summaryrefslogtreecommitdiff
path: root/doc/tuning.md
diff options
context:
space:
mode:
Diffstat (limited to 'doc/tuning.md')
-rw-r--r--doc/tuning.md10
1 files changed, 9 insertions, 1 deletions
diff --git a/doc/tuning.md b/doc/tuning.md
index eaafa536..36aee530 100644
--- a/doc/tuning.md
+++ b/doc/tuning.md
@@ -26,15 +26,19 @@ The CLBlast library is already tuned for the most commonly used OpenCL devices a
- GeForce GTX 1070 Ti
- GeForce GTX 1080
- GeForce GTX 1080 Ti
+ - GeForce GTX 2080 Ti
+ - GeForce GTX 3090
- GeForce GTX TITAN
- GeForce GTX TITAN Black
- GeForce GTX TITAN X
- TITAN X (Pascal)
- TITAN RTX
+ - Tesla A100
- Tesla K20m
- Tesla K40m
- Tesla P100 16GB
- Tesla T4
+ - Tesla T2000
- Tesla V100
- Quadro T2000
- Quadro GV100
@@ -49,15 +53,19 @@ The CLBlast library is already tuned for the most commonly used OpenCL devices a
- Radeon R9 380
- Radeon RX 480
- Radeon R9 Fury X
+ - Radeon Pro 450
- Radeon Pro 580
- Radeon RX Vega
+ - Radeon RX 5700 XT
- Radeon RX 6500 XT
+ - Radeon RX 6600 XT
- Radeon RX 6800 XT
* Intel GPUs:
- HD Graphics 530
- HD Graphics 5500 BroadWell U-Processor GT2
- HD Graphics 6000 BroadWell U-Processor GT3
- HD Graphics 630
+ - HD Graphics 770
- HD Graphics Haswell Ultrabook GT2 Mobile
- HD Graphics IvyBridge M GT2
- HD Graphics Skylake ULT GT2
@@ -173,7 +181,7 @@ Here are all the tuners included in the `make alltuners` target (in the same ord
Using the tuning results
-------------
-The tuners output a JSON-file with the results. The best results need to be added to `src/database/kernels/xxxxx.hpp` in the appropriate section. However, this can be done automatically based on the JSON-data using a Python (2.7 or 3.x) script in `scripts/database/database.py`. If you want the found parameters to be included in future releases of CLBlast, please attach the JSON files to the corresponding issue on GitHub or [email the main author](http://www.cedricnugteren.nl).
+The tuners output a JSON-file with the results. The best results need to be added to `src/database/kernels/xxxxx.hpp` in the appropriate section. However, this can be done automatically based on the JSON-data using a Python (2.7 or 3.x) script in `scripts/database/database.py`. If you want the found parameters to be included in future releases of CLBlast, please attach the JSON files [to the corresponding issue](https://github.com/CNugteren/CLBlast/issues/1) on GitHub or [email the main author](http://www.cedricnugteren.nl).
In summary, tuning the entire library for your device can be done as follows (starting from the root of the CLBlast folder):