virtualenv/FFmpeg
1
0
Fork 0
mirror of https://github.com/FFmpeg/FFmpeg.git synced 2024-12-23 12:43:46 +02:00
Code Issues Releases Activity

lavfi/vulkan: use all enabled queues in the queue family

Browse Source 
This should significantly improve the performance with certain
filterchains.
This commit is contained in:
Lynne 2020-05-14 00:37:21 +01:00
parent fac17fd46f
commit 727cac88b8
No known key found for this signature in database
GPG Key ID: A2FEA5F03F034464
6 changed files with 372 additions and 136 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

39
libavfilter/vf_avgblur_vulkan.c
View File

@ -97,6 +97,10 @@ static av_cold int init_filter(AVFilterContext *ctx, AVFrame *in)
if (!sampler)
return AVERROR_EXTERNAL;
s->vkctx.queue_family_idx = s->vkctx.hwctx->queue_family_comp_index;
s->vkctx.queue_count = GET_QUEUE_COUNT(s->vkctx.hwctx, 0, 1, 0);
s->vkctx.cur_queue_idx = rand() % s->vkctx.queue_count;
{ /* Create shader for the horizontal pass */
desc_i[0].updater = s->input_images;
desc_i[1].updater = s->tmp_images;
@ -184,8 +188,7 @@ static av_cold int init_filter(AVFilterContext *ctx, AVFrame *in)
}
/* Execution context */
RET(ff_vk_create_exec_ctx(ctx, &s->exec,
s->vkctx.hwctx->queue_family_comp_index));
RET(ff_vk_create_exec_ctx(ctx, &s->exec));
s->initialized = 1;
@ -198,22 +201,30 @@ fail:
static int process_frames(AVFilterContext *avctx, AVFrame *out_f, AVFrame *tmp_f, AVFrame *in_f)
{
int err;
VkCommandBuffer cmd_buf;
AvgBlurVulkanContext *s = avctx->priv;
AVVkFrame *in = (AVVkFrame *)in_f->data[0];
AVVkFrame *tmp = (AVVkFrame *)tmp_f->data[0];
AVVkFrame *out = (AVVkFrame *)out_f->data[0];
int planes = av_pix_fmt_count_planes(s->vkctx.output_format);
/* Update descriptors and init the exec context */
ff_vk_start_exec_recording(avctx, s->exec);
cmd_buf = ff_vk_get_exec_buf(avctx, s->exec);
for (int i = 0; i < planes; i++) {
RET(ff_vk_create_imageview(avctx, &s->input_images[i].imageView, in->img[i],
RET(ff_vk_create_imageview(avctx, s->exec, &s->input_images[i].imageView,
in->img[i],
av_vkfmt_from_pixfmt(s->vkctx.input_format)[i],
ff_comp_identity_map));
RET(ff_vk_create_imageview(avctx, &s->tmp_images[i].imageView, tmp->img[i],
RET(ff_vk_create_imageview(avctx, s->exec, &s->tmp_images[i].imageView,
tmp->img[i],
av_vkfmt_from_pixfmt(s->vkctx.output_format)[i],
ff_comp_identity_map));
RET(ff_vk_create_imageview(avctx, &s->output_images[i].imageView, out->img[i],
RET(ff_vk_create_imageview(avctx, s->exec, &s->output_images[i].imageView,
out->img[i],
av_vkfmt_from_pixfmt(s->vkctx.output_format)[i],
ff_comp_identity_map));
@ -225,8 +236,6 @@ static int process_frames(AVFilterContext *avctx, AVFrame *out_f, AVFrame *tmp_f
ff_vk_update_descriptor_set(avctx, s->pl_hor, 0);
ff_vk_update_descriptor_set(avctx, s->pl_ver, 0);
ff_vk_start_exec_recording(avctx, s->exec);
for (int i = 0; i < planes; i++) {
VkImageMemoryBarrier bar[] = {
{
@ -270,7 +279,7 @@ static int process_frames(AVFilterContext *avctx, AVFrame *out_f, AVFrame *tmp_f
},
};
vkCmdPipelineBarrier(s->exec->buf, VK_PIPELINE_STAGE_TOP_OF_PIPE_BIT,
vkCmdPipelineBarrier(cmd_buf, VK_PIPELINE_STAGE_TOP_OF_PIPE_BIT,
VK_PIPELINE_STAGE_COMPUTE_SHADER_BIT, 0,
0, NULL, 0, NULL, FF_ARRAY_ELEMS(bar), bar);
@ -286,12 +295,12 @@ static int process_frames(AVFilterContext *avctx, AVFrame *out_f, AVFrame *tmp_f
ff_vk_bind_pipeline_exec(avctx, s->exec, s->pl_hor);
vkCmdDispatch(s->exec->buf, FFALIGN(s->vkctx.output_width, CGS)/CGS,
vkCmdDispatch(cmd_buf, FFALIGN(s->vkctx.output_width, CGS)/CGS,
s->vkctx.output_height, 1);
ff_vk_bind_pipeline_exec(avctx, s->exec, s->pl_ver);
vkCmdDispatch(s->exec->buf, s->vkctx.output_width,
vkCmdDispatch(cmd_buf, s->vkctx.output_width,
FFALIGN(s->vkctx.output_height, CGS)/CGS, 1);
ff_vk_add_exec_dep(avctx, s->exec, in_f, VK_PIPELINE_STAGE_TOP_OF_PIPE_BIT);
@ -301,14 +310,10 @@ static int process_frames(AVFilterContext *avctx, AVFrame *out_f, AVFrame *tmp_f
if (err)
return err;
return err;
fail:
for (int i = 0; i < planes; i++) {
ff_vk_destroy_imageview(avctx, &s->input_images[i].imageView);
ff_vk_destroy_imageview(avctx, &s->tmp_images[i].imageView);
ff_vk_destroy_imageview(avctx, &s->output_images[i].imageView);
}
ff_vk_discard_exec_deps(avctx, s->exec);
