Dr-Noob
|
3e730468d8
|
[v0.20] Fixes from previous commit
|
2021-12-19 10:18:23 +01:00 |
|
Dr-Noob
|
981bfabdc8
|
[v0.20] Merge Intel iGPU branch for preeliminary Intel GPU support
|
2021-12-19 10:11:23 +01:00 |
|
Dr-Noob
|
a397eb398e
|
[v0.11] Handle the case where the GPU is not found in the pci LUT
|
2021-12-18 20:12:41 +01:00 |
|
Dr-Noob
|
bfb9738132
|
[v0.11] Do not show error message when there is no Intel iGPU
|
2021-12-18 10:35:51 +01:00 |
|
Dr-Noob
|
6d4d8b621b
|
[v0.11] Fix compilation error and ambiguity with CUDA and Intel backend when enabled at the same time due to functions with the same name
|
2021-12-18 10:14:14 +01:00 |
|
Dr-Noob
|
93889b2b18
|
[v0.11] Small adjustments to fix compilation on older compilers
|
2021-12-10 16:18:39 +01:00 |
|
Dr-Noob
|
b6ce96e746
|
[v0.11] Add missing Intel iGPU topologies. Add script to check for missing topo/uarchs
|
2021-12-10 15:55:59 +01:00 |
|
Dr-Noob
|
5f52f73fe0
|
[v0.11] Completed most of Intel iGPU topologies
|
2021-12-10 15:32:29 +01:00 |
|
Dr-Noob
|
e5deeb1309
|
[v0.11] Adding more Intel iGPU topologies
|
2021-12-10 15:16:29 +01:00 |
|
Dr-Noob
|
44a884fd07
|
[v0.11] Print peak performance in Intel iGPU
|
2021-12-09 20:28:07 +01:00 |
|
Dr-Noob
|
1663a36135
|
[v0.11] Fetch and print max Intel iGPU frequency using sysfs
|
2021-12-09 20:18:39 +01:00 |
|
Dr-Noob
|
844377f17a
|
[v0.11] Add support for printing EUs (currently only in Gen9/Gen9.5)
|
2021-12-08 11:15:59 +01:00 |
|
Dr-Noob
|
38b8949e1c
|
[v0.11] Fix tensor cores calculation for Ampere. Add a brief explanation
|
2021-11-30 16:03:36 +01:00 |
|
Dr-Noob
|
2034bac006
|
[v0.11] Displaying Graphics Tier in Intel iGPUs
|
2021-11-27 14:02:02 +01:00 |
|
Dr-Noob
|
e7c4d5bf91
|
[v0.11] Adding Gen6, 7, 7.5 and 8 to database
|
2021-11-27 12:23:41 +01:00 |
|
Dr-Noob
|
b00050e739
|
[v0.11] Print available more information for iGPU
|
2021-11-27 11:22:16 +01:00 |
|
Dr-Noob
|
8db60b614d
|
[v0.11] Adding most of Gen9/9.5 iGPUs to database
|
2021-11-27 11:10:01 +01:00 |
|
Dr-Noob
|
8740337145
|
[v0.11] Adding uarch backend for intel iGPUs
|
2021-11-26 12:52:45 +01:00 |
|
Dr-Noob
|
ce004725ad
|
[v0.11] Working in printer backend to show logo and text for intel iGPU
|
2021-11-26 09:58:45 +01:00 |
|
Dr-Noob
|
310486a6a2
|
[v0.11] Fixes to recover CUDA functionality, ready for implementing Intel iGPU code
|
2021-11-26 09:33:57 +01:00 |
|
Dr-Noob
|
461e0d2ede
|
[v0.11] Working in master GPU handler for supporting diverse GPU vendors
|
2021-11-26 08:22:30 +01:00 |
|
Dr-Noob
|
149e5ad62c
|
[v0.11] Working for future support of Intel iGPUs
|
2021-11-25 19:03:52 +01:00 |
|
Dr-Noob
|
cedcfecb80
|
[v0.11] Dont show tensor cores when there is 0. Use MMA (matrix multiply accumulate) instead of TC (tensor cores)
|
2021-11-25 17:52:58 +01:00 |
|
Dr-Noob
|
32b2c59b50
|
[v0.11] Add peak performance with tensor cores to the output
|
2021-11-23 18:49:34 +01:00 |
|
Dr-Noob
|
8bf0276aae
|
[v0.10] Simple refactoring
|
2021-11-23 18:17:12 +01:00 |
|
Dr-Noob
|
821b6e760e
|
