summaryrefslogtreecommitdiff
path: root/vpx_dsp/vpx_dsp.mk
diff options
context:
space:
mode:
authorLuca Barbato <lu_zero@gentoo.org>2018-06-06 21:10:18 +0000
committerLuca Barbato <lu_zero@gentoo.org>2018-06-08 05:26:05 +0200
commitd468fd90e05ba7f5173d849c63f6a50115c9769b (patch)
treeb60507eb7ba4aa901f0c116ca4785f8e4184b08b /vpx_dsp/vpx_dsp.mk
parent034f94c127b4d608200d94889c52e7e42b2f62e4 (diff)
downloadlibvpx-d468fd90e05ba7f5173d849c63f6a50115c9769b.tar
libvpx-d468fd90e05ba7f5173d849c63f6a50115c9769b.tar.gz
libvpx-d468fd90e05ba7f5173d849c63f6a50115c9769b.tar.bz2
libvpx-d468fd90e05ba7f5173d849c63f6a50115c9769b.zip
Implement subtract_block for VSX
~2x speedup or better. [ RUN ] C/VP9SubtractBlockTest.Speed/0 [ BENCH ] 4x4 365.1 ms ( ±2.2 ms ) [ BENCH ] 8x4 258.5 ms ( ±0.3 ms ) [ BENCH ] 4x8 202.7 ms ( ±0.2 ms ) [ BENCH ] 8x8 162.2 ms ( ±0.5 ms ) [ BENCH ] 16x8 138.8 ms ( ±0.3 ms ) [ BENCH ] 8x16 121.5 ms ( ±0.4 ms ) [ BENCH ] 16x16 110.2 ms ( ±0.5 ms ) [ BENCH ] 32x16 104.8 ms ( ±0.1 ms ) [ BENCH ] 16x32 32.7 ms ( ±0.1 ms ) [ BENCH ] 32x32 30.0 ms ( ±0.0 ms ) [ BENCH ] 64x32 28.7 ms ( ±0.0 ms ) [ BENCH ] 32x64 20.1 ms ( ±0.0 ms ) [ BENCH ] 64x64 19.3 ms ( ±0.0 ms ) [ RUN ] VSX/VP9SubtractBlockTest.Speed/0 [ BENCH ] 4x4 155.3 ms ( ±0.9 ms ) [ BENCH ] 8x4 99.3 ms ( ±0.4 ms ) [ BENCH ] 4x8 77.2 ms ( ±0.1 ms ) [ BENCH ] 8x8 45.7 ms ( ±0.0 ms ) [ BENCH ] 16x8 34.1 ms ( ±0.0 ms ) [ BENCH ] 8x16 29.5 ms ( ±0.0 ms ) [ BENCH ] 16x16 19.9 ms ( ±0.0 ms ) [ BENCH ] 32x16 15.1 ms ( ±0.0 ms ) [ BENCH ] 16x32 16.7 ms ( ±0.0 ms ) [ BENCH ] 32x32 14.1 ms ( ±0.0 ms ) [ BENCH ] 64x32 12.6 ms ( ±0.0 ms ) [ BENCH ] 32x64 12.0 ms ( ±0.0 ms ) [ BENCH ] 64x64 11.2 ms ( ±0.0 ms ) Change-Id: I89ce12b6475871dc9e8fde84d0b6fe5c420c28c7
Diffstat (limited to 'vpx_dsp/vpx_dsp.mk')
-rw-r--r--vpx_dsp/vpx_dsp.mk1
1 files changed, 1 insertions, 0 deletions
diff --git a/vpx_dsp/vpx_dsp.mk b/vpx_dsp/vpx_dsp.mk
index 573d6fef1..c12dab736 100644
--- a/vpx_dsp/vpx_dsp.mk
+++ b/vpx_dsp/vpx_dsp.mk
@@ -342,6 +342,7 @@ DSP_SRCS-$(HAVE_SSE2) += x86/sad_sse2.asm
DSP_SRCS-$(HAVE_SSE2) += x86/subtract_sse2.asm
DSP_SRCS-$(HAVE_VSX) += ppc/sad_vsx.c
+DSP_SRCS-$(HAVE_VSX) += ppc/subtract_vsx.c
ifeq ($(CONFIG_VP9_HIGHBITDEPTH),yes)
DSP_SRCS-$(HAVE_SSE2) += x86/highbd_sad4d_sse2.asm