-
Notifications
You must be signed in to change notification settings - Fork 80
Expand file tree
/
Copy pathversions.json
More file actions
275 lines (275 loc) · 10.1 KB
/
versions.json
File metadata and controls
275 lines (275 loc) · 10.1 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
{
"packages" :
{
"CCCL" :
{
"always_download" : true,
"git_shallow" : false,
"git_tag" : "05e019afe53f9b0e4454cbd822f9bdda18df49bb",
"git_url" : "https://github.com/NVIDIA/cccl.git",
"patches" :
[
{
"fixed_in" : "",
"inline_patch" :
{
"content" :
[
"diff --git a/cub/cub/block/block_merge_sort.cuh b/cub/cub/block/block_merge_sort.cuh",
"index 29510db5e..cf57e5786 100644",
"--- a/cub/cub/block/block_merge_sort.cuh",
"+++ b/cub/cub/block/block_merge_sort.cuh",
"@@ -95,7 +95,7 @@ _CCCL_DEVICE _CCCL_FORCEINLINE void SerialMerge(",
" KeyT key1 = keys_shared[keys1_beg];",
" KeyT key2 = keys_shared[keys2_beg];",
"",
"-#pragma unroll",
"+#pragma unroll 1",
" for (int item = 0; item < ITEMS_PER_THREAD; ++item)",
" {",
" const bool p = (keys2_beg < keys2_end) && ((keys1_beg >= keys1_end) || compare_op(key2, key1));",
"@@ -374,7 +374,7 @@ public:",
" //",
" KeyT max_key = oob_default;",
"",
"-#pragma unroll",
"+#pragma unroll 1",
" for (int item = 1; item < ITEMS_PER_THREAD; ++item)",
" {",
" if (ITEMS_PER_THREAD * linear_tid + item < valid_items)",
"diff --git a/cub/cub/thread/thread_sort.cuh b/cub/cub/thread/thread_sort.cuh",
"index 7d9e8622f..da5627306 100644",
"--- a/cub/cub/thread/thread_sort.cuh",
"+++ b/cub/cub/thread/thread_sort.cuh",
"@@ -87,10 +87,10 @@ StableOddEvenSort(KeyT (&keys)[ITEMS_PER_THREAD], ValueT (&items)[ITEMS_PER_THRE",
" {",
" constexpr bool KEYS_ONLY = ::cuda::std::is_same<ValueT, NullType>::value;",
"",
"-#pragma unroll",
"+#pragma unroll 1",
" for (int i = 0; i < ITEMS_PER_THREAD; ++i)",
" {",
"-#pragma unroll",
"+#pragma unroll 1",
" for (int j = 1 & i; j < ITEMS_PER_THREAD - 1; j += 2)",
" {",
" if (compare_op(keys[j + 1], keys[j]))"
],
"type" : "diff"
},
"issue" : "Improve Thrust sort compile times by not unrolling loops for inlined comparators [https://github.com/rapidsai/cudf/pull/10577]"
},
{
"fixed_in" : "",
"inline_patch" :
{
"content" :
[
"diff --git a/cub/cub/device/dispatch/dispatch_radix_sort.cuh b/cub/cub/device/dispatch/dispatch_radix_sort.cuh",
"index 0606485bb..dbb99ff13 100644",
"--- a/cub/cub/device/dispatch/dispatch_radix_sort.cuh",
"+++ b/cub/cub/device/dispatch/dispatch_radix_sort.cuh",
"@@ -1085,7 +1085,7 @@ struct DeviceRadixSortPolicy",
" };",
" ",
" /// SM60 (GP100)",
"- struct Policy600 : ChainedPolicy<600, Policy600, Policy500>",
"+ struct Policy600 : ChainedPolicy<600, Policy600, Policy600>",
" {",
" enum",
" {",
"diff --git a/cub/cub/device/dispatch/dispatch_reduce.cuh b/cub/cub/device/dispatch/dispatch_reduce.cuh",
"index f39613adb..75bd16ff9 100644",
"--- a/cub/cub/device/dispatch/dispatch_reduce.cuh",
"+++ b/cub/cub/device/dispatch/dispatch_reduce.cuh",
"@@ -488,7 +488,7 @@ struct DeviceReducePolicy",
" };",
" ",
" /// SM60",
"- struct Policy600 : ChainedPolicy<600, Policy600, Policy350>",
"+ struct Policy600 : ChainedPolicy<600, Policy600, Policy600>",
" {",
" static constexpr int threads_per_block = 256;",
" static constexpr int items_per_thread = 16;",
"diff --git a/cub/cub/device/dispatch/tuning/tuning_scan.cuh b/cub/cub/device/dispatch/tuning/tuning_scan.cuh",
"index 419908c4e..6ab0840e1 100644",
"--- a/cub/cub/device/dispatch/tuning/tuning_scan.cuh",
"+++ b/cub/cub/device/dispatch/tuning/tuning_scan.cuh",
"@@ -339,7 +339,7 @@ struct DeviceScanPolicy",
" /// SM600",
" struct Policy600",
" : DefaultTuning",
"- , ChainedPolicy<600, Policy600, Policy520>",
"+ , ChainedPolicy<600, Policy600, Policy600>",
" {};",
" ",
" /// SM800"
],
"type" : "diff"
},
"issue" : "Improve Thrust scan compile times by reducing the number of kernels generated [https://github.com/rapidsai/cudf/pull/8183]"
}
],
"version" : "2.7.0"
},
"GTest" :
{
"always_download" : true,
"git_shallow" : false,
