Hui Liu
8fab17ae8f
rm hip.h files
2023-10-30 21:20:28 -07:00
Hui Liu
6762230d9a
namespace to reduce code
2023-10-27 10:51:32 -07:00
Hui Liu
4a4b528d54
add namespace aliases to reduce code
2023-10-27 09:11:55 -07:00
Hui Liu
3752b06550
Merge branch 'master' into sync-condition-2023Oct11
2023-10-24 10:46:38 -07:00
Jiaming Yuan
7a02facc9d
Serialize expand entry for allgather. ( #9702 )
2023-10-24 14:33:28 +08:00
Hui Liu
79319dfd4d
format
2023-10-23 22:29:48 -07:00
Hui Liu
15421e40d9
enable ROCm on latest XGBoost
2023-10-23 11:07:08 -07:00
Your Name
ffbbc9c968
add cuda to hip wrapper
2023-10-17 12:42:37 -07:00
Your Name
ea19555474
temp merge, disable 1 line, SetValid
2023-10-12 16:16:44 -07:00
Jiaming Yuan
8c676c889d
Remove internal use of gpu_id. ( #9568 )
2023-09-20 23:29:51 +08:00
Rong Ou
9bab06cbca
Support column split in gpu hist updater ( #9384 )
2023-08-31 18:09:35 +08:00
Jiaming Yuan
942b957eef
Fix GPU categorical split memory allocation. ( #9529 )
2023-08-29 10:06:03 +08:00
Rong Ou
6103dca0bb
Support column split in GPU evaluate splits ( #9511 )
2023-08-23 16:33:43 +08:00
Jiaming Yuan
912e341d57
Initial GPU support for the approx tree method. ( #9414 )
2023-07-31 15:50:28 +08:00
Rong Ou
7579905e18
Retry switching to per-thread default stream ( #9416 )
2023-07-26 07:09:12 +08:00
Jiaming Yuan
3a9996173e
Revert "Switch to per-thread default stream ( #9396 )" ( #9413 )
...
This reverts commit f7f673b00c15458fb4dd74a2a0d2ba80369c5faf.
2023-07-24 12:03:28 -07:00
Rong Ou
f7f673b00c
Switch to per-thread default stream ( #9396 )
2023-07-20 08:21:00 +08:00
Jiaming Yuan
ee6809e642
Use mmap for external memory. ( #9282 )
...
- Have basic infrastructure for mmap.
- Release file write handle.
2023-06-19 18:52:55 +08:00
amdsc21
5ca7daaa13
merge latest changes
2023-06-15 21:39:14 +02:00
ZHAOKAI WANG
2b76061659
remove redundant method in expand_entry ( #9283 )
2023-06-10 05:18:21 +08:00
amdsc21
b22644fc10
add hip.h
2023-05-20 01:25:33 +02:00
amdsc21
5446c501af
merge 23Mar01
2023-05-02 00:05:58 +02:00
amdsc21
313a74b582
add Shap Magic to check if use cat
2023-05-01 21:55:14 +02:00
Jiaming Yuan
08ce495b5d
Use Booster context in DMatrix. ( #8896 )
...
- Pass context from booster to DMatrix.
- Use context instead of integer for `n_threads`.
- Check the consistency configuration for `max_bin`.
- Test for all combinations of initialization options.
2023-04-28 21:47:14 +08:00
amdsc21
65d83e288f
fix device query
2023-04-19 19:53:26 +02:00
amdsc21
18034a4291
tune histogram
2023-03-26 01:42:51 +01:00
amdsc21
7ee4734d3a
rm device_helpers.hip.h from cu
2023-03-26 00:24:11 +01:00
amdsc21
ee582f03c3
rm device_helpers.hip.h from cuh
2023-03-25 23:35:57 +01:00
amdsc21
595cd81251
add max shared mem workaround
2023-03-19 20:08:42 +01:00
amdsc21
a79a35c22c
add warp size
2023-03-15 22:00:26 +01:00
amdsc21
4484c7f073
disable Optin Shared Mem
2023-03-15 02:10:16 +01:00
amdsc21
364df7db0f
fix ../tree/gpu_hist/evaluate_splits.hip bugs, size 64
2023-03-14 06:17:21 +01:00
amdsc21
7d96758382
macro format
2023-03-11 06:57:24 +01:00
amdsc21
500428cc0f
finish row_partitioner.cu
2023-03-09 22:31:11 +01:00
amdsc21
495816f694
finished gradient_based_sampler.cu
2023-03-09 22:26:08 +01:00
amdsc21
df42dd2c53
finished evaluator.cu
2023-03-09 22:22:05 +01:00
amdsc21
f55243fda0
finish evaluate_splits.cu
2023-03-09 22:15:10 +01:00
amdsc21
1e09c21456
finished feature_groups.cu
2023-03-09 21:31:00 +01:00
amdsc21
0ed5d3c849
finished histogram.cu
2023-03-09 21:28:37 +01:00
amdsc21
270c7b4802
enable rocm, fix row_partitioner.cuh
2023-03-08 06:22:25 +01:00
amdsc21
f2009533e1
rm hip.h
2023-03-08 06:04:01 +01:00
amdsc21
ed45aa2816
Merge branch 'master' into dev-hui
2023-03-08 00:39:33 +01:00
amdsc21
c51a1c9aae
rename hip.cc to hip
2023-03-07 05:39:53 +01:00
amdsc21
cafbfce51f
add hip.h
2023-03-07 03:46:26 +01:00
amdsc21
6039a71e6c
add hip structure
2023-03-07 02:17:19 +01:00
Jiaming Yuan
4d665b3fb0
Restore clang tidy test. ( #8861 )
2023-03-03 13:47:04 -08:00
Jiaming Yuan
594371e35b
Fix CPP lint. ( #8807 )
2023-02-15 20:16:35 +08:00
Jiaming Yuan
70c9b885ef
Extract floating point rounding routines. ( #8771 )
2023-02-12 04:26:41 +08:00
Rory Mitchell
7214a45e83
Fix different number of features in gpu_hist evaluator. ( #8754 )
2023-02-06 23:15:16 +08:00
Jiaming Yuan
c6a8754c62
Define CUDA Context. ( #8604 )
...
We will transition to non-default and non-blocking CUDA stream.
2022-12-20 15:15:07 +08:00
