AI/rocm-systems
2
0
Forkuj 0
Kod Zgłoszenia Oczekujące zmiany Actions Packages Projekty Wydania Wiki Aktywność
1 384 Commity 3 Gałęzie 0 Tagi
4e9f1e8a66398209c033c5b0f10144cdbd5ebe3d
Wykres commitów

1384 Commity

This Branch
This Branch
Wszystkie gałęzie
Autor SHA1 Wiadomość Data
Maneesh Gupta 4e9f1e8a66 Fix arch specific hcc extra libs env var 
Change-Id: I7429da2f1cb98750d6a9601e7e5bde844a098487


[ROCm/hip commit: d14b239dd3]
 2017-02-09 14:38:39 +05:30
Aditya Atluri d48f7e93cc added architecture specific macros 
1. Added __HIP_ARCH_GFXNUM__
2. Usage, -D__HIP_ARCH_GFX803__=1

Change-Id: I68b3a85d62cfab3a45d2b7a70cb3518ab2565236


[ROCm/hip commit: 9a1989193a]
 2017-02-08 19:45:32 -06:00
pensun 036a95a4db Add pseudo code example for hip_bugs.md 
Change-Id: Ia2af8e6165faeb3fbb81428e20d4dc5b19b2fa9e


[ROCm/hip commit: 79978182f9]
 2017-02-08 16:20:01 -06:00
Aditya Atluri 8794954411 fixed hipcc for new compiler flags 
Change-Id: I49ec059be20ff26b7482c84d91ab7a43826c6a8d


[ROCm/hip commit: 55d92833fb]
 2017-02-08 14:06:01 -06:00
Aditya Atluri c692cd5d4a include arch specific ir on fallback path 
Change-Id: Ib04996aae2c21eb73ef2a9f6305915e0caccd704


[ROCm/hip commit: 27d2fc99ca]
 2017-02-08 12:19:06 -06:00
Aditya Atluri 82c0dcb03f 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/hip commit: 01b66dd998]
 2017-02-08 12:04:05 -06:00
Evgeny Mankov dbd5346cff [HIPIFY] Readme.md update. 
[ROCm/hip commit: 9ba480037a]
 2017-02-08 19:50:05 +03:00
Evgeny Mankov 655045d722 [HIPIFY] Readme.md update. 
+ Launching example.
+ Delimiter "--" is strongly recommended.
+ "-x cuda" option is mentioned as well.


[ROCm/hip commit: 841510481e]
 2017-02-08 19:43:32 +03:00
Aditya Atluri e0f5912899 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/hip commit: 05c8aa1cf5]
 2017-02-07 13:15:36 -06:00
Aditya Atluri 172161a5b5 fixed vector types for c 
Change-Id: I2330e976060f9a038929cd51be07ae2ee98e81ce


[ROCm/hip commit: 3664e8784f]
 2017-02-07 11:09:54 -06:00
Rahul Garg 3d04971de3 Command scripts for latency measurements 
Change-Id: I8c28765a09fb0358447367939de524b12699a317


[ROCm/hip commit: 55df1b6ff2]
 2017-02-07 15:03:46 +05:30
Maneesh Gupta 82e6141cfd Disable broken test: hipC 
Change-Id: I061aa125bbdc9f14bc870266ab0735593c861903


[ROCm/hip commit: 939909e96c]
 2017-02-06 13:00:50 +05:30
Aditya Atluri 6d5992d445 changed __global__ attribute 
1. Moved around tests and added them to HIT

Change-Id: I5d75280c42a5af852670ebabc7305ee56721ec7b


[ROCm/hip commit: 5e3d63c0a3]
 2017-02-03 10:53:36 -06:00
Aditya Atluri afb38e15de fixed symbol memcpy issue 
Change-Id: I89d7401be51d194bcbf771020ba66e3d3b6a18f8


[ROCm/hip commit: 2790e9a448]
 2017-02-01 17:54:59 -06:00
Aditya Atluri 76fa20bd89 removed host math functions from math_functions.h 
Change-Id: I90d8784e2d6b58c6fade9f0fa12c0db3ee417d3e


