Edit Values
SX-Aurora µarch
General Info
Arch Type	VPU
Designer	NEC
Manufacturer	TSMC
Introduction	2018
Core Configs	8
Pipeline
Type	Superscalar, Pipelined
OoOE	Yes
Speculative	Yes
Reg Renaming	Yes
Stages	8
Decode	4-way
Cache
L1I Cache	32 KiB/core
L1D Cache	32 KiB/core
L2 Cache	256 KiB/core
L3 Cache	16 MiB/chip
Succession
SX-ACE

SX-Aurora is NEC's successor to the SX-ACE, a 16 nm microarchitecture for vector processors first introduced in 2018.

History

This section is empty; you can help add the missing info by editing this page.

Architecture

Key changes from SX-ACE

This section is empty; you can help add the missing info by editing this page.

Block Diagram

This section is empty; you can help add the missing info by editing this page.

Memory Hierarchy

• Vector core
  • SPU
    • L1I Cache:
      • 32 KiB
    • L1D Cache:
      • 32 KiB
    • L2 Cache:
      • 256 KiB
  • VPU
    • 120 KiB load buffer
    • 64 KiB store buffer
• L3 Cache/LLC:
  • 16 MiB
    • 8 x 2 MiB
    • write-back
    • inclusive of L1 & L2
    • 128 banks
    • 3 TiB/s bandwidth
• System DRAM:
  • 4Hi / 8Hi HBM2
  • 6 SDRAM KGDs
  • 1.2 TiB/s

Overview

Overview of the SX-Aurora

The SX-Aurora is NEC's successor to the SX-ACE, a vector processor designed for high-performance scientific/research applications and supercomputers. The SX-Aurora deviates from all prior chips in the kind of markets it's designed to address. Therefore, NEC made slightly different design choice compared to prior generations of vector processors. In an attempt to broaden their market, NEC extended beyond supercomputers to the conventional server and workstation market. This is done through the use of PCIe-based accelerator cards.

Moving to an accelerator card is not without its challenges. To keep the high memory bandwidth, and thus high bytes per FLOP, while moving a smaller form factor, it was necessary to drop the large amount of DDR memory channels. Instead, NEC opted to utilizing high-bandwidth memory on-chip instead. The card itself is designed communicate with other cards on the system in order to scale up from just a single card for workstation use to a supercomputer with 64 cards per rack.

The chip itself consists of eight very big cores along with 16 MiB of last level cache on a 2-dimensional mesh. Attached to the LLC are the two memory controllers which interface with the six high-bandwidth memory sitting on an interposer. Fabricated on TSMC's 16 nm process, the SX-Aurora operates at up to 1.6 GHz delivering up to 307.2 gigaFLOPS (double-precision) per core for a total of up to 2.45 teraFLOPS.

Vector engine (VE) card

This section is empty; you can help add the missing info by editing this page.

Die

• 16 nm process
• 4,800,000,000 transistors
• 14.96 mm x 33.00 mm
  • 493.68 mm² die size

Bibliography

• Template:hcbib
• Supercomputing 2018, NEC Aurora Forum
• Some information was obtained directly from NEC