vo_gpu: vulkan: initial implementation
This time based on ra/vo_gpu. 2017 is the year of the vulkan desktop!
Current problems / limitations / improvement opportunities:
1. The swapchain/flipping code violates the vulkan spec, by assuming
that the presentation queue will be bounded (in cases where rendering
is significantly faster than vsync). But apparently, there's simply
no better way to do this right now, to the point where even the
stupid cube.c examples from LunarG etc. do it wrong.
(cf. https://github.com/KhronosGroup/Vulkan-Docs/issues/370)
2. The memory allocator could be improved. (This is a universal
constant)
3. Could explore using push descriptors instead of descriptor sets,
especially since we expect to switch descriptors semi-often for some
passes (like interpolation). Probably won't make a difference, but
the synchronization overhead might be a factor. Who knows.
4. Parallelism across frames / async transfer is not well-defined, we
either need to use a better semaphore / command buffer strategy or a
resource pooling layer to safely handle cross-frame parallelism.
(That said, I gave resource pooling a try and was not happy with the
result at all - so I'm still exploring the semaphore strategy)
5. We aggressively use pipeline barriers where events would offer a much
more fine-grained synchronization mechanism. As a result of this, we
might be suffering from GPU bubbles due to too-short dependencies on
objects. (That said, I'm also exploring the use of semaphores as a an
ordering tactic which would allow cross-frame time slicing in theory)
Some minor changes to the vo_gpu and infrastructure, but nothing
consequential.
NOTE: For safety, all use of asynchronous commands / multiple command
pools is currently disabled completely. There are some left-over relics
of this in the code (e.g. the distinction between dev_poll and
pool_poll), but that is kept in place mostly because this will be
re-extended in the future (vulkan rev 2).
The queue count is also currently capped to 1, because of the lack of
cross-frame semaphores means we need the implicit synchronization from
the same-queue semantics to guarantee a correct result.
2016-09-14 18:54:18 +00:00
|
|
|
#pragma once
|
|
|
|
|
|
|
|
#include <stdlib.h>
|
|
|
|
#include <stdio.h>
|
|
|
|
#include <stdint.h>
|
|
|
|
#include <stdbool.h>
|
|
|
|
#include <assert.h>
|
|
|
|
|
|
|
|
#include "config.h"
|
|
|
|
|
|
|
|
#include "common/common.h"
|
|
|
|
#include "common/msg.h"
|
|
|
|
|
|
|
|
// We need to define all platforms we want to support. Since we have
|
|
|
|
// our own mechanism for checking this, we re-define the right symbols
|
2017-09-16 02:46:38 +00:00
|
|
|
#if HAVE_WAYLAND
|
|
|
|
#define VK_USE_PLATFORM_WAYLAND_KHR
|
|
|
|
#endif
|
vo_gpu: vulkan: initial implementation
This time based on ra/vo_gpu. 2017 is the year of the vulkan desktop!
Current problems / limitations / improvement opportunities:
1. The swapchain/flipping code violates the vulkan spec, by assuming
that the presentation queue will be bounded (in cases where rendering
is significantly faster than vsync). But apparently, there's simply
no better way to do this right now, to the point where even the
stupid cube.c examples from LunarG etc. do it wrong.
(cf. https://github.com/KhronosGroup/Vulkan-Docs/issues/370)
2. The memory allocator could be improved. (This is a universal
constant)
3. Could explore using push descriptors instead of descriptor sets,
especially since we expect to switch descriptors semi-often for some
passes (like interpolation). Probably won't make a difference, but
the synchronization overhead might be a factor. Who knows.
4. Parallelism across frames / async transfer is not well-defined, we
either need to use a better semaphore / command buffer strategy or a
resource pooling layer to safely handle cross-frame parallelism.
(That said, I gave resource pooling a try and was not happy with the
result at all - so I'm still exploring the semaphore strategy)
5. We aggressively use pipeline barriers where events would offer a much
more fine-grained synchronization mechanism. As a result of this, we
might be suffering from GPU bubbles due to too-short dependencies on
objects. (That said, I'm also exploring the use of semaphores as a an
ordering tactic which would allow cross-frame time slicing in theory)
Some minor changes to the vo_gpu and infrastructure, but nothing
consequential.
NOTE: For safety, all use of asynchronous commands / multiple command
pools is currently disabled completely. There are some left-over relics
of this in the code (e.g. the distinction between dev_poll and
pool_poll), but that is kept in place mostly because this will be
re-extended in the future (vulkan rev 2).
The queue count is also currently capped to 1, because of the lack of
cross-frame semaphores means we need the implicit synchronization from
the same-queue semantics to guarantee a correct result.
2016-09-14 18:54:18 +00:00
|
|
|
#if HAVE_X11
|
|
|
|
#define VK_USE_PLATFORM_XLIB_KHR
|
|
|
|
#endif
|
2017-09-24 06:45:56 +00:00
|
|
|
#if HAVE_WIN32_DESKTOP
|
|
|
|
#define VK_USE_PLATFORM_WIN32_KHR
|
|
|
|
#endif
|
vo_gpu: vulkan: initial implementation
This time based on ra/vo_gpu. 2017 is the year of the vulkan desktop!
Current problems / limitations / improvement opportunities:
1. The swapchain/flipping code violates the vulkan spec, by assuming
that the presentation queue will be bounded (in cases where rendering
is significantly faster than vsync). But apparently, there's simply
no better way to do this right now, to the point where even the
stupid cube.c examples from LunarG etc. do it wrong.
