Also make D2H and H2D keep track of the chain of events
when we need to use a different HostQueue.
Change-Id: I1c5da6ea6104b37ad7aac00f0eb8ea9371e6ba1c
[ROCm/clr commit: 2bdfc73649]
The current texture implementation is based off the one for HIP-HCC. There's a lot of problems with it - only creating images from buffers, hard coding logic and ignoring user parameters. This leads to a whole lot of UB even with simple examples (as seen with RedShift's code).
This CL is aimed to bring the HIP-VDI texture implementation closer to what is described by Cuda.
hipMemcpyAtoA() - image to image copy.
hipMemcpyHtoA()/hipMemcpyDtoA() - buffer to image copy.
hipMemcpyAtoH()/hipMemcpyAtoD() - image to buffer copy.
hipArrayCreate()/hipArray3DCreate()/hipMallocArray()/hipMalloc3DArray() - creates 1D/2D/3D/1D Array/2D Array images.
hipCreateTextureObject() - creates sampler, (optional) creates 1D/2D image from buffer, (optional) creates image views.
hipBindTexture() - creates 1D image from buffer (should create a typed buffer, however this is not compatible with HIP-HCC).
hipBindTexture2D() - creates 2D image form buffer.
hipBindTextureToArray() - creates image view.
hipTexRefSetAddress() - creates 1D image from buffer (should create a typed buffer, however this is not compatible with HIP-HCC).
hipTexRefSetAddress2D() - creates 2D image from buffer.
hipTexRefSetArray() - creates image view.
There are still a lot of TODOs in the code, here's a few important ones:
1. VDI doesn't support a lot of sampler flags.
2. VDI doesn't support device to image 2D/3D copy.
3. Mipmaps implementation is incomplete.
4. Image view implementation is incomplete.
Change-Id: Ia374ee27aa14f76451fee7667495036f4419a487
[ROCm/clr commit: f71817a342]
Review comments - generate hiprtc lib everytime when HIP_PLATFORM is hcc
Changes for hip-clang
Removing pre processor directive to simplify
Change-Id: Id38ab368362b58ee0458baeb8051fea709ae6bba
[ROCm/clr commit: 8bf287ef18]
~45% to 50% of Performance drop on rocBLAS_int8 test
Use the last command in the queue for a wait.
Add extra print information about processed commands.
Add an option to disable file location printing.
Change-Id: I4187883e1a90e571fde3128af98368108fda8785
[ROCm/clr commit: a66d09f5a3]
The current implementation of surd2D{read/write} directly addresses into
the image buffer via the hipArray::data ptr. This is incorrect to do
since we don't know the layout of the image. Also with VDI we won't have
access to the underlying image buffer.
Disable the surface api untill the device functions are switched to
using __ockl_image_{load/store}().
Change-Id: I19a33680176812d5aad3660e9045812061a1c443
[ROCm/clr commit: 8c8d963c65]
When we're aligning rowPitch to imagePitchAlignment, rowPitch is in pixels,
but imagePitchAlignment_ is bytes, so we end up overaligning the pitch.
Convert imagePitchAlignment_ to pixels before doing any logic.
Change-Id: Ia5ab9d54bed150fe974e86b060dbadc196165b29
[ROCm/clr commit: 696d00e71b]
Make __gnu_h2f_ieee and __gnu_f2h_ieee visible so that hipTestHalf
test can succeed in Clang compiler + Hcc RT.
Change-Id: I5f7d5db19e559b3b66356f0170a8dbc1e5505f3e
[ROCm/clr commit: 314766b4c2]
hip_threadfence_system passes locally with this change. This also fixes
hipHostMalloc() failures when hipHostMallocMapped flag is used.
Change-Id: Id412efe502accc7c6e7676b52c05ccb9d8fbbe67
[ROCm/clr commit: 5de65ba4a0]
Remove a workaround to CS_PARTIAL_FLUSH added in CL#1495187,
since PAL is no longer uses CS_PARTIAL_FLUSH.
Change-Id: I03edc7595459e19aad33b2b0901f0ebe4754d310
[ROCm/clr commit: 1d25343af8]
[hipclang-vdi-rocm][perf]~45% to 50% of Performance drop on
rocBLAS_int8 test
- Enable AMD_OPT_FLUSH optimization by default to match HCC
- Disable CPU writes to GPU memory on boards with large bar,
because it requires HDP flush tracking.
- Enable L2 cache on kernel arguments, because L2 will be
invalidated on memory reuse .
Change-Id: I124cf250bdd4d19c523ce542c163813828f8fbdc
[ROCm/clr commit: 374f612b7c]
Payam
Christophe Paquot
Vladislav Sytchenko
jujiang
Jatin Chaudhary
German Andryeyev
Chauncey Hui
Tao Sang
Karthik Jayaprakash
Jason Tang
agodavar
Sarbojit2019
eshcherb
Evgeny Shcherbakov