return err;
}

30
libavfilter/vf_chromaber_vulkan.c
View File

@ -73,6 +73,10 @@ static av_cold int init_filter(AVFilterContext *ctx, AVFrame *in)
if (!sampler)
return AVERROR_EXTERNAL;
s->vkctx.queue_family_idx = s->vkctx.hwctx->queue_family_comp_index;
s->vkctx.queue_count = GET_QUEUE_COUNT(s->vkctx.hwctx, 0, 1, 0);
s->vkctx.cur_queue_idx = rand() % s->vkctx.queue_count;
s->pl = ff_vk_create_pipeline(ctx);
if (!s->pl)
return AVERROR(ENOMEM);
@ -154,8 +158,7 @@ static av_cold int init_filter(AVFilterContext *ctx, AVFrame *in)
RET(ff_vk_init_compute_pipeline(ctx, s->pl));
/* Execution context */
RET(ff_vk_create_exec_ctx(ctx, &s->exec,
s->vkctx.hwctx->queue_family_comp_index));
RET(ff_vk_create_exec_ctx(ctx, &s->exec));
s->initialized = 1;
@ -168,17 +171,24 @@ fail:
static int process_frames(AVFilterContext *avctx, AVFrame *out_f, AVFrame *in_f)
{
int err = 0;
VkCommandBuffer cmd_buf;
ChromaticAberrationVulkanContext *s = avctx->priv;
AVVkFrame *in = (AVVkFrame *)in_f->data[0];
AVVkFrame *out = (AVVkFrame *)out_f->data[0];
int planes = av_pix_fmt_count_planes(s->vkctx.output_format);
/* Update descriptors and init the exec context */
ff_vk_start_exec_recording(avctx, s->exec);
cmd_buf = ff_vk_get_exec_buf(avctx, s->exec);
for (int i = 0; i < planes; i++) {
RET(ff_vk_create_imageview(avctx, &s->input_images[i].imageView, in->img[i],
RET(ff_vk_create_imageview(avctx, s->exec, &s->input_images[i].imageView,
in->img[i],
av_vkfmt_from_pixfmt(s->vkctx.input_format)[i],
ff_comp_identity_map));
RET(ff_vk_create_imageview(avctx, &s->output_images[i].imageView, out->img[i],
RET(ff_vk_create_imageview(avctx, s->exec, &s->output_images[i].imageView,
out->img[i],
av_vkfmt_from_pixfmt(s->vkctx.output_format)[i],
ff_comp_identity_map));
@ -188,8 +198,6 @@ static int process_frames(AVFilterContext *avctx, AVFrame *out_f, AVFrame *in_f)
ff_vk_update_descriptor_set(avctx, s->pl, 0);
ff_vk_start_exec_recording(avctx, s->exec);
for (int i = 0; i < planes; i++) {
VkImageMemoryBarrier bar[2] = {
{
@ -220,7 +228,7 @@ static int process_frames(AVFilterContext *avctx, AVFrame *out_f, AVFrame *in_f)
},
};
vkCmdPipelineBarrier(s->exec->buf, VK_PIPELINE_STAGE_TOP_OF_PIPE_BIT,
vkCmdPipelineBarrier(cmd_buf, VK_PIPELINE_STAGE_TOP_OF_PIPE_BIT,
VK_PIPELINE_STAGE_COMPUTE_SHADER_BIT, 0,
0, NULL, 0, NULL, FF_ARRAY_ELEMS(bar), bar);
@ -236,7 +244,7 @@ static int process_frames(AVFilterContext *avctx, AVFrame *out_f, AVFrame *in_f)
ff_vk_update_push_exec(avctx, s->exec, VK_SHADER_STAGE_COMPUTE_BIT,
0, sizeof(s->opts), &s->opts);
vkCmdDispatch(s->exec->buf,
vkCmdDispatch(cmd_buf,
FFALIGN(s->vkctx.output_width, CGROUPS[0])/CGROUPS[0],
FFALIGN(s->vkctx.output_height, CGROUPS[1])/CGROUPS[1], 1);
@ -247,12 +255,10 @@ static int process_frames(AVFilterContext *avctx, AVFrame *out_f, AVFrame *in_f)
if (err)
return err;
for (int i = 0; i < planes; i++) {
ff_vk_destroy_imageview(avctx, &s->input_images[i].imageView);
ff_vk_destroy_imageview(avctx, &s->output_images[i].imageView);
}
return err;
fail:
ff_vk_discard_exec_deps(avctx, s->exec);
return err;
}

37
libavfilter/vf_overlay_vulkan.c
View File

@ -87,6 +87,10 @@ static av_cold int init_filter(AVFilterContext *ctx)
if (!s->pl)
return AVERROR(ENOMEM);
s->vkctx.queue_family_idx = s->vkctx.hwctx->queue_family_comp_index;
s->vkctx.queue_count = GET_QUEUE_COUNT(s->vkctx.hwctx, 0, 1, 0);
s->vkctx.cur_queue_idx = rand() % s->vkctx.queue_count;
{ /* Create the shader */
const int planes = av_pix_fmt_count_planes(s->vkctx.output_format);
const int ialpha = av_pix_fmt_desc_get(s->vkctx.input_format)->flags & AV_PIX_FMT_FLAG_ALPHA;
@ -211,8 +215,7 @@ static av_cold int init_filter(AVFilterContext *ctx)
}
/* Execution context */
RET(ff_vk_create_exec_ctx(ctx, &s->exec,
s->vkctx.hwctx->queue_family_comp_index));
RET(ff_vk_create_exec_ctx(ctx, &s->exec));
s->initialized = 1;
@ -226,6 +229,7 @@ static int process_frames(AVFilterContext *avctx, AVFrame *out_f,
AVFrame *main_f, AVFrame *overlay_f)
{
int err;
VkCommandBuffer cmd_buf;
OverlayVulkanContext *s = avctx->priv;
int planes = av_pix_fmt_count_planes(s->vkctx.output_format);
@ -236,16 +240,23 @@ static int process_frames(AVFilterContext *avctx, AVFrame *out_f,
