Commit Graph

490 Commitit

Tekijä SHA1 Viesti Päivämäärä
gilbertlee-amd 2b8184808d Initial support for clique-based kernels (#276)
* Initial support for clique-based kernels
2020-10-13 11:22:04 -06:00
Wenkai Du ae008fd2db Rework Rome detection and add multiple network ports models (#274)
* Rework Rome detection and add multiple network ports models

* Remove unused opCount in p2p transport
2020-10-07 13:37:36 -07:00
Wenkai Du 88a062342b Don't download GTest unless building unit test (#275) 2020-10-02 15:25:40 -07:00
Wenkai Du b871ea3c0c Add Alltoallv RCCL kernel implementation (#269)
* Add alltoallv API and implementation

* Extend Rome P2P channel limit to multinode and alltoall kernels

* topo_expl: fix compilation and sync up with main

* gtest: use RCCL alltoallv API

* Code review changes
2020-09-30 16:25:36 -07:00
nunnikri aa985bfb7e SWDEV-253325 : Chaning amdgpu-target to cuda-gpu-arch (#268) 2020-09-25 15:44:56 -06:00
Stanley Tsang acca2ae20a Updating inline asm to not require explicit L1 cache invalidation (#270) 2020-09-25 13:46:26 -06:00
gilbertlee-amd ee262819a7 New TransferBench features (#273)
* Upgrading TransferBench to support pinned CPU memory, expanding functionality, cleaning up env vars
2020-09-25 12:20:48 -06:00
gilbertlee-amd 01bd2573db Changes to topology based on XGMI (#272)
* Alterations to topology search to improve XGMI-enabled nodes
2020-09-25 12:20:09 -06:00
Wenkai Du 44fcde7835 Ensure all ranks on same send/receive or alltoall kernel path (#271) 2020-09-24 08:25:04 -07:00
Wenkai Du d871fceb54 Change network plugin name to librccl-net.so (#266) 2020-09-18 13:23:30 -07:00
Wenkai Du 45a8f09e97 Merge pull request #267 from wenkaidu/p2p
Limit P2P channels on Rome
2020-09-18 11:35:35 -07:00
Wenkai Du 42955f5f4f Limit P2P channels on Rome 2020-09-17 17:20:32 -07:00
lijietang bbe233f8c1 Add rccl bw test script in tools (#255) 2020-09-11 16:59:03 +08:00
Stanley Tsang 8c90aefb6d Adding the ability to force install dependencies (namely gtest); gtest library installation fix for centos (#265)
* Adding the ability to force install dependencies (namely gtest); gtest library installation fix for centos

* Removing potentially unneccessary dependencies from install script
2020-09-10 17:27:22 -06:00
Wenkai Du 60819dcf8d Merge pull request #262 from wenkaidu/alignment
Make data alignment requirements matching ISA manual
2020-09-08 10:40:42 -07:00
Stanley Tsang f2e5db7bf7 Adding XNACK flags. (#264)
* Adding XNACK flags.
2020-09-08 11:36:30 -06:00
Aaron Enye Shi 958b213428 Add RCCL Static Lib Creation with -fgpu-rdc
RCCL uses -fgpu-rdc to compile its source objects. When linking
the RCCL static library, the link and archive step must do through
hipcc and uses the flag --emit-static-lib. When compiling
UnitTests, the librccl.a must be consumed through -l and -L.
2020-09-03 11:25:41 -04:00
Wenkai Du e2042ccf8a Fix broken profiling build (#263) 2020-09-02 15:39:52 -07:00
Wenkai Du b163a8898f gtest: add alltoallv test 2020-09-02 21:28:32 +00:00
Wenkai Du 4751992231 Make data alignment requirements matching ISA manual
From https://developer.amd.com/wp-content/resources/Vega_Shader_ISA.pdf

8.1.7. Alignment
For Dword or larger reads or writes, the two LSBs of the byte-address
are ignored, thus forcing Dword alignment.
2020-09-01 21:21:58 +00:00
Wenkai Du 4180e6409e Fix incorrect threads split in sendrecv (#261) 2020-08-31 17:33:22 -07:00
Wenkai Du c5cbece6d0 Increase minimal channels for gfx908 (#259) 2020-08-26 11:40:11 -07:00
Wenkai Du b0919dc46c Only use software barrier for synchronization (#258) 2020-08-25 13:16:34 -07:00
Wenkai Du 391bbf3f1e Add NPS4 support on some models (#256)
* Add NPS4 support on some models

* Add XML models
2020-08-19 11:03:20 -07:00
gilbertlee-amd ec9af40fcd Upgrading various TransferBench features (#257) 2020-08-19 09:47:19 -06:00
Wenkai Du a51e4071e3 Add another Rome model (#249)
* Add another Rome model

* Add gfx908 4P3L models and support

* Revert "Use cached value for detecting GDR support only once"

This reverts commit 67c8e72ce3.

