RepoMirrors/mpv
1
0
Fork 0
mirror of https://github.com/mpv-player/mpv synced 2025-01-02 04:42:10 +00:00
Code Issues Releases Wiki Activity

vo_gpu: aggressively prefer async compute

Browse Source 
On AMD devices, we only get one graphics pipe but several compute pipes
which can (in theory) run independently. As such, we should prefer
compute shaders over fragment shaders in scenarios where we expect them
to be better for parallelism.

This is amusingly trivial to do, and actually improves performance even
in a single-queue scenario.
This commit is contained in:
Niklas Haas 2017-09-24 15:21:37 +02:00 committed by Martin Herkt
parent bded247fb5
commit dcda8bd36a
3 changed files with 12 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
video/out/gpu/ra.h
View File

@ -53,6 +53,7 @@ enum {
RA_CAP_GLOBAL_UNIFORM = 1 << 8, // supports using "naked" uniforms (not UBO)
RA_CAP_GATHER = 1 << 9, // supports textureGather in GLSL
RA_CAP_FRAGCOORD = 1 << 10, // supports reading from gl_FragCoord
RA_CAP_PARALLEL_COMPUTE = 1 << 11, // supports parallel compute shaders
};
enum ra_ctype {

5
video/out/gpu/video.c
View File

@ -1237,6 +1237,11 @@ static void finish_pass_tex(struct gl_video *p, struct ra_tex **dst_tex,
return;
}
// If RA_CAP_PARALLEL_COMPUTE is set, try to prefer compute shaders
// over fragment shaders wherever possible.
if (!p->pass_compute.active && (p->ra->caps & RA_CAP_PARALLEL_COMPUTE))
pass_is_compute(p, 16, 16);
if (p->pass_compute.active) {
gl_sc_uniform_image2D_wo(p->sc, "out_image", *dst_tex);
if (!p->pass_compute.directly_writes)

7
video/out/vulkan/ra_vk.c
View File

@ -208,8 +208,13 @@ struct ra *ra_create_vk(struct mpvk_ctx *vk, struct mp_log *log)
ra->max_shmem = vk->limits.maxComputeSharedMemorySize;
ra->max_pushc_size = vk->limits.maxPushConstantsSize;
if (vk->pool_compute)
if (vk->pool_compute) {
ra->caps |= RA_CAP_COMPUTE;
// If we have more compute queues than graphics queues, we probably
// want to be using them. (This seems mostly relevant for AMD)
if (vk->pool_compute->num_queues > vk->pool_graphics->num_queues)
ra->caps |= RA_CAP_PARALLEL_COMPUTE;
}
if (!vk_setup_formats(ra))
goto error;