76333 Коммитов
Автор SHA1 Сообщение Дата
Vladislav Sytchenko 762d6f3212 Don't hardcode the texture read mode
The readmode needs to be inferred from the template arguments.

Change-Id: I067037035e2492a24eac47e16d4015f879be0ea7


[ROCm/clr commit: b4b05e2ab0]
2020-03-18 18:07:33 -04:00
Vladislav Sytchenko b4b05e2ab0 Don't hardcode the texture read mode
The readmode needs to be inferred from the template arguments.

Change-Id: I067037035e2492a24eac47e16d4015f879be0ea7
2020-03-18 18:07:33 -04:00
Vladislav Sytchenko 07f864f128 Don't hardcode the texture read mode
The readmode needs to be inferred from the template arguments.

Change-Id: I067037035e2492a24eac47e16d4015f879be0ea7


[ROCm/hip commit: 99e744ab4a]
2020-03-18 18:07:33 -04:00
Vladislav Sytchenko 99e744ab4a Don't hardcode the texture read mode
The readmode needs to be inferred from the template arguments.

Change-Id: I067037035e2492a24eac47e16d4015f879be0ea7
2020-03-18 18:07:33 -04:00
Vladislav Sytchenko b255d351b0 Merge "Start the lifetime of the texture reference" into amd-master-next
[ROCm/clr commit: da5f852cdd]
2020-03-18 18:07:24 -04:00
Vladislav Sytchenko da5f852cdd Merge "Start the lifetime of the texture reference" into amd-master-next 2020-03-18 18:07:24 -04:00
Vladislav Sytchenko 67e8b8bcd2 Merge "Start the lifetime of the texture reference" into amd-master-next
[ROCm/hip commit: 816a56a70b]
2020-03-18 18:07:24 -04:00
Vladislav Sytchenko 816a56a70b Merge "Start the lifetime of the texture reference" into amd-master-next 2020-03-18 18:07:24 -04:00
Divya Shikre 96259b5830 kfdtest: Provide Unique ID information.
Signed-off-by: Divya Shikre <DivyaUday.Shikre@amd.com>
Change-Id: I9a837a3d1ab38f5ad05673406874d862c9e97541
2020-03-18 15:55:59 -04:00
Divya Shikre 24a2a3295c kfdtest: Provide Unique ID information.
Signed-off-by: Divya Shikre <DivyaUday.Shikre@amd.com>
Change-Id: I9a837a3d1ab38f5ad05673406874d862c9e97541


[ROCm/ROCR-Runtime commit: 96259b5830]
2020-03-18 15:55:59 -04:00
Aaron Enye Shi 908396dca0 SWDEV-227621 - Fix OpenCL CMake Packaging
Update the packaging code to be CMake 3.5 compatible for CI. Create two
packages rocm-opencl and rocm-opencl-dev on Ubuntu and CentOS. Add
proper versioning into naming.

Change-Id: I116081b7f6f7efa4be43ab3a66e4d3bff0589298


[ROCm/clr commit: b3d035b1dc]
2020-03-18 15:22:11 -04:00
Aaron Enye Shi b3d035b1dc SWDEV-227621 - Fix OpenCL CMake Packaging
Update the packaging code to be CMake 3.5 compatible for CI. Create two
packages rocm-opencl and rocm-opencl-dev on Ubuntu and CentOS. Add
proper versioning into naming.

Change-Id: I116081b7f6f7efa4be43ab3a66e4d3bff0589298
2020-03-18 15:22:11 -04:00
Jiabao Xie 7c5db60141 Merge "Cleaned include statements and deleted unnecessary operator overloads" into amd-master-next
[ROCm/clr commit: bbfba3bae1]
2020-03-18 14:37:19 -04:00
Jiabao Xie bbfba3bae1 Merge "Cleaned include statements and deleted unnecessary operator overloads" into amd-master-next 2020-03-18 14:37:19 -04:00
Jiabao Xie c12977513d Merge "Cleaned include statements and deleted unnecessary operator overloads" into amd-master-next
[ROCm/hip commit: ae6dd6c2fc]
2020-03-18 14:37:19 -04:00
Jiabao Xie ae6dd6c2fc Merge "Cleaned include statements and deleted unnecessary operator overloads" into amd-master-next 2020-03-18 14:37:19 -04:00
kjayapra-amd 68fc604f5d SWDEV-216213 - Function to lookup module functions from COMGR.
Change-Id: I3890fb188b5b3ae44d2bb161d1b7e75228e30942


[ROCm/clr commit: d961c64b00]
2020-03-18 12:45:21 -04:00
kjayapra-amd d961c64b00 SWDEV-216213 - Function to lookup module functions from COMGR.
Change-Id: I3890fb188b5b3ae44d2bb161d1b7e75228e30942
2020-03-18 12:45:21 -04:00
rkebichi 30817d2aa7 Update merge_jsons.py
Fixed inclusion of metadata for rocminfo/hipcc_version, also fixed that no shift happens for 1st json

