AI/rocm-systems
2
0
Fork 0
Código Issues Pull Requests Ações Pacotes Projetos Versões Wiki Atividade
1.386 Commits 3 Branches 0 Tags
7a146c9d3db97cf116a72c751afd672bb3bd88b1
Gráfico de Commits

1386 Commits

Este Branch
Este Branch
Todos os Branches
Autor SHA1 Mensagem Data
Maneesh Gupta 7a146c9d3d Update hip_hcc packaging script 
Change-Id: I2dc96545c472942bcf2bc8a2e88735f3ba26d1e1


[ROCm/clr commit: 7f62529b1f]
 2017-02-09 20:28:28 +05:30
Maneesh Gupta 90a03f8684 Disable failing directed tests 
- hipTestDeviceSymbol
- hipTestConstant
- hipTestMallocKernel

Change-Id: Ibfe9fc0b8a59882f1de64b42e18777a7bd56ee97


[ROCm/clr commit: 6659eb8d16]
 2017-02-09 14:48:22 +05:30
Maneesh Gupta 2b6171816d Fix arch specific hcc extra libs env var 
Change-Id: I7429da2f1cb98750d6a9601e7e5bde844a098487


[ROCm/clr commit: 71363810dd]
 2017-02-09 14:38:39 +05:30
Aditya Atluri ba45e02007 added architecture specific macros 
1. Added __HIP_ARCH_GFXNUM__
2. Usage, -D__HIP_ARCH_GFX803__=1

Change-Id: I68b3a85d62cfab3a45d2b7a70cb3518ab2565236


[ROCm/clr commit: c6c90f6f5a]
 2017-02-08 19:45:32 -06:00
pensun b411549397 Add pseudo code example for hip_bugs.md 
Change-Id: Ia2af8e6165faeb3fbb81428e20d4dc5b19b2fa9e


[ROCm/clr commit: f2bfc8a405]
 2017-02-08 16:20:01 -06:00
Aditya Atluri 76a58521f5 fixed hipcc for new compiler flags 
Change-Id: I49ec059be20ff26b7482c84d91ab7a43826c6a8d


[ROCm/clr commit: 400d0d4f78]
 2017-02-08 14:06:01 -06:00
Aditya Atluri 248b42d3e3 include arch specific ir on fallback path 
Change-Id: Ib04996aae2c21eb73ef2a9f6305915e0caccd704


[ROCm/clr commit: 26b5e57cfd]
 2017-02-08 12:19:06 -06:00
Aditya Atluri 14dcdff8f4 Fixed Hawaii link issues 
1. Split hip_ir.ll to hip_hc.ll and hip_hc_gfx803.ll
 a. hip_hc.ll contains arch generic ir implementations
 b. hip_hc_gfx803.ll contains gfx803 (fiji, polaris) specific ir
2. HIPCC can now parse --amdgpu-target=*.
 a. Usage: hipcc --amdgpu-target=gfx803 --amdgpu-target=gfx701
 b. TODO: Convert to --amdgpu-target=gfx803,gfx701
3. With LLC in HCC able to generate native f16 isa, removed inline half asm math ops
4. Fixed threadfence and threadfence_block to use functions in rocdl

Change-Id: Ic9a9e3e04139b0d75d2c2a263c030ca77adc1019


[ROCm/clr commit: 60ec83c683]
 2017-02-08 12:04:05 -06:00
Evgeny Mankov 2cef50ac30 [HIPIFY] Readme.md update. 
[ROCm/clr commit: cc8a7f3d3e]
 2017-02-08 19:50:05 +03:00
Evgeny Mankov 508311dafe [HIPIFY] Readme.md update. 
+ Launching example.
+ Delimiter "--" is strongly recommended.
+ "-x cuda" option is mentioned as well.


[ROCm/clr commit: b3098091fd]
 2017-02-08 19:43:32 +03:00
Aditya Atluri d191eac0e2 Fixed HIP for C runtime 
1. fixed constant memory test
2. added runtime gcc/g++ test
3. added fix for runtime with gcc/g++

Change-Id: Ie14dad6633411b188bdeea044e140b6d5beabe16


[ROCm/clr commit: be6d01ebc3]
 2017-02-07 13:15:36 -06:00
Aditya Atluri 110303c087 fixed vector types for c 
Change-Id: I2330e976060f9a038929cd51be07ae2ee98e81ce


[ROCm/clr commit: 6d8007e28c]
 2017-02-07 11:09:54 -06:00
Rahul Garg 1b11b60e9d Command scripts for latency measurements 
Change-Id: I8c28765a09fb0358447367939de524b12699a317


[ROCm/clr commit: 73b56e690f]
 2017-02-07 15:03:46 +05:30
Maneesh Gupta c072d54c50 Disable broken test: hipC 
Change-Id: I061aa125bbdc9f14bc870266ab0735593c861903


