Revīziju grafs

54851 Revīzijas

Autors SHA1 Ziņojums Datums
Maneesh Gupta b250c5a7b3 module_api: HCC path no longer needs mangled kernel name
Change-Id: I4c1cb218bfdd05c9fba57276167e3e4205b93614
2016-09-04 16:26:16 +05:30
Maneesh Gupta cdfbacb907 module_api: HCC path no longer needs mangled kernel name
Change-Id: I4c1cb218bfdd05c9fba57276167e3e4205b93614


[ROCm/clr commit: 34a3766ae3]
2016-09-04 16:26:16 +05:30
Maneesh Gupta 34a3766ae3 module_api: HCC path no longer needs mangled kernel name
Change-Id: I4c1cb218bfdd05c9fba57276167e3e4205b93614
2016-09-04 16:26:16 +05:30
Maneesh Gupta 7020584cdf module_api: HCC path no longer needs mangled kernel name
Change-Id: I4c1cb218bfdd05c9fba57276167e3e4205b93614
2016-09-04 16:26:16 +05:30
Maneesh Gupta 6ee4b53784 hip_kernel_language.md: Update documentation for kernel compilation
Change-Id: I51073363c3e8a8837c5fe2ae5a04dae0d441229e


[ROCm/clr commit: d58d796ec5]
2016-09-04 16:25:02 +05:30
Maneesh Gupta d58d796ec5 hip_kernel_language.md: Update documentation for kernel compilation
Change-Id: I51073363c3e8a8837c5fe2ae5a04dae0d441229e
2016-09-04 16:25:02 +05:30
Maneesh Gupta b8495e5961 hip_kernel_language.md: Update documentation for kernel compilation
Change-Id: I51073363c3e8a8837c5fe2ae5a04dae0d441229e
2016-09-04 16:25:02 +05:30
Maneesh Gupta 9461fc1cec hipgenisa.sh improvements
- hipgenisa now unmangles kernel names
 - hipgenisa now uses a random temporary directory

Change-Id: I1d0204336bd8042dcf3f39c8f905fcceebd6b785


[ROCm/clr commit: 2c11ce3515]
2016-09-04 16:20:49 +05:30
Maneesh Gupta 2c11ce3515 hipgenisa.sh improvements
- hipgenisa now unmangles kernel names
 - hipgenisa now uses a random temporary directory

Change-Id: I1d0204336bd8042dcf3f39c8f905fcceebd6b785
2016-09-04 16:20:49 +05:30
Maneesh Gupta fbc726d1b9 hipgenisa.sh improvements
- hipgenisa now unmangles kernel names
 - hipgenisa now uses a random temporary directory

Change-Id: I1d0204336bd8042dcf3f39c8f905fcceebd6b785
2016-09-04 16:20:49 +05:30
Maneesh Gupta c63944fc08 module_api sample: no longer need EXTERN_C workaround
Change-Id: Ida087d832df8e1f3620b38f920ec2853aad641c8
2016-09-04 13:49:43 +05:30
Maneesh Gupta b3779207c3 module_api sample: no longer need EXTERN_C workaround
Change-Id: Ida087d832df8e1f3620b38f920ec2853aad641c8


[ROCm/clr commit: 257774f8f0]
2016-09-04 13:49:43 +05:30
Maneesh Gupta 257774f8f0 module_api sample: no longer need EXTERN_C workaround
Change-Id: Ida087d832df8e1f3620b38f920ec2853aad641c8
2016-09-04 13:49:43 +05:30
Maneesh Gupta ba8a05a3c0 module_api sample: no longer need EXTERN_C workaround
Change-Id: Ida087d832df8e1f3620b38f920ec2853aad641c8
2016-09-04 13:49:43 +05:30
Maneesh Gupta c32eca602d hipgenisa.sh: handle extern C on HCC path
Change-Id: I2daf09d2cb323ab34653988b668e8bd89f6db94a


[ROCm/clr commit: 16c61fd6e2]
2016-09-04 13:48:44 +05:30
Maneesh Gupta 16c61fd6e2 hipgenisa.sh: handle extern C on HCC path
Change-Id: I2daf09d2cb323ab34653988b668e8bd89f6db94a
2016-09-04 13:48:44 +05:30
Maneesh Gupta fcd401dfb7 hipgenisa.sh: handle extern C on HCC path
Change-Id: I2daf09d2cb323ab34653988b668e8bd89f6db94a
2016-09-04 13:48:44 +05:30
foreman 79c5cc6014 P4 to Git Change 1310723 by johtaylo@johtaylo-JTBUILDER03-increment on 2016/09/04 03:00:08
SWDEV-2 - Change OpenCL version number from 2216 to 2217.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1963 edit