* Skip using ibverb for GPU direct RDMA detection

* Fine tune one Rome model
2020-08-17 10:51:02 -07:00
gilbertlee-amd c985478133 Fixes to make TransferBench compile for hipclang (#254) 2020-08-13 12:25:28 -06:00
saadrahim 6d8e19929c Adding gfx908 to CI (#253) 2020-08-13 11:07:33 -06:00
Wenkai Du 7e3d8a31cc Collect gcnArch and hipDeviceArch_t in XML (#252) 2020-08-12 15:48:38 -07:00
saadrahim 50af2e9b66 Cleaning up CI code be removing overrides (#251) 2020-08-12 12:38:10 -06:00
Wenkai Du 066223333d Merge pull request #248 from wenkaidu/2.7.8
2.7.8
2020-08-11 08:20:37 -07:00
Wenkai Du 7e3f841fab Merge remote-tracking branch 'nccl/master' into 2.7.8 2020-08-10 16:11:00 +00:00
Wenkai Du 3c46cb8ad4 Merge pull request #247 from wenkaidu/rome
Additional Rome models support
2020-08-07 10:56:12 -07:00
MurtadhaAldallal 390c63cf0d Update rccl_prim_test.cpp (#246)
Adding doublelocalcopy operation and freeing buffer memory at end.
DoubleLocalCopy Patch Added
2020-08-07 08:20:14 -07:00
Wenkai Du 09ef75656a Add more Rome 4P2H models 2020-08-06 18:20:02 +00:00
Stanley Tsang c5d4d9eb76 Adding static library building option. (#244)
* Adding static library building option.

* Disabling running tests for static build

* Removing static packaging in CI

Co-authored-by: Saad Rahim <saad.rahim@amd.com>
2020-08-06 11:19:43 -06:00
saadrahim 0dc019e35f Download GTest if not found in system (#237)
Co-authored-by: Stanley Tsang <stanley.tsang@amd.com>
2020-08-06 09:36:58 -06:00
Jack Snyder de49a77074 Setting type when gpu sub node is discovered 2020-08-05 13:39:23 -07:00
Sylvain Jeaugey 3d63f89068 Merge pull request #364 from badgerious/net-class
Add GPUs and NICs based on XML sub tags instead of PCI class.
2020-08-05 12:52:38 -07:00
Eric Badger 700c0e0f24 Don't require NIC devices to have specific PCI class
If a PCI node is the parent of a NIC, treat it as such, regardless of
the PCI class code for the device. This allows non-traditional devices
to act as NICs via the net plugin mechanism.

For consistency, treat GPUs similarly.
2020-08-05 12:46:29 -07:00
Wenkai Du 5b03132ace Allow setup ring through NCCL_RINGS to facilitate testing 2020-08-04 21:07:00 +00:00
Wenkai Du d1e20b4c5e Improve 4P2H topology on Rome (#243)
1. Use bi-directional rings
2. GPU search is sorted by PCI device ID to get consistent results
2020-07-28 14:21:44 -07:00
David Addison 033d799524 2.7.8-1
Fix collective mismatch error when using ncclSend/ncclRecv
2020-07-27 16:34:09 -07:00
Wenkai Du e7a10aa0e4 Topology tuning for 4P2H on Rome (#242)
* Topology tuning for 4P2H on Rome

* Use ncclTopoIdToIndex
2020-07-27 11:53:57 -07:00
Wenkai Du 8d5fb920b6 ib-test: support multiple channels (#241) 2020-07-27 11:03:12 -07:00
Sourav Chakraborty fe3d520601 Merge pull request #240 from ROCmSoftwarePlatform/sourav/topo-expl-1
simplify model definitions in topo expl
2020-07-22 12:35:17 -05:00
Sourav Chakraborty 2475daafee add 4 node 8P6L 1 NIC 2nd Hive model 2020-07-22 16:27:15 +00:00
Sourav Chakraborty db55afb014 simplify model definitions in topo expl 2020-07-22 16:05:53 +00:00
Wenkai Du d5f90e19b5 Add 8P6L multi-node models (#239) 2020-07-21 14:10:36 -07:00
Stanley Tsang 684f3e6af4 Adding better naming to unit tests for filtering; adding short and full unit test suites (#235) 2020-07-21 12:19:47 -06:00