Differences

This shows you the differences between two versions of the page.

--- cluster:200 [2021/02/15 18:23]
hmeij07
+++ cluster:200 [2021/02/18 18:33] (current)
hmeij07
@@ Line 8: / Line 8: @@
 ----
-For CUDA_ARCH (or ''nvcc -arch'') versions check this [[http://arnon.dk/matching-sm-architectures-arch-and-gencode-for-various-nvidia-cards/|Matching CUDA arch and CUDA gencode for various NVIDIA architectures]] web page. "When you compile CUDA code, you should always compile only one ‘-arch‘ flag that matches your most used GPU cards. This will enable faster runtime, because code generation will occur during compilation." //All gpu models RTX2080, RTX5000 and RTX6000 use CUDA_ARCH sm_75// The former model is consumer grade, the latter two  models are enterprise grade. See performance differences below.
+For CUDA_ARCH (or ''nvcc -arch'') versions check this [[http://arnon.dk/matching-sm-architectures-arch-and-gencode-for-various-nvidia-cards/|Matching CUDA arch and CUDA gencode for various NVIDIA architectures]] web page. "When you compile CUDA code, you should always compile only one ‘-arch‘ flag that matches your most used GPU cards. This will enable faster runtime, because code generation will occur during compilation." //All Turing gpu models RTX2080, RTX5000 and RTX6000 use CUDA_ARCH sm_75// The former model is consumer grade, the latter two  models are enterprise grade. See performance differences below. The consumer grade RTX3060Ti is CUDA ARCH sm_86 (Ampere).
 ----
@@ Line 19: / Line 19: @@
   * Noteworthy re RTX3060Ti
     * VendorB "The 3060 Ti does not have the proper cooling for data center use and are not built for that environment"
+    * VendorA "Lead times on the new GPUs are generally 2 months or more."
 ^  VendorB1  ^^  Notes  ^  VendorA1  ^^^  VendorA2  ^^^

DokuWiki

User Tools

Site Tools

Differences

Page Tools