[ROCm/clr commit: 9951309118]
2016-09-04 03:09:27 -04:00
foreman 9951309118 P4 to Git Change 1310723 by johtaylo@johtaylo-JTBUILDER03-increment on 2016/09/04 03:00:08
SWDEV-2 - Change OpenCL version number from 2216 to 2217.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1963 edit
2016-09-04 03:09:27 -04:00
Maneesh Gupta 6618c010b5 module_api: workaround to use vcpy_kernel.cpp for NV path
Change-Id: Ib4868bf02c64070e846c19427c39289609909466
2016-09-04 12:35:08 +05:30
Maneesh Gupta 7974137a91 module_api: workaround to use vcpy_kernel.cpp for NV path
Change-Id: Ib4868bf02c64070e846c19427c39289609909466


[ROCm/clr commit: fa85974c47]
2016-09-04 12:35:08 +05:30
Maneesh Gupta fa85974c47 module_api: workaround to use vcpy_kernel.cpp for NV path
Change-Id: Ib4868bf02c64070e846c19427c39289609909466
2016-09-04 12:35:08 +05:30
Maneesh Gupta 07badd6f4e module_api: workaround to use vcpy_kernel.cpp for NV path
Change-Id: Ib4868bf02c64070e846c19427c39289609909466
2016-09-04 12:35:08 +05:30
pensun 49971e8c9e For module_api sample, use vcpy_kernel.cu to generate ptx file for NV path.
Change-Id: Id0033678834288c4eaa56b12e7d447119be99deb
2016-09-03 21:06:58 -05:00
pensun dd92a59939 For module_api sample, use vcpy_kernel.cu to generate ptx file for NV path.
Change-Id: Id0033678834288c4eaa56b12e7d447119be99deb


[ROCm/clr commit: 793dc2bce0]
2016-09-03 21:06:58 -05:00
pensun 793dc2bce0 For module_api sample, use vcpy_kernel.cu to generate ptx file for NV path.
Change-Id: Id0033678834288c4eaa56b12e7d447119be99deb
2016-09-03 21:06:58 -05:00
pensun e08f4513c1 For module_api sample, use vcpy_kernel.cu to generate ptx file for NV path.
Change-Id: Id0033678834288c4eaa56b12e7d447119be99deb
2016-09-03 21:06:58 -05:00
Sean Keely 1bc15bbf79 Switch atomic_helpers.h from C11 atomics to GCC __atomic builtins.
C11 atomics are not statically guaranteed to be lock free and so
may not be atomic with respect to atomic operations originating
outside the standard library, such as platform atomics.

C11 macros to statically discover always lock free operations
(ATOMIC_*_LOCK_FREE) do not cover uint64_t in GCC and
std::atomic<uint64_t> is not a type alias of any covered type.

All use of __atomic by atomic_helpers.h is statically checked to be
always lock free.

GCC builtin fencing does not appear to be strong enough for WC memory.
Added an option (enabled) to enforce consistency for WC memory on x64.

__sync builtin's were not used as they were declared legacy by GCC.

Added a strongly conservative option (ALWAYS_CONSERVATIVE) to enable
use of full memory fences in place of partial fences and compiler
driven processor specific optimization.

Change-Id: Id7aaaca626144070f58759f6a348cbee4612bbc0
2016-09-03 06:22:42 -04:00
Sean Keely 1306432ae1 Switch atomic_helpers.h from C11 atomics to GCC __atomic builtins.
C11 atomics are not statically guaranteed to be lock free and so
may not be atomic with respect to atomic operations originating
outside the standard library, such as platform atomics.

C11 macros to statically discover always lock free operations
(ATOMIC_*_LOCK_FREE) do not cover uint64_t in GCC and
std::atomic<uint64_t> is not a type alias of any covered type.

All use of __atomic by atomic_helpers.h is statically checked to be
always lock free.

GCC builtin fencing does not appear to be strong enough for WC memory.
Added an option (enabled) to enforce consistency for WC memory on x64.

__sync builtin's were not used as they were declared legacy by GCC.

Added a strongly conservative option (ALWAYS_CONSERVATIVE) to enable
use of full memory fences in place of partial fences and compiler
driven processor specific optimization.