[v0.10] Add support for displaying the number of tensor cores
|
2021-11-23 18:09:13 +01:00 |
|
Dr-Noob
|
f212fb88d4
|
[v0.10] Fix pci initialization
|
2021-09-08 08:17:06 +02:00 |
|
Dr-Noob
|
039e7c350d
|
[v0.10] Replace nvml by pciutils to get pci ids. Needs work to integrate it properly. NVML is enough in the case of NVIDIA GPUs, but because more GPUs will be added in the future, a solution like pciutils is needed
|
2021-09-04 12:19:42 +02:00 |
|
Dr-Noob
|
4b4d1bc030
|
[v0.10] Add --list-gpus option
|
2021-08-23 22:39:31 +02:00 |
|
Dr-Noob
|
f4a96cefbd
|
[v0.10] Bump version
|
2021-08-23 21:57:15 +02:00 |
|
Dr-Noob
|
a7036218a0
|
[v0.06] Add check in memory guess to allow guessing only valid memory types for the uarch
|
2021-08-17 15:09:13 +02:00 |
|
Dr-Noob
|
db81586853
|
[v0.06] Fix nvidia color when the small logo is used
|
2021-08-16 22:27:39 +02:00 |
|
Dr-Noob
|
9f52f4916d
|
[v0.06] Add --color option
|
2021-08-16 22:24:02 +02:00 |
|
Dr-Noob
|
6afe26f884
|
[v0.05] Fix a bug that caused segfault when terminal size cannot be retrieved (e.g, redirection)
|
2021-08-16 22:07:52 +02:00 |
|
Dr-Noob
|
ad75c7e6ca
|
[v0.05] Fix truncate function
|
2021-08-16 21:49:03 +02:00 |
|
Dr-Noob
|
ea11da2368
|
[v0.05] Discard specific chips endings when printing the chip to stdout, which looks cleaner
|
2021-08-16 18:36:45 +02:00 |
|
Dr-Noob
|
f989b435b2
|
[v0.05] Fix custom trunc function. Replace # by M in nvidia logo
|
2021-08-16 18:28:29 +02:00 |
|
Dr-Noob
|
617228ce17
|
[v0.05] Allow user to change CUDA_PATH. Add CMakeLists.txt in case I decide to change to CMake later
|
2021-08-16 18:16:32 +02:00 |
|
Dr-Noob
|
7b1018b577
|
[v0.04] Fix some presentation issues
|
2021-08-16 15:54:09 +02:00 |
|
Dr-Noob
|
dea5211791
|
[v0.04] Fix bug in which NVML was using the wrong GPU id
|
2021-08-16 15:18:55 +02:00 |
|
Dr-Noob
|
fd15008ab2
|
[v0.04] Add error checking for CUDA calls
|
2021-08-16 13:52:57 +02:00 |
|
Dr-Noob
|
c7a08e7fd0
|
[v0.04] Add option to select GPU
|
2021-08-16 13:41:39 +02:00 |
|
Dr-Noob
|
eecc040e98
|
[v0.04] Small fixes to presentation
|
2021-08-16 13:11:54 +02:00 |
|
Dr-Noob
|
9a5bc9f3ed
|
[v0.04] Improved long nvidia logo. Finished the logos part
|
2021-08-16 12:27:42 +02:00 |
|
Dr-Noob
|
7b2328589a
|
[v0.03] Added different versions of long NVIDIA logo
|
2021-08-16 11:36:12 +02:00 |
|
Dr-Noob
|
9d88abebb8
|
[v0.03] Added different versions of NVIDIA logo
|
2021-08-16 10:04:47 +02:00 |
|
Dr-Noob
|
a84c27a84c
|
[v0.03] Add better output for memory and uarch attributes
|
2021-08-15 23:36:03 +02:00 |
|
Dr-Noob
|
7ad484b938
|
[v0.03] Add printer backend from cpufetch (still printing CPU logo)
|
2021-08-15 23:23:36 +02:00 |
|
Dr-Noob
|
8f31748d1e
|
[v0.02] Fix typos. Divide memory detection in two phases. Show real memory frequency, instead of the returned by CUDA
|
2021-08-15 22:17:46 +02:00 |
|
Dr-Noob
|
8386052b10
|
[v0.02] Add warning message. Hide the waiting message when CUDA initialization is done. Fix compiler warnings
|
2021-08-15 21:56:51 +02:00 |
|