Andreas Sandberg
YOU?
Author Swipe
View article: The Fake-Busy and True-Idle Problems of Running Graph Applications on Chiplet-Based Multi-cores
The Fake-Busy and True-Idle Problems of Running Graph Applications on Chiplet-Based Multi-cores Open
The open-source and community-supported gem5 simulator is one of the most popular tools for computer architecture research. This simulation infrastructure allows researchers to model modern computer hardware at the cycle level, and it has …
View article: The Last-Level Branch Predictor
The Last-Level Branch Predictor Open
Branch prediction is crucial for modern highperformance processors, ensuring efficient execution by anticipating branch outcomes. Despite decades of research, achieving high prediction accuracy remains challenging, particularly in server w…
View article: Warming Up a Cold Front-End with Ignite
Warming Up a Cold Front-End with Ignite Open
Serverless computing is a popular software deployment model for the cloud, in which applications are designed as a collection of stateless tasks. Developers are charged for the CPU time and memory footprint during the execution of each ser…
View article: The Lyα Reference Sample. XIV. Lyα Imaging of 45 Low-redshift Star-forming Galaxies and Inferences on Global Emission
The Lyα Reference Sample. XIV. Lyα Imaging of 45 Low-redshift Star-forming Galaxies and Inferences on Global Emission Open
We present Ly α imaging of 45 low-redshift star-forming galaxies observed with the Hubble Space Telescope. The galaxies have been selected to have moderate to high star formation rates (SFRs) using far-ultraviolet (FUV) luminosity and H α …
View article: The Lyman $α$ Reference Sample XIV: Lyman $α$ imaging of 45 low redshift star-forming galaxies and inferences on global emission
The Lyman $α$ Reference Sample XIV: Lyman $α$ imaging of 45 low redshift star-forming galaxies and inferences on global emission Open
We present Ly $α$ imaging of 45 low redshift star-forming galaxies observed with the Hubble Space Telescope. The galaxies have been selected to have moderate to high star formation rates using far-ultraviolet (FUV) luminosity and \ha equiv…
View article: Every walk’s a hit: making page walks single-access cache hits
Every walk’s a hit: making page walks single-access cache hits Open
As memory capacity has outstripped TLB coverage, large data applications suffer from frequent page table walks. We investigate two complementary techniques for addressing this cost: reducing the number of accesses required and reducing the…
View article: Branch Predicting with Sparse Distributed Memories
Branch Predicting with Sparse Distributed Memories Open
Modern processors rely heavily on speculation to keep the pipeline filled and consequently execute and commit instructions as close to maximum capacity as possible. To improve instruction-level parallelism, the processor core needs to fetc…
View article: Page Tables: Keeping them Flat and Hot (Cached)
Page Tables: Keeping them Flat and Hot (Cached) Open
As memory capacity has outstripped TLB coverage, large data applications suffer from frequent page table walks. We investigate two complementary techniques for addressing this cost: reducing the number of accesses required and reducing the…
View article: The gem5 Simulator: Version 20.0+
The gem5 Simulator: Version 20.0+ Open
The open-source and community-supported gem5 simulator is one of the most popular tools for computer architecture research. This simulation infrastructure allows researchers to model modern computer hardware at the cycle level, and it has …
View article: Complementary dataset to "BRB: Mitigating Branch Predictor Side-Channels."
Complementary dataset to "BRB: Mitigating Branch Predictor Side-Channels." Open
This dataset supports the article "BRB: Mitigating Branch Predictor Side-Channels.", accepted for publication at HPCA '19, The 25th International Symposium on High-Performance Computer Architecture.
View article: jlpresearch/gem5: gem5 with Spectre code added
jlpresearch/gem5: gem5 with Spectre code added Open
Adds code for Spectre, updates configs to be vulnerable to Spectre, and adds documentation for how to exploit Spectre in gem5.
View article: Will it blend? Merging heterogeneous cores
Will it blend? Merging heterogeneous cores Open
Heterogeneous processors allow different performance/power operation points by pairing high performance Outof-Order (OoO) cores with small energy efficient In-Order cores. Timely switching between the cores types allows the system to tailo…
View article: Complementary dataset to "Nucleus: Finding the sharing limit of heterogeneous cores"
Complementary dataset to "Nucleus: Finding the sharing limit of heterogeneous cores" Open
This dataset supports the article "Nucleus: Finding the sharing limit of heterogeneous cores", accepted for publication at the Transactions on Embedded Computing Systems (TECS) ACM journal