← 研踪 PaperTrailarXiv:2610.02502 · v2
BROAD: Bit-Parallel Row-Oriented Arithmetic in DRAM
首次提交 2026-10-02 05:24
版本更新 2026-11-19 10:49
雷达观测 2026-11-20 10:50
摘要
Processing-using-memory (PUM) architectures perform computation directly within DRAM to reduce costly data movement between memory and processors. Because charge-sharing operations are confined to individual bitlines, existing DRAM-PUM architectures reorganize data into column-oriented, bit-serial representations. This organization is fundamentally incompatible with the row-oriented, word-parallel layouts used by conventional processors and accelerators, requiring expensive data-layout transformations whenever computation transitions between PUM and conventional execution. In this paper, we present BROAD, or Bit-Parallel Row-Oriented Arithmetic in DRAM. BROAD augments the DRAM subarray with two lightweight extensions: migration cells that enable localized horizontal data movement between neighboring bitlines and inversion cells that provide efficient in-array logical inversion. These primitives enable BROAD to operate directly on row-parallel, bit-parallel data, preserving CPU-compatible layouts while exploiting the massive parallelism of the DRAM subarray. In particular, BROAD demonstrates that localized horizontal communication is sufficient to realize shallow arithmetic networks and efficient parallel reduction for multiplication, reducing arithmetic latency while preserving throughput and eliminating costly data-layout transformations, all while maintaining the conventional DRAM array organization. We demonstrate the feasibility and overhead of augmenting DRAM subarrays with migration and inversion cells through detailed transistor-level layout and SPICE-validated circuit simulations. Using the BROAD compiler it is possible to evaluate the performance and data reorganization tradeoffs to ensure the best execution across combined CPU and PUM. Evaluating BROAD on 19 MLPerf benchmarks, there is a 5.9x higher end-to-end performance compared to SIMDRAM for DDR4 PUM execution.
观测到的版本
相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。
v2 · 2026-11-19 10:49 · 最新观测版本
BROAD: Bit-Parallel Row-Oriented Arithmetic in DRAM
Processing-using-memory (PUM) architectures perform computation directly within DRAM to reduce costly data movement between memory and processors. Because charge-sharing operations are confined to individual bitlines, existing DRAM-PUM architectures reorganize data into column-oriented, bit-serial representations. This organization is fundamentally incompatible with the row-oriented, word-parallel layouts used by conventional processors and accelerators, requiring expensive data-layout transformations whenever computation transitions between PUM and conventional execution. In this paper, we present BROAD, or Bit-Parallel Row-Oriented Arithmetic in DRAM. BROAD augments the DRAM subarray with two lightweight extensions: migration cells that enable localized horizontal data movement between neighboring bitlines and inversion cells that provide efficient in-array logical inversion. These primitives enable BROAD to operate directly on row-parallel, bit-parallel data, preserving CPU-compatible layouts while exploiting the massive parallelism of the DRAM subarray. In particular, BROAD demonstrates that localized horizontal communication is sufficient to realize shallow arithmetic networks and efficient parallel reduction for multiplication, reducing arithmetic latency while preserving throughput and eliminating costly data-layout transformations, all while maintaining the conventional DRAM array organization. We demonstrate the feasibility and overhead of augmenting DRAM subarrays with migration and inversion cells through detailed transistor-level layout and SPICE-validated circuit simulations. Using the BROAD compiler it is possible to evaluate the performance and data reorganization tradeoffs to ensure the best execution across combined CPU and PUM. Evaluating BROAD on 19 MLPerf benchmarks, there is a 5.9x higher end-to-end performance compared to SIMDRAM for DDR4 PUM execution.
查看此版本解读 →查看此版本原文 ↗