[x265] [PATCH] AArch64: Remove the redudant _S_ define macros
Li Zhang
li.zhang2 at arm.com
Thu Jun 12 10:32:07 UTC 2025
Remove redundant _S_ define macros that do the same as the general
define macros when initializing the Neon intrinsics pixel primitives.
---
source/common/aarch64/pixel-prim.cpp | 36 ++--------------------------
1 file changed, 2 insertions(+), 34 deletions(-)
diff --git a/source/common/aarch64/pixel-prim.cpp b/source/common/aarch64/pixel-prim.cpp
index f4df6786e..57a6e1265 100644
--- a/source/common/aarch64/pixel-prim.cpp
+++ b/source/common/aarch64/pixel-prim.cpp
@@ -2116,13 +2116,6 @@ void setupPixelPrimitives_neon(EncoderPrimitives &p)
p.chroma[X265_CSP_I420].cu[BLOCK_420_ ## W ## x ## H].sub_ps = pixel_sub_ps_neon<W, H>; \
p.chroma[X265_CSP_I420].cu[BLOCK_420_ ## W ## x ## H].add_ps[NONALIGNED] = pixel_add_ps_neon<W, H>; \
p.chroma[X265_CSP_I420].cu[BLOCK_420_ ## W ## x ## H].add_ps[ALIGNED] = pixel_add_ps_neon<W, H>;
-
-#define CHROMA_CU_S_420(W, H) \
- p.chroma[X265_CSP_I420].cu[BLOCK_420_ ## W ## x ## H].copy_pp = blockcopy_pp_neon<W, H>; \
- p.chroma[X265_CSP_I420].cu[BLOCK_420_ ## W ## x ## H].copy_ss = blockcopy_ss_neon<W, H>; \
- p.chroma[X265_CSP_I420].cu[BLOCK_420_ ## W ## x ## H].sub_ps = pixel_sub_ps_neon<W, H>; \
- p.chroma[X265_CSP_I420].cu[BLOCK_420_ ## W ## x ## H].add_ps[NONALIGNED] = pixel_add_ps_neon<W, H>; \
- p.chroma[X265_CSP_I420].cu[BLOCK_420_ ## W ## x ## H].add_ps[ALIGNED] = pixel_add_ps_neon<W, H>;
#else // !HIGH_BIT_DEPTH
#define CHROMA_CU_420(W, H) \
p.chroma[X265_CSP_I420].cu[BLOCK_420_ ## W ## x ## H].copy_pp = blockcopy_pp_neon<W, H>; \
@@ -2132,18 +2125,9 @@ void setupPixelPrimitives_neon(EncoderPrimitives &p)
p.chroma[X265_CSP_I420].cu[BLOCK_420_ ## W ## x ## H].sub_ps = pixel_sub_ps_neon<W, H>; \
p.chroma[X265_CSP_I420].cu[BLOCK_420_ ## W ## x ## H].add_ps[NONALIGNED] = pixel_add_ps_neon<W, H>; \
p.chroma[X265_CSP_I420].cu[BLOCK_420_ ## W ## x ## H].add_ps[ALIGNED] = pixel_add_ps_neon<W, H>;
-
-#define CHROMA_CU_S_420(W, H) \
- p.chroma[X265_CSP_I420].cu[BLOCK_420_ ## W ## x ## H].copy_pp = blockcopy_pp_neon<W, H>; \
- p.chroma[X265_CSP_I420].cu[BLOCK_420_ ## W ## x ## H].copy_ps = blockcopy_ps_neon<W, H>; \
- p.chroma[X265_CSP_I420].cu[BLOCK_420_ ## W ## x ## H].copy_ss = blockcopy_ss_neon<W, H>; \
- p.chroma[X265_CSP_I420].cu[BLOCK_420_ ## W ## x ## H].copy_sp = blockcopy_sp_neon<W, H>; \
- p.chroma[X265_CSP_I420].cu[BLOCK_420_ ## W ## x ## H].sub_ps = pixel_sub_ps_neon<W, H>; \
- p.chroma[X265_CSP_I420].cu[BLOCK_420_ ## W ## x ## H].add_ps[NONALIGNED] = pixel_add_ps_neon<W, H>; \
- p.chroma[X265_CSP_I420].cu[BLOCK_420_ ## W ## x ## H].add_ps[ALIGNED] = pixel_add_ps_neon<W, H>;
#endif // HIGH_BIT_DEPTH
- CHROMA_CU_S_420(4, 4)
+ CHROMA_CU_420(4, 4)
CHROMA_CU_420(8, 8)
