summaryrefslogtreecommitdiffstats
path: root/history/section_research.txt
diff options
context:
space:
mode:
Diffstat (limited to 'history/section_research.txt')
-rw-r--r--history/section_research.txt31
1 files changed, 31 insertions, 0 deletions
diff --git a/history/section_research.txt b/history/section_research.txt
new file mode 100644
index 0000000..156ce5c
--- /dev/null
+++ b/history/section_research.txt
@@ -0,0 +1,31 @@
+Variants
+========
+1. GPU computing for high-speed tomographic reconstruction~\cite{csa2011pyhst}
+2. Optimization of synchtrotron tomography with GPU computing~\cite{csa2011pyhst}
+3. Collaborated with researchers from ESRF facility on high-speed tomographic reconstruction and improved performance of PyHST software by factor of 30~\cite{csa2011pyhst}.
+
+Variants
+========
+1. Approximate computing to enable reconstruction of large datasets using memory-intensive
+regularization methods
+2. Applied methods of approximate computing to enable reconstruction of large datasets using memory-intensive
+regularization methods
+3. Collaborated with scientists from University of Manchester on optimization of their tomography software: suggested methods of approximate computing to enable also reconstruction of large datasets
+
+
+Doubts - contribution unclea
+=======
+1. A case study on application of GPUs in L1 track trigger for the next upgrade of CMS experiment
+2. Superivised a case study on application of GPUs in L1 track trigger for the next upgrade of CMS experiment
+3. Superivised aspects of low-latency FPGA-to-GPU communication in a case study on application of GPUs in L1 track trigger for the next upgrade of CMS experiment
+
+Doubts - contribution unclea
+=======
+1. Streaming data acquisition platform for control systems with image-based feedback loops
+3. Participated in the development of streaming data acquisition platform aimed at control systems with image-based feedback loops and was responsible for the software part
+
+
+Unclear?
+========
+1. Hidden parallelism in GPU architectures
+2. Researched hidden parallelism in GPU architectures