Differences

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

--- cluster:182 [2019/08/12 14:21]
hmeij07 [the DPP]
+++ cluster:182 [2019/08/12 14:39]
hmeij07 [the DPP]
@@ Line 22: / Line 22: @@
 [[https://en.wikipedia.org/wiki/List_of_Nvidia_graphics_processing_units|List of Nvidia Graphics Processing Units]]
-"Every GPU with SM 1.3 (Tesla/GTX2xx) or better has hardware double-precision support. Starting with the Fermi architecture, Quadro and Tesla variants have better double-precision support than consumer Ge Force models." So I'm utterly confused by this outcome. The P100 is best at double precision (fp64), the RXT6000 is modest and the T4 actually has no specs regarding fp64. Running a colloid example in Lammps compiled for these GPUs with DOUBLE_DOUBLE, all three models obtain the same result in 500,000 loops.
+"Every GPU with SM 1.3 (Tesla/GTX2xx) or better has hardware double-precision support. Starting with the Fermi architecture, Quadro and Tesla variants have better double-precision support than consumer Ge Force models." So I'm utterly confused by this outcome. The P100 is best at double precision (FP64), the RXT6000 is modest and the T4 actually has no specs regarding FP64. Nvidia does not publish any data on FP64 for T4 and certain RTX models. But running a colloid example in Lammps compiled for these GPUs with DOUBLE_DOUBLE, all three models obtain the same result in 500,000 loops.
 The explanation was found [[https://www.microway.com/hpc-tech-tips/nvidia-turing-tesla-t4-hpc-performance-benchmarks/|T4 benchmarks fp64 and fp32]].  The T4 can do double precision if needed but it's strength is mixed  and single precision.
@@ Line 41: / Line 41: @@
 </code>
+==== Amber ====
+^    ^    ^  P100[1]  ^  P100[4]  ^  RTX[1]  ^  T4[1]  ^  T4[4]  ^  Notes  ^
 \\
 **[[cluster:0|Back]]**

DokuWiki

User Tools

Site Tools

Differences

Page Tools