[ROCm/roctracer commit: 2ac70a3fb9]
2020-03-18 12:36:07 -04:00
rkebichi 2ac70a3fb9 Update merge_jsons.py
Fixed inclusion of metadata for rocminfo/hipcc_version, also fixed that no shift happens for 1st json
2020-03-18 12:36:07 -04:00
Vladislav Sytchenko 84ba26979a Start the lifetime of the texture reference
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]
2020-03-18 12:30:11 -04:00
Vladislav Sytchenko b4a0008b36 Start the lifetime of the texture reference
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
2020-03-18 12:30:11 -04:00
Vladislav Sytchenko a7ff065adc Start the lifetime of the texture reference
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/hip commit: 292d008a64]
2020-03-18 12:30:11 -04:00
Vladislav Sytchenko 292d008a64 Start the lifetime of the texture reference
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
2020-03-18 12:30:11 -04:00
Vladislav Sytchenko ebd1dec272 Add constraints to texture indirect functions
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]
2020-03-18 12:24:40 -04:00
Vladislav Sytchenko 8667e21b25 Add constraints to texture indirect functions
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
2020-03-18 12:24:40 -04:00
Vladislav Sytchenko 34bf0bd816 Add constraints to texture indirect functions
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/hip commit: 117f0ab102]
2020-03-18 12:24:40 -04:00
Vladislav Sytchenko 117f0ab102 Add constraints to texture indirect functions
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
2020-03-18 12:24:40 -04:00
Vladislav Sytchenko 8b211978a7 Add constraints to texture fetch functions
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]
2020-03-18 12:24:40 -04:00
Vladislav Sytchenko a994da8af6 Add constraints to texture fetch functions
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
2020-03-18 12:24:40 -04:00
Vladislav Sytchenko e120f9164e Add constraints to texture fetch functions
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/hip commit: ef2415edc7]
2020-03-18 12:24:40 -04:00
Vladislav Sytchenko ef2415edc7 Add constraints to texture fetch functions
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
2020-03-18 12:24:40 -04:00
Sarbojit Sarkar bfc7d1c663 Merge "[hip-vdi]Fix for TF build failure [SWDEV-225827]" into amd-master-next
[ROCm/clr commit: 4cd02f20cf]
2020-03-18 11:52:46 -04:00
Sarbojit Sarkar 4cd02f20cf Merge "[hip-vdi]Fix for TF build failure [SWDEV-225827]" into amd-master-next 2020-03-18 11:52:46 -04:00
Sarbojit Sarkar ac7f37d9c3 Merge "[hip-vdi]Fix for TF build failure [SWDEV-225827]" into amd-master-next
[ROCm/hip commit: 0a35286988]
2020-03-18 11:52:46 -04:00
Sarbojit Sarkar 0a35286988 Merge "[hip-vdi]Fix for TF build failure [SWDEV-225827]" into amd-master-next 2020-03-18 11:52:46 -04:00
Evgeny Mankov 0844a41baa Merge pull request #1955 from emankov/hipify-clang
[HIPIFY][perl] Fix missed sync with hipify-clang

[ROCm/clr commit: 01bcc0015c]
2020-03-18 14:30:11 +03:00
Evgeny Mankov 01bcc0015c Merge pull request #1955 from emankov/hipify-clang
[HIPIFY][perl] Fix missed sync with hipify-clang
2020-03-18 14:30:11 +03:00
Evgeny Mankov ac8c11974e Merge pull request #1955 from emankov/hipify-clang
[HIPIFY][perl] Fix missed sync with hipify-clang

[ROCm/hip commit: ee15f951b4]
2020-03-18 14:30:11 +03:00
Evgeny Mankov ee15f951b4 Merge pull request #1955 from emankov/hipify-clang
[HIPIFY][perl] Fix missed sync with hipify-clang
2020-03-18 14:30:11 +03:00
Evgeny Mankov 677f9a3eb7 [HIPIFY][perl] Fix missed sync with hipify-clang
[ROCm/clr commit: 758b3864b7]
2020-03-18 14:24:02 +03:00
Evgeny Mankov 758b3864b7 [HIPIFY][perl] Fix missed sync with hipify-clang 2020-03-18 14:24:02 +03:00
Evgeny Mankov 4bd8b4d462 [HIPIFY][perl] Fix missed sync with hipify-clang
[ROCm/hip commit: c9672b8de5]
2020-03-18 14:24:02 +03:00
Evgeny Mankov c9672b8de5 [HIPIFY][perl] Fix missed sync with hipify-clang 2020-03-18 14:24:02 +03:00
Evgeny Mankov 02294f492f Merge pull request #1954 from emankov/hipify-clang
[HIPIFY][SPARSE] sync with hipSPARSE's "added csrsm2" (#83)

[ROCm/clr commit: 6ce54a6e25]
2020-03-18 13:46:05 +03:00
Evgeny Mankov 6ce54a6e25 Merge pull request #1954 from emankov/hipify-clang
[HIPIFY][SPARSE] sync with hipSPARSE's "added csrsm2" (#83)
2020-03-18 13:46:05 +03:00
Evgeny Mankov bfb0e13c23 Merge pull request #1954 from emankov/hipify-clang
[HIPIFY][SPARSE] sync with hipSPARSE's "added csrsm2" (#83)

[ROCm/hip commit: 0f23a0b6db]
2020-03-18 13:46:05 +03:00
Evgeny Mankov 0f23a0b6db Merge pull request #1954 from emankov/hipify-clang
[HIPIFY][SPARSE] sync with hipSPARSE's "added csrsm2" (#83)
2020-03-18 13:46:05 +03:00
Evgeny Mankov a82c69da48 [HIPIFY][SPARSE] sync with hipSPARSE's "added csrsm2" (#83)
+ https://github.com/ROCmSoftwarePlatform/hipSPARSE/pull/83
+ Update doc and hipify-perl accordingly


[ROCm/clr commit: 126ebadcc6]
2020-03-18 13:44:50 +03:00
Evgeny Mankov 126ebadcc6 [HIPIFY][SPARSE] sync with hipSPARSE's "added csrsm2" (#83)
+ https://github.com/ROCmSoftwarePlatform/hipSPARSE/pull/83
+ Update doc and hipify-perl accordingly
2020-03-18 13:44:50 +03:00