(cf. https://github.com/KhronosGroup/Vulkan-Docs/issues/370)
2. The memory allocator could be improved. (This is a universal
constant)
3. Could explore using push descriptors instead of descriptor sets,
especially since we expect to switch descriptors semi-often for some
passes (like interpolation). Probably won't make a difference, but
the synchronization overhead might be a factor. Who knows.
4. Parallelism across frames / async transfer is not well-defined, we
either need to use a better semaphore / command buffer strategy or a
resource pooling layer to safely handle cross-frame parallelism.
(That said, I gave resource pooling a try and was not happy with the
result at all - so I'm still exploring the semaphore strategy)
5. We aggressively use pipeline barriers where events would offer a much
more fine-grained synchronization mechanism. As a result of this, we
might be suffering from GPU bubbles due to too-short dependencies on
objects. (That said, I'm also exploring the use of semaphores as a an
ordering tactic which would allow cross-frame time slicing in theory)
Some minor changes to the vo_gpu and infrastructure, but nothing
consequential.
NOTE: For safety, all use of asynchronous commands / multiple command
pools is currently disabled completely. There are some left-over relics
of this in the code (e.g. the distinction between dev_poll and
pool_poll), but that is kept in place mostly because this will be
re-extended in the future (vulkan rev 2).
The queue count is also currently capped to 1, because of the lack of
cross-frame semaphores means we need the implicit synchronization from
the same-queue semantics to guarantee a correct result.
2016-09-14 18:54:18 +00:00
|
|
|
|
|
|
|
#include <vulkan/vulkan.h>
|
|
|
|
|
|
|
|
// Vulkan allows the optional use of a custom allocator. We don't need one but
|
|
|
|
// mark this parameter with a better name in case we ever decide to change this
|
|
|
|
// in the future. (And to make the code more readable)
|
|
|
|
#define MPVK_ALLOCATOR NULL
|
|
|
|
|
|
|
|
// A lot of things depend on streaming resources across frames. Depending on
|
|
|
|
// how many frames we render ahead of time, we need to pick enough to avoid
|
|
|
|
// any conflicts, so make all of these tunable relative to this constant in
|
|
|
|
// order to centralize them.
|
|
|
|
#define MPVK_MAX_STREAMING_DEPTH 8
|
|
|
|
|
|
|
|
// Shared struct used to hold vulkan context information
|
|
|
|
struct mpvk_ctx {
|
|
|
|
struct mp_log *log;
|
|
|
|
VkInstance inst;
|
|
|
|
VkPhysicalDevice physd;
|
|
|
|
VkDebugReportCallbackEXT dbg;
|
|
|
|
VkDevice dev;
|
|
|
|
|
|
|
|
// Surface, must be initialized fter the context itself
|
|
|
|
VkSurfaceKHR surf;
|
|
|
|
VkSurfaceFormatKHR surf_format; // picked at surface initialization time
|
|
|
|
|
|
|
|
struct vk_malloc *alloc; // memory allocator for this device
|
|
|
|
struct vk_cmdpool *pool; // primary command pool for this device
|
|
|
|
struct vk_cmd *last_cmd; // most recently submitted command
|
2017-09-13 01:09:48 +00:00
|
|
|
struct spirv_compiler *spirv; // GLSL -> SPIR-V compiler
|
vo_gpu: vulkan: initial implementation
This time based on ra/vo_gpu. 2017 is the year of the vulkan desktop!
Current problems / limitations / improvement opportunities:
1. The swapchain/flipping code violates the vulkan spec, by assuming
that the presentation queue will be bounded (in cases where rendering
is significantly faster than vsync). But apparently, there's simply
no better way to do this right now, to the point where even the
stupid cube.c examples from LunarG etc. do it wrong.
(cf. https://github.com/KhronosGroup/Vulkan-Docs/issues/370)
2. The memory allocator could be improved. (This is a universal
constant)
3. Could explore using push descriptors instead of descriptor sets,
especially since we expect to switch descriptors semi-often for some
passes (like interpolation). Probably won't make a difference, but
the synchronization overhead might be a factor. Who knows.
4. Parallelism across frames / async transfer is not well-defined, we
either need to use a better semaphore / command buffer strategy or a
resource pooling layer to safely handle cross-frame parallelism.
(That said, I gave resource pooling a try and was not happy with the
result at all - so I'm still exploring the semaphore strategy)
5. We aggressively use pipeline barriers where events would offer a much
more fine-grained synchronization mechanism. As a result of this, we
might be suffering from GPU bubbles due to too-short dependencies on
objects. (That said, I'm also exploring the use of semaphores as a an
ordering tactic which would allow cross-frame time slicing in theory)
Some minor changes to the vo_gpu and infrastructure, but nothing
consequential.
NOTE: For safety, all use of asynchronous commands / multiple command
pools is currently disabled completely. There are some left-over relics
of this in the code (e.g. the distinction between dev_poll and
pool_poll), but that is kept in place mostly because this will be
re-extended in the future (vulkan rev 2).
The queue count is also currently capped to 1, because of the lack of
cross-frame semaphores means we need the implicit synchronization from
the same-queue semantics to guarantee a correct result.
2016-09-14 18:54:18 +00:00
|
|
|
|
|
|
|
// Cached capabilities
|
|
|
|
VkPhysicalDeviceLimits limits;
|
|
|
|
};
|