"git_tag" : "b796f7d44681514f58a683a3a71ff17c94edb0c1",
"git_url" : "https://github.com/google/googletest.git",
"version" : "1.13.0"
},
"bs_thread_pool" :
{
"always_download" : true,
"git_shallow" : false,
"git_tag" : "097aa718f25d44315cadb80b407144ad455ee4f9",
"git_url" : "https://github.com/bshoshany/thread-pool.git",
"version" : "4.1.0"
},
"cuco" :
{
"always_download" : true,
"git_shallow" : false,
"git_tag" : "7b422c00f3541e2472e8d1047b7c3bb4e83c7e2c",
"git_url" : "https://github.com/NVIDIA/cuCollections.git",
"version" : "0.0.1"
},
"dlpack" :
{
"always_download" : true,
"git_shallow" : false,
"git_tag" : "365b823cedb281cd0240ca601aba9b78771f91a3",
"git_url" : "https://github.com/dmlc/dlpack.git",
"version" : "0.8"
},
"flatbuffers" :
{
"always_download" : true,
"git_shallow" : false,
"git_tag" : "595bf0007ab1929570c7671f091313c8fc20644e",
"git_url" : "https://github.com/google/flatbuffers.git",
"version" : "24.3.25"
},
"fmt" :
{
"always_download" : true,
"git_shallow" : false,
"git_tag" : "0c9fce2ffefecfdce794e1859584e25877b7b592",
"git_url" : "https://github.com/fmtlib/fmt.git",
"patches" :
[
{
"inline_patch" :
{
"content" :
[
"diff --git a/include/fmt/base.h b/include/fmt/base.h",
"index 62764942..60f7483b 100644",
"--- a/include/fmt/base.h",
"+++ b/include/fmt/base.h",
"@@ -464,6 +464,9 @@ template <typename Char> FMT_CONSTEXPR auto length(const Char* s) -> size_t {",
" return len;",
" }",
" ",
"+#if defined(__NVCC__)",
"+#pragma nv_diag_suppress 128",
"+#endif",
" template <typename Char>",
" FMT_CONSTEXPR auto compare(const Char* s1, const Char* s2, std::size_t n)",
" -> int {",
"@@ -474,6 +477,9 @@ FMT_CONSTEXPR auto compare(const Char* s1, const Char* s2, std::size_t n)",
" }",
" return 0;",
" }",
"+#if defined(__NVCC__)",
"+#pragma nv_diag_default 128",
"+#endif",
" ",
" namespace adl {",
" using namespace std;"
],
"type" : "diff"
},
"issue" : "fmt 11.0.2 produces a warning about an unreachable loop when compiled with nvcc"
}
],
"version" : "11.0.2"
},
"jitify" :
{
"always_download" : true,
"git_shallow" : false,
"git_tag" : "e38b993f4cb3207745735c51d4f61cdaa735b7ac",
"git_url" : "https://github.com/rapidsai/jitify.git",
"version" : "2.0.0"
},
"kvikio" :
{
"always_download" : true,
"git_shallow" : false,
"git_tag" : "d3dc14af5f6d6a57287eb4fd45ef173174334ea4",
"git_url" : "https://github.com/rapidsai/kvikio.git",
"version" : "25.04"
},
"nanoarrow" :
{
"always_download" : true,
"git_shallow" : false,
"git_tag" : "4bf5a9322626e95e3717e43de7616c0a256179eb",
"git_url" : "https://github.com/apache/arrow-nanoarrow.git",
"version" : "0.7.0.dev"
},
"nvcomp" :
{
"always_download" : true,
"git_shallow" : false,
"git_tag" : "v2.2.0",
"git_url" : "https://github.com/NVIDIA/nvcomp.git",
"proprietary_binary" :
{
"aarch64-linux" : "https://developer.download.nvidia.com/compute/nvcomp/redist/nvcomp/linux-sbsa/nvcomp-linux-sbsa-${version}_cuda${cuda-toolkit-version-mapping}-archive.tar.xz",
"x86_64-linux" : "https://developer.download.nvidia.com/compute/nvcomp/redist/nvcomp/linux-x86_64/nvcomp-linux-x86_64-${version}_cuda${cuda-toolkit-version-mapping}-archive.tar.xz"
},
"proprietary_binary_cuda_version_mapping" :
{
"11" : "11",
"12" : "12"
},
"version" : "4.2.0.11"
},
"nvtx3" :
{
"always_download" : true,
"git_shallow" : false,
"git_tag" : "e170594ac7cf1dac584da473d4ca9301087090c1",
"git_url" : "https://github.com/NVIDIA/NVTX.git",
"version" : "3.1.0"
},
"rapids_logger" :
{
"always_download" : true,
"git_shallow" : false,
"git_tag" : "46070bb255482f0782ca840ae45de9354380e298",
"git_url" : "https://github.com/rapidsai/rapids-logger.git",
"version" : "0.1.0"
},
"rmm" :
{
"always_download" : true,
"git_shallow" : false,
"git_tag" : "4a1727e78dce17b638a167786e9761775f36ddfa",
"git_url" : "https://github.com/rapidsai/rmm.git",
"version" : "25.04"
},
"spdlog" :
{
"always_download" : true,
"git_shallow" : false,
"git_tag" : "27cb4c76708608465c413f6d0e6b8d99a4d84302",
"git_url" : "https://github.com/gabime/spdlog.git",
"version" : "1.14.1"
}
}
}