You are viewing an old version of this page. View the current version.

Compare with Current View Page History

« Previous Version 12 Next »


TDT01 is a specialization course focusing on specialized topics within computer architecture. This year's edition will focus on GPU, Microarchitecture, and Evaluation.

Course responsible: Magnus Själander and Magnus Jahre


Final test 2022

Date: TBD


Students 2022

   

Aurud, Lars Murud
Baumann, Henrik Rambech
Bergquist, Jon Åby
Bjørstad, Halvor
Frøyland, Hans Erik
Harnes, Vetle
Harnes, Håkon Anthonsen
Hozman, Ole Ludvig
Larsson, Jonas Brunvoll
Nesset, Erling Feet
Reinfjell, Jørgen Bele
Willa, Lisa
Wittersø, Eirik
Young, Marcus Stensby


    If you are not on this list, but intend to follow TDT01 you need to contact Magnus J ASAP.


Meetings (Date, time, and venue)

    Meeting 1: Startup meeting - 5/9-22, 1400-1430, ITV-454 (Slides)

    Meeting 2: Discussion 1 - 26/9-22, 1300-1430, ITV-454 (Topic: GPU)

    Meeting 3: Discussion 2 - 10/10-22, 1300-1430, ITV-454 (Topic: Microarchitecture)

    Meeting 4: Discussion 3 - 7/11-22, 1300-1430, ITV-454 (Topic: Evaluation)


Reading list (preliminary)

 Note: To access the full versions of the papers from IEEE and ACM you need to have an NTNU IP address. If you are not on campus, try VPN or a terminal server.


GPU (Resp: Magnus J):

1. Get out of the valley: Power-efficient address mapping for GPUs (TBD)

2. HSM: A Hybrid Slowdown Model for Multitasking GPUs (TBD)

3. Delegated Replies: Alleviating Network Clogging in Heterogeneous Architectures (TBD)


Microarchitecture (Resp: Magnus S):

4. The load slice core microarchitecture (TBD)

5. Complexity-Effective Superscalar Processors (TBD)

6. Speculative Taint Tracking (STT): A Comprehensive Protection for Speculatively Accessed Data (TBD)


Evaluation (Resp: Magnus J):

7. FireSim: FPGA-Accelerated Cycle-Exact Scale-OutSystem Simulation in the Public Cloud (TBD)

8. TIP: Time-Proportional Instruction Profiling (TBD)

9. Sniper: Exploring the level of abstraction for scalable and accurate parallel multi-core simulation (TBD)


  • No labels