What Cuda refers to "linear texture memory" is the OpenCL equivalent of CL_MEM_OBJECT_IMAGE1D_BUFFER. For these types of allocations we should create a typed buffer instead of an image.
Currently there is no check in the texture fetch functions as to what kind of SRD is written into the texture object, so any kind of incorrect programming will cause the TA to hang. Fortunately for us, every one writes correct code :)
Change-Id: I80dab85a992f2c0754ebf303d40ac6b5e045c7c1
[ROCm/clr commit: 78f7954765]
These are artifacts left from HIP-HCC and now are not needed by HIP-VDI.
Change-Id: Ib25a1081fe6146c8a89659395151e9d5bdaf7519
[ROCm/clr commit: 8083935855]
Currently the texture C++ API is forwarded to the ihip*Impl() calls, which are not even a part of Cuda. These should be forwarded to their respective Cuda C APIs instead.
This change also fixes a bug with hipUnbindTexture() creating a dangling pointer.
Change-Id: Ifafc9d106855a11bec84a18ea214b3d89e39990d
[ROCm/clr commit: 53dd6b7a66]
Currently we extract the read mode from the ihip*impl() calls, which is not correct. We should be getting it from the texture itself directly.
Change-Id: Idf6449fefa395a887138a252e8ea937a6897e600
[ROCm/clr commit: 42b149fe3c]
hipBindTextureToMipmappedArray()
The texture reference needs to be passed as a constant pointer.
Change-Id: I6d31204c7f2325a5bc1e8b6e089fd9f8d21d1d78
[ROCm/clr commit: 9731b61a60]
reinterpret_cast<> doesn't create an object, so the texref is actually unitiliazed. This may lead to garbage data in some of its struct members.
Initialize it by performing a placement new. The constructer should set all of its members to default values. There's no way currently to extract the channel type, so use single channel char for now.
Change-Id: I41b305a75bb3f30130324de785099f55b3e130c7
[ROCm/clr commit: b4a0008b36]
Similar to the previous patch, this change adds type constraints to texture indirect functions. Since we don't have to deduce the return type for these, we simply just have to check if the user provided a valid channel type.
Change-Id: Ia094bd6126e01df2ea90902c9aa59cb6cfe85773
[ROCm/clr commit: 8667e21b25]
When sampling a pixel the hw always returns a float4. The type in the texture reference controls the bitcast that we perform before returning the sampled pixel. Creating a texture with an unsupported will lead to potential UB.
This change makes it so that it's only possible to use textures with a type that makes sense. Using something like texture<int, hipTextureType1D, hipReadModeNormalizedFloat> will now lead to a compilation error with a message "Invalid channel type!".
Change-Id: I7fde44cb1d4b9737e0c48c28cb59c018c59ccaa2
[ROCm/clr commit: a994da8af6]
HIP-Clang cuda_wrapper headers require clang include path before standard C++ include path.
However libc++ include path requires to be before clang include path.
To workaround this, we pass -isystem with the parent directory of clang include
path instead of the clang include path itself.
[ROCm/clr commit: 0307ae4c9a]
This PR takes ensures that the maxThreadsPerBlock returned by hipFuncGetAttributes is both a multiple of the warp size and that the register usage of the maximum block does not exceed the number of available registers.
Fixes#1662
[ROCm/clr commit: ea28d64297]
This change addresses three things.
First the available APIs are brought up to par with Cuda (missing ones are added and incorrect ones removed).
Second the size of hip/hcc_detail/texture_functions.h. Using some template magic we can bring down the code size down from ~11k lines to only ~900 lines in total.
Third this change fixes some bugs in the declaration of the texture fetch funcitons. Currently the return type for textures with read mode set to hipReadModeNormalizedFloat is not float. This causes pixel data to be lost during the bitcast when the texture pixel element size is less than the size of float.
The new headers will only be enabled for VDI to avoid breaking HCC.
Change-Id: I77cb29293fb79e55681be094c37702a48d80b64c
[ROCm/clr commit: 3d7945faae]
This is currently so buggy that it causes a runtime crash on Nvidia platfrom...
Disable the new version for hcc and vdi, header fixes are required for it to pass.
Currently tex1D<char, hipTextureType1D, hipReadModeNormalizedFloat> returns a char, when the actual sampled pixel value is a float, so the hi 3 bytes get lost.
Change-Id: I8222a4d8d1d8b101eb43f3f8dfbe4818f885f8ea
[ROCm/clr commit: 3abd89925a]
Implement _ihipGetGlobalVar() and ihipGetGlobalVar() to
get global variables.
