This adds swiftshader as a dependency of Dawn, and when it is present
dawn_use_swiftshader=true will force usage of it. (due to a Vulkan
loader limitation we can't have both regular drivers and swiftshader in
the same VkInstance).
BUG=dawn:283
Change-Id: Ib94f4dcca652eb380e994f007cdcfb145b1a5102
Reviewed-on: https://dawn-review.googlesource.com/c/dawn/+/13440
Reviewed-by: Austin Eng <enga@chromium.org>
Commit-Queue: Corentin Wallez <cwallez@chromium.org>
Disabling this while refactoring how dependencies are set up to avoid
breaking various builds and rolls.
BUG=dawn:285
Change-Id: Iaca2614fb73277a1ea850f90a487693cd4c54fcb
Reviewed-on: https://dawn-review.googlesource.com/c/dawn/+/14040
Reviewed-by: Austin Eng <enga@chromium.org>
Commit-Queue: Ryan Harrison <rharrison@chromium.org>
This change adds GPU memory synchronization tests for buffer. The tests cover
data flow from render pass to compute pass via storage buffer, and vice versa.
It is the last one for the series of memory sync tests for buffer.
BUG=dawn:275
Change-Id: Ic866161cadc0fa9df4c441f3970783077f3a9bd0
Reviewed-on: https://dawn-review.googlesource.com/c/dawn/+/13921
Commit-Queue: Yunchao He <yunchao.he@intel.com>
Reviewed-by: Austin Eng <enga@chromium.org>
This patch makes the |layout| member of the Render|ComputePipelineDescriptor
optional. If it is not provided, a default layout is created from the
ShaderModules provided and used to replace the layout in the descriptor.
Then, pipeline.GetBindGroupLayout may be called to get the existing, or
the computed bind group layout. If no bind group layout exists at the
provided index, an empty bind group layout is returned.
Bug: dawn:276
Change-Id: I276ed0296a2f1f2d8131fa906a4aefe85d75b3a7
Reviewed-on: https://dawn-review.googlesource.com/c/dawn/+/13741
Commit-Queue: Austin Eng <enga@chromium.org>
Reviewed-by: Corentin Wallez <cwallez@chromium.org>
Reviewed-by: Jiawei Shao <jiawei.shao@intel.com>
The TextureComponentType and TextureViewDimension of resources in
the shader must match those in the bind group layout.
This patch also extracts the texture view dimension from the SPIRV.
Bug: dawn:202
Change-Id: Ie155f17109f4f1b5d9b386d757062ae5ffe5da67
Reviewed-on: https://dawn-review.googlesource.com/c/dawn/+/13861
Reviewed-by: Corentin Wallez <cwallez@chromium.org>
Commit-Queue: Austin Eng <enga@chromium.org>
This patch factors resource usage tracking so it is separate from
command validation, allowing the bulk of command validation to be
completely skipped.
In DrawCallPerfRun/Vulkan_DynamicPipeline_DynamicBindGroup, disabling
validation cuts roughly 74 nanoseconds (20%) of CPU time, per draw.
In DrawCallPerfRun/Vulkan_DynamicBindGroup, disabling validation
cuts roughly 35 nanoseconds (17%) of CPU time, per draw.
In DrawCallPerfRun/Vulkan_MultipleBindGroups, disabling validation
cuts roughly 45 nanoseconds (14%) of CPU time, per draw.
Bug: dawn:271
Change-Id: I517b85840ba18c6a554b83f34a1d0aef1a8c56a6
Reviewed-on: https://dawn-review.googlesource.com/c/dawn/+/13520
Commit-Queue: Austin Eng <enga@chromium.org>
Reviewed-by: Corentin Wallez <cwallez@chromium.org>
This reverts commit 1954436fe28557dab8381f5b0f8ca7d68ab091c8.
Reason for revert:
The shaderc side of this multi-patch brings in a dependency on glslang, which uses a static initializer, which chromium doesn't like.
Original change's description:
> Convert spvc build flag to a runtime toggle
>
> Also moves some of the spirv_cross code into the main library that was
> feature guarded, since spvc requires it.
