Re: [FFmpeg-devel] [PATCH] avcodec/mips: preload data in hevc sao edge 90 degree filter msa functions

2017-09-22 Thread Michael Niedermayer 
On Thu, Sep 21, 2017 at 12:01:45PM +, Manojkumar Bhosale wrote:
> LGTM

applied

[...]
-- 
Michael GnuPG fingerprint: 9FF2128B147EF6730BADF133611EC787040B0FAB

I am the wisest man alive, for I know one thing, and that is that I know
nothing. -- Socrates


signature.asc
Description: Digital signature
___
ffmpeg-devel mailing list
ffmpeg-devel@ffmpeg.org
http://ffmpeg.org/mailman/listinfo/ffmpeg-devel

Re: [FFmpeg-devel] [PATCH] avcodec/mips: preload data in hevc sao edge 90 degree filter msa functions

2017-09-21 Thread Manojkumar Bhosale 
LGTM

-Original Message-
From: ffmpeg-devel [mailto:ffmpeg-devel-boun...@ffmpeg.org] On Behalf Of 
kaustubh.ra...@imgtec.com
Sent: Thursday, September 21, 2017 12:18 PM
To: ffmpeg-devel@ffmpeg.org
Cc: Kaustubh Raste
Subject: [FFmpeg-devel] [PATCH] avcodec/mips: preload data in hevc sao edge 90 
degree filter msa functions

From: Kaustubh Raste <kaustubh.ra...@imgtec.com>

Signed-off-by: Kaustubh Raste <kaustubh.ra...@imgtec.com>
---
 libavcodec/mips/hevc_lpf_sao_msa.c |  181 
 1 file changed, 122 insertions(+), 59 deletions(-)

diff --git a/libavcodec/mips/hevc_lpf_sao_msa.c 
b/libavcodec/mips/hevc_lpf_sao_msa.c
index 3472d32..39c647e 100644
--- a/libavcodec/mips/hevc_lpf_sao_msa.c
+++ b/libavcodec/mips/hevc_lpf_sao_msa.c
@@ -1568,23 +1568,25 @@ static void 
hevc_sao_edge_filter_90degree_4width_msa(uint8_t *dst,
  int16_t *sao_offset_val,
  int32_t height)  {
-int32_t h_cnt;
 uint32_t dst_val0, dst_val1;
-v8i16 edge_idx = { 1, 2, 0, 3, 4, 0, 0, 0 };
+v16i8 edge_idx = { 1, 2, 0, 3, 4, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 
+ };
 v16u8 const1 = (v16u8) __msa_ldi_b(1);
 v16i8 dst0;
-v16i8 zero = { 0 };
+v16i8 sao_offset = LD_SB(sao_offset_val);
 v16u8 cmp_minus10, diff_minus10, cmp_minus11, diff_minus11;
 v16u8 src_minus10, src_minus11, src10, src11;
 v16i8 src_zero0, src_zero1;
-v8i16 sao_offset, src00, src01, offset_mask0, offset_mask1;
+v16i8 offset;
+v8i16 offset_mask0, offset_mask1;
 
-sao_offset = LD_SH(sao_offset_val);
+sao_offset = __msa_pckev_b(sao_offset, sao_offset);
 
+/* load in advance */
 LD_UB2(src - src_stride, src_stride, src_minus10, src_minus11);
+LD_UB2(src + src_stride, src_stride, src10, src11);
 
-for (h_cnt = (height >> 1); h_cnt--;) {
-LD_UB2(src + src_stride, src_stride, src10, src11);
+for (height -= 2; height; height -= 2) {
+src += (src_stride << 1);
 
 src_minus10 = (v16u8) __msa_ilvr_b((v16i8) src10, (v16i8) src_minus10);
 src_zero0 = __msa_ilvr_b((v16i8) src_minus11, (v16i8) src_minus11); @@ 
-1604,19 +1606,22 @@ static void 
hevc_sao_edge_filter_90degree_4width_msa(uint8_t *dst,
 offset_mask0 = (v8i16) (__msa_hadd_u_h(diff_minus10, diff_minus10) + 
2);
 offset_mask1 = (v8i16) (__msa_hadd_u_h(diff_minus11, diff_minus11) + 
2);
 
