[FFmpeg-devel] [PATCH 2/5] [inline assembly] merges contiguous assembly statements

[frederic.recoules at univ-grenoble-alpes.fr]

From: Frédéric Recoules <frederic.recoules at orange.fr>

---
 libavcodec/x86/hpeldsp_init.c |  8 ++++++++
 libavcodec/x86/rnd_template.c | 14 +++++++-------
 2 files changed, 15 insertions(+), 7 deletions(-)

diff --git a/libavcodec/x86/hpeldsp_init.c b/libavcodec/x86/hpeldsp_init.c
index d89928cec6..c99513035b 100644
--- a/libavcodec/x86/hpeldsp_init.c
+++ b/libavcodec/x86/hpeldsp_init.c
@@ -95,6 +95,8 @@ void ff_avg_approx_pixels8_xy2_3dnow(uint8_t *block, const uint8_t *pixels,
 /* MMX no rounding */
 #define DEF(x, y) x ## _no_rnd_ ## y ## _mmx
 #define SET_RND  MOVQ_WONE
+#define SET_RND_TPL MOVQ_WONE_TPL
+#define COMMA_SET_RND_IN
 #define PAVGBP(a, b, c, d, e, f)        PAVGBP_MMX_NO_RND(a, b, c, d, e, f)
 #define PAVGB(a, b, c, e)               PAVGB_MMX_NO_RND(a, b, c, e)
 #define STATIC static
@@ -104,6 +106,8 @@ void ff_avg_approx_pixels8_xy2_3dnow(uint8_t *block, const uint8_t *pixels,
 
 #undef DEF
 #undef SET_RND
+#undef SET_RND_TPL
+#undef COMMA_SET_RND_IN
 #undef PAVGBP
 #undef PAVGB
 #undef STATIC
@@ -121,6 +125,8 @@ CALL_2X_PIXELS(put_no_rnd_pixels16_xy2_mmx, put_no_rnd_pixels8_xy2_mmx, 8)
 
 #define DEF(x, y) x ## _ ## y ## _mmx
 #define SET_RND  MOVQ_WTWO
+#define SET_RND_TPL MOVQ_WTWO_TPL
+#define COMMA_SET_RND_IN COMMA_MOVQ_WTWO_IN
 #define PAVGBP(a, b, c, d, e, f)        PAVGBP_MMX(a, b, c, d, e, f)
 #define PAVGB(a, b, c, e)               PAVGB_MMX(a, b, c, e)
 
@@ -134,6 +140,8 @@ CALL_2X_PIXELS(put_no_rnd_pixels16_xy2_mmx, put_no_rnd_pixels8_xy2_mmx, 8)
 
 #undef DEF
 #undef SET_RND
+#undef SET_RND_TPL
+#undef COMMA_SET_RND_IN
 #undef PAVGBP
 #undef PAVGB
 
diff --git a/libavcodec/x86/rnd_template.c b/libavcodec/x86/rnd_template.c
index 09946bd23f..a98fbc10ab 100644
--- a/libavcodec/x86/rnd_template.c
+++ b/libavcodec/x86/rnd_template.c
@@ -33,9 +33,9 @@
 av_unused STATIC void DEF(put, pixels8_xy2)(uint8_t *block, const uint8_t *pixels,
                                   ptrdiff_t line_size, int h)
 {
-    MOVQ_ZERO(mm7);
-    SET_RND(mm6); // =2 for rnd  and  =1 for no_rnd version
     __asm__ volatile(
+	MOVQ_ZERO_TPL(mm7)
+	SET_RND_TPL(mm6) // =2 for rnd  and  =1 for no_rnd version
         "movq   (%1), %%mm0             \n\t"
         "movq   1(%1), %%mm4            \n\t"
         "movq   %%mm0, %%mm1            \n\t"
@@ -93,7 +93,7 @@ av_unused STATIC void DEF(put, pixels8_xy2)(uint8_t *block, const uint8_t *pixel
         "subl   $2, %0                  \n\t"
         "jnz    1b                      \n\t"
         :"+g"(h), "+S"(pixels)
-        :"D"(block), "r"((x86_reg)line_size)
+        :"D"(block), "r"((x86_reg)line_size) COMMA_SET_RND_IN
         :FF_REG_a, "memory");
 }
 
@@ -102,10 +102,10 @@ av_unused STATIC void DEF(put, pixels8_xy2)(uint8_t *block, const uint8_t *pixel
 av_unused STATIC void DEF(avg, pixels8_xy2)(uint8_t *block, const uint8_t *pixels,
                                   ptrdiff_t line_size, int h)
 {
-    MOVQ_ZERO(mm7);
-    SET_RND(mm6); // =2 for rnd  and  =1 for no_rnd version
     __asm__ volatile(
-        "movq   (%1), %%mm0             \n\t"
+        MOVQ_ZERO_TPL(mm7)
+        SET_RND_TPL(mm6) // =2 for rnd  and  =1 for no_rnd version
+	"movq   (%1), %%mm0             \n\t"
         "movq   1(%1), %%mm4            \n\t"
         "movq   %%mm0, %%mm1            \n\t"
         "movq   %%mm4, %%mm5            \n\t"
@@ -170,6 +170,6 @@ av_unused STATIC void DEF(avg, pixels8_xy2)(uint8_t *block, const uint8_t *pixel
         "subl   $2, %0                  \n\t"
         "jnz    1b                      \n\t"
         :"+g"(h), "+S"(pixels)
-        :"D"(block), "r"((x86_reg)line_size)
+        :"D"(block), "r"((x86_reg)line_size) COMMA_SET_RND_IN
         :FF_REG_a, "memory");
 }
-- 
2.17.1