From 46d86da6300ebcd2134996c76b9238fcf8e0fb6e Mon Sep 17 00:00:00 2001 From: Niklas Haas Date: Wed, 16 Aug 2017 22:13:51 +0200 Subject: vo_opengl: refactor RA texture and buffer updates MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit - tex_uploads args are moved to a struct - the ability to directly upload texture data without going through a buffer is made explicit - the concept of buffer updates and buffer polling is made more explicit and generalized to buf_update as well (not just mapped buffers) - the ability to call tex_upload/buf_update on a tex/buf is made explicit during tex/buf creation - uploading from buffers now uses an explicit offset instead of implicitly comparing *src against buf->data, because not all buffers may actually be persistently mapped - the initial_data = immutable requirement is dropped. (May be re-added later for D3D11 if that ever becomes a thing) This change helps the vulkan abstraction immensely and also helps move common code (like the PBO pooling) out of ra_gl and into the opengl/utils.c This also technically has the side-benefit / side-constraint of using PBOs for OSD texture uploads as well, which actually seems to help performance on machines where --opengl-pbo is faster than the naive code path. Because of this, I decided to hook up the OSD code to the opengl-pbo option as well. One drawback of this refactor is that the GL_STREAM_COPY hack for texture uploads "got lost", but I think I'm happy with that going away anyway since DR almost fully deprecates it, and it's not the "right thing" anyway - but instead an nvidia-only hack to make this stuff work somewhat better on NUMA systems with discrete GPUs. Another change is that due to the way fencing works with ra_buf (we get one fence per ra_buf per upload) we have to use multiple ra_bufs instead of offsets into a shared buffer. But for OpenGL this is probably better anyway. It's possible that in future, we could support having independent “buffer slices” (each with their own fence/sync object), but this would be an optimization more than anything. I also think that we could address the underlying problem (memory closeness) differently by making the ra_vk memory allocator smart enough to chunk together allocations under the hood. --- video/out/opengl/gl_utils.h | 15 --------------- 1 file changed, 15 deletions(-) (limited to 'video/out/opengl/gl_utils.h') diff --git a/video/out/opengl/gl_utils.h b/video/out/opengl/gl_utils.h index cb7bcf34cb..306ee23f65 100644 --- a/video/out/opengl/gl_utils.h +++ b/video/out/opengl/gl_utils.h @@ -51,21 +51,6 @@ void gl_vao_draw_data(struct gl_vao *vao, GLenum prim, void *ptr, size_t num); void gl_set_debug_logger(GL *gl, struct mp_log *log); -#define NUM_PBO_BUFFERS 3 - -struct gl_pbo_upload { - GL *gl; - int index; - GLuint buffer; - size_t buffer_size; -}; - -void gl_pbo_upload_tex(struct gl_pbo_upload *pbo, GL *gl, bool use_pbo, - GLenum target, GLenum format, GLenum type, - int tex_w, int tex_h, const void *dataptr, int stride, - int x, int y, int w, int h); -void gl_pbo_upload_uninit(struct gl_pbo_upload *pbo); - int gl_get_fb_depth(GL *gl, int fbo); #endif -- cgit v1.2.3