AVHWFramesContext *main_fc = (AVHWFramesContext*)main_f->hw_frames_ctx->data;
AVHWFramesContext *overlay_fc = (AVHWFramesContext*)overlay_f->hw_frames_ctx->data;
/* Update descriptors and init the exec context */
ff_vk_start_exec_recording(avctx, s->exec);
cmd_buf = ff_vk_get_exec_buf(avctx, s->exec);
for (int i = 0; i < planes; i++) {
RET(ff_vk_create_imageview(avctx, &s->main_images[i].imageView, main->img[i],
RET(ff_vk_create_imageview(avctx, s->exec, &s->main_images[i].imageView,
main->img[i],
av_vkfmt_from_pixfmt(main_fc->sw_format)[i],
ff_comp_identity_map));
RET(ff_vk_create_imageview(avctx, &s->overlay_images[i].imageView, overlay->img[i],
RET(ff_vk_create_imageview(avctx, s->exec, &s->overlay_images[i].imageView,
overlay->img[i],
av_vkfmt_from_pixfmt(overlay_fc->sw_format)[i],
ff_comp_identity_map));
RET(ff_vk_create_imageview(avctx, &s->output_images[i].imageView, out->img[i],
RET(ff_vk_create_imageview(avctx, s->exec, &s->output_images[i].imageView,
out->img[i],
av_vkfmt_from_pixfmt(s->vkctx.output_format)[i],
ff_comp_identity_map));
@ -256,8 +267,6 @@ static int process_frames(AVFilterContext *avctx, AVFrame *out_f,
ff_vk_update_descriptor_set(avctx, s->pl, 0);
ff_vk_start_exec_recording(avctx, s->exec);
for (int i = 0; i < planes; i++) {
VkImageMemoryBarrier bar[3] = {
{
@ -301,7 +310,7 @@ static int process_frames(AVFilterContext *avctx, AVFrame *out_f,
},
};
vkCmdPipelineBarrier(s->exec->buf, VK_PIPELINE_STAGE_TOP_OF_PIPE_BIT,
vkCmdPipelineBarrier(cmd_buf, VK_PIPELINE_STAGE_TOP_OF_PIPE_BIT,
VK_PIPELINE_STAGE_COMPUTE_SHADER_BIT, 0,
0, NULL, 0, NULL, FF_ARRAY_ELEMS(bar), bar);
@ -317,7 +326,7 @@ static int process_frames(AVFilterContext *avctx, AVFrame *out_f,
ff_vk_bind_pipeline_exec(avctx, s->exec, s->pl);
vkCmdDispatch(s->exec->buf,
vkCmdDispatch(cmd_buf,
FFALIGN(s->vkctx.output_width, CGROUPS[0])/CGROUPS[0],
FFALIGN(s->vkctx.output_height, CGROUPS[1])/CGROUPS[1], 1);
@ -329,14 +338,10 @@ static int process_frames(AVFilterContext *avctx, AVFrame *out_f,
if (err)
return err;
return err;
fail:
for (int i = 0; i < planes; i++) {
ff_vk_destroy_imageview(avctx, &s->main_images[i].imageView);
ff_vk_destroy_imageview(avctx, &s->overlay_images[i].imageView);
ff_vk_destroy_imageview(avctx, &s->output_images[i].imageView);
}
ff_vk_discard_exec_deps(avctx, s->exec);
return err;
}

30
libavfilter/vf_scale_vulkan.c
View File

@ -115,6 +115,10 @@ static av_cold int init_filter(AVFilterContext *ctx, AVFrame *in)
int crop_w = in->width - (in->crop_left + in->crop_right);
int crop_h = in->height - (in->crop_top + in->crop_bottom);
s->vkctx.queue_family_idx = s->vkctx.hwctx->queue_family_comp_index;
s->vkctx.queue_count = GET_QUEUE_COUNT(s->vkctx.hwctx, 0, 1, 0);
s->vkctx.cur_queue_idx = rand() % s->vkctx.queue_count;
switch (s->scaler) {
case F_NEAREST:
sampler_mode = VK_FILTER_NEAREST;
@ -276,8 +280,7 @@ static av_cold int init_filter(AVFilterContext *ctx, AVFrame *in)
}
/* Execution context */
RET(ff_vk_create_exec_ctx(ctx, &s->exec,
s->vkctx.hwctx->queue_family_comp_index));
RET(ff_vk_create_exec_ctx(ctx, &s->exec));
s->initialized = 1;
@ -290,14 +293,20 @@ fail:
static int process_frames(AVFilterContext *avctx, AVFrame *out_f, AVFrame *in_f)
{
int err = 0;
VkCommandBuffer cmd_buf;
ScaleVulkanContext *s = avctx->priv;
AVVkFrame *in = (AVVkFrame *)in_f->data[0];
AVVkFrame *out = (AVVkFrame *)out_f->data[0];
VkImageMemoryBarrier barriers[AV_NUM_DATA_POINTERS*2];
int barrier_count = 0;
/* Update descriptors and init the exec context */
ff_vk_start_exec_recording(avctx, s->exec);
cmd_buf = ff_vk_get_exec_buf(avctx, s->exec);
for (int i = 0; i < av_pix_fmt_count_planes(s->vkctx.input_format); i++) {
RET(ff_vk_create_imageview(avctx, &s->input_images[i].imageView, in->img[i],
RET(ff_vk_create_imageview(avctx, s->exec, &s->input_images[i].imageView,
in->img[i],
av_vkfmt_from_pixfmt(s->vkctx.input_format)[i],
ff_comp_identity_map));
@ -305,7 +314,8 @@ static int process_frames(AVFilterContext *avctx, AVFrame *out_f, AVFrame *in_f)
}
for (int i = 0; i < av_pix_fmt_count_planes(s->vkctx.output_format); i++) {
RET(ff_vk_create_imageview(avctx, &s->output_images[i].imageView, out->img[i],
RET(ff_vk_create_imageview(avctx, s->exec, &s->output_images[i].imageView,
out->img[i],