Change-Id: I442ab6712e12306c3316f114f5dc42f6daefaad9
[ROCm/clr commit: 8e9e6a44a4]
This allows printf to work with hip-clang and HCC runtime. See comments under #1919 for a reported bug and feature request.
[ROCm/clr commit: 446a9e82e2]
GCC emits a warning about using static functions like
hipCUDAErrorTohipError inside this function, because it has an
inline directive, but it's not static. Adding static to this function
to silence warnings (and prevent potential problems in the future).
[ROCm/clr commit: dc9ecf03f8]
NVCC warned if you tried to use hipOccupancyMaxActiveBlocksPerMultiprocessor
because when passing in a device function pointer, "const void* func" was
insufficient to describe it accurately. Adding a C++ templated class type
definition for this function.
[ROCm/clr commit: 7f49e47217]
Fixes SWDEV-207362,
The output file name should not contribute to picking up the right flags for the compiler. This fix solves issues when the output has conflicting extensions which confuses hipcc to treat them as the source files and add the required flags for them.
PS: Output file refers to the file followed by -o
Example: hipcc test.o -o test.hip will add the flags for .hip compilation ignoring the fact that it is an output file
[ROCm/clr commit: 59b8dabbd0]
Query ROCr to see if we have the proper lower-level support for
cooperative groups -- GWS support through the firmware, driver,
thunk, and ROCr. ROCr does these checks for us, and presents a
query that allows us to see if GWS entries are available for use.
If so, then we have all the lower-level technologies needed, and
we should enable cooperative groups support for HIP.
[ROCm/clr commit: 35a68596f9]
Fixes SWDEV-226025,
Right now -x c++ can come before libhip_hcc.so which forces the compiler to treat libhip_hcc.so as a text file and generates a lot of gibberish unicode. This PR changes the order of flags ensuring that -x c++ and similar flags come after libhip_hcc.so
Hopefully, this will not have any negative side effect.
[ROCm/clr commit: 4a9793e2e2]
The maxSharedMemoryPerMultiProcessor attribute is meant to describe
the number of bytes of shared memory (LDS space in AMD terminology)
in each SM (CU in AMD terminology). For instance, on AMD GPUs this
is often 64KB per CU, and some Nvidia GPUs it's 96KB per SM.
This shared memory is a different address space from the normal
global memory. However, the current HIP-HCC properties fill this
in with a size that matches the totalGlboalMem property. This gives
a drastically too-high calculation for the amount of LDS space that
each CU has -- tens of GBs vs. 10s of KBs.
This patch fixes this by pulling the maxSharedMemoryPerMultiProcessor
property from the HSA pool that describes how much workgroup-local
space is available on each CU. The HSA runtime eventually pulls
this from the topology information about LDSSizeInKB, defined as
"Size of Local Data Store in Kilobytes per SIMD".
Previously, this HSA query was used to fill in the value of the
sharedMemPerBlock property. On today's AMD GPUs, we know that
the amount of LDS avaialble to the workgroup is identical to the
amount of LDS space in the CU. However, in the future this may
differ. As such, this patch changes around the order and fills
in the "PerMultiProcessor" property from the HSA query (since
what's what the query is defined to return), and then separately
fills in the "PerBlock" property as we know it.
[ROCm/clr commit: 44b16df84f]
Fix two errors in hipOccupancyMaxActiveBlocksPerMultiprocessor.
1) Fix a possible segfault if the user passed in a null pointer for
the numBlocks value.
2) Handle the situation when the user is asking for a block size
that is larger than what the target device can hold within a
single block.
[ROCm/clr commit: 6ae1b1a321]
Currently there is a clang bug on Windows causing duplicate -mllvm options in clang -cc1.
Tempoarily disable -mllvm options for HIP-Clang on Windows until the bug is fixed.
Change-Id: I3a4393ba7745989398dc6c6001722837dad18704
[ROCm/clr commit: 6b1956d139]
Vladislav Sytchenko
Jiabao Xie
Sarbojit Sarkar
Evgeny Mankov
Jatin Chaudhary
Nagy-Egri Máté Ferenc
Aryan Salmanpour
Yaxun (Sam) Liu
jglaser
Paul Fultz II
Tao Sang
Saleel Kudchadker
Jatin Chaudhary
zhaozhangjian
Sameer Sahasrabuddhe
Joseph Greathouse
Reshabh Sharma
Sarbojit2019
Maneesh Gupta