AArch64: Optimize Armv8.0 Neon path of SBD H/HV 6-tap filters

The 6-tap horizontal and the horizontal parts of 6-tap HV subpel filters can be further improved by some pointer arithmetic and saving some EXT instructions in their data rearrangement codes.

Relative runtime of micro benchmarks after this patch on some Cortex CPU cores:

SBD mct h         X1     A78     A76     A72     A55
 regular  w8:  0.878x  0.894x  0.990x  0.923x  0.944x
 regular w16:  0.962x  0.931x  0.943x  0.949x  0.949x
 regular w32:  0.937x  0.937x  0.972x  0.938x  0.947x
 regular w64:  0.920x  0.965x  0.992x  0.936x  0.944x

SBD mct hv        X1     A78     A76     A72     A55
 regular  w8:  0.931x  0.970x  0.951x  0.950x  0.971x
 regular w16:  0.940x  0.971x  0.941x  0.952x  0.967x
 regular w32:  0.943x  0.972x  0.946x  0.961x  0.974x
 regular w64:  0.943x  0.973x  0.952x  0.944x  0.975x

examples/dav1dplay.c

@@ -240,35 +240,37 @@ static Dav1dPlayRenderContext *dp_rd_ctx_create(int argc, char **argv)
         return NULL;
     }
 
+    // Parse and validate arguments
+    dav1d_default_settings(&rd_ctx->lib_settings);
+    memset(&rd_ctx->settings, 0, sizeof(rd_ctx->settings));
+    dp_rd_ctx_parse_args(rd_ctx, argc, argv);
+
+    // Init SDL2 library
+    if (SDL_Init(SDL_INIT_VIDEO | SDL_INIT_TIMER) < 0) {
+        fprintf(stderr, "SDL_Init failed: %s\n", SDL_GetError());
+        goto fail;
+    }
+
     // Register a custom event to notify our SDL main thread
     // about new frames
     rd_ctx->event_types = SDL_RegisterEvents(3);
     if (rd_ctx->event_types == UINT32_MAX) {
         fprintf(stderr, "Failure to create custom SDL event types!\n");
-        free(rd_ctx);
-        return NULL;
+        goto fail;
     }
 
     rd_ctx->fifo = dp_fifo_create(5);
     if (rd_ctx->fifo == NULL) {
         fprintf(stderr, "Failed to create FIFO for output pictures!\n");
-        free(rd_ctx);
-        return NULL;
+        goto fail;
     }
 
     rd_ctx->lock = SDL_CreateMutex();
     if (rd_ctx->lock == NULL) {
         fprintf(stderr, "SDL_CreateMutex failed: %s\n", SDL_GetError());
-        dp_fifo_destroy(rd_ctx->fifo);
-        free(rd_ctx);
-        return NULL;
+        goto fail;
     }
 
-    // Parse and validate arguments
-    dav1d_default_settings(&rd_ctx->lib_settings);
-    memset(&rd_ctx->settings, 0, sizeof(rd_ctx->settings));
-    dp_rd_ctx_parse_args(rd_ctx, argc, argv);
-
     // Select renderer
     renderer_info = dp_get_renderer(rd_ctx->settings.renderer_name);
 
@@ -281,13 +283,19 @@ static Dav1dPlayRenderContext *dp_rd_ctx_create(int argc, char **argv)
 
     rd_ctx->rd_priv = (renderer_info) ? renderer_info->create_renderer() : NULL;
     if (rd_ctx->rd_priv == NULL) {
-        SDL_DestroyMutex(rd_ctx->lock);
-        dp_fifo_destroy(rd_ctx->fifo);
-        free(rd_ctx);
-        return NULL;
+        goto fail;
     }
 
     return rd_ctx;
+
+fail:
+    if (rd_ctx->lock)
+        SDL_DestroyMutex(rd_ctx->lock);
+    if (rd_ctx->fifo)
+        dp_fifo_destroy(rd_ctx->fifo);
+    free(rd_ctx);
+    SDL_Quit();
+    return NULL;
 }
 
 /**
@@ -662,10 +670,6 @@ int main(int argc, char **argv)
         return 1;
     }
 
-    // Init SDL2 library
-    if (SDL_Init(SDL_INIT_VIDEO | SDL_INIT_TIMER) < 0)
-        return 10;
-
     // Create render context
     Dav1dPlayRenderContext *rd_ctx = dp_rd_ctx_create(argc, argv);
     if (rd_ctx == NULL) {
@@ -776,5 +780,6 @@ out:;
     int decoder_ret = 0;
     SDL_WaitThread(decoder_thread, &decoder_ret);
     dp_rd_ctx_destroy(rd_ctx);
+    SDL_Quit();
     return decoder_ret;
 }