av_vkfmt_from_pixfmt(s->vkctx.output_format)[i],
ff_comp_identity_map));
@ -314,8 +324,6 @@ static int process_frames(AVFilterContext *avctx, AVFrame *out_f, AVFrame *in_f)
ff_vk_update_descriptor_set(avctx, s->pl, 0);
ff_vk_start_exec_recording(avctx, s->exec);
for (int i = 0; i < av_pix_fmt_count_planes(s->vkctx.input_format); i++) {
VkImageMemoryBarrier bar = {
.sType = VK_STRUCTURE_TYPE_IMAGE_MEMORY_BARRIER,
@ -358,13 +366,13 @@ static int process_frames(AVFilterContext *avctx, AVFrame *out_f, AVFrame *in_f)
out->access[i] = bar.dstAccessMask;
}
vkCmdPipelineBarrier(s->exec->buf, VK_PIPELINE_STAGE_TOP_OF_PIPE_BIT,
vkCmdPipelineBarrier(cmd_buf, VK_PIPELINE_STAGE_TOP_OF_PIPE_BIT,
VK_PIPELINE_STAGE_COMPUTE_SHADER_BIT, 0,
0, NULL, 0, NULL, barrier_count, barriers);
ff_vk_bind_pipeline_exec(avctx, s->exec, s->pl);
vkCmdDispatch(s->exec->buf,
vkCmdDispatch(cmd_buf,
FFALIGN(s->vkctx.output_width, CGROUPS[0])/CGROUPS[0],
FFALIGN(s->vkctx.output_height, CGROUPS[1])/CGROUPS[1], 1);
@ -375,12 +383,10 @@ static int process_frames(AVFilterContext *avctx, AVFrame *out_f, AVFrame *in_f)
if (err)
return err;
for (int i = 0; i < av_pix_fmt_count_planes(s->vkctx.input_format); i++)
ff_vk_destroy_imageview(avctx, &s->input_images[i].imageView);
for (int i = 0; i < av_pix_fmt_count_planes(s->vkctx.output_format); i++)
ff_vk_destroy_imageview(avctx, &s->output_images[i].imageView);
return err;
fail:
ff_vk_discard_exec_deps(avctx, s->exec);
return err;
}

298
libavfilter/vulkan.c
View File

@ -311,72 +311,116 @@ int ff_vk_add_push_constant(AVFilterContext *avctx, VulkanPipeline *pl,
}
FN_CREATING(VulkanFilterContext, FFVkExecContext, exec_ctx, exec_ctx, exec_ctx_num)
int ff_vk_create_exec_ctx(AVFilterContext *avctx, FFVkExecContext **ctx, int queue)
int ff_vk_create_exec_ctx(AVFilterContext *avctx, FFVkExecContext **ctx)
{
VkResult ret;
FFVkExecContext *e;
VulkanFilterContext *s = avctx->priv;
int queue_family = s->queue_family_idx;
int nb_queues = s->queue_count;
VkCommandPoolCreateInfo cqueue_create = {
.sType = VK_STRUCTURE_TYPE_COMMAND_POOL_CREATE_INFO,
.flags = VK_COMMAND_POOL_CREATE_RESET_COMMAND_BUFFER_BIT,
.queueFamilyIndex = queue,
.queueFamilyIndex = queue_family,
};
VkCommandBufferAllocateInfo cbuf_create = {
.sType = VK_STRUCTURE_TYPE_COMMAND_BUFFER_ALLOCATE_INFO,
.level = VK_COMMAND_BUFFER_LEVEL_PRIMARY,
.commandBufferCount = 1,
.commandBufferCount = nb_queues,
};
VkFenceCreateInfo fence_spawn = { VK_STRUCTURE_TYPE_FENCE_CREATE_INFO };
e = create_exec_ctx(s);
if (!e)
return AVERROR(ENOMEM);
e->queues = av_mallocz(nb_queues * sizeof(*e->queues));
if (!e->queues)
return AVERROR(ENOMEM);
e->bufs = av_mallocz(nb_queues * sizeof(*e->bufs));
if (!e->bufs)
return AVERROR(ENOMEM);
/* Create command pool */
ret = vkCreateCommandPool(s->hwctx->act_dev, &cqueue_create,
s->hwctx->alloc, &e->pool);
if (ret != VK_SUCCESS) {
av_log(avctx, AV_LOG_ERROR, "Command pool creation failure: %s\n",
ff_vk_ret2str(ret));
return 1;
return AVERROR_EXTERNAL;
}
cbuf_create.commandPool = e->pool;
ret = vkAllocateCommandBuffers(s->hwctx->act_dev, &cbuf_create, &e->buf);
/* Allocate command buffer */
ret = vkAllocateCommandBuffers(s->hwctx->act_dev, &cbuf_create, e->bufs);
if (ret != VK_SUCCESS) {
av_log(avctx, AV_LOG_ERROR, "Command buffer alloc failure: %s\n",
ff_vk_ret2str(ret));
return 1;
return AVERROR_EXTERNAL;
}
ret = vkCreateFence(s->hwctx->act_dev, &fence_spawn,
s->hwctx->alloc, &e->fence);
if (ret != VK_SUCCESS) {
av_log(avctx, AV_LOG_ERROR, "Failed to create frame fence: %s\n",
ff_vk_ret2str(ret));
return 1;
for (int i = 0; i < nb_queues; i++) {
FFVkQueueCtx *q = &e->queues[i];
vkGetDeviceQueue(s->hwctx->act_dev, queue_family, i, &q->queue);
}
vkGetDeviceQueue(s->hwctx->act_dev, queue, 0, &e->queue);
*ctx = e;
return 0;
}
void ff_vk_discard_exec_deps(AVFilterContext *avctx, FFVkExecContext *e)
{
VulkanFilterContext *s = avctx->priv;
FFVkQueueCtx *q = &e->queues[s->cur_queue_idx];
for (int j = 0; j < q->nb_buf_deps; j++)
av_buffer_unref(&q->buf_deps[j]);
q->nb_buf_deps = 0;
for (int j = 0; j < q->nb_frame_deps; j++)
av_frame_free(&q->frame_deps[j]);
q->nb_frame_deps = 0;
e->sem_wait_cnt = 0;
e->sem_sig_cnt = 0;
}
int ff_vk_start_exec_recording(AVFilterContext *avctx, FFVkExecContext *e)
