[x264-devel] Patch - Altivec Quant 4x4x4

[Philipp Sibler]

Hi x264,

this patch introduces an Altivec version of the 4x4x4 quantization step. 
On the current master branch the 4x4x4 quantization on PowerPC Altivec 
machines defaults to the plain scalar C routine.

Patch was tested on a PowerMac G4 and generates an encoding speedup of 
about 14 percent there.

Cheers,
Philipp
-------------- next part --------------
>From 951350060c745c1c33bf814f87621e2763143a50 Mon Sep 17 00:00:00 2001
From: Philipp Sibler <philipp.sibler at gmail.com>
Date: Sun, 29 Sep 2013 17:48:36 +0200
Subject: [PATCH] Introduced Altivec version of quant 4x4x4

---
 common/ppc/quant.c |   17 +++++++++++++++++
 common/ppc/quant.h |    1 +
 common/quant.c     |    1 +
 3 files changed, 19 insertions(+), 0 deletions(-)

diff --git a/common/ppc/quant.c b/common/ppc/quant.c
index f11938a..0fff340 100644
--- a/common/ppc/quant.c
+++ b/common/ppc/quant.c
@@ -90,6 +90,23 @@ int x264_quant_4x4_altivec( int16_t dct[16], uint16_t mf[16], uint16_t bias[16]
     return vec_any_ne(nz, zero_s16v);
 }
 
+int x264_quant_4x4x4_altivec( int16_t dct[4][16], uint16_t mf[16], uint16_t bias[16] )
+{
+    int nza = 0;
+    int nz = 0;
+
+	nz = x264_quant_4x4_altivec(dct[0], mf, bias);
+	nza |= (!!nz);
+	nz = x264_quant_4x4_altivec(dct[1], mf, bias);
+	nza |= (!!nz)<<1;
+	nz = x264_quant_4x4_altivec(dct[2], mf, bias);
+	nza |= (!!nz)<<2;
+	nz = x264_quant_4x4_altivec(dct[3], mf, bias);
+	nza |= (!!nz)<<3;
+	
+    return nza;
+}
+
 // DC quant of a whole 4x4 block, unrolled 2x and "pre-scheduled"
 #define QUANT_16_U_DC( idx0, idx1 )                                 \
 {                                                                   \
diff --git a/common/ppc/quant.h b/common/ppc/quant.h
index 1f789c3..2f22d91 100644
--- a/common/ppc/quant.h
+++ b/common/ppc/quant.h
@@ -27,6 +27,7 @@
 #define X264_PPC_QUANT_H
 
 int x264_quant_4x4_altivec( int16_t dct[16], uint16_t mf[16], uint16_t bias[16] );
+int x264_quant_4x4x4_altivec( int16_t dct[4][16], int16_t mf[16], int16_t bias[16] );
 int x264_quant_8x8_altivec( int16_t dct[64], uint16_t mf[64], uint16_t bias[64] );
 
 int x264_quant_4x4_dc_altivec( int16_t dct[16], int mf, int bias );
diff --git a/common/quant.c b/common/quant.c
index 7aa851e..8101535 100644
--- a/common/quant.c
+++ b/common/quant.c
@@ -717,6 +717,7 @@ void x264_quant_init( x264_t *h, int cpu, x264_quant_function_t *pf )
         pf->quant_4x4_dc = x264_quant_4x4_dc_altivec;
         pf->quant_4x4 = x264_quant_4x4_altivec;
         pf->quant_8x8 = x264_quant_8x8_altivec;
+		pf->quant_4x4x4 = x264_quant_4x4x4_altivec;
 
         pf->dequant_4x4 = x264_dequant_4x4_altivec;
         pf->dequant_8x8 = x264_dequant_8x8_altivec;
-- 
1.7.7.4