Ben Sander
ce01d26a87
Add additional controls for forcing serialization and blocking.
...
Move HIP_COHERENT_HOST_ALLOC so it is read once at init time.
Add HIP_LAUNCH_BLOCKING_KERNELS, HIP_API_BLOCKING.
Update docs on debug and chicken bits.
Conflicts:
src/hip_hcc.cpp
[ROCm/hip commit: ff2f54c1bf ]
2016-12-02 18:03:59 -06:00
Aditya Atluri
cdbc90d490
added half add and fma intrinsic
...
Change-Id: Ifa60c1a7065f524f069291bb00d987b11c836cc4
[ROCm/hip commit: 7b0650773c ]
2016-11-29 19:46:01 -06:00
pensun
cd92d2a145
Change to use produce device name by default
...
Change-Id: Ie2cee2a2e94a08b5874a2f5abee5d1ab6c9fdf47
[ROCm/hip commit: 0dfcd3e664 ]
2016-11-29 11:34:06 -06:00
Rahul Garg
a523bc5632
Added support for hipMemGetAddressRange
...
Change-Id: I99a796a4eb765152cf15a12d6a86b58684d34f50
[ROCm/hip commit: fe6ba656c9 ]
2016-11-29 22:04:09 +05:30
pensun
ab5cb4bce6
Change the parameter type of hipDeviceGetPCIBusID to char*
...
Change-Id: Ia72f403126e95f65da53208fc246f45d1417381f
[ROCm/hip commit: 2fbbf2b136 ]
2016-11-28 10:47:18 -06:00
Ben Sander
e7edba491b
Add more debug info
...
[ROCm/hip commit: ce92a53f25 ]
2016-11-26 08:56:02 -06:00
Ben Sander
1cbb76ba24
Improve docs in some places
...
Change-Id: If31e84fbf0c8595ca72edb842dce7ce47783579b
[ROCm/hip commit: dec59d9909 ]
2016-11-23 08:16:18 -06:00
Ben Sander
2693958431
Improve debug capabilities.
...
Print TID mapping at init when HIP_TRACE_API=1.
Print base host/dev info from tracker during copy.
Change-Id: I84e26d7b801567e5a91baad36126fb590920ec87
[ROCm/hip commit: b6ae6b08fb ]
2016-11-23 08:16:18 -06:00
Rahul Garg
a4123e291e
Removed nested HIP calls from hip_device functions
...
Change-Id: I18785b0ee27e32fb8950982fa5c3a64d1ae6a9b8
[ROCm/hip commit: 6a4f44bce0 ]
2016-11-23 18:37:06 +05:30
Aditya Atluri
467d8d1aea
added fast math intrinsics to HIP
...
1. Added fast math intrinsics for single precision data types
2. Added test to check the intrinsics
3. Added HIP_PRECISE_MATH macro to enable precise math on fast math
Change-Id: Iadacbb6182c31252c5e3252854372d1b80dfd27b
[ROCm/hip commit: f843928ddd ]
2016-11-22 15:26:00 -06:00
Aditya Atluri
c8071e3d84
added fast math APIs
...
1. Added fast math apis for sin, cos, tan, sincos
2. Added test for trig math functions
3. Added logarithm fast math
4. Changed how hipGetDevice, hipDeviceGetCacheConfig emit errors
Change-Id: Ie6ab594ddd5853cbe85e39a2f6d3479a807fa323
[ROCm/hip commit: 94d2115d6d ]
2016-11-22 10:20:09 -06:00
Rahul Garg
c49562d59c
Removed hsaKmtReleaseSystemProperties call
...
Change-Id: I7cb992cccf587c333f0ca0cb518409f3944bdb06
[ROCm/hip commit: 2dcf20ac6f ]
2016-11-22 06:15:35 +05:30
Aditya Atluri
a9737bd2d0
fixed error output for hipDeviceGetAttribute
...
