User Tools

Site Tools


buzzwords

Buzzwords

Buzzwords are terms that are mentioned during lecture which are particularly important to understand thoroughly. This page tracks the buzzwords for each of the lectures and can be used as a reference for finding gaps in your understanding of course material.

Lecture 1 (25.02 Thu.)

  • Computer Architecture
  • The transformation hierarchy
    • Levels of transformation
  • Design goals
  • Google tensor processing unit (TPU)
  • Tesla self-driving computer
  • Redundant cores for better safety
  • Energy efficiency and performance
  • Intel Optane persistent memory (3D-XPoint)
  • Cerebra's wafer scale engine
  • Graphics processing unit (GPU)
  • UPMEM processing-in-DRAM
  • Samsung Function-in-Memory DRAM
  • Processing-in-memory
  • AI/ML chips
  • Reliability and security
  • RowHammer
  • DRAM row
  • Meltdown and Spectre
  • Genome sequencing
    • Covid-19 nanopore sequencing
  • Computing paradigms
  • Accelerators (algorithm-hardware codesign)
  • Memory and storage systems
  • Bahnhof Stadelhofen
  • Santiago Calatrava
  • Architecture
  • Tradeoffs
  • Evaluation criteria
  • Principled design
  • Design constrains

Lecture 2 (04.03 Thu.)

  • Data Movement
  • Processing in memory (PIM)
  • In-memory computation/processing
  • Near-data processing (NDP)
  • UPMEM Processing-in-DRAM Engine
  • 3D-stacked memory
  • RowClone
  • Gather/Scatter DRAM
  • Bulk data copy and initialization
  • In-Memory copy
  • Intra-subarray
  • Inter-bank
  • Memory as an accelerator
  • Low-cost Inter-linked subarrays (LISA)
  • Fine-Grained In-DRAM Copy (FIGARO)
  • Network-On-Memory
  • Bulk Bitwise in-DRAM Computation (Ambit)
  • Intelligent Memory Device
  • ComputeDRAM
  • Dual Contact Cell
  • New memory technologies

Lecture 4 (18.03 Thu.)

  • Bioinformatics
  • Genome Analysis
  • DNA Testing
  • Chromosomes
  • SNPs
  • Personalized Medicine
  • Phenotypes
  • Privacy-Preserving Genome Analysis
  • SARS-CoV-2
  • Microbiome Profiling
  • High-Throughput Sequencers
  • Genome Sequencing
  • PacBio
  • DNA
  • Reference Genome
  • Metagenomics
  • Read Mapping
  • Hashing
  • Seeds
  • Read Alignment
  • Smith-Waterman
  • Hamming distance
  • Accelerating Read Mapping
  • Seed Filtering
  • Pre-alignment Filtering
  • Read Alignment Acceleration
  • FastHASH
  • Cheap K-mer Selection
  • GateKeeper
  • Shifted Hamming Distance
  • FPGA
  • Shouji
  • SneakySnake
  • Hybrid Memory Cube
  • Ambit
  • RowClone
  • Pinatubo
  • Tesseract
  • GRIM-Filter
  • GenCache
  • Darwin
  • GenASM
  • AirLift
  • UPMEM

Session 1 (25.03 Thu.)

  • Spectre
  • Branches
  • Misspeculation
  • Out-of-Order
  • Flush cache
  • Side-channel attack
  • Rowhammer
  • DRAM scaling
  • Bloom filter
  • Blockhammer
  • Throttle
  • Blacklisting

Session 2 (10.04 Thu.)

  • True Random Number Generators (TRNGs)
  • NIST tests
  • DRAM cell Activation failure
  • Entropy source
  • DRAM timing constraints
  • Startup values
  • Data retention
  • Charge sharing
  • Bit-serial operations
  • Bit-parallel arithmetics
  • DRAM subarray

Session 3 (15.04 Thu.)

  • PageRank
  • Spatial/temporal locality
  • 3D stacking
  • PIM
  • PEI
  • Intrinsics
  • Locality-aware
  • Through-Silicon Via (TSV)
  • Hybrid Memory Cube (HMC)
  • PIM Computation Unit (PCU)
  • PIM Management Unit (PMU)
  • Atomicity
  • Reader-writer lock
  • Cache coherence
  • Locality-aware execution

Session 4 (22.04 Thu.)

  • On-chip networks
  • Chip router
  • Buffer routing
  • Bufferless routing
  • Reroute
  • Youngest flit
  • Head flit
  • Worm deflection
  • Worm truncation
  • Routing mechanism
  • Homogeneous
  • High propability
  • Congestion control
  • Network type
  • Prefetcher
  • Data-indirect workloads
  • Data indirection graph
  • Indirect memory accesses
  • Breadth-First Search
  • Data-dependent loads
  • Load-dependent branches
  • Allocator calls
  • Dependent loads
  • Adjacent bounds
  • No inbound edges
  • Dedicated SRAM
  • Prefetch Status Handling Registers

Session 5 (29.04 Thu.)

  • Branch prediction
  • Perceptron
  • Pipeline
  • Control hazard
  • Branch history table (BHT)
  • Pattern History Table (PHT)
  • Memory controller
  • Machine Learning
  • Reinforcement learning
  • Chip Multiprocessors
  • Off-chip bandwidth
  • Memory
  • Self-optimizing
  • Environment
  • Agent
  • Reward
  • Bus utilization
  • Feature selection
  • Q-values
  • CMAC representation

Session 6 (06.05 Thu.)

  • Deep Neural Network (DNN)
  • Approximation
  • Quantization
  • Huffman Coding
  • Pruning
  • Training
  • Inference
  • Sparsity
  • Robustness
  • SneakySnake
  • Genome Pre-alignment
  • Hardware Acceleration
  • Read Mapping
  • Sequence Alignment
  • Approximate String Matching (ASM)
  • Single Net Routing (SNR)
  • Filtering Accuracy
  • Short Sequences
  • Long Sequence

Session 9 (03.06 Thu.)

  • DRAM Access Latency
  • DRAM Subarray
  • DRAM Row Buffer Hit Rate
  • In-DRAM Caching
  • Heterogeneous DRAM Bank
  • Heterogeneous DRAM Subarray
  • DRAM Row
  • Bulk In-DRAM Data Movement
  • Fine-Grained In-DRAM Data Movement
  • Local Row Buffer
  • Global Bitline
  • Global Row Buffer
  • Simultaneous Row Activation
  • Column Decoding
  • Cache Miss/Hit
  • Cache Line Replacement Policy
  • Software Instrumentation
  • Misses Per Kilo Instruction (MPKI)
  • Weighted Speedup
  • ECC Memory
  • On-Die ECC
buzzwords.txt · Last modified: 2021/06/03 17:01 by hluo