CHROMA_CU_420(16, 16)
CHROMA_CU_420(32, 32)
@@ -2222,13 +2206,6 @@ void setupPixelPrimitives_neon(EncoderPrimitives &p)
p.chroma[X265_CSP_I422].cu[BLOCK_422_ ## W ## x ## H].sub_ps = pixel_sub_ps_neon<W, H>; \
p.chroma[X265_CSP_I422].cu[BLOCK_422_ ## W ## x ## H].add_ps[NONALIGNED] = pixel_add_ps_neon<W, H>; \
p.chroma[X265_CSP_I422].cu[BLOCK_422_ ## W ## x ## H].add_ps[ALIGNED] = pixel_add_ps_neon<W, H>;
-
-#define CHROMA_CU_S_422(W, H) \
- p.chroma[X265_CSP_I422].cu[BLOCK_422_ ## W ## x ## H].copy_pp = blockcopy_pp_neon<W, H>; \
- p.chroma[X265_CSP_I422].cu[BLOCK_422_ ## W ## x ## H].copy_ss = blockcopy_ss_neon<W, H>; \
- p.chroma[X265_CSP_I422].cu[BLOCK_422_ ## W ## x ## H].sub_ps = pixel_sub_ps_neon<W, H>; \
- p.chroma[X265_CSP_I422].cu[BLOCK_422_ ## W ## x ## H].add_ps[NONALIGNED] = pixel_add_ps_neon<W, H>; \
- p.chroma[X265_CSP_I422].cu[BLOCK_422_ ## W ## x ## H].add_ps[ALIGNED] = pixel_add_ps_neon<W, H>;
#else // !HIGH_BIT_DEPTH
#define CHROMA_CU_422(W, H) \
p.chroma[X265_CSP_I422].cu[BLOCK_422_ ## W ## x ## H].copy_pp = blockcopy_pp_neon<W, H>; \
@@ -2238,19 +2215,10 @@ void setupPixelPrimitives_neon(EncoderPrimitives &p)
p.chroma[X265_CSP_I422].cu[BLOCK_422_ ## W ## x ## H].sub_ps = pixel_sub_ps_neon<W, H>; \
p.chroma[X265_CSP_I422].cu[BLOCK_422_ ## W ## x ## H].add_ps[NONALIGNED] = pixel_add_ps_neon<W, H>; \
p.chroma[X265_CSP_I422].cu[BLOCK_422_ ## W ## x ## H].add_ps[ALIGNED] = pixel_add_ps_neon<W, H>;
-
-#define CHROMA_CU_S_422(W, H) \
- p.chroma[X265_CSP_I422].cu[BLOCK_422_ ## W ## x ## H].copy_pp = blockcopy_pp_neon<W, H>; \
- p.chroma[X265_CSP_I422].cu[BLOCK_422_ ## W ## x ## H].copy_ps = blockcopy_ps_neon<W, H>; \
- p.chroma[X265_CSP_I422].cu[BLOCK_422_ ## W ## x ## H].copy_ss = blockcopy_ss_neon<W, H>; \
- p.chroma[X265_CSP_I422].cu[BLOCK_422_ ## W ## x ## H].copy_sp = blockcopy_sp_neon<W, H>; \
- p.chroma[X265_CSP_I422].cu[BLOCK_422_ ## W ## x ## H].sub_ps = pixel_sub_ps_neon<W, H>; \
- p.chroma[X265_CSP_I422].cu[BLOCK_422_ ## W ## x ## H].add_ps[NONALIGNED] = pixel_add_ps_neon<W, H>; \
- p.chroma[X265_CSP_I422].cu[BLOCK_422_ ## W ## x ## H].add_ps[ALIGNED] = pixel_add_ps_neon<W, H>;
#endif // HIGH_BIT_DEPTH
- CHROMA_CU_S_422(4, 8)
+ CHROMA_CU_422(4, 8)
CHROMA_CU_422(8, 16)
CHROMA_CU_422(16, 32)
CHROMA_CU_422(32, 64)
--
2.39.5 (Apple Git-154)
-------------- next part --------------
>From c80e5fa5da5ee1e35f06040db27860c8d55c4107 Mon Sep 17 00:00:00 2001
Message-Id: <c80e5fa5da5ee1e35f06040db27860c8d55c4107.1749724221.git.li.zhang2 at arm.com>
From: Li Zhang <li.zhang2 at arm.com>
Date: Mon, 2 Jun 2025 16:36:59 +0200
Subject: [PATCH] AArch64: Remove the redudant _S_ define macros
Remove redundant _S_ define macros that do the same as the general
define macros when initializing the Neon intrinsics pixel primitives.