{
VkResult ret;
VulkanFilterContext *s = avctx->priv;
FFVkQueueCtx *q = &e->queues[s->cur_queue_idx];
VkCommandBufferBeginInfo cmd_start = {
.sType = VK_STRUCTURE_TYPE_COMMAND_BUFFER_BEGIN_INFO,
.flags = VK_COMMAND_BUFFER_USAGE_ONE_TIME_SUBMIT_BIT,
};
e->sem_wait_cnt = 0;
e->sem_sig_cnt = 0;
/* Create the fence and don't wait for it initially */
if (!q->fence) {
VkFenceCreateInfo fence_spawn = {
.sType = VK_STRUCTURE_TYPE_FENCE_CREATE_INFO,
};
ret = vkCreateFence(s->hwctx->act_dev, &fence_spawn, s->hwctx->alloc,
&q->fence);
if (ret != VK_SUCCESS) {
av_log(avctx, AV_LOG_ERROR, "Failed to queue frame fence: %s\n",
ff_vk_ret2str(ret));
return AVERROR_EXTERNAL;
}
} else {
vkWaitForFences(s->hwctx->act_dev, 1, &q->fence, VK_TRUE, UINT64_MAX);
vkResetFences(s->hwctx->act_dev, 1, &q->fence);
}
ret = vkBeginCommandBuffer(e->buf, &cmd_start);
/* Discard queue dependencies */
ff_vk_discard_exec_deps(avctx, e);
ret = vkBeginCommandBuffer(e->bufs[s->cur_queue_idx], &cmd_start);
if (ret != VK_SUCCESS) {
av_log(avctx, AV_LOG_ERROR, "Failed to start command recoding: %s\n",
ff_vk_ret2str(ret));
@ -386,28 +430,43 @@ int ff_vk_start_exec_recording(AVFilterContext *avctx, FFVkExecContext *e)
return 0;
}
VkCommandBuffer ff_vk_get_exec_buf(AVFilterContext *avctx, FFVkExecContext *e)
{
VulkanFilterContext *s = avctx->priv;
return e->bufs[s->cur_queue_idx];
}
int ff_vk_add_exec_dep(AVFilterContext *avctx, FFVkExecContext *e,
AVFrame *frame, VkPipelineStageFlagBits in_wait_dst_flag)
{
AVFrame **dst;
VulkanFilterContext *s = avctx->priv;
AVVkFrame *f = (AVVkFrame *)frame->data[0];
FFVkQueueCtx *q = &e->queues[s->cur_queue_idx];
AVHWFramesContext *fc = (AVHWFramesContext *)frame->hw_frames_ctx->data;
int planes = av_pix_fmt_count_planes(fc->sw_format);
for (int i = 0; i < planes; i++) {
e->sem_wait = av_fast_realloc(e->sem_wait, &e->sem_wait_alloc,
(e->sem_wait_cnt + 1)*sizeof(*e->sem_wait));
if (!e->sem_wait)
if (!e->sem_wait) {
ff_vk_discard_exec_deps(avctx, e);
return AVERROR(ENOMEM);
}
e->sem_wait_dst = av_fast_realloc(e->sem_wait_dst, &e->sem_wait_dst_alloc,
(e->sem_wait_cnt + 1)*sizeof(*e->sem_wait_dst));
if (!e->sem_wait_dst)
if (!e->sem_wait_dst) {
ff_vk_discard_exec_deps(avctx, e);
return AVERROR(ENOMEM);
}
e->sem_sig = av_fast_realloc(e->sem_sig, &e->sem_sig_alloc,
(e->sem_sig_cnt + 1)*sizeof(*e->sem_sig));
if (!e->sem_sig)
if (!e->sem_sig) {
ff_vk_discard_exec_deps(avctx, e);
return AVERROR(ENOMEM);
}
e->sem_wait[e->sem_wait_cnt] = f->sem[i];
e->sem_wait_dst[e->sem_wait_cnt] = in_wait_dst_flag;
@ -417,6 +476,21 @@ int ff_vk_add_exec_dep(AVFilterContext *avctx, FFVkExecContext *e,
e->sem_sig_cnt++;
}
dst = av_fast_realloc(q->frame_deps, &q->frame_deps_alloc_size,
(q->nb_frame_deps + 1) * sizeof(*dst));
if (!dst) {
ff_vk_discard_exec_deps(avctx, e);
return AVERROR(ENOMEM);
}
q->frame_deps = dst;
q->frame_deps[q->nb_frame_deps] = av_frame_clone(frame);
if (!q->frame_deps[q->nb_frame_deps]) {
ff_vk_discard_exec_deps(avctx, e);
return AVERROR(ENOMEM);
}
q->nb_frame_deps++;
return 0;
}
@ -424,11 +498,12 @@ int ff_vk_submit_exec_queue(AVFilterContext *avctx, FFVkExecContext *e)
{
VkResult ret;
VulkanFilterContext *s = avctx->priv;
FFVkQueueCtx *q = &e->queues[s->cur_queue_idx];
VkSubmitInfo s_info = {
.sType = VK_STRUCTURE_TYPE_SUBMIT_INFO,
.commandBufferCount = 1,
.pCommandBuffers = &e->buf,
.pCommandBuffers = &e->bufs[s->cur_queue_idx],
.pWaitSemaphores = e->sem_wait,
.pWaitDstStageMask = e->sem_wait_dst,
@ -438,21 +513,57 @@ int ff_vk_submit_exec_queue(AVFilterContext *avctx, FFVkExecContext *e)
.signalSemaphoreCount = e->sem_sig_cnt,
};
vkEndCommandBuffer(e->buf);
ret = vkEndCommandBuffer(e->bufs[s->cur_queue_idx]);
if (ret != VK_SUCCESS) {
av_log(avctx, AV_LOG_ERROR, "Unable to finish command buffer: %s\n",
ff_vk_ret2str(ret));
return AVERROR_EXTERNAL;
}
ret = vkQueueSubmit(e->queue, 1, &s_info, e->fence);
ret = vkQueueSubmit(q->queue, 1, &s_info, q->fence);
if (ret != VK_SUCCESS) {
av_log(avctx, AV_LOG_ERROR, "Unable to submit command buffer: %s\n",
ff_vk_ret2str(ret));
return AVERROR_EXTERNAL;
}
vkWaitForFences(s->hwctx->act_dev, 1, &e->fence, VK_TRUE, UINT64_MAX);
vkResetFences(s->hwctx->act_dev, 1, &e->fence);
/* Rotate queues */
