|
@@ -23,8 +23,9 @@
|
|
|
Modern physics experiments have reached multi-GB/s data rates. Fast data
|
|
|
links and high performance computing stages are required for continuous
|
|
|
acquisition and processing. Because of their intrinsic parallelism and
|
|
|
- % I would remove the computing from here and leave "ideal solution",
|
|
|
+ % LR: I would remove the computing from here and leave "ideal solution",
|
|
|
% afterwards we have again computing...
|
|
|
+ % MV: that was your original content, I just rephrased it a bit
|
|
|
computational power, GPUs emerged as an ideal computing solution for high
|
|
|
performance computing applications. To connect a fast data acquisition stage
|
|
|
with a GPU's processing power, we developed an architecture consisting of a
|
|
@@ -71,9 +72,10 @@ of AMD's DirectGMA technology into our processing pipeline. In our solution,
|
|
|
PCI-express (PCIe) has been chosen as a data link between FPGA boards and the
|
|
|
host computer. Due to its high bandwidth and modularity, PCIe quickly became the
|
|
|
commercial standard for connecting high-throughput peripherals such as GPUs or
|
|
|
-solid state disks. Optical PCIe networks have been demonstrated
|
|
|
+solid state disks. Optical PCIe networks have been demonstrated
|
|
|
% JESUS: time span -> for, point in time -> since ...
|
|
|
% BUDDHA: Ok boss. I wanted to say "since 10 years ago...", is for ok?
|
|
|
+% DEUS: "since 10 years ago" is also wrong, it means that something happened at that time
|
|
|
for nearly a decade~\cite{optical_pcie}, opening the possibility of using PCIe
|
|
|
as a communication bus over long distances. In particular, in HEP DAQ systems,
|
|
|
optical links are preferred over electrical ones because of their superior
|
|
@@ -266,7 +268,7 @@ page sizes}
|
|
|
% compared to the previous setup, making it a more cost-effective solution.
|
|
|
|
|
|
\begin{figure}
|
|
|
- \includegraphics[width=\textwidth]{figures/latency-michele}
|
|
|
+ \includegraphics[width=\textwidth]{figures/latency}
|
|
|
\caption{%
|
|
|
Relative frequency of measured latencies for a single 4 KB packet transfered
|
|
|
from the GPU to the FPGA.
|