---
source/common/aarch64/pixel-prim.cpp | 36 ++--------------------------
1 file changed, 2 insertions(+), 34 deletions(-)
diff --git a/source/common/aarch64/pixel-prim.cpp b/source/common/aarch64/pixel-prim.cpp
index f4df6786e..57a6e1265 100644
--- a/source/common/aarch64/pixel-prim.cpp
+++ b/source/common/aarch64/pixel-prim.cpp
@@ -2116,13 +2116,6 @@ void setupPixelPrimitives_neon(EncoderPrimitives &p)
p.chroma[X265_CSP_I420].cu[BLOCK_420_ ## W ## x ## H].sub_ps = pixel_sub_ps_neon<W, H>; \
p.chroma[X265_CSP_I420].cu[BLOCK_420_ ## W ## x ## H].add_ps[NONALIGNED] = pixel_add_ps_neon<W, H>; \
p.chroma[X265_CSP_I420].cu[BLOCK_420_ ## W ## x ## H].add_ps[ALIGNED] = pixel_add_ps_neon<W, H>;
-
-#define CHROMA_CU_S_420(W, H) \
- p.chroma[X265_CSP_I420].cu[BLOCK_420_ ## W ## x ## H].copy_pp = blockcopy_pp_neon<W, H>; \
- p.chroma[X265_CSP_I420].cu[BLOCK_420_ ## W ## x ## H].copy_ss = blockcopy_ss_neon<W, H>; \
- p.chroma[X265_CSP_I420].cu[BLOCK_420_ ## W ## x ## H].sub_ps = pixel_sub_ps_neon<W, H>; \
- p.chroma[X265_CSP_I420].cu[BLOCK_420_ ## W ## x ## H].add_ps[NONALIGNED] = pixel_add_ps_neon<W, H>; \
- p.chroma[X265_CSP_I420].cu[BLOCK_420_ ## W ## x ## H].add_ps[ALIGNED] = pixel_add_ps_neon<W, H>;
#else // !HIGH_BIT_DEPTH
#define CHROMA_CU_420(W, H) \
p.chroma[X265_CSP_I420].cu[BLOCK_420_ ## W ## x ## H].copy_pp = blockcopy_pp_neon<W, H>; \
@@ -2132,18 +2125,9 @@ void setupPixelPrimitives_neon(EncoderPrimitives &p)
p.chroma[X265_CSP_I420].cu[BLOCK_420_ ## W ## x ## H].sub_ps = pixel_sub_ps_neon<W, H>; \
p.chroma[X265_CSP_I420].cu[BLOCK_420_ ## W ## x ## H].add_ps[NONALIGNED] = pixel_add_ps_neon<W, H>; \
p.chroma[X265_CSP_I420].cu[BLOCK_420_ ## W ## x ## H].add_ps[ALIGNED] = pixel_add_ps_neon<W, H>;
-
-#define CHROMA_CU_S_420(W, H) \
- p.chroma[X265_CSP_I420].cu[BLOCK_420_ ## W ## x ## H].copy_pp = blockcopy_pp_neon<W, H>; \
- p.chroma[X265_CSP_I420].cu[BLOCK_420_ ## W ## x ## H].copy_ps = blockcopy_ps_neon<W, H>; \
- p.chroma[X265_CSP_I420].cu[BLOCK_420_ ## W ## x ## H].copy_ss = blockcopy_ss_neon<W, H>; \
- p.chroma[X265_CSP_I420].cu[BLOCK_420_ ## W ## x ## H].copy_sp = blockcopy_sp_neon<W, H>; \
- p.chroma[X265_CSP_I420].cu[BLOCK_420_ ## W ## x ## H].sub_ps = pixel_sub_ps_neon<W, H>; \
- p.chroma[X265_CSP_I420].cu[BLOCK_420_ ## W ## x ## H].add_ps[NONALIGNED] = pixel_add_ps_neon<W, H>; \
- p.chroma[X265_CSP_I420].cu[BLOCK_420_ ## W ## x ## H].add_ps[ALIGNED] = pixel_add_ps_neon<W, H>;