s->cur_queue_idx = (s->cur_queue_idx + 1) % s->queue_count;
return 0;
}
int ff_vk_add_dep_exec_ctx(AVFilterContext *avctx, FFVkExecContext *e,
AVBufferRef **deps, int nb_deps)
{
AVBufferRef **dst;
VulkanFilterContext *s = avctx->priv;
FFVkQueueCtx *q = &e->queues[s->cur_queue_idx];
if (!deps || !nb_deps)
return 0;
dst = av_fast_realloc(q->buf_deps, &q->buf_deps_alloc_size,
(q->nb_buf_deps + nb_deps) * sizeof(*dst));
if (!dst)
goto err;
q->buf_deps = dst;
for (int i = 0; i < nb_deps; i++) {
q->buf_deps[q->nb_buf_deps] = deps[i];
if (!q->buf_deps[q->nb_buf_deps])
goto err;
q->nb_buf_deps++;
}
return 0;
err:
ff_vk_discard_exec_deps(avctx, e);
return AVERROR(ENOMEM);
}
int ff_vk_filter_query_formats(AVFilterContext *avctx)
{
static const enum AVPixelFormat pixel_formats[] = {
@ -685,9 +796,24 @@ const char *ff_vk_shader_rep_fmt(enum AVPixelFormat pixfmt)
return high ? "rgba16f" : "rgba8";
}
int ff_vk_create_imageview(AVFilterContext *avctx, VkImageView *v, VkImage img,
VkFormat fmt, const VkComponentMapping map)
typedef struct ImageViewCtx {
VkImageView view;
} ImageViewCtx;
static void destroy_imageview(void *opaque, uint8_t *data)
{
VulkanFilterContext *s = opaque;
ImageViewCtx *iv = (ImageViewCtx *)data;
vkDestroyImageView(s->hwctx->act_dev, iv->view, s->hwctx->alloc);
av_free(iv);
}
int ff_vk_create_imageview(AVFilterContext *avctx, FFVkExecContext *e,
VkImageView *v, VkImage img, VkFormat fmt,
const VkComponentMapping map)
{
int err;
AVBufferRef *buf;
VulkanFilterContext *s = avctx->priv;
VkImageViewCreateInfo imgview_spawn = {
.sType = VK_STRUCTURE_TYPE_IMAGE_VIEW_CREATE_INFO,
@ -705,24 +831,32 @@ int ff_vk_create_imageview(AVFilterContext *avctx, VkImageView *v, VkImage img,
},
};
ImageViewCtx *iv = av_mallocz(sizeof(*iv));
VkResult ret = vkCreateImageView(s->hwctx->act_dev, &imgview_spawn,
s->hwctx->alloc, v);
s->hwctx->alloc, &iv->view);
if (ret != VK_SUCCESS) {
av_log(s, AV_LOG_ERROR, "Failed to create imageview: %s\n",
av_log(avctx, AV_LOG_ERROR, "Failed to create imageview: %s\n",
ff_vk_ret2str(ret));
return AVERROR_EXTERNAL;
}
return 0;
}
void ff_vk_destroy_imageview(AVFilterContext *avctx, VkImageView *v)
{
VulkanFilterContext *s = avctx->priv;
if (v && *v) {
vkDestroyImageView(s->hwctx->act_dev, *v, s->hwctx->alloc);
*v = NULL;
buf = av_buffer_create((uint8_t *)iv, sizeof(*iv), destroy_imageview, s, 0);
if (!buf) {
destroy_imageview(s, (uint8_t *)iv);
return AVERROR(ENOMEM);
}
/* Add to queue dependencies */
err = ff_vk_add_dep_exec_ctx(avctx, e, &buf, 1);
if (err) {
av_buffer_unref(&buf);
return err;
}
*v = iv->view;
return 0;
}
FN_CREATING(VulkanPipeline, SPIRVShader, shader, shaders, shaders_num)
@ -870,11 +1004,11 @@ int ff_vk_add_descriptor_set(AVFilterContext *avctx, VulkanPipeline *pl,
goto print;
pl->desc_layout = av_realloc_array(pl->desc_layout, sizeof(*pl->desc_layout),
pl->descriptor_sets_num + 1);
pl->desc_layout_num + 1);
if (!pl->desc_layout)
return AVERROR(ENOMEM);
layout = &pl->desc_layout[pl->descriptor_sets_num];
layout = &pl->desc_layout[pl->desc_layout_num];
memset(layout, 0, sizeof(*layout));
{ /* Create descriptor set layout descriptions */
@ -946,11 +1080,11 @@ int ff_vk_add_descriptor_set(AVFilterContext *avctx, VulkanPipeline *pl,
pl->desc_template_info = av_realloc_array(pl->desc_template_info,
sizeof(*pl->desc_template_info),
pl->descriptor_sets_num + 1);
pl->desc_layout_num + 1);
if (!pl->desc_template_info)
return AVERROR(ENOMEM);
dt = &pl->desc_template_info[pl->descriptor_sets_num];
dt = &pl->desc_template_info[pl->desc_layout_num];
memset(dt, 0, sizeof(*dt));
dt->sType = VK_STRUCTURE_TYPE_DESCRIPTOR_UPDATE_TEMPLATE_CREATE_INFO;
@ -960,13 +1094,13 @@ int ff_vk_add_descriptor_set(AVFilterContext *avctx, VulkanPipeline *pl,
dt->descriptorUpdateEntryCount = num;
}
pl->descriptor_sets_num++;
pl->desc_layout_num++;
print:
/* Write shader info */
for (int i = 0; i < num; i++) {
const struct descriptor_props *prop = &descriptor_props[desc[i].type];
GLSLA("layout (set = %i, binding = %i", pl->descriptor_sets_num - 1, i);
GLSLA("layout (set = %i, binding = %i", pl->desc_layout_num - 1, i);
if (desc[i].mem_layout)
GLSLA(", %s", desc[i].mem_layout);
@ -1004,15 +1138,17 @@ void ff_vk_update_descriptor_set(AVFilterContext *avctx, VulkanPipeline *pl,