-VSHF_H2_SH(edge_idx, edge_idx, sao_offset, sao_offset, offset_mask0,
-   offset_mask0, offset_mask0, offset_mask0);
-VSHF_H2_SH(edge_idx, edge_idx, sao_offset, sao_offset, offset_mask1,
-   offset_mask1, offset_mask1, offset_mask1);
-ILVEV_B2_SH(src_zero0, zero, src_zero1, zero, src00, src01);
-ADD2(offset_mask0, src00, offset_mask1, src01, offset_mask0,
- offset_mask1);
-CLIP_SH2_0_255(offset_mask0, offset_mask1);
-dst0 = __msa_pckev_b((v16i8) offset_mask1, (v16i8) offset_mask0);
+offset = __msa_pckev_b((v16i8) offset_mask1, (v16i8) offset_mask0);
+dst0 = __msa_pckev_b((v16i8) src_zero1, (v16i8) src_zero0);
+
+VSHF_B2_SB(edge_idx, edge_idx, sao_offset, sao_offset, offset, offset,
+   offset, offset);
+
+dst0 = (v16i8) __msa_xori_b((v16u8) dst0, 128);
+dst0 = __msa_adds_s_b(dst0, offset);
+dst0 = (v16i8) __msa_xori_b((v16u8) dst0, 128);
 
 src_minus10 = src10;
 src_minus11 = src11;
 
+/* load in advance */
+LD_UB2(src + src_stride, src_stride, src10, src11);
+
 dst_val0 = __msa_copy_u_w((v4i32) dst0, 0);
 dst_val1 = __msa_copy_u_w((v4i32) dst0, 2);
 SW(dst_val0, dst);
@@ -1624,8 +1629,41 @@ static void 
hevc_sao_edge_filter_90degree_4width_msa(uint8_t *dst,
 SW(dst_val1, dst);
 
 dst += dst_stride;
-src += (src_stride << 1);
 }
+
+src_minus10 = (v16u8) __msa_ilvr_b((v16i8) src10, (v16i8) src_minus10);
+src_zero0 = __msa_ilvr_b((v16i8) src_minus11, (v16i8) src_minus11);
+src_minus11 = (v16u8) __msa_ilvr_b((v16i8) src11, (v16i8) src_minus11);
+src_zero1 = __msa_ilvr_b((v16i8) src10, (v16i8) src10);
+
+cmp_minus10 = ((v16u8) src_zero0 == src_minus10);
+diff_minus10 = __msa_nor_v(cmp_minus10, cmp_minus10);
+cmp_minus10 = (src_minus10 < (v16u8) src_zero0);
+diff_minus10 = __msa_bmnz_v(diff_minus10, const1, cmp_minus10);
+
+cmp_minus11 = ((v16u8) src_zero1 == src_minus11);
+diff_minus11 = __msa_nor_v(cmp_minus11, cmp_minus11);
+cmp_minus11 = (src_minus11 < (v16u8) src_zero1);
+diff_minus11 = __msa_bmnz_v(diff_minus11, const1, cmp_minus11);
+
+offset_mask0 = (v8i16) (__msa_hadd_u_h(diff_minus10, diff_minus10) + 2);
+offset_mask1 = (v8i16) (__msa_hadd_u_h(diff_minus11, diff_minus11) 
+ + 2);
+
+offset = __msa_pckev_b((v16i8) offset_mask1, (v16i8) offset_mask

[FFmpeg-devel] [PATCH] avcodec/mips: preload data in hevc sao edge 90 degree filter msa functions

2017-09-21 Thread kaustubh.raste 
From: Kaustubh Raste 

Signed-off-by: Kaustubh Raste 
---
 libavcodec/mips/hevc_lpf_sao_msa.c |  181 
 1 file changed, 122 insertions(+), 59 deletions(-)

diff --git a/libavcodec/mips/hevc_lpf_sao_msa.c 
b/libavcodec/mips/hevc_lpf_sao_msa.c
index 3472d32..39c647e 100644
--- a/libavcodec/mips/hevc_lpf_sao_msa.c
+++ b/libavcodec/mips/hevc_lpf_sao_msa.c
@@ -1568,23 +1568,25 @@ static void 
hevc_sao_edge_filter_90degree_4width_msa(uint8_t *dst,
  int16_t *sao_offset_val,
  int32_t height)
 {
-int32_t h_cnt;
 uint32_t dst_val0, dst_val1;
-v8i16 edge_idx = { 1, 2, 0, 3, 4, 0, 0, 0 };
+v16i8 edge_idx = { 1, 2, 0, 3, 4, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 };
 v16u8 const1 = (v16u8) __msa_ldi_b(1);
 v16i8 dst0;
-v16i8 zero = { 0 };
+v16i8 sao_offset = LD_SB(sao_offset_val);
 v16u8 cmp_minus10, diff_minus10, cmp_minus11, diff_minus11;
 v16u8 src_minus10, src_minus11, src10, src11;
 v16i8 src_zero0, src_zero1;
-v8i16 sao_offset, src00, src01, offset_mask0, offset_mask1;
+v16i8 offset;
+v8i16 offset_mask0, offset_mask1;
 
-sao_offset = LD_SH(sao_offset_val);
+sao_offset = __msa_pckev_b(sao_offset, sao_offset);
 
+/* load in advance */
 LD_UB2(src - src_stride, src_stride, src_minus10, src_minus11);
+LD_UB2(src + src_stride, src_stride, src10, src11);
 