[ROCm/hip commit: 60013396f6]
 2017-01-27 17:38:43 -06:00
Aditya Atluri 9d445cbf35 changed device code tests to work not to work as one 
Change-Id: I0eec1eab19dda3b703bc3a0d778a6bbb2802a412


[ROCm/hip commit: 66dc2d42db]
 2017-01-27 09:20:14 -06:00
Aditya Atluri 08a67a522d fixed arch compiler flag 
Change-Id: I19f7a0ea513d6b8059f0c10cd0e7a5ead510e246


[ROCm/hip commit: b37422d30b]
 2017-01-27 08:51:48 -06:00
Aditya Atluri ad08bdcfb0 fixed threadfence ir 
Change-Id: Ia3afb54bdb50864e678d849608d72a3c321edba1


[ROCm/hip commit: f7ff199daa]
 2017-01-27 08:42:26 -06:00
Aditya Atluri a13cb5af4f fixed kernel only compilation for module api 
Change-Id: I567992fa9b87125318edba41fd82d2f7bc5504a1


[ROCm/hip commit: 6ba848a40f]
 2017-01-27 08:41:42 -06:00
Rahul Garg 1d4c0862f1 hipMallocArray fixes for NV path 
Change-Id: I1ca43e6bc0cd405998888005c20dfb1ea57003d5


[ROCm/hip commit: 3e21d55c98]
 2017-01-27 14:32:08 +05:30
pensun 58721e8b7d more fix on hipmallocarray on NV path 
Change-Id: I890a36cab10c101f4a112bc4567f765b318d486c


[ROCm/hip commit: 2e1a66103a]
 2017-01-26 12:30:52 -06:00
pensun 5eb33462b7 fix missing semicolon on NV path 
Change-Id: I3cfecb7bd534578a1f5a07ca9397092dcf01db07


[ROCm/hip commit: 8404215658]
 2017-01-26 11:28:15 -06:00
Ben Sander bf3b6354ae 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/hip commit: 0409bf639c]
 2017-01-25 21:53:17 -06:00
Ben Sander e129b09a6f Read HCC_OPT_FLUSH and optimize dispatch accordingly. 
If HCC is in this mode, we can use less aggressive flushes in some
cases.


[ROCm/hip commit: 1635b8f43f]
 2017-01-25 21:50:52 -06:00
Aditya Atluri 4395881206 added device functions header to hip_runtime.h 
Change-Id: I635931e1fbe4b7f0f64f3a126c0f1badcd6d234b


[ROCm/hip commit: d75d0596bf]
 2017-01-25 08:14:30 -06:00
pensun 716d972e53 Add more hip_bug.md entry, regarding hang after hipLaunchKernel 
Change-Id: I5800cb627179ec0e913cd36d332fb8c2994ab71e


[ROCm/hip commit: 95677edabb]
 2017-01-24 22:43:25 -06:00
pensun 90a02002c9 Initial commit on hip_bugs markdown doc 
Change-Id: I5a6915337b8664cfed9eaee9443c6e4406348574


[ROCm/hip commit: f3da91de4e]
 2017-01-24 22:30:36 -06:00
Ben Sander 0e2ccecc0b Add debug tip to docs 
[ROCm/hip commit: 9dff0782a4]
 2017-01-23 22:34:41 -06:00
Ben Sander e95ebf93b1 Show dynamic shared mem usage not static. 
[ROCm/hip commit: 813c189b33]
 2017-01-23 22:34:41 -06:00
Ben Sander 3be19a4ffa Move core env var processing to env.cpp 
[ROCm/hip commit: 0dabdeb01f]
 2017-01-23 22:34:41 -06:00
Ben Sander f9ecf383e3 Add debug tips to docs 
[ROCm/hip commit: 96eac67929]
 2017-01-23 22:34:41 -06:00
Ben Sander d1c61adcf9 Add debug tips to docs 
[ROCm/hip commit: 85d41dcd05]
 2017-01-23 22:34:41 -06:00
Ben Sander c275c0ff72 Log error with ihipLogError. Cleans up CXL trace display. 
[ROCm/hip commit: 4586091dfe]
 2017-01-23 22:34:41 -06:00
Ben Sander bda5602f06 Add HIP_IGNORE_HCC_VERSION. 
Ignores strict checking of HCC and HIP version.
Can be useful when developing new HCC code.