VulkanFilterContext *s = avctx->priv;
vkUpdateDescriptorSetWithTemplate(s->hwctx->act_dev,
pl->desc_set[set_id],
pl->desc_template[set_id], s);
pl->desc_set[set_id * s->cur_queue_idx],
pl->desc_template[set_id],
s);
}
void ff_vk_update_push_exec(AVFilterContext *avctx, FFVkExecContext *e,
VkShaderStageFlagBits stage, int offset,
size_t size, void *src)
{
vkCmdPushConstants(e->buf, e->bound_pl->pipeline_layout,
VulkanFilterContext *s = avctx->priv;
vkCmdPushConstants(e->bufs[s->cur_queue_idx], e->bound_pl->pipeline_layout,
stage, offset, size, src);
}
@ -1021,6 +1157,10 @@ int ff_vk_init_pipeline_layout(AVFilterContext *avctx, VulkanPipeline *pl)
VkResult ret;
VulkanFilterContext *s = avctx->priv;
int queues_count = 1;
pl->descriptor_sets_num = pl->desc_layout_num * queues_count;
{ /* Init descriptor set pool */
VkDescriptorPoolCreateInfo pool_create_info = {
.sType = VK_STRUCTURE_TYPE_DESCRIPTOR_POOL_CREATE_INFO,
@ -1063,7 +1203,7 @@ int ff_vk_init_pipeline_layout(AVFilterContext *avctx, VulkanPipeline *pl)
{ /* Finally create the pipeline layout */
VkPipelineLayoutCreateInfo spawn_pipeline_layout = {
.sType = VK_STRUCTURE_TYPE_PIPELINE_LAYOUT_CREATE_INFO,
.setLayoutCount = pl->descriptor_sets_num,
.setLayoutCount = pl->desc_layout_num,
.pSetLayouts = pl->desc_layout,
.pushConstantRangeCount = pl->push_consts_num,
.pPushConstantRanges = pl->push_consts,
@ -1089,7 +1229,7 @@ int ff_vk_init_pipeline_layout(AVFilterContext *avctx, VulkanPipeline *pl)
/* Create update templates for the descriptor sets */
for (int i = 0; i < pl->descriptor_sets_num; i++) {
desc_template_info = &pl->desc_template_info[i];
desc_template_info = &pl->desc_template_info[i % pl->desc_layout_num];
desc_template_info->pipelineLayout = pl->pipeline_layout;
ret = vkCreateDescriptorUpdateTemplate(s->hwctx->act_dev,
desc_template_info,
@ -1153,27 +1293,53 @@ int ff_vk_init_compute_pipeline(AVFilterContext *avctx, VulkanPipeline *pl)
void ff_vk_bind_pipeline_exec(AVFilterContext *avctx, FFVkExecContext *e,
VulkanPipeline *pl)
{
vkCmdBindPipeline(e->buf, pl->bind_point, pl->pipeline);
VulkanFilterContext *s = avctx->priv;
vkCmdBindDescriptorSets(e->buf, pl->bind_point, pl->pipeline_layout, 0,
pl->descriptor_sets_num, pl->desc_set, 0, 0);
vkCmdBindPipeline(e->bufs[s->cur_queue_idx], pl->bind_point, pl->pipeline);
vkCmdBindDescriptorSets(e->bufs[s->cur_queue_idx], pl->bind_point,
pl->pipeline_layout, 0, pl->descriptor_sets_num,
pl->desc_set, 0, 0);
e->bound_pl = pl;
}
static void free_exec_ctx(VulkanFilterContext *s, FFVkExecContext *e)
{
vkDestroyFence(s->hwctx->act_dev, e->fence, s->hwctx->alloc);
/* Make sure all queues have finished executing */
for (int i = 0; i < s->queue_count; i++) {
FFVkQueueCtx *q = &e->queues[i];
if (e->buf != VK_NULL_HANDLE)
vkFreeCommandBuffers(s->hwctx->act_dev, e->pool, 1, &e->buf);
if (e->pool != VK_NULL_HANDLE)
if (q->fence) {
vkWaitForFences(s->hwctx->act_dev, 1, &q->fence, VK_TRUE, UINT64_MAX);
vkResetFences(s->hwctx->act_dev, 1, &q->fence);
}
/* Free the fence */
if (q->fence)
vkDestroyFence(s->hwctx->act_dev, q->fence, s->hwctx->alloc);
/* Free buffer dependencies */
for (int j = 0; j < q->nb_buf_deps; j++)
av_buffer_unref(&q->buf_deps[j]);
av_free(q->buf_deps);
/* Free frame dependencies */
for (int j = 0; j < q->nb_frame_deps; j++)
av_frame_free(&q->frame_deps[j]);
av_free(q->frame_deps);
}
if (e->bufs)
vkFreeCommandBuffers(s->hwctx->act_dev, e->pool, s->queue_count, e->bufs);
if (e->pool)
vkDestroyCommandPool(s->hwctx->act_dev, e->pool, s->hwctx->alloc);
av_free(e->sem_wait);
av_free(e->sem_wait_dst);
av_free(e->sem_sig);
av_freep(&e->bufs);
av_freep(&e->queues);
av_freep(&e->sem_sig);
av_freep(&e->sem_wait);
av_freep(&e->sem_wait_dst);
av_free(e);
}
@ -1191,7 +1357,7 @@ static void free_pipeline(VulkanFilterContext *s, VulkanPipeline *pl)
vkDestroyPipelineLayout(s->hwctx->act_dev, pl->pipeline_layout,
s->hwctx->alloc);
for (int i = 0; i < pl->descriptor_sets_num; i++) {
for (int i = 0; i < pl->desc_layout_num; i++) {
if (pl->desc_template && pl->desc_template[i])
vkDestroyDescriptorUpdateTemplate(s->hwctx->act_dev, pl->desc_template[i],
s->hwctx->alloc);
@ -1229,6 +1395,10 @@ void ff_vk_filter_uninit(AVFilterContext *avctx)