[ROCm/clr commit: 0bef861f1a]
 2017-02-06 13:00:50 +05:30
Aditya Atluri 3937b398e9 changed __global__ attribute 
1. Moved around tests and added them to HIT

Change-Id: I5d75280c42a5af852670ebabc7305ee56721ec7b


[ROCm/clr commit: f009f3533d]
 2017-02-03 10:53:36 -06:00
Aditya Atluri f36992067b fixed symbol memcpy issue 
Change-Id: I89d7401be51d194bcbf771020ba66e3d3b6a18f8


[ROCm/clr commit: 0d4e6ae60a]
 2017-02-01 17:54:59 -06:00
Aditya Atluri 4085e01263 removed host math functions from math_functions.h 
Change-Id: I90d8784e2d6b58c6fade9f0fa12c0db3ee417d3e


[ROCm/clr commit: a5d017e406]
 2017-01-27 17:38:43 -06:00
Aditya Atluri 324409b2bb changed device code tests to work not to work as one 
Change-Id: I0eec1eab19dda3b703bc3a0d778a6bbb2802a412


[ROCm/clr commit: eee520def9]
 2017-01-27 09:20:14 -06:00
Aditya Atluri ebb51a54b9 fixed arch compiler flag 
Change-Id: I19f7a0ea513d6b8059f0c10cd0e7a5ead510e246


[ROCm/clr commit: a8c51b822b]
 2017-01-27 08:51:48 -06:00
Aditya Atluri 6c272debb9 fixed threadfence ir 
Change-Id: Ia3afb54bdb50864e678d849608d72a3c321edba1


[ROCm/clr commit: 537dc7597b]
 2017-01-27 08:42:26 -06:00
Aditya Atluri 4b732551bb fixed kernel only compilation for module api 
Change-Id: I567992fa9b87125318edba41fd82d2f7bc5504a1


[ROCm/clr commit: 33d89d06aa]
 2017-01-27 08:41:42 -06:00
Rahul Garg 24a50f7606 hipMallocArray fixes for NV path 
Change-Id: I1ca43e6bc0cd405998888005c20dfb1ea57003d5


[ROCm/clr commit: 125983eed9]
 2017-01-27 14:32:08 +05:30
pensun 41bb48dd49 more fix on hipmallocarray on NV path 
Change-Id: I890a36cab10c101f4a112bc4567f765b318d486c


[ROCm/clr commit: f18efd5d15]
 2017-01-26 12:30:52 -06:00
pensun 0ecc88bebd fix missing semicolon on NV path 
Change-Id: I3cfecb7bd534578a1f5a07ca9397092dcf01db07


[ROCm/clr commit: 42f22162e0]
 2017-01-26 11:28:15 -06:00
Ben Sander b46ee1d193 Add HIP_FAIL_SOC. 
Fail sub-optimal-copies rather than perform them slowly.
SOC occur on async copy of unpinned memory, or P2P copy between GPUs
that are not peers.


[ROCm/clr commit: 1a24178c78]
 2017-01-25 21:53:17 -06:00
Ben Sander ad2ba66ce6 Read HCC_OPT_FLUSH and optimize dispatch accordingly. 
If HCC is in this mode, we can use less aggressive flushes in some
cases.


[ROCm/clr commit: 2f7a8ec39c]
 2017-01-25 21:50:52 -06:00
Aditya Atluri 38a90f6119 added device functions header to hip_runtime.h 
Change-Id: I635931e1fbe4b7f0f64f3a126c0f1badcd6d234b


[ROCm/clr commit: 33a3ebad27]
 2017-01-25 08:14:30 -06:00
pensun 8bcdd56fa0 Add more hip_bug.md entry, regarding hang after hipLaunchKernel 
Change-Id: I5800cb627179ec0e913cd36d332fb8c2994ab71e


[ROCm/clr commit: a8fcbb2584]
 2017-01-24 22:43:25 -06:00
pensun 5d356d12de Initial commit on hip_bugs markdown doc 
Change-Id: I5a6915337b8664cfed9eaee9443c6e4406348574


[ROCm/clr commit: 24d9827688]
 2017-01-24 22:30:36 -06:00
Ben Sander 4d0c383c9c Add debug tip to docs 
[ROCm/clr commit: 73ef364c74]
 2017-01-23 22:34:41 -06:00
Ben Sander 2ea139e30f Show dynamic shared mem usage not static. 
[ROCm/clr commit: 27447f10c2]
 2017-01-23 22:34:41 -06:00
Ben Sander a55362f753 Move core env var processing to env.cpp 
[ROCm/clr commit: bc809460f5]
 2017-01-23 22:34:41 -06:00
Ben Sander 57e1efebab Add debug tips to docs 
[ROCm/clr commit: 4de3df746c]
 2017-01-23 22:34:41 -06:00
Ben Sander 948c5e013c Add debug tips to docs 
[ROCm/clr commit: fe24996326]
 2017-01-23 22:34:41 -06:00
Ben Sander 1ff12d95a6 Log error with ihipLogError. Cleans up CXL trace display. 
[ROCm/clr commit: d19c4767b7]
 2017-01-23 22:34:41 -06:00
Ben Sander 6f2a8bf97b Add HIP_IGNORE_HCC_VERSION. 
Ignores strict checking of HCC and HIP version.
Can be useful when developing new HCC code.