Change-Id: I1e343a4e4e20e1a550d419f701cc1e60e9d03af4
[ROCm/hip commit: 7145ea6a4a ]
2016-11-21 18:07:01 -06:00
Aditya Atluri
75fbf16ca9
fixed compilation bugs
...
1. Texture functions are now compiling fine
2. Fixed hipFuncCache to hipFuncCache_t
Change-Id: I8f815887e4de43ee115bbaff249905b236541c39
[ROCm/hip commit: 2412c9a061 ]
2016-11-21 08:56:30 -06:00
Aditya Atluri
a5bb0c6960
Fixed hipDeviceGetCacheConfig on nvcc path
...
1. Changed test macro to emit line numbers
2. Added getcacheconfig api test for nvcc path
3. Fixed hipFuncCache_t data type
TODO: With this commit, right now there are 2 func cache datatypes
a. hipFuncCache_t for runtime API
b. hipFuncCache for driver API
Map these to a single data type
Change-Id: Ia47c9f5d7c2633638051bf17b1103048a1ede973
[ROCm/hip commit: afaa5fcf96 ]
2016-11-20 12:18:08 -06:00
Maneesh Gupta
2234b57513
Refactor for building HIP as dynamic library
...
Change-Id: I65a3d9d589c4fdbbdcf1611e5427224253be8260
[ROCm/hip commit: c0419cc749 ]
2016-11-18 14:33:20 +05:30
Aditya Atluri
7192577e38
added texture header to memory api source
...
Change-Id: I1af6d60aca5a9a9ef1cadf8c304bea892acbe061
[ROCm/hip commit: c20c524400 ]
2016-11-17 11:57:53 -06:00
Aditya Atluri
da0a8cd032
Added i8 packed math intrinsics
...
1. Added add, sub, mul packed math i8 intrinsics
2. Removed c++ packed data structures included from HCC
Change-Id: I1d109c5ce10c48b7cd3ea059478b88fc1de78499
TODO: Add better packed data structures support
[ROCm/hip commit: 12dd9df88f ]
2016-11-17 01:09:12 -06:00
Maneesh Gupta
c7f6ddd612
Enable USE_COPY_EXT_V2 by default
...
Change-Id: I2c0dc80f85a0ccb5744715b5418a604e38b249ed
[ROCm/hip commit: 888a3528d2 ]
2016-11-15 10:42:27 +05:30
pensun
a446102fcc
Add direct test case for threadfence_system workaround
...
Change-Id: I5b21b590e957c901044741ac94e816cd8b1426f9
[ROCm/hip commit: 50867efa10 ]
2016-11-11 15:09:43 -06:00
Aditya Atluri
96f7a083c9
fixed multi-dim module kernel launch
...
Change-Id: Id1d81f2375d058979ab526433f905cf0ea3d23d6
[ROCm/hip commit: abf6872b2b ]
2016-11-11 12:25:23 -06:00
Ben Sander
1c7e71e1b3
Add option to deny peer access.
...
Also fix test.
Change-Id: I1b247f6c4271442b008e560669bca4daf8eb94c7
[ROCm/hip commit: 1e5515ee9f ]
2016-11-10 23:12:48 -06:00
Ben Sander
99ce555300
Use forceUnpinnedCopy to resolve P2p corner cases.
...
Change-Id: I2aebb419881246cebb696bec87798635bc71acc2
[ROCm/hip commit: 65584e48de ]
2016-11-10 23:12:48 -06:00
Ben Sander
9828c7e51c
Enable async copy again.
...
Also add HIP_FORCE_SYNC_COPY chicken bit.
Change-Id: I76a385410494b99bf27305d3c08f55dd81987565
[ROCm/hip commit: d3d6feb4de ]
2016-11-10 23:12:48 -06:00
Ben Sander
e0ef3bb319
Refactor copy and P2P logic.
...
Prefer use of source-engine for DMA copies, even if user submits copy
in a stream attached to a different device.
The stream is now used only for synchronization, and HIP
makes the most optimal decision for which engine to perform the
copy - typically the source copy engine.