>
> BUG=dawn:281
>
> Change-Id: I482d1d5a5c851956d3815bad90665c52a1ea15bb
> Reviewed-on: https://dawn-review.googlesource.com/c/dawn/+/13860
> Reviewed-by: Corentin Wallez <cwallez@chromium.org>
TBR=cwallez@chromium.org,kainino@chromium.org,enga@chromium.org,rharrison@chromium.org
Change-Id: Ia9a025fb4440c96874d1b45776a9f97023ca591d
No-Presubmit: true
No-Tree-Checks: true
No-Try: true
Bug: dawn:281
Reviewed-on: https://dawn-review.googlesource.com/c/dawn/+/13941
Reviewed-by: Ryan Harrison <rharrison@chromium.org>
Commit-Queue: Ryan Harrison <rharrison@chromium.org>
There were some missing DAWN_NATIVE_EXPORT arributes for new structures
in VulkanBackend.h which resulted in linking errors.
BUG=chromium:996470
Change-Id: I45deb56faf5fd77ecfa96ebda99d31d0109d98ec
Reviewed-on: https://dawn-review.googlesource.com/c/dawn/+/13900
Commit-Queue: Corentin Wallez <cwallez@chromium.org>
Reviewed-by: Austin Eng <enga@chromium.org>
It is invalid to specify a resolve source region on GPUs that do not
support sample positions. Instead, the entire region rect should be
set to all zeros or "empty" to always resolve the entire region.
Bug: dawn:36
Change-Id: I23575b2186bffbcb2e236988558b78f97375a126
Reviewed-on: https://dawn-review.googlesource.com/c/dawn/+/13501
Reviewed-by: Austin Eng <enga@chromium.org>
Commit-Queue: Bryan Bernhart <bryan.bernhart@intel.com>
Also moves some of the spirv_cross code into the main library that was
feature guarded, since spvc requires it.
BUG=dawn:281
Change-Id: I482d1d5a5c851956d3815bad90665c52a1ea15bb
Reviewed-on: https://dawn-review.googlesource.com/c/dawn/+/13860
Reviewed-by: Corentin Wallez <cwallez@chromium.org>
This CL implements the MemoryService for importing memory and
creating VkImages from a dma-buf handle. Under the hood, it uses the
VK_EXT_external_memory_dma_buf and
VK_EXT_image_drm_format_modifier extensions to find a memory type
that supports dma-buf import. In addition, the extensions are also
used to properly specify the stride and tiling of the dma-buf to
vkAllocateMemory and vkCreateImage.
BUG=chromium:996470
Change-Id: Ie72d73117a4cbafcb40468aab0952b783351d499
Reviewed-on: https://dawn-review.googlesource.com/c/dawn/+/13785
Commit-Queue: Brian Ho <hob@chromium.org>
Reviewed-by: Corentin Wallez <cwallez@chromium.org>
The test would previously fail because the mappedData pointer stayed
non-null which meant the spin-loop waiting for the map read callback
would exit immediately.
BUG=dawn:278
BUG=dawn:280
Change-Id: I53e5974571d7684b09903c599bb65c0d8efe4d8a
Reviewed-on: https://dawn-review.googlesource.com/c/dawn/+/13821
Reviewed-by: Yunchao He <yunchao.he@intel.com>
Reviewed-by: Austin Eng <enga@chromium.org>
Commit-Queue: Corentin Wallez <cwallez@chromium.org>
Trusted users of Dawn should be able to use it without the
overhead of command validation. This patch adds the toggle and
skips validation for object creation.
Bug: dawn:271
Change-Id: Ica9a1988177685d73e2c36e05c4d525ad1ab0fdb
Reviewed-on: https://dawn-review.googlesource.com/c/dawn/+/13802
Commit-Queue: Austin Eng <enga@chromium.org>
Reviewed-by: Jiawei Shao <jiawei.shao@intel.com>
This CL adds an API to import a dma-buf into Dawn as a WGPUTexture.
We also add a descriptor type enum to the base
ExternalImageDescriptor struct. This is because all memory import
code (e.g. MemoryService, Texture::CreateFromExternal) takes the
a base ExternalImageDescriptor as a parameter. The dma-buf external
memory and image services, however, will need to downcast to
ExternalImageDescriptorDmaBuf to access import parameters like
stride. Explicitly adding a type enum will let us more safely verify
the type before downcasting.
BUG=chromium:996470
Change-Id: I2d9883a15e9059a91f2c7bdb7a96d74373e18c56
Reviewed-on: https://dawn-review.googlesource.com/c/dawn/+/13782
Reviewed-by: Austin Eng <enga@chromium.org>
Commit-Queue: Brian Ho <hob@chromium.org>
This CL introduces SupportsCreateImage and CreateImage to the
external memory service API to provide different implementations for
creating VkImages for different types of external image handles.