glslang_uninit();
for (int i = 0; i < s->exec_ctx_num; i++)
free_exec_ctx(s, s->exec_ctx[i]);
av_freep(&s->exec_ctx);
for (int i = 0; i < s->samplers_num; i++) {
vkDestroySampler(s->hwctx->act_dev, *s->samplers[i], s->hwctx->alloc);
av_free(s->samplers[i]);
@ -1239,10 +1409,6 @@ void ff_vk_filter_uninit(AVFilterContext *avctx)
free_pipeline(s, s->pipelines[i]);
av_freep(&s->pipelines);
for (int i = 0; i < s->exec_ctx_num; i++)
free_exec_ctx(s, s->exec_ctx[i]);
av_freep(&s->exec_ctx);
av_freep(&s->scratch);
s->scratch_size = 0;

74
libavfilter/vulkan.h
View File

@ -49,6 +49,17 @@
goto fail; \
} while (0)
/* Gets the queues count for a single queue family */
#define GET_QUEUE_COUNT(hwctx, graph, comp, tx) ( \
graph ? hwctx->nb_graphics_queues : \
comp ? (hwctx->nb_comp_queues ? \
hwctx->nb_comp_queues : hwctx->nb_graphics_queues) : \
tx ? (hwctx->nb_tx_queues ? hwctx->nb_tx_queues : \
(hwctx->nb_comp_queues ? \
hwctx->nb_comp_queues : hwctx->nb_graphics_queues)) : \
0 \
)
/* Useful for attaching immutable samplers to arrays */
#define DUP_SAMPLER_ARRAY4(x) (VkSampler []){ x, x, x, x, }
@ -98,6 +109,7 @@ typedef struct VulkanPipeline {
VkDescriptorPool desc_pool;
VkDescriptorSet *desc_set;
VkDescriptorUpdateTemplate *desc_template;
int desc_layout_num;
int descriptor_sets_num;
int pool_size_desc_num;
@ -106,11 +118,29 @@ typedef struct VulkanPipeline {
VkDescriptorPoolSize *pool_size_desc;
} VulkanPipeline;
typedef struct FFVkQueueCtx {
VkFence fence;
VkQueue queue;
/* Buffer dependencies */
AVBufferRef **buf_deps;
int nb_buf_deps;
int buf_deps_alloc_size;
/* Frame dependencies */
AVFrame **frame_deps;
int nb_frame_deps;
int frame_deps_alloc_size;
} FFVkQueueCtx;
typedef struct FFVkExecContext {
VkCommandPool pool;
VkCommandBuffer buf;
VkQueue queue;
VkFence fence;
VkCommandBuffer *bufs;
FFVkQueueCtx *queues;
AVBufferRef ***deps;
int *nb_deps;
int *dep_alloc_size;
VulkanPipeline *bound_pl;
@ -134,6 +164,11 @@ typedef struct VulkanFilterContext {
AVHWDeviceContext *device;
AVVulkanDeviceContext *hwctx;
/* State - mirrored with the exec ctx */
int cur_queue_idx;
int queue_family_idx;
int queue_count;
/* Properties */
int output_width;
int output_height;
@ -192,15 +227,12 @@ VkSampler *ff_vk_init_sampler(AVFilterContext *avctx, int unnorm_coords,
/**
* Create an imageview.
* Guaranteed to remain alive until the queue submission has finished executing,
* and will be destroyed after that.
*/
int ff_vk_create_imageview(AVFilterContext *avctx, VkImageView *v, VkImage img,
VkFormat fmt, const VkComponentMapping map);
/**
* Destroy an imageview. Command buffer must have completed executing, which
* ff_vk_submit_exec_queue() will ensure
*/
void ff_vk_destroy_imageview(AVFilterContext *avctx, VkImageView *v);
int ff_vk_create_imageview(AVFilterContext *avctx, FFVkExecContext *e,
VkImageView *v, VkImage img, VkFormat fmt,
const VkComponentMapping map);
/**
* Define a push constant for a given stage into a pipeline.
@ -264,7 +296,7 @@ void ff_vk_update_descriptor_set(AVFilterContext *avctx, VulkanPipeline *pl,
* Init an execution context for command recording and queue submission.
* WIll be auto-freed on uninit.
*/
int ff_vk_create_exec_ctx(AVFilterContext *avctx, FFVkExecContext **ctx, int queue);
int ff_vk_create_exec_ctx(AVFilterContext *avctx, FFVkExecContext **ctx);
/**
* Begin recording to the command buffer. Previous execution must have been
@ -288,7 +320,23 @@ void ff_vk_update_push_exec(AVFilterContext *avctx, FFVkExecContext *e,
size_t size, void *src);
/**
* Adds a frame as a queue dependency. This manages semaphore signalling.
* Gets the command buffer to use for this submission from the exe context.
*/
VkCommandBuffer ff_vk_get_exec_buf(AVFilterContext *avctx, FFVkExecContext *e);
/**
* Adds a generic AVBufferRef as a queue depenency.
*/
int ff_vk_add_dep_exec_ctx(AVFilterContext *avctx, FFVkExecContext *e,
AVBufferRef **deps, int nb_deps);
/**
* Discards all queue dependencies
*/
void ff_vk_discard_exec_deps(AVFilterContext *avctx, FFVkExecContext *e);
/**
* Adds a frame as a queue dependency. This also manages semaphore signalling.
* Must be called before submission.
*/
int ff_vk_add_exec_dep(AVFilterContext *avctx, FFVkExecContext *e,