-for (h_cnt = (height >> 1); h_cnt--;) {
-LD_UB2(src + src_stride, src_stride, src10, src11);
+for (height -= 2; height; height -= 2) {
+src += (src_stride << 1);
 
 src_minus10 = (v16u8) __msa_ilvr_b((v16i8) src10, (v16i8) src_minus10);
 src_zero0 = __msa_ilvr_b((v16i8) src_minus11, (v16i8) src_minus11);
@@ -1604,19 +1606,22 @@ static void 
hevc_sao_edge_filter_90degree_4width_msa(uint8_t *dst,
 offset_mask0 = (v8i16) (__msa_hadd_u_h(diff_minus10, diff_minus10) + 
2);
 offset_mask1 = (v8i16) (__msa_hadd_u_h(diff_minus11, diff_minus11) + 
2);
 
-VSHF_H2_SH(edge_idx, edge_idx, sao_offset, sao_offset, offset_mask0,
-   offset_mask0, offset_mask0, offset_mask0);
-VSHF_H2_SH(edge_idx, edge_idx, sao_offset, sao_offset, offset_mask1,
-   offset_mask1, offset_mask1, offset_mask1);
-ILVEV_B2_SH(src_zero0, zero, src_zero1, zero, src00, src01);
-ADD2(offset_mask0, src00, offset_mask1, src01, offset_mask0,
- offset_mask1);
-CLIP_SH2_0_255(offset_mask0, offset_mask1);
-dst0 = __msa_pckev_b((v16i8) offset_mask1, (v16i8) offset_mask0);
+offset = __msa_pckev_b((v16i8) offset_mask1, (v16i8) offset_mask0);
+dst0 = __msa_pckev_b((v16i8) src_zero1, (v16i8) src_zero0);
+
+VSHF_B2_SB(edge_idx, edge_idx, sao_offset, sao_offset, offset, offset,
+   offset, offset);
+
+dst0 = (v16i8) __msa_xori_b((v16u8) dst0, 128);
+dst0 = __msa_adds_s_b(dst0, offset);
+dst0 = (v16i8) __msa_xori_b((v16u8) dst0, 128);
 
 src_minus10 = src10;
 src_minus11 = src11;
 
+/* load in advance */
+LD_UB2(src + src_stride, src_stride, src10, src11);
+
 dst_val0 = __msa_copy_u_w((v4i32) dst0, 0);
 dst_val1 = __msa_copy_u_w((v4i32) dst0, 2);
 SW(dst_val0, dst);
@@ -1624,8 +1629,41 @@ static void 
hevc_sao_edge_filter_90degree_4width_msa(uint8_t *dst,
 SW(dst_val1, dst);
 
 dst += dst_stride;
-src += (src_stride << 1);
 }
+
+src_minus10 = (v16u8) __msa_ilvr_b((v16i8) src10, (v16i8) src_minus10);
+src_zero0 = __msa_ilvr_b((v16i8) src_minus11, (v16i8) src_minus11);
+src_minus11 = (v16u8) __msa_ilvr_b((v16i8) src11, (v16i8) src_minus11);
+src_zero1 = __msa_ilvr_b((v16i8) src10, (v16i8) src10);
+
+cmp_minus10 = ((v16u8) src_zero0 == src_minus10);
+diff_minus10 = __msa_nor_v(cmp_minus10, cmp_minus10);
+cmp_minus10 = (src_minus10 < (v16u8) src_zero0);
+diff_minus10 = __msa_bmnz_v(diff_minus10, const1, cmp_minus10);
+
+cmp_minus11 = ((v16u8) src_zero1 == src_minus11);
+diff_minus11 = __msa_nor_v(cmp_minus11, cmp_minus11);
+cmp_minus11 = (src_minus11 < (v16u8) src_zero1);
+diff_minus11 = __msa_bmnz_v(diff_minus11, const1, cmp_minus11);
+
+offset_mask0 = (v8i16) (__msa_hadd_u_h(diff_minus10, diff_minus10) + 2);
+offset_mask1 = (v8i16) (__msa_hadd_u_h(diff_minus11, diff_minus11) + 2);
+
+offset = __msa_pckev_b((v16i8) offset_mask1, (v16i8) offset_mask0);
+dst0 = __msa_pckev_b((v16i8) src_zero1, (v16i8) src_zero0);
+
+VSHF_B2_SB(edge_idx, edge_idx, sao_offset, sao_offset, offset,
+   offset, offset, offset);
+
+dst0 = (v16i8) __msa_xori_b((v16u8) dst0, 128);
+dst0 = __msa_adds_s_b(dst0, offset);
+dst0 = (v16i8) __msa_xori_b((v16u8) dst0, 128);
+
+dst_val0 = __msa_copy_u_w((v4i32) dst0,