While opaque FD and Zircon seem to share the same vkCreateImage
implementation, dma-buf import will require the use of the
VkImageDrmFormatModifierExplicitCreateInfoEXT [1] struct (among
other differences) with vkCreateImage.
[1] https://www.khronos.org/registry/vulkan/specs/1.1-extensions/man/html/VkImageDrmFormatModifierExplicitCreateInfoEXT.html
BUG=chromium:996470
Change-Id: I3eb11f8877d4465f5fcdd4089d5fdd8acbc1da10
Reviewed-on: https://dawn-review.googlesource.com/c/dawn/+/13781
Reviewed-by: Austin Eng <enga@chromium.org>
Commit-Queue: Brian Ho <hob@chromium.org>
This CL adds a few Vulkan extensions to be used for importing
dma-bufs as VkImages.
In particular, we need:
- VK_EXT_external_memory_dma_buf
- VK_EXT_image_drm_format_modifier
BUG=chromium:996470
Change-Id: I7a3dfd0184177c756b07613fbfe140506f54584c
Reviewed-on: https://dawn-review.googlesource.com/c/dawn/+/13783
Commit-Queue: Brian Ho <hob@chromium.org>
Reviewed-by: Austin Eng <enga@chromium.org>
When vkDestroyDebugReportCallbackEXT() is called in Backend::~Backend()
and Vulkan validation layers are in use, the variable unique_id_mapping
is referenced internally[1]. However, the variable is global[2] and it's
destructed before Backend::~Backend(), which causes a use-after-free
issue. The issue was unnoticed on Windows, but we observed the crash at
exit on Linux.
[1] 9fba37afae/layers/generated/layer_chassis_dispatch.cpp (4961)
[2] 9fba37afae/layers/generated/chassis.cpp (40)
Bug: dawn:150
Change-Id: I505373a88ef9795243dd18da9785fb49d253e498
Reviewed-on: https://dawn-review.googlesource.com/c/dawn/+/13787
Reviewed-by: Austin Eng <enga@chromium.org>
Reviewed-by: Corentin Wallez <cwallez@chromium.org>
Commit-Queue: Corentin Wallez <cwallez@chromium.org>
This CL is part of a chain of CLs that imports dma-bufs as VkImages
to support WebGPU on Chrome OS.
There are currently two steps for importing external memory into
Vulkan:
1. DeviceVk::ImportExternalImage: calls into
MemoryServiceOpaqueFD::ImportMemory which in turn calls into
vkAllocateMemory and outputs a VkDeviceMemory handle to the
imported memory.
2. TextureVk::CreateFromExternal: creates the actual TextureVk
object, creates the VkImage, and binds the VkDeviceMemory from
ImportExternalImage to the VkImage.
For dma-buf support, however, we need to re-order these two steps
because importing dma-buf memory requires a handle to the VkImage
that will alias it [1].
This CL splits these two steps into three steps to ensure we create
the VkImage first so we can use it in vkAllocateMemory:
1. TextureVk::CreateFromExternal: creates the TextureVk and
VkImage (no longer concerns itself with vkBindImageMemory).
2. DeviceVk::ImportExternalImage: now takes the VkImage as input
but is otherwise unchanged.
3. TextureVk::BindExternalMemory: calls vkBindImageMemory with
handles to VkDeviceMemory and VkImage.
[1] https://www.khronos.org/registry/vulkan/specs/1.1-extensions/man/html/VkMemoryDedicatedAllocateInfo.html
BUG=chromium:996470
Change-Id: Id2d5951e9b573af79c44ce8c63be5210a279f946
Reviewed-on: https://dawn-review.googlesource.com/c/dawn/+/13780
Commit-Queue: Brian Ho <hob@chromium.org>
Reviewed-by: Austin Eng <enga@chromium.org>
This CL adds end2end tests for memory synchronization tests for buffer.
It adds a few tests that iterate data read-add-write operations a few
times in buffer for compute and render respectively, and verifies
that data dependency among interations is well synchronized.