#endif // HIGH_BIT_DEPTH
- CHROMA_CU_S_420(4, 4)
+ CHROMA_CU_420(4, 4)
CHROMA_CU_420(8, 8)
CHROMA_CU_420(16, 16)
CHROMA_CU_420(32, 32)
@@ -2222,13 +2206,6 @@ void setupPixelPrimitives_neon(EncoderPrimitives &p)
p.chroma[X265_CSP_I422].cu[BLOCK_422_ ## W ## x ## H].sub_ps = pixel_sub_ps_neon<W, H>; \
p.chroma[X265_CSP_I422].cu[BLOCK_422_ ## W ## x ## H].add_ps[NONALIGNED] = pixel_add_ps_neon<W, H>; \
p.chroma[X265_CSP_I422].cu[BLOCK_422_ ## W ## x ## H].add_ps[ALIGNED] = pixel_add_ps_neon<W, H>;
-
-#define CHROMA_CU_S_422(W, H) \
- p.chroma[X265_CSP_I422].cu[BLOCK_422_ ## W ## x ## H].copy_pp = blockcopy_pp_neon<W, H>; \
- p.chroma[X265_CSP_I422].cu[BLOCK_422_ ## W ## x ## H].copy_ss = blockcopy_ss_neon<W, H>; \
- p.chroma[X265_CSP_I422].cu[BLOCK_422_ ## W ## x ## H].sub_ps = pixel_sub_ps_neon<W, H>; \
- p.chroma[X265_CSP_I422].cu[BLOCK_422_ ## W ## x ## H].add_ps[NONALIGNED] = pixel_add_ps_neon<W, H>; \
- p.chroma[X265_CSP_I422].cu[BLOCK_422_ ## W ## x ## H].add_ps[ALIGNED] = pixel_add_ps_neon<W, H>;
#else // !HIGH_BIT_DEPTH
#define CHROMA_CU_422(W, H) \
p.chroma[X265_CSP_I422].cu[BLOCK_422_ ## W ## x ## H].copy_pp = blockcopy_pp_neon<W, H>; \
@@ -2238,19 +2215,10 @@ void setupPixelPrimitives_neon(EncoderPrimitives &p)
p.chroma[X265_CSP_I422].cu[BLOCK_422_ ## W ## x ## H].sub_ps = pixel_sub_ps_neon<W, H>; \
p.chroma[X265_CSP_I422].cu[BLOCK_422_ ## W ## x ## H].add_ps[NONALIGNED] = pixel_add_ps_neon<W, H>; \
p.chroma[X265_CSP_I422].cu[BLOCK_422_ ## W ## x ## H].add_ps[ALIGNED] = pixel_add_ps_neon<W, H>;
-
-#define CHROMA_CU_S_422(W, H) \
- p.chroma[X265_CSP_I422].cu[BLOCK_422_ ## W ## x ## H].copy_pp = blockcopy_pp_neon<W, H>; \
- p.chroma[X265_CSP_I422].cu[BLOCK_422_ ## W ## x ## H].copy_ps = blockcopy_ps_neon<W, H>; \
- p.chroma[X265_CSP_I422].cu[BLOCK_422_ ## W ## x ## H].copy_ss = blockcopy_ss_neon<W, H>; \
- p.chroma[X265_CSP_I422].cu[BLOCK_422_ ## W ## x ## H].copy_sp = blockcopy_sp_neon<W, H>; \
- p.chroma[X265_CSP_I422].cu[BLOCK_422_ ## W ## x ## H].sub_ps = pixel_sub_ps_neon<W, H>; \
- p.chroma[X265_CSP_I422].cu[BLOCK_422_ ## W ## x ## H].add_ps[NONALIGNED] = pixel_add_ps_neon<W, H>; \
- p.chroma[X265_CSP_I422].cu[BLOCK_422_ ## W ## x ## H].add_ps[ALIGNED] = pixel_add_ps_neon<W, H>;
#endif // HIGH_BIT_DEPTH
- CHROMA_CU_S_422(4, 8)
+ CHROMA_CU_422(4, 8)
CHROMA_CU_422(8, 16)
CHROMA_CU_422(16, 32)
CHROMA_CU_422(32, 64)
--
2.39.5 (Apple Git-154)
More information about the x265-devel
mailing list