754bf2a4f4af6aa1695 # Parent ed310b17ff6681f191c85341cf6efe7a50770143 asm: added 16bpp support for dct[4x4, 8x8], idct4x4, dst4x4 and idst4x4 primitives ___ x265-devel mailing list x265-devel@videolan.org https://mailman.videolan.org/listinfo/x265-devel
Re: [x265] [PATCH] asm: added 16bpp support for dct[4x4, 8x8], idct4x4, dst4x4 and idst4x4 primitives
On Fri, Feb 14, 2014 at 4:41 AM, dnyanesh...@multicorewareinc.com wrote:
# HG changeset patch
# User Dnyaneshwar G dnyanesh...@multicorewareinc.com
# Date 1392374441 -19800
# Fri Feb 14 16:10:41 2014 +0530
# Node ID 831536babdc08f1553a10754bf2a4f4af6aa1695
# Parent ed310b17ff6681f191c85341cf6efe7a50770143
asm: added 16bpp support for dct[4x4, 8x8], idct4x4, dst4x4 and idst4x4
primitives
with this patch applied, if I fixup the elif problems, I get occasional
dequant test failures on 8bpp mac.
steve@zeppelin ./test/TestBench
Using random seed 52FE6216 8bpp
Testing primitives: SSE2
Testing primitives: SSE3
Testing primitives: SSSE3
Testing primitives: SSE4
dequant: Failed!
diff -r ed310b17ff66 -r 831536babdc0 source/common/x86/asm-primitives.cpp
--- a/source/common/x86/asm-primitives.cpp Fri Feb 14 02:30:52 2014
-0600
+++ b/source/common/x86/asm-primitives.cpp Fri Feb 14 16:10:41 2014
+0530
@@ -726,6 +726,10 @@
p.calcrecon[BLOCK_8x8] = x265_calcRecons8_sse2;
p.calcrecon[BLOCK_16x16] = x265_calcRecons16_sse2;
p.calcrecon[BLOCK_32x32] = x265_calcRecons32_sse2;
+
+p.dct[DCT_4x4] = x265_dct4_sse2;
+p.idct[IDCT_4x4] = x265_idct4_sse2;
+p.idct[IDST_4x4] = x265_idst4_sse2;
}
if (cpuMask X265_CPU_SSSE3)
{
@@ -740,9 +744,12 @@
SETUP_INTRA_ANG32(2, 2, ssse3);
SETUP_INTRA_ANG32(34, 2, ssse3);
+
+p.dct[DST_4x4] = x265_dst4_ssse3;
}
if (cpuMask X265_CPU_SSE4)
{
+p.dct[DCT_8x8] = x265_dct8_sse4;
p.cvt16to32_shl = x265_cvt16to32_shl_sse4;
p.intra_pred[BLOCK_4x4][0] = x265_intra_pred_planar4_sse4;
diff -r ed310b17ff66 -r 831536babdc0 source/common/x86/const-a.asm
--- a/source/common/x86/const-a.asm Fri Feb 14 02:30:52 2014 -0600
+++ b/source/common/x86/const-a.asm Fri Feb 14 16:10:41 2014 +0530
@@ -72,6 +72,8 @@
const pd_1,times 4 dd 1
const pd_2,times 4 dd 2
+const pd_4,times 4 dd 4
+const pd_8,times 4 dd 8
const pd_16, times 4 dd 16
const pd_32, times 4 dd 32
const pd_64, times 4 dd 64
diff -r ed310b17ff66 -r 831536babdc0 source/common/x86/dct8.asm
--- a/source/common/x86/dct8.asmFri Feb 14 02:30:52 2014 -0600
+++ b/source/common/x86/dct8.asmFri Feb 14 16:10:41 2014 +0530
@@ -67,6 +67,10 @@
cextern pd_1
cextern pd_2
+cextern pd_4
+cextern pd_8
+cextern pd_16
+cextern pd_32
cextern pd_64
cextern pd_128
cextern pd_256
@@ -79,6 +83,15 @@
;--
INIT_XMM sse2
cglobal dct4, 3, 4, 8
+%if BIT_DEPTH == 10
+ %define DCT_SHIFT 3
+ mova m7, [pd_4]
+%else if BIT_DEPTH == 8
%elif BIT_DEPTH == 8
+ %define DCT_SHIFT 1
+ mova m7, [pd_1]
+%else
+ %error Unsupported BIT_DEPTH!