BUG=dawn:275
Change-Id: Idfe627e90de795d664ee64787d5c5d2bfcee676b
Reviewed-on: https://dawn-review.googlesource.com/c/dawn/+/13700
Commit-Queue: Yunchao He <yunchao.he@intel.com>
Reviewed-by: Austin Eng <enga@chromium.org>
This patch add end2end tests for map buffer twice for map read, map
write, and SetSubData.
BUG=dawn:278
Change-Id: Ibe57d7923310d2513e314fa9bf185677a706d6da
Reviewed-on: https://dawn-review.googlesource.com/c/dawn/+/13801
Commit-Queue: Yunchao He <yunchao.he@intel.com>
Reviewed-by: Austin Eng <enga@chromium.org>
This changes RefCounted to increment and decrement the refcount by steps
of 2, so that a 1 bit payload can be inlined in the refcount. This
avoids using a whole boolean + padding (4 or 8 bytes in general) to know
if objects are errors.
Fixes a longstanding optimization TODO.
BUG=dawn:105
Change-Id: I5e8f66465d23772fb6082ea3e0d5d4aba2132648
Reviewed-on: https://dawn-review.googlesource.com/c/dawn/+/13680
Commit-Queue: Corentin Wallez <cwallez@chromium.org>
Reviewed-by: Kai Ninomiya <kainino@chromium.org>
Fixes a bug where SetBindGroup command would fail to be skipped.
BUG=dawn:256
Change-Id: I9815c9d31aa88f6881274a1873cabe17379cc2e0
Reviewed-on: https://dawn-review.googlesource.com/c/dawn/+/13800
Reviewed-by: Austin Eng <enga@chromium.org>
Commit-Queue: Bryan Bernhart <bryan.bernhart@intel.com>
This seems to be a regression introduced by CL:12022, where the
previously recorded semaphores are leaked while resetting the recording
context. The Vulkan validation layers will complain about this when
running the Linux-only image wrapping tests. Also, the semaphores are
queued for deletion with the right serial now.
Bug: dawn:19, dawn:150
Change-Id: I50fd46ca9de9199b29be2f85d5e9bd7394a10f1a
Reviewed-on: https://dawn-review.googlesource.com/c/dawn/+/13420
Reviewed-by: Corentin Wallez <cwallez@chromium.org>
Reviewed-by: Kai Ninomiya <kainino@chromium.org>
Commit-Queue: Jiajie Hu <jiajie.hu@intel.com>
This CL adds end2end tests for memory synchronization tests for buffer.
It adds a few tests that write into storage buffer in compute pass,
then read via uniform binding from the same buffer in render pass.
BUG=dawn:275
Change-Id: Ic98a10aab4cdcddecd60662438d4b8bdd34fafbc
Reviewed-on: https://dawn-review.googlesource.com/c/dawn/+/13580
Commit-Queue: Yunchao He <yunchao.he@intel.com>
Reviewed-by: Austin Eng <enga@chromium.org>
Reviewed-by: Corentin Wallez <cwallez@chromium.org>
The cpu_time metric measures the amount of CPU time spent on a step.
It excludes time spent waiting for the GPU or time between frames.
Bug: dawn:208
Change-Id: I5624d45557716c02bb7da632d2347eca0b81ad41
Reviewed-on: https://dawn-review.googlesource.com/c/dawn/+/13640
Reviewed-by: Corentin Wallez <cwallez@chromium.org>
Reviewed-by: Kai Ninomiya <kainino@chromium.org>
Commit-Queue: Austin Eng <enga@chromium.org>
TerribleCommandBuffer has space for 10,000,000 bytes worth of commands. If
commands contain super large data block (e.g. setsubdata), it will
return nullptr and crash dawn wire layer.
This patch adds a large buffer to handle super large data block.
BUG=dawn:251
Change-Id: Ib007e92b5282afbb93aef63cfffe5a3965f6d5c1
Reviewed-on: https://dawn-review.googlesource.com/c/dawn/+/13040
Reviewed-by: Corentin Wallez <cwallez@chromium.org>
Reviewed-by: Austin Eng <enga@chromium.org>
Commit-Queue: Corentin Wallez <cwallez@chromium.org>
This was unnecessary verbosity. Fix this by having the ProcTable
generator using type aliases so all types appear like they have
"Base".
BUG=
Change-Id: I8c472fb924f6ce739e4e41038452381b4f727a2b
Reviewed-on: https://dawn-review.googlesource.com/c/dawn/+/13442
Commit-Queue: Corentin Wallez <cwallez@chromium.org>
Reviewed-by: Kai Ninomiya <kainino@chromium.org>
This patch adds an interface GetAdapterProperties() on Adapter which can
directly return a WGPUDeviceProperties object that includes the
information of the adapter.
