diff mbox series

[FFmpeg-devel,v3,3/5] avcodec/ac3: Implement ac3_extract_exponents for aarch64 NEON

Message ID 9c17becb-dbec-40cd-9def-84d956bf397f@geoffhill.org
State New
Headers show
Series avcodec/ac3: Add aarch64 NEON DSP | expand

Checks

Context Check Description
yinshiyou/make_loongarch64 success Make finished
yinshiyou/make_fate_loongarch64 success Make fate finished
andriy/make_x86 success Make finished
andriy/make_fate_x86 success Make fate finished

Commit Message

Geoff Hill April 3, 2024, 6:43 a.m. UTC 
Signed-off-by: Geoff Hill <geoff@geoffhill.org>
---
 libavcodec/aarch64/ac3dsp_init_aarch64.c |  2 ++
 libavcodec/aarch64/ac3dsp_neon.S         | 15 ++++++++++
 tests/checkasm/ac3dsp.c                  | 36 ++++++++++++++++++++++++
 3 files changed, 53 insertions(+)
diff mbox series

Patch

diff --git a/libavcodec/aarch64/ac3dsp_init_aarch64.c b/libavcodec/aarch64/ac3dsp_init_aarch64.c
index 8874b41393..1bdc215b51 100644
--- a/libavcodec/aarch64/ac3dsp_init_aarch64.c
+++ b/libavcodec/aarch64/ac3dsp_init_aarch64.c
@@ -26,6 +26,7 @@ 
 #include "config.h"
 
 void ff_ac3_exponent_min_neon(uint8_t *exp, int num_reuse_blocks, int nb_coefs);
+void ff_ac3_extract_exponents_neon(uint8_t *exp, int32_t *coef, int nb_coefs);
 void ff_float_to_fixed24_neon(int32_t *dst, const float *src, size_t len);
 
 av_cold void ff_ac3dsp_init_aarch64(AC3DSPContext *c)
@@ -34,5 +35,6 @@  av_cold void ff_ac3dsp_init_aarch64(AC3DSPContext *c)
     if (!have_neon(cpu_flags)) return;
 
     c->ac3_exponent_min = ff_ac3_exponent_min_neon;
+    c->extract_exponents = ff_ac3_extract_exponents_neon;
     c->float_to_fixed24 = ff_float_to_fixed24_neon;
 }
diff --git a/libavcodec/aarch64/ac3dsp_neon.S b/libavcodec/aarch64/ac3dsp_neon.S
index c8bdbb1bd3..b26f71a3f6 100644
--- a/libavcodec/aarch64/ac3dsp_neon.S
+++ b/libavcodec/aarch64/ac3dsp_neon.S
@@ -36,6 +36,21 @@  function ff_ac3_exponent_min_neon, export=1
 2:      ret
 endfunc
 
+function ff_ac3_extract_exponents_neon, export=1
+        cbz    w2, 1f
+        movi   v1.4s, #8
+0:      ld1    {v0.4s}, [x1], #16
+        abs    v0.4s, v0.4s
+        clz    v0.4s, v0.4s
+        sub    v0.4s, v0.4s, v1.4s
+        xtn    v0.4h, v0.4s
+        xtn    v0.8b, v0.8h
+        st1    {v0.s}[0], [x0], #4
+        subs   w2, w2, #4
+        b.gt   0b
+1:      ret
+endfunc
+
 function ff_float_to_fixed24_neon, export=1
 0:      ld1         {v0.4s, v1.4s}, [x1], #32
         fcvtzs      v0.4s, v0.4s, #24
diff --git a/tests/checkasm/ac3dsp.c b/tests/checkasm/ac3dsp.c
index acb00b6fe1..a8a20349f9 100644
--- a/tests/checkasm/ac3dsp.c
+++ b/tests/checkasm/ac3dsp.c
@@ -18,6 +18,7 @@ 
  * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
  */
 
+#include <stdint.h>
 #include <string.h>
 
 #include "libavutil/mem.h"
@@ -35,6 +36,14 @@ 
         }                              \
     } while (0)                        \
 
+#define randomize_i24(buf, len)                   \
+    do {                                          \
+        int i;                                    \
+        for (i = 0; i < len; i++) {               \
+            buf[i] = (int32_t)rnd() & 0xFFFFFF;   \
+        }                                         \
+    } while (0)                                   \
+
 #define randomize_float(buf, len)                               \
     do {                                                        \
         int i;                                                  \
@@ -76,6 +85,32 @@  static void check_ac3_exponent_min(AC3DSPContext *c) {
     report("ac3_exponent_min");
 }
 
+static void check_ac3_extract_exponents(AC3DSPContext *c) {
+#define MAX_EXPS 3072
+    LOCAL_ALIGNED_16(int32_t, src, [MAX_EXPS]);
+    LOCAL_ALIGNED_16(uint8_t, v1, [MAX_EXPS]);
+    LOCAL_ALIGNED_16(uint8_t, v2, [MAX_EXPS]);
+    int n;
+
+    declare_func(void, uint8_t *, int32_t *, int);
+
+    for (n = 512; n <= MAX_EXPS; n += 256) {
+        if (check_func(c->extract_exponents, "ac3_extract_exponents_n%d", n)) {
+            randomize_i24(src, n);
+
+            call_ref(v1, src, n);
+            call_new(v2, src, n);
+
+            if (memcmp(v1, v2, n) != 0)
+                fail();
+
+            bench_new(v1, src, n);
+        }
+    }
+
+    report("ac3_extract_exponents");
+}
+
 static void check_float_to_fixed24(AC3DSPContext *c) {
 #define BUF_SIZE 1024
     LOCAL_ALIGNED_32(float, src, [BUF_SIZE]);
@@ -107,5 +142,6 @@  void checkasm_check_ac3dsp(void)
     ff_ac3dsp_init(&c);
 
     check_ac3_exponent_min(&c);
+    check_ac3_extract_exponents(&c);
     check_float_to_fixed24(&c);
 }