+%endif
add r2d, r2d
lea r3, [tab_dct4]
@@ -87,8 +100,6 @@
movam5, [r3 + 1 * 16]
movam6, [r3 + 2 * 16]
-movam7, [pd_1]
-
movhm0, [r0 + 0 * r2]
movhm1, [r0 + 1 * r2]
punpcklqdq m0, m1
@@ -110,11 +121,11 @@
pmaddwd m0, m1, m4
paddd m0, m7
-psrad m0, 1
+psrad m0, DCT_SHIFT
pmaddwd m3, m2, m5
paddd m3, m7
-psrad m3, 1
+psrad m3, DCT_SHIFT
packssdwm0, m3
pshufd m0, m0, 0xD8
@@ -122,11 +133,11 @@
pmaddwd m1, m6
paddd m1, m7
-psrad m1, 1
+psrad m1, DCT_SHIFT
pmaddwd m2, [r3 + 3 * 16]
paddd m2, m7
-psrad m2, 1
+psrad m2, DCT_SHIFT
packssdwm1, m2
pshufd m1, m1, 0xD8
@@ -179,7 +190,7 @@
%define IDCT4_OFFSET [pd_512]
%define IDCT4_SHIFT 10
%else
- %error Unsupport BIT_DEPTH!
+ %error Unsupported BIT_DEPTH!
%endif
add r2d, r2d
lea r3, [tab_dct4]
@@ -268,25 +279,28 @@
INIT_XMM ssse3
%if ARCH_X86_64
cglobal dst4, 3, 4, 8+2
+ %define coef2 m8
+ %define coef3 m9
%else ; ARCH_X86_64 = 0
cglobal dst4, 3, 4, 8
+ %define coef2 [r3 + 2 * 16]
+ %define coef3 [r3 + 3 * 16]
%endif ; ARCH_X86_64
-%define coef0 m6
-%define coef1 m7
-%if ARCH_X86_64
-%define coef2 m8
-%define coef3 m9
-%else
-%define coef2 [r3 + 2 * 16]
-%define coef3 [r3 + 3 * 16]
-%endif
+%define coef0 m6
+%define coef1 m7
+
+%if BIT_DEPTH == 8
+ %define DST_SHIFT 1
+ mova m5, [pd_1]
+%else if BIT_DEPTH == 10
%elif BIT_DEPTH == 10, there's one more of these below
+ %define DST_SHIFT 3
+ mova m5, [pd_4]
+%endif
add r2d, r2d
lea r3, [tab_dst4]
-movam5, [pd_1]
-
movacoef0, [r3 + 0 * 16]
movacoef1, [r3 + 1 * 16]
Re: [x265] [PATCH] asm: added 16bpp support for dct[4x4, 8x8], idct4x4, dst4x4 and idst4x4 primitives
On Fri, Feb 14, 2014 at 12:39 PM, Steve Borho st...@borho.org wrote: On Fri, Feb 14, 2014 at 4:41 AM, dnyanesh...@multicorewareinc.com wrote: # HG changeset patch # User Dnyaneshwar G dnyanesh...@multicorewareinc.com # Date 1392374441 -19800 # Fri Feb 14 16:10:41 2014 +0530 # Node ID 831536babdc08f1553a10754bf2a4f4af6aa1695 # Parent ed310b17ff6681f191c85341cf6efe7a50770143 asm: added 16bpp support for dct[4x4, 8x8], idct4x4, dst4x4 and idst4x4 primitives with this patch applied, if I fixup the elif problems, I get occasional dequant test failures on 8bpp mac. steve@zeppelin ./test/TestBench Using random seed 52FE6216 8bpp Testing primitives: SSE2 Testing primitives: SSE3 Testing primitives: SSSE3 Testing primitives: SSE4 dequant: Failed! Sorry, the dequant test failures appear to be caused by Murugan's testbench changes. I'm dequeuing those as well until we understand why the test is failing. -- Steve Borho ___ x265-devel mailing list x265-devel@videolan.org https://mailman.videolan.org/listinfo/x265-devel