Change-Id: Id7aaaca626144070f58759f6a348cbee4612bbc0


[ROCm/ROCR-Runtime commit: 1bc15bbf79]
2016-09-03 06:22:42 -04:00
foreman d318c61b0c P4 to Git Change 1310684 by johtaylo@johtaylo-JTBUILDER03-increment on 2016/09/03 03:00:09
SWDEV-2 - Change OpenCL version number from 2215 to 2216.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1962 edit


[ROCm/clr commit: d914798797]
2016-09-03 03:09:06 -04:00
foreman d914798797 P4 to Git Change 1310684 by johtaylo@johtaylo-JTBUILDER03-increment on 2016/09/03 03:00:09
SWDEV-2 - Change OpenCL version number from 2215 to 2216.

Affected files ...

... //depot/stg/opencl/drivers/opencl/runtime/utils/versions.hpp#1962 edit
2016-09-03 03:09:06 -04:00
Ben Sander b47c7dc8aa remove printf
Change-Id: I36510a7ff0425f05a6d0b9c65cda4397c9cc2d95


[ROCm/clr commit: 3c90766c70]
2016-09-02 17:50:31 -05:00
Ben Sander 3c90766c70 remove printf
Change-Id: I36510a7ff0425f05a6d0b9c65cda4397c9cc2d95
2016-09-02 17:50:31 -05:00
Ben Sander 64bc513df9 remove printf
Change-Id: I36510a7ff0425f05a6d0b9c65cda4397c9cc2d95
2016-09-02 17:50:31 -05:00
Ben Sander 2d662d866f add hipStreamQuery on nvcc, fix hipStreamWaitEvent for nvcc
[ROCm/clr commit: 9466ab4fca]
2016-09-02 17:26:16 -05:00
Ben Sander 9466ab4fca add hipStreamQuery on nvcc, fix hipStreamWaitEvent for nvcc 2016-09-02 17:26:16 -05:00
Ben Sander 1f40a73ae1 add hipStreamQuery on nvcc, fix hipStreamWaitEvent for nvcc 2016-09-02 17:26:16 -05:00
Evgeny Mankov a65cc67602 [HIPIFY] CUDA Driver API porting to HIP : populate Replacer's rules with enum members.
enum members for:
CUdevice_attribute/hipDeviceAttribute_t
CUfunc_cache/hipFuncCache
CUsharedconfig/hipSharedMemConfig


[ROCm/clr commit: 7062586103]
2016-09-02 22:23:13 +03:00
Evgeny Mankov 7062586103 [HIPIFY] CUDA Driver API porting to HIP : populate Replacer's rules with enum members.
enum members for:
CUdevice_attribute/hipDeviceAttribute_t
CUfunc_cache/hipFuncCache
CUsharedconfig/hipSharedMemConfig
2016-09-02 22:23:13 +03:00
Evgeny Mankov 8bc7aba719 [HIPIFY] CUDA Driver API porting to HIP : populate Replacer's rules with enum members.
enum members for:
CUdevice_attribute/hipDeviceAttribute_t
CUfunc_cache/hipFuncCache
CUsharedconfig/hipSharedMemConfig
2016-09-02 22:23:13 +03:00
Lan Xiao df593aa076 libhsakmt: Marketing Name and AMDName support for APUs
For APUs, use /proc/cpuinfo to get Marketing name.



Change-Id: I4a17516d26a092683f36631032be00ad44f7e7fe
Signed-off-by: Lan Xiao <Lan.Xiao@amd.com>
2016-09-02 15:16:18 -04:00
Lan Xiao a015256f33 libhsakmt: Marketing Name and AMDName support for APUs
For APUs, use /proc/cpuinfo to get Marketing name.



Change-Id: I4a17516d26a092683f36631032be00ad44f7e7fe
Signed-off-by: Lan Xiao <Lan.Xiao@amd.com>


[ROCm/ROCR-Runtime commit: df593aa076]
2016-09-02 15:16:18 -04:00
Aditya Atluri 6ca7a87e0e corrected offline kernel compilation on hipcc path
1. hipgenisa.sh now adds int main(){} during kernel compilation. User does not have to put it there
2. Renamed vcpy_isa.cpp to vcpy_kernel.cpp
3. Removed vcpy_isa.cu as the kernel code should be common for both paths
4. Changed Makefile and runkernel.cpp to work with above changes

