From 601f3a886e4f643783fd5fe824dcb9b79e251111 Mon Sep 17 00:00:00 2001
From: Yaowu Xu <yaowu@google.com>
Date: Tue, 16 Sep 2014 10:46:18 -0700
Subject: [PATCH] Fix a performance regression
This commit adds back sse2 or ssse3 optimized versio of a couple of
functions, fixes a ~10% performance regression.
Change-Id: I049786906e5a641224dced63c6492aec9d86d183
---
vp9/common/vp9_rtcd_defs.pl | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/vp9/common/vp9_rtcd_defs.pl b/vp9/common/vp9_rtcd_defs.pl
index 32bcf9a774..c695a5dc07 100644
--- a/vp9/common/vp9_rtcd_defs.pl
+++ b/vp9/common/vp9_rtcd_defs.pl
@@ -838,7 +838,7 @@ if (vpx_config("CONFIG_VP9_HIGHBITDEPTH") eq "yes") {
specialize qw/vp9_quantize_b_32x32/;
} else {
add_proto qw/int64_t vp9_block_error/, "const tran_low_t *coeff, const tran_low_t *dqcoeff, intptr_t block_size, int64_t *ssz";
- specialize qw/vp9_block_error avx2/;
+ specialize qw/vp9_block_error avx2/, "$sse2_x86inc";
add_proto qw/void vp9_quantize_fp/, "const tran_low_t *coeff_ptr, intptr_t n_coeffs, int skip_block, const int16_t *zbin_ptr, const int16_t *round_ptr, const int16_t *quant_ptr, const int16_t *quant_shift_ptr, tran_low_t *qcoeff_ptr, tran_low_t *dqcoeff_ptr, const int16_t *dequant_ptr, int zbin_oq_value, uint16_t *eob_ptr, const int16_t *scan, const int16_t *iscan";
specialize qw/vp9_quantize_fp neon/, "$ssse3_x86_64";
@@ -850,7 +850,7 @@ if (vpx_config("CONFIG_VP9_HIGHBITDEPTH") eq "yes") {
specialize qw/vp9_quantize_b/, "$ssse3_x86_64";
add_proto qw/void vp9_quantize_b_32x32/, "const tran_low_t *coeff_ptr, intptr_t n_coeffs, int skip_block, const int16_t *zbin_ptr, const int16_t *round_ptr, const int16_t *quant_ptr, const int16_t *quant_shift_ptr, tran_low_t *qcoeff_ptr, tran_low_t *dqcoeff_ptr, const int16_t *dequant_ptr, int zbin_oq_value, uint16_t *eob_ptr, const int16_t *scan, const int16_t *iscan";
- specialize qw/vp9_quantize_b_32x32/;
+ specialize qw/vp9_quantize_b_32x32/, "$ssse3_x86_64";
}
#
--
GitLab