[ROCm/clr commit: df74158d1c]
 2017-01-23 22:34:41 -06:00
Aditya Atluri 35631ea2a2 added ir code sad u8 
Change-Id: Ie0d454b3bb9a6c9a028c091ad3aa969719b02cc9


[ROCm/clr commit: 9952117d64]
 2017-01-20 17:21:51 -06:00
Aditya Atluri 11cf5fc117 added driver_types.h and texture_types.h header files to hip 
Change-Id: Ic3b2403f07d6767dadf83d6c278fd14e87f6acdb


[ROCm/clr commit: 97315e8748]
 2017-01-20 17:09:52 -06:00
Aditya Atluri 0e061ea69a fixed hipArray issues 
1. Fixed build issues produced from previous commit
2. Create new header files to manage data structures better

Change-Id: I704d82c196c1858ed7617d76e40612eb507d2aa0


[ROCm/clr commit: 5b2d4c0e60]
 2017-01-20 16:54:48 -06:00
Aditya Atluri 5d51e1ddbd changes device functions documentation according to the supported apis 
Change-Id: I47ac6bbde11d54d8265e0d27ec8cd5da4d03eb8e


[ROCm/clr commit: 5f10a69ef7]
 2017-01-20 14:19:09 -06:00
Aditya Atluri 100ef6d9b2 added nvcc backend for hipArrays 
1. Added hip_texture.h to hip_runtime_api.h as cuda does declare array runtime apis inside cuda_runtime_api.h
2. Added nvcc backend for hipArray runtime apis
3. Didn't test on nvidia platform (should work)

Change-Id: I1a14aef41840e4f55e5535132e3443a918b55967


[ROCm/clr commit: a7fa600176]
 2017-01-20 14:11:45 -06:00
Aditya Atluri f6d09573aa added more test coverage for vector data types 
Change-Id: I9f57a8b597bd2ee4b265eadfd0859531497a6ada


[ROCm/clr commit: fd2e6ac2f0]
 2017-01-20 13:52:02 -06:00
Aditya Atluri b6f4fedaaf fixed compilation issues for vector types and math functions 
1. Added math_functions.h to hip_runtime.h
2. Changed operator overloading classifier static to static inline
3. Added vector types test for gpu
4. Seperated __host__ and __device__ for math functions in headers

Change-Id: I499862fad5d7b10da686da9011d7ecefe523f8e2


[ROCm/clr commit: 02190736e3]
 2017-01-20 09:49:11 -06:00
Ben Sander 81488d5d00 Add HIP_SYNC_HOST_ALLOC, HipReadEnv 
[ROCm/clr commit: db3f4889ca]
 2017-01-19 23:55:24 -06:00
Ben Sander 7a992b9fc3 Change ihipDeviceSetState,ihipDevice* so it doesn't log error 
Cleans up debug trace.


[ROCm/clr commit: 6de88d4293]
 2017-01-19 23:55:24 -06:00
Aditya Atluri c50f5cbd2c added operator overloading for complex data types 
Change-Id: Id96d5d000651914169f04497af6ff78ad96d846a


[ROCm/clr commit: fe5f45caaf]
 2017-01-19 15:15:25 -06:00
Ben Sander 48bd62db9a Doc update - describe debug techniques 
Also tweak sample to remove unneeded HIP_KERNEL_NAME.
Comment update


[ROCm/clr commit: ca1cef4e06]
 2017-01-19 12:40:45 -06:00
Ben Sander 3bc2e3ba02 Fix debug display for Module launch kernels 
[ROCm/clr commit: 2ffc9f4e22]
 2017-01-19 12:40:45 -06:00
Rahul Garg 707c31913d Fixed hipcommander default execution for HCSWAP-106 
Change-Id: I9fbd10dfaeeb4928b2ec23ceed131b5200a658f9


[ROCm/clr commit: aa3f278475]
 2017-01-19 15:04:32 +05:30
Aditya Atluri d84be1d089 moved half device function declarations to top of the file 
1. Moved half device functions around so that script can catch the signatures
2. Generated docs for half precision apis

Change-Id: Iee27658e3a639fdb02af135e71841dc6427f15e2


[ROCm/clr commit: 706a032a29]
 2017-01-18 15:06:18 -06:00