Change-Id: I9f8c84706b44bb500bc493a68e959762b55a0142
2016-09-02 13:17:17 -05:00
Aditya Atluri d864a28183 corrected offline kernel compilation on hipcc path
1. hipgenisa.sh now adds int main(){} during kernel compilation. User does not have to put it there
2. Renamed vcpy_isa.cpp to vcpy_kernel.cpp
3. Removed vcpy_isa.cu as the kernel code should be common for both paths
4. Changed Makefile and runkernel.cpp to work with above changes

Change-Id: I9f8c84706b44bb500bc493a68e959762b55a0142


[ROCm/clr commit: 8f536d8580]
2016-09-02 13:17:17 -05:00
Aditya Atluri 8f536d8580 corrected offline kernel compilation on hipcc path
1. hipgenisa.sh now adds int main(){} during kernel compilation. User does not have to put it there
2. Renamed vcpy_isa.cpp to vcpy_kernel.cpp
3. Removed vcpy_isa.cu as the kernel code should be common for both paths
4. Changed Makefile and runkernel.cpp to work with above changes

Change-Id: I9f8c84706b44bb500bc493a68e959762b55a0142
2016-09-02 13:17:17 -05:00
Aditya Atluri 4f8c45d05a corrected offline kernel compilation on hipcc path
1. hipgenisa.sh now adds int main(){} during kernel compilation. User does not have to put it there
2. Renamed vcpy_isa.cpp to vcpy_kernel.cpp
3. Removed vcpy_isa.cu as the kernel code should be common for both paths
4. Changed Makefile and runkernel.cpp to work with above changes

Change-Id: I9f8c84706b44bb500bc493a68e959762b55a0142
2016-09-02 13:17:17 -05:00
foreman 764d09238f P4 to Git Change 1310397 by lmoriche@lmoriche_opencl_dev on 2016/09/02 13:55:00
SWDEV-101169 - Compile the PCH file from <stdin> instead of a file reference. This removes the requirement to have the original file present when using the PCH file.

Affected files ...

... //depot/stg/opencl/drivers/opencl/make/amdgcn.git/headers/build/Makefile.headers#9 edit
... //depot/stg/opencl/drivers/opencl/make/amdgcn.git/irif/build/Makefile.irif#6 edit
... //depot/stg/opencl/drivers/opencl/make/amdgcn.git/ockl/build/Makefile.ockl#7 edit
... //depot/stg/opencl/drivers/opencl/make/amdgcn.git/oclc/build/Makefile.oclc#9 edit
... //depot/stg/opencl/drivers/opencl/make/amdgcn.git/ocml/build/Makefile.ocml#7 edit
... //depot/stg/opencl/drivers/opencl/make/amdgcn.git/opencl/build/Makefile.opencl#9 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/roccompiler.cpp#14 edit


[ROCm/clr commit: 7937fd1812]
2016-09-02 14:05:40 -04:00
foreman 7937fd1812 P4 to Git Change 1310397 by lmoriche@lmoriche_opencl_dev on 2016/09/02 13:55:00
SWDEV-101169 - Compile the PCH file from <stdin> instead of a file reference. This removes the requirement to have the original file present when using the PCH file.

Affected files ...

... //depot/stg/opencl/drivers/opencl/make/amdgcn.git/headers/build/Makefile.headers#9 edit
... //depot/stg/opencl/drivers/opencl/make/amdgcn.git/irif/build/Makefile.irif#6 edit
... //depot/stg/opencl/drivers/opencl/make/amdgcn.git/ockl/build/Makefile.ockl#7 edit
... //depot/stg/opencl/drivers/opencl/make/amdgcn.git/oclc/build/Makefile.oclc#9 edit
... //depot/stg/opencl/drivers/opencl/make/amdgcn.git/ocml/build/Makefile.ocml#7 edit
... //depot/stg/opencl/drivers/opencl/make/amdgcn.git/opencl/build/Makefile.opencl#9 edit
... //depot/stg/opencl/drivers/opencl/runtime/device/rocm/roccompiler.cpp#14 edit
2016-09-02 14:05:40 -04:00
Ben Sander 512ff8ec8e Fix double-lock of stream on hipModuleLaunchKernel
Change-Id: I4ca164971c25f4eb8fbcca11d6258367bb3d2ab4
2016-09-02 12:47:49 -05:00
Ben Sander f3da27cd5a Fix double-lock of stream on hipModuleLaunchKernel
Change-Id: I4ca164971c25f4eb8fbcca11d6258367bb3d2ab4


[ROCm/clr commit: 0fdb5bf517]
2016-09-02 12:47:49 -05:00