BUG=chromium:996713
Change-Id: I9a7b1512d259761e198dfac3eafa718171d47241
Reviewed-on: https://dawn-review.googlesource.com/c/dawn/+/13340
Reviewed-by: Corentin Wallez <cwallez@chromium.org>
Reviewed-by: Austin Eng <enga@chromium.org>
Commit-Queue: Jiawei Shao <jiawei.shao@intel.com>
This changes the methods of Dawn's SwapChain to match webgpu.h, namely
Present() now doesn't take arguments, and GetNextTexture() is replaced
with GetCurrentTextureView().
BUG=dawn:269
Change-Id: Ia0debefb170caf799c3310b1dad5535c4c5f59ca
Reviewed-on: https://dawn-review.googlesource.com/c/dawn/+/13441
Commit-Queue: Corentin Wallez <cwallez@chromium.org>
Reviewed-by: Austin Eng <enga@chromium.org>
Uses D3D12 native render pass API when possible. On pre-RS5 builds of
Windows, Dawn will fall back to a software emulated render pass. A
toggle was added to provide test coverage to the emulated render pass
implementation and used in tests that test render pass functionality in
particular.
Bug: dawn:36
Change-Id: I297a3ec7655b68d28204db2d3ab78cb82bb4e7a5
Reviewed-on: https://dawn-review.googlesource.com/c/dawn/+/13082
Reviewed-by: Austin Eng <enga@chromium.org>
Commit-Queue: Brandon Jones <brandon1.jones@intel.com>
The Metal driver calls command buffer completion callbacks on a
separate thread so enqueueing these trace events needs to be made
thread-safe. In the future, Dawn will probably have other threads
that also require thread-safe tracing.
In this CL, each thread records trace events into its own buffer,
and all buffers concatenated when trace events are acquired.
Bug: dawn:254, dawn:208
Change-Id: I0f1abd404568d838091066a8f27a3bf98fa764b9
Reviewed-on: https://dawn-review.googlesource.com/c/dawn/+/13080
Reviewed-by: Corentin Wallez <cwallez@chromium.org>
Commit-Queue: Austin Eng <enga@chromium.org>
This patch adds validation code for shader side for readonly storage
buffer. It also adds unit tests for validation.
BUG=dawn:180
Change-Id: Ib5789381d41d77867dd6e6aa1f1ccbc8fa43a382
Reviewed-on: https://dawn-review.googlesource.com/c/dawn/+/12941
Reviewed-by: Corentin Wallez <cwallez@chromium.org>
Reviewed-by: Austin Eng <enga@chromium.org>
Commit-Queue: Yunchao He <yunchao.he@intel.com>
This patch sets proper value in a few end2end tests for BindGroup/BindGroupLayout.
It also removes unused variables in unittest test for BindGroup/BindGroupLayout.
Bug=dawn:180
Change-Id: Ie5c8b2fd8265fe90b7b54c48af48106c356564b6
Reviewed-on: https://dawn-review.googlesource.com/c/dawn/+/13300
Reviewed-by: Corentin Wallez <cwallez@chromium.org>
Reviewed-by: Austin Eng <enga@chromium.org>
Commit-Queue: Yunchao He <yunchao.he@intel.com>
Subtle change to how results are handled requiring another change.
Rolling DEPS ahead to pick up change.
Roll third_party/shaderc/ 76ee91e12..f4cf10c66 (4 commits)
76ee91e126..f4cf10c66f
$ git log 76ee91e12..f4cf10c66 --date=short --no-merges --format='%ad %ae %s'
2019-11-11 rharrison Correct Unicode issue with add_copyright.py (#876)
2019-11-08 rharrison Another major API rework (#871)
2019-11-07 rharrison Remove deprecated API elements (#870)
2019-11-07 9856269+sarahM0 Add support and unit test for OpTypeInt, OpTypePointer and OpConstant (#872)
Created with:
roll-dep third_party/shaderc
Change-Id: Ic461c3ec135d2c73ebadede62fb34c90e7961eda
Reviewed-on: https://dawn-review.googlesource.com/c/dawn/+/13380
Commit-Queue: Corentin Wallez <cwallez@chromium.org>
Reviewed-by: Corentin Wallez <cwallez@chromium.org>
ResourceAllocatorManager::DeallocateMemory was correctly invalidating the
passed in allocation object. However, since the subclass
ResourceHeapAllocation class was not overriding the Invalidate method and
clearing out the D3D12Resource pointer, the resource ended up being tied
to the lifetime of the Texture object instead of being released on Destroy.
