Required: "Programming Massively Parallel Processors - A hands on approach - 4rd edition" - David B Kirk, Wen-mei W. Hwu; Morgan Kaufmann
Optional :
"An Introduction to Parallel Programming" Peter S. Pacheco - Morgan Kaufamnn/Elsevier. 2011 - This one is available in paperback.
"Computer Organization and Design", Patterson and Hennessy - this has more background than Computer Architecture: A Quantitative Approach. There are multiple versions, I have the MIPS versions but there are ARM versions and maybe even RISC-V. For our class, the version doesn't matter. (6th edition (2021) available for free online from ucsd network courtesy of UCSD library and O'Reilly).
"Computer Architecture: A Quantitative Approach ", Hennessy and Patterson. - available for free online from ucsd network courtesy of UCSD library.
Note: Patterson and Hennessy is an undergraduate text with more background. Hennessy and Patterson is a graduate text and has less background information.
Caches and Memory Hierarchy Patterson and Hennessy , 6th Edition - chapter 5
SIMD, Patterson and Hennessy , 6th Edition - 3.6 - 3.8
"Synthesis Lectures on Computer Architecture #20: Performance Analysis and Tuning for General Purpose Graphics Processing Units (GPGPU)", Hyesoon Kin, Richard Vuduc, Sara Baghsorkhi, Jee Choi, Wen-mei Hwu, Editor Mark Hill, Morgan & Claypool Publishers - available for free on ucsd network
“Synthesis Lectures on Computer Architecture: Single-Instruction Multiple-Data Execution”, Hughes, Morgan & Claypool - available for free on ucsd network
www.hpcwire.com sends me email's pretty regularly with news of things happening in the hpc world. I think its pretty straightforward to get on their mailing list if you are interested.
ISCA 2021 - Ten Lessons From Three Generations Shaped Google's TPUv4i.