vulkan/prores: use cached bitstream reader

Speedup is around 75% on NVIDIA 3050, 20% on AMD 6700XT, 5% on Intel TigerLake.

libavcodec/vulkan_prores.c

@@ -21,7 +21,6 @@
 #include "hwaccel_internal.h"
 #include "libavutil/mem.h"
 #include "libavutil/vulkan.h"
-#include "libavutil/vulkan_loader.h"
 #include "libavutil/vulkan_spirv.h"
 
 extern const char *ff_source_common_comp;
@@ -207,14 +206,12 @@ static int vk_prores_end_frame(AVCodecContext *avctx)
     RET(ff_vk_exec_mirror_sem_value(&ctx->s, exec, &vp->sem, &vp->sem_value,
                                     pr->frame));
 
+    /* Transfer ownership to the exec context */
     RET(ff_vk_exec_add_dep_buf(&ctx->s, exec, &vp->slices_buf, 1, 0));
     vp->slices_buf = NULL;
     RET(ff_vk_exec_add_dep_buf(&ctx->s, exec, &pp->metadata_buf, 1, 0));
     pp->metadata_buf = NULL;
 
-    /* Transfer ownership to the exec context */
-    vp->slices_buf = pp->metadata_buf = NULL;
-
     /* Input barrier */
     ff_vk_frame_barrier(&ctx->s, exec, pr->frame, img_bar, &nb_img_bar,
                         VK_PIPELINE_STAGE_2_ALL_COMMANDS_BIT,
@@ -404,6 +401,11 @@ static int init_shader(AVCodecContext *avctx, FFVulkanContext *s,
                           local_size >> 16 & 0xff, local_size >> 8 & 0xff, local_size >> 0 & 0xff,
                           0));
 
+    av_bprintf(&shd->src, "#define GET_BITS_SMEM\n");
+
+    if (interlaced)
+        av_bprintf(&shd->src, "#define INTERLACED\n");
+
     /* Common code */
     GLSLD(ff_source_common_comp);
 
@@ -412,9 +414,6 @@ static int init_shader(AVCodecContext *avctx, FFVulkanContext *s,
 
     RET(ff_vk_shader_add_descriptor_set(s, shd, descs, num_descs, 0, 0));
 
-    if (interlaced)
-        av_bprintf(&shd->src, "#define INTERLACED\n");
-
     /* Main code */
     GLSLD(source);
 
@@ -494,6 +493,7 @@ static int vk_decode_prores_init(AVCodecContext *avctx)
     RET(init_shader(avctx, &ctx->s, &ctx->exec_pool, spv, &pv->reset,
                     "prores_dec_reset", "main", desc_set, 1,
                     ff_source_prores_reset_comp, 0x080801, pr->frame_type != 0));
+
     desc_set = (FFVulkanDescriptorSetBinding []) {
         {
             .name        = "slice_offsets_buf",