In Chromium, this bug was particularly egregious as it meant swap chain
texture cleanup was at the whims of the Javascript garbage collector.
Bug: dawn:242
Change-Id: Ia5856c61c8d3b92a2247a9aaa5f91c5de0a99dcb
Reviewed-on: https://dawn-review.googlesource.com/c/dawn/+/13200
Commit-Queue: Rafael Cintron <rafael.cintron@microsoft.com>
Reviewed-by: Austin Eng <enga@chromium.org>
Due to a renaming/refactoring of the spvc API Dawn is currently using
a deprecated class name. Fixing this, so the deprecated APIs can be
removed.
Also including the roll to pick up the API changes.
Roll third_party/shaderc/ 0a260d789..76ee91e12 (7 commits)
0a260d789f..76ee91e126
$ git log 0a260d789..76ee91e12 --date=short --no-merges --format='%ad %ae %s'
2019-11-06 9856269+sarahM0 Fix spvc test machanism and adds unit tests for OpSource (#868)
2019-11-06 rharrison Move spirv_cross state out of result and rename opaque state handle (#865)
2019-11-05 9856269+sarahM0 Add unit test for spvcir parser (#866)
2019-11-04 rharrison Rolling 5 dependencies (#862)
2019-11-04 9856269+sarahM0 Add --emit-line-drective option (#861)
2019-11-01 9856269+sarahM0 Add spvcir unit test - OpCapability (#857)
2019-11-01 rharrison Add flag for updating invalid expecations and rewrite end logic (#856)
Created with:
roll-dep third_party/shaderc
Change-Id: I81649618da6753657ef5a7533785559c2a13c416
Reviewed-on: https://dawn-review.googlesource.com/c/dawn/+/13180
Commit-Queue: Ryan Harrison <rharrison@chromium.org>
Commit-Queue: Corentin Wallez <cwallez@chromium.org>
Reviewed-by: Austin Eng <enga@chromium.org>
Reviewed-by: Corentin Wallez <cwallez@chromium.org>
Deploy self-built Vulkan validation layers instead of system installed
one. And it will reuse third_party/angle's Vulkan validation layers if
building with chromium.
Bug: dawn:150
Change-Id: I94e26f7a152fb2a1c39bcb102d60024f4d65eee6
Reviewed-on: https://dawn-review.googlesource.com/c/dawn/+/11120
Commit-Queue: Corentin Wallez <cwallez@chromium.org>
Reviewed-by: Corentin Wallez <cwallez@chromium.org>
This is a reland of 34ac535f02fb8157fde501810ae038914d21b122
Original change's description:
> Implement readonly storage buffer - validation at API side
>
> This patch adds validation code for API side for readonly storage
> buffer. It also adds unit tests for API validation.
>
> BUG=dawn:180
>
> Change-Id: I9a97c5f3aa23e720619d138ca55d7b17f08d64c9
> Reviewed-on: https://dawn-review.googlesource.com/c/dawn/+/12620
> Reviewed-by: Austin Eng <enga@chromium.org>
> Commit-Queue: Yunchao He <yunchao.he@intel.com>
Bug: dawn:180
Change-Id: I1e107ff6168279940496317b973f2d8c7c3c6114
Reviewed-on: https://dawn-review.googlesource.com/c/dawn/+/13083
Reviewed-by: Yunchao He <yunchao.he@intel.com>
Reviewed-by: Austin Eng <enga@chromium.org>
Commit-Queue: Austin Eng <enga@chromium.org>
Enables use of 4KB resource alignments where permitted.
This saves heap memory (4KB vs 64KB per allocation) and improves re-use.
BUG=dawn:27
Change-Id: I7a0a30252f480db2d0fa7f5d949207a56e3aa2e9
Reviewed-on: https://dawn-review.googlesource.com/c/dawn/+/12900
Commit-Queue: Bryan Bernhart <bryan.bernhart@intel.com>
Reviewed-by: Corentin Wallez <cwallez@chromium.org>