[ROCm/hip commit: 138cf36547]
 2017-01-23 22:34:41 -06:00
Aditya Atluri b734000109 added ir code sad u8 
Change-Id: Ie0d454b3bb9a6c9a028c091ad3aa969719b02cc9


[ROCm/hip commit: 4e3afa6514]
 2017-01-20 17:21:51 -06:00
Aditya Atluri ed03475a09 added driver_types.h and texture_types.h header files to hip 
Change-Id: Ic3b2403f07d6767dadf83d6c278fd14e87f6acdb


[ROCm/hip commit: 8ddec0426b]
 2017-01-20 17:09:52 -06:00
Aditya Atluri d48571b65b 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/hip commit: 22acd654cf]
 2017-01-20 16:54:48 -06:00
Aditya Atluri 83260101e1 changes device functions documentation according to the supported apis 
Change-Id: I47ac6bbde11d54d8265e0d27ec8cd5da4d03eb8e


[ROCm/hip commit: 7765469987]
 2017-01-20 14:19:09 -06:00
Aditya Atluri 35d8bac542 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/hip commit: b1eca6c855]
 2017-01-20 14:11:45 -06:00
Aditya Atluri 6119b9c475 added more test coverage for vector data types 
Change-Id: I9f57a8b597bd2ee4b265eadfd0859531497a6ada


[ROCm/hip commit: b134a1a640]
 2017-01-20 13:52:02 -06:00
Aditya Atluri f5e3b72d0a 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/hip commit: f537d96633]
 2017-01-20 09:49:11 -06:00
Ben Sander 7a402a7fb1 Add HIP_SYNC_HOST_ALLOC, HipReadEnv 
[ROCm/hip commit: 927ac3d81c]
 2017-01-19 23:55:24 -06:00
Ben Sander b6c7c5bd8b Change ihipDeviceSetState,ihipDevice* so it doesn't log error 
Cleans up debug trace.


[ROCm/hip commit: 8209320ef0]
 2017-01-19 23:55:24 -06:00
Aditya Atluri 584a4a10c1 added operator overloading for complex data types 
Change-Id: Id96d5d000651914169f04497af6ff78ad96d846a


[ROCm/hip commit: 6ca2b289a2]
 2017-01-19 15:15:25 -06:00
Ben Sander 5998ca2d85 Doc update - describe debug techniques 
Also tweak sample to remove unneeded HIP_KERNEL_NAME.
Comment update


[ROCm/hip commit: 1f5d16afe7]
 2017-01-19 12:40:45 -06:00
Ben Sander 93642a85c7 Fix debug display for Module launch kernels 
[ROCm/hip commit: 1c73e44ebe]
 2017-01-19 12:40:45 -06:00
Rahul Garg dc2f0fdeba Fixed hipcommander default execution for HCSWAP-106 
Change-Id: I9fbd10dfaeeb4928b2ec23ceed131b5200a658f9


[ROCm/hip commit: cc0d2a6753]
 2017-01-19 15:04:32 +05:30
Aditya Atluri 99fc61be65 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/hip commit: 56d73aaee7]
 2017-01-18 15:06:18 -06:00
Aditya Atluri 13c7583874 more clarification about using device_md_gen.py 
Change-Id: I3e207b65683f34d62be3454444ffb32f8814c0aa


[ROCm/hip commit: db99ac798b]
 2017-01-18 14:49:41 -06:00
Aditya Atluri 94da0fdcee Added script for generating math api docs 
1. Commented out unsupported device math functions
2. Moved function signatures to the top of implementation snippets
3. Added script to generate markdown documentation for device math apis
4. Added the generated file from the script which should be present everytime

Change-Id: Ic579dd8b8fdffa6e1b4d4f5f3fd8a803f4dcaac7


[ROCm/hip commit: 91ae5d6bd7]
 2017-01-18 14:40:50 -06:00