HIP now makes decision on which engine should perform the copy
and passes this to HCC using new apis.
HIP has additional information about peer
visibility and will make a decision which agent should perform
the copy .
Change-Id: I0cf4cfebeae256e6ca795f08a7ed7130f4857d1f
[ROCm/hip commit: ced9d72d94 ]
2016-11-10 23:12:48 -06:00
Ben Sander
67a305ec9e
Improve memory debug
...
Change-Id: I0f033139aa4e4b47039eb016e404009127bd0a44
[ROCm/hip commit: 2dea3a0b1a ]
2016-11-10 23:12:48 -06:00
pensun
bbd526b7e5
resolve conflicts for git pull
...
Change-Id: Ie353b831e2241bc28042069b6cc7405257e871e1
[ROCm/hip commit: 4d7ac1e091 ]
2016-11-09 21:38:43 -06:00
pensun
74b0840cc6
Add option to alloc fingrained system memory
...
Change-Id: Ia13c8e058cb988b5857e75a590a4d67411362ae1
[ROCm/hip commit: f7e9f12bf1 ]
2016-11-09 21:36:30 -06:00
Ben Sander
56cd9ce82f
Improve Peer support and testing.
...
Change-Id: Icadc65988aaf145a265587ab0357c5bf4d26f3eb
[ROCm/hip commit: d728819d17 ]
2016-11-06 03:22:36 -06:00
Ben Sander
2a9aa89491
Set forceHostCopyEngine for other copy dirs. Support HIP_FORCE_P2P_HOST
...
Also: more debug for copy and P2p.
Change-Id: I87030c525410e041b2a00baaf6c68e6c0977ff42
[ROCm/hip commit: 092b3dacda ]
2016-11-04 19:53:23 -05:00
Ben Sander
fe1d895f07
Refactor resolve-mem step1
...
Change-Id: I7b8b2bbb56d7b31a97b48ebd42002641cd07a460
[ROCm/hip commit: 5d79384832 ]
2016-11-04 09:37:56 -05:00
Ben Sander
1e5540e07f
Add debug for Peer APIs. Enable PeerMemcpy APIs by default.
...
Change-Id: I46e39a9e7b07686a78484c1f3b5495b08e052fbb
[ROCm/hip commit: 3f0a2b8dc1 ]
2016-11-04 08:51:16 -05:00
Aditya Atluri
42130918bb
added inter thread data movement intrinsics
...
Change-Id: I2a8a8ed49429cb7f96439bd28c4b83b5142737df
[ROCm/hip commit: f48c53534e ]
2016-11-01 16:37:33 -05:00
Rahul Garg
0aa4468ac3
Added hipDeviceGetByPCIBusId in hip/hcc path
...
Change-Id: I3cca0dc533d0281689d8a407c7da16ca1ba6a3a8
[ROCm/hip commit: 2d15d0741c ]
2016-11-01 10:57:48 +05:30
Ben Sander
22b87992cf
Print short hipLaunchKernel correctly.
...
Change-Id: I6ca03d7c707cd03d6982199830213953d5855f17
[ROCm/hip commit: 024d9ab090 ]
2016-10-27 23:09:32 -05:00
Ben Sander
2cfd770f1b
Add initial hipProfileStart/Stop
...
And modify sample to show how to use.
Still needs some work to understand interaction with CXL.
Change-Id: I2579824d2dd7863ea23874d34f0dabb3cb305d3e
[ROCm/hip commit: bb58f4f6fc ]
2016-10-27 23:09:32 -05:00
Ben Sander
9022f04992
Add two levels of HIP_PROFILE_API (1=short,2=long)
...
Change-Id: I7ef98589f8731fb879db109fd573c62b489f2b61
[ROCm/hip commit: ef8eac9b66 ]
2016-10-27 23:09:31 -05:00
Ben Sander
591f91f2da
Fix scoped marker so begin/end ATP timestamps correct
...
