- PDC Curriculum Home
- Early Adopter Program
- CDER Book Project
- CDER Center
- Call for Book Chapter Proposals
- PDC Training Program
- EduHPC-25 Workshop
- EduPar-25 Workshop
- SIGCSE-25 Booth and Tutorial
- EduHiPC-2025 Workshop
- JPDC special issue-2024
- Presentations and Publications
- NSF Workshop on PDC
- PDC Institute Planning Grant - Final Report
- Peachy Assignments
- Related Projects
- Previous Workshops
- Courseware
- CDER Cluster
- Login
Sponsors
® Intel, the Intel logo are trademarks or registered trademarks of Intel Corporation or its subsidiaries in the United States and other Countries.
You are here
Appendix I: Cross Reference Matrix – Core Courses vs. Topics
For ease of reference by adopters/instructors of core courses, here are the core courses cross-referenced with topics for the four areas, with information extracted from the previous four tables..
| Topics | DS/A | CS2 |
| ● Costs of computation: | ||
| Asymptotics | 1 | |
| time | 1 | |
| space | 1 | |
| speedup | 1 | |
| ● Cost reduction: | ||
| space compression, etc. | ||
| ● Cost tradeoffs: | ||
| time vs. space, | 1 | |
| power vs. time, etc. | 1 | |
| ● Scalability in algorithms and architectures | 1 | |
| ● Model-based notions: | ||
| – Notions from complexity-theory: | ||
| PRAM | 1 | |
| BSP/CILK | 1 | |
| simulation/emulation, | ||
| P-completeness, | ||
| #P-completeness | ||
| Cellular automata | ||
| Notions from scheduling | ||
| dependencies, | 1 | 1 |
| task graphs, | 1 | |
| work, | 1 | |
| (make)span | 1 | |
| ● Divide & conquer (parallel aspects) | 1 | 1 |
| ● Recursion (parallel aspects) | 1 | 1 |
| ● Scan (parallel-prefix) | ||
| ● reduction (map-reduce) | ||
| ● Stencil-based iteration | ||
| ● Dependencies: | ||
| "oblivious” algorithms | ||
| blocking | ||
| striping | ||
| “out-of-core” algorithms | ||
| ● Series-parallel composition | 1 | |
| ● Graph embedding as an algorithmic tool | ||
| ● Communication: | ||
| broadcast, | 1 | |
| multicast, | 1 | |
| scatter/gather | 1 | |
| gossip | ||
| ● Asynchrony | 1 | |
| ● Synchronization | 1 | 1 |
| Sorting | 1 | 1 |
| Selection | 1 | 1 |
| ● Graph algorithms: | ||
| search | ||
| path selection | ||
| ● Specialized computations: | 1 | 1 |
| convolutions | ||
| matrix computations | ||
| matrix product | ||
| linear systems | ||
| matrix arithmetic | ||
| matrix transpose | ||
| Termination detection | ||
| Leader election/symmetry breaking |
| Topics | Systems | DS/A | CS2 |
| Parallel Programming paradigms and Notations | |||
| By the target machine model | |||
| SIMD | 1 | 1 | |
| Processor vector extensions | 1 | ||
| Shared memory | 1 | 1 | |
| Distributed memory | 1 | 1 | |
| Client Server | 1 | 1 | |
| Hybrid | 1 | ||
| By the control statement | |||
| Task/thread spawning | 1 | 1 | |
| SPMD | 1 | 1 | |
| Data parallel | 1 | 1 | |
| Parallel loops for shared memory | 1 | 1 | |
| Semantics and correctness issues | |||
| Tasks and threads | 1 | 1 | |
| Synchronization | 1 | 1 | |
| Concurrency defects | 1 | 1 | |
| Tools to detect concurrency defects | 1 | 1 | |
| Performance issues | |||
| Computation | 1 | 1 | |
| Load balancing | 1 | 1 | |
| Scheduling and mapping | 1 | 1 | |
| Data (distribution, layout, locality) | 1 | ||
| Performance monitoring tools | 1 | 1 | |
| Performance metrics | 1 | 1 |
| Topics | CS1 | CS2 | Systems |
| Superscalar (ILP) | 1 | ||
| SIMD/Vector (e.g., SSE, Cray) | 1 | ||
| Pipelines | |||
| (Single vs. multicycle) | 1 | ||
| Data and control hazards | |||
| OoO execution | |||
| Streams (e.g., GPU) | 1 | ||
| Dataflow | |||
| MIMD | 1 | ||
| Simultaneous Multithreading (e.g., Hyperthreading) | 1 | ||
| Highly Multithreaded (e.g., MTA) | |||
| Multicore | 1 | ||
| Cluster | |||
| Heterogeneous (e.g., Cell) | 1 | ||
| Grid/cloud | 1 | ||
| SMP | |||
| Buses | 1 | ||
| NUMA (Shared Memory) | |||
| CC-NUMA | |||
| Directory-based CC-NUMA | |||
| Message passing (no shared memory) | |||
| Topologies | 1 | ||
| Diameter | 1 | ||
| Latency | 1 | ||
| Bandwidth | 1 | ||
| Circuit switching | |||
| Packet switching | |||
| Routing | |||
| Cache organization | 1 | ||
| Atomicity | |||
| Consistency | |||
| Coherence | |||
| False sharing | |||
| Impact on software | |||
| Range | 1 | 1 | 1 |
| Precision | 1 | 1 | 1 |
| Rounding issues | |||
| Error propagation | |||
| 754 standard | 1 | ||
| cycles per instruction (CPI) | 1 | ||
| Benchmarks | 1 | ||
| Spec mark | 1 | ||
| Bandwidth benchmarks | |||
| Peak performance | 1 | ||
| MIPS/FLOPS | 1 | ||
| Sustained performance | 1 | ||
| LinPack |
| Topics \ Where Covered | CS1 | CS2 | Systems | DS/A |
| High level themes: | ||||
| Why and what is parallel/distributed computing? | 1 | 1 | ||
| Crosscutting topics: | ||||
| Concurrency | 1 | 1 | ||
| Non-determinism | 1 | 1 | ||
| Power | 1 | 1 | ||
| Locality | 1 | 1 | ||
| Current/Hot/Advanced Topics | ||||
| Cluster | 1 | 1 | 1 | |
| cloud/grid | 1 | 1 | 1 | |
| p2p | 1 | 1 | ||
| fault tolerance | 1 | |||
| Security in Distributed System | 1 | |||
| Distributed transactions | 1 | 1 | ||
| web search | 1 | 1 | ||
| Social Networking/Context | ||||
| Collaborative Computing | ||||
| performance modeling | ||||
| web services | ||||
| pervasive computing | ||||
| mobile computing |