Differences

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

--- cluster:184 [2019/09/27 12:34]
hmeij07 [AWS deploys T4]
+++ cluster:184 [2019/09/27 12:38]
hmeij07 [AWS deploys T4]
@@ Line 6: / Line 6: @@
   * https://www.hpcwire.com/2019/09/20/aws-makes-t4-gpu-instances-broadly-available-for-inferencing-graphics/
-Look at this, the smallest Elastic Cloud Compute Instances are **g4dn.xlarge** yielding access to 4 vCPUs and 1x T4 GPU. The largest is **g4dn.12xlarge** yielding access to 48 vCPUs and 4 x T4 GPUs. Now the smallest is priced at $ 0.526/hr, and running that card 24/7 for a year is a cost of $ 4,607.76 ... meaning ... option #7 below with 26 GPUs would cost you a whopping $ 119,802. Annually! That's the low water tide mark. The largest instance is priced at $ 4.352 and would cost you near one million dollars to run per year if you matched option #7.
+Look at this, the smallest Elastic Cloud Compute Instances are **g4dn.xlarge** yielding access to 4 vCPUs and 1x T4 GPU. The largest is **g4dn.16xlarge** yielding access to 64 vCPUs and 1x T4 GPUs. Now the smallest is priced at $0.526/hr, and running that card 24/7 for a year is a cost of $4,607.76 ... meaning ... option #7 below with 26 GPUs would cost you a whopping $119,802. Annually! That's the low tide water mark.
+The high tide water mark? The largest instance is priced at $4.352 and would cost you near one million dollars to run per year if you matched option #7.

DokuWiki