Change-Id: Ic944d3fc00d7bc31b756c0e6c327b99eb489537e
[ROCm/hip commit: ab1836544a ]
2016-10-27 23:09:31 -05:00
Ben Sander
0845025a21
Rename HIP_ATP_MARKER and profiling vars
...
HIP_PROFILE_API
HIP_DB_START_API
HIP_DB_STOP_API
Change-Id: I6c4da67212ff8217e6356a2622d4c6278a188c34
[ROCm/hip commit: e9056798f6 ]
2016-10-27 23:09:31 -05:00
Ben Sander
6972e6d87a
Allow HIP_DB to be number or string flags (ie HIP_DB=api+mem+sync)
...
Add callbacks for processing env vars.
Change-Id: I4ddf50e2da56b1dae43f50657bc693b07b23c03d
[ROCm/hip commit: f5e8090f2f ]
2016-10-27 23:09:31 -05:00
Ben Sander
770ae2611f
Add HIP_PROFILE_START_API, HIP_PROFILE_STOP_API
...
Refactor HIP_INIT_API to call recordApiTrace.
Change-Id: Ieff4b5018236f59e49e1b9841474440a34f821df
[ROCm/hip commit: 710be682ca ]
2016-10-27 23:09:31 -05:00
Ben Sander
494239ad61
Add per-thread API seqnum to debug
...
Change-Id: Ib13733a3e84cd56bae13a32bae40f936c20b7543
[ROCm/hip commit: 739bc37503 ]
2016-10-27 23:09:31 -05:00
Ben Sander
04691cdff8
Don't call allow-access if allocating device's only peer is self.
...
Change-Id: Iac58e6c3e460675833f10b1e8b2e393de223654d
[ROCm/hip commit: 354091f357 ]
2016-10-27 23:09:31 -05:00
Ben Sander
a27124c1f6
Improve HIP TID printing in debug mode.
...
Map long thread-id to a short one that is printed with each message.
Remove clunky stirng creation code for tid_tr.
Print TID on every message.
Change-Id: I780a91d8ce789cb4957789036b478bf5cde8c4e4
[ROCm/hip commit: 346c519ace ]
2016-10-27 23:09:31 -05:00
Aditya Atluri
84d64ef382
reverted change for cache size query
...
Change-Id: I44a1f43818cd287a2a3b6265f43d183f9bd5b71c
[ROCm/hip commit: e1c1b4c009 ]
2016-10-25 11:03:35 -05:00
Aditya Atluri
8580bba30c
correct cachesize to output correct value
...
Change-Id: I5db031591eb718b0c12e78a35e4b19349de9526d
[ROCm/hip commit: 820a914b98 ]
2016-10-25 09:33:45 -05:00
pensun
9f4cb7d4de
Add workaround for hipStreamAddCallback function: call stream synchronize on host and then add execute the call back function
...
Change-Id: If361f8e053949904b19b9e09245d267f05e29f7b
[ROCm/hip commit: 1f11a9554e ]
2016-10-22 23:59:39 -05:00
Ben Sander
548a902c4b
Fix P2P for async
...
Also improve HIP debug message: Add more DB_COPY1 messages. memcpyStr,
expand HIP_DB bitmask.
[ROCm/hip commit: 203348ac9b ]
2016-10-20 10:02:23 -05:00
Rahul Garg
eb8bcfaebe
Quickfix for HCSWAP-60, support for hipHostMallocPortable
...
Change-Id: I2a4fcacea9d916ef222324fc9e9d8191f6dc12d0
[ROCm/hip commit: cd6eb7af78 ]
2016-10-20 10:44:30 +05:30
Ben Sander
56cc2e3deb
Add HIP_WAIT_MODE env var.
...
Also weaken cases where hipSetDeviceFlags returns hipErrorInvalidValue.
Change-Id: I7f113338be6fe498eaf1ab40fd0fd6b23849bb5e
[ROCm/hip commit: 000d75de95 ]
2016-10-18 22:27:16 -05:00