Vendor: SmartDV Technologies Category: GDDR

GDDR6X Memory Model

GDDR6X Memory Model provides an smart way to verify the GDDR6X component of a SOC or a ASIC.

Overview

GDDR6X Memory Model provides an smart way to verify the GDDR6X component of a SOC or a ASIC. The SmartDV's GDDR6X memory model is fully compliant with GDDR6X draft Specification and provides the following features. Better than Denali Memory Models.

GDDR6X Memory Model is supported natively in SystemVerilog, VMM, RVM, AVM, OVM, UVM, Verilog, SystemC, VERA, Specman E and non-standard verification env

GDDR6X Memory Model comes with optional Smart Visual Protocol Debugger (Smart ViPDebug), which is GUI based debugger to speed up debugging.

Key features

  • Supports GDDR6X memory devices from all leading vendors.
  • Supports 100% of GDDR6X protocol draft specification
  • Supports all the GDDR6X commands as per the specs.
  • Supports 2 separate independent channels with point-to-point interface for data, address and command.
  • Supports Double Data Rate (DDR) data.
  • Supports up to 8GB device density.
  • Supports X8 and X16 Mode.
  • Supports PAM4 and RDQS Modes.
  • Supports DQ preamble.
  • Supports Programmable READ/WRITE latency.
  • Supports Bank grouping and 16 internal banks per channel.
  • Supports Data bus inversion (DBI) & Command Address bus inversion (CABI).
  • Supports Read/Write data transmission integrity secured by cyclic redundancy check.
  • Supports WRITE Data mask function (single/double byte mask).
  • Supports Programmable EDC hold pattern for CDR.
  • Supports Programmable CRC READ/WRITE latency.
  • Supports Low Power modes.
  • Supports Auto refresh & self-refresh modes.
  • Supports On-die termination operation.
  • Supports Vendor ID for device identification.
  • Supports command address, WCK2CK, read/write training mode’s.
  • Supports IEEE.1149.1 boundary scan operation.
  • Checks for following
    • Check-points include power on, Initialization and power off rules,
    • State based rules, Active Command rules,
    • Read/Write Command rules etc.
    • All timing violations.
  • Supports callbacks for user to get command data on bus.
  • Supports all mode registers programming.
  • Supports for power down features.
  • Quickly validates the implementation of the GDDR6X protocol draft specification.
  • Bus-accurate timing for min, max and typical values.
  • Constantly monitors GDDR6X behavior during simulation.
  • Protocol checker fully compliant with GDDR6X protocol draft specification.
  • Notifies the test bench of significant events such as transactions, warnings, timing and protocol violations.
  • Built in functional coverage analysis.
  • Supports Callbacks, so that user can access the data observed by monitor.

Block Diagram

Benefits

  • Faster testbench development and more complete verification of GDDR6X designs.
  • Easy to use command interface simplifies monitor control and configuration.
  • Simplifies results analysis.
  • Runs in every major simulation environment.

What’s Included?

  • Complete regression suite containing all the GDDR6X testcases.
  • Examples showing how to connect and usage of Model.
  • Detailed documentation of all class, task and function's used in verification env.
  • Documentation also contains User's Guide and Release notes.

Specifications

Identity

Part Number
GDDR6X Memory Model
Vendor
SmartDV Technologies
Type
Silicon IP
Controller / PHY
Controller

Files

Note: some files may require an NDA depending on provider policy.

Provider

Learn more about GDDR IP core

Selection Criteria for Using DDR, GDDR or MobileDDR Memories in System Designs

This paper will include a short review of the key features of DDR, GDDR and MobileDDR memory architectures, covering power, speed and cost characteristics as well as key functionality differences that can impact overall system architecture. Using real system design experiences each of the main memory architectures will be used to address system design challenges of sustained bandwidth, reliability, access priority, power savings, and interface requirements.

SPAD: Specialized Prefill and Decode Hardware for Disaggregated LLM Inference

Large Language Models (LLMs) have gained popularity in recent years, driving up the demand for inference. LLM inference is composed of two phases with distinct characteristics: a compute-bound prefill phase followed by a memory-bound decode phase. This paper proposes SPAD (Specialized Prefill and Decode hardware), adopting a less-is-more methodology to design specialized chips tailored to the distinct characteristics of prefill and decode phases.

High Bandwidth Memory Evolution from First Generation HBM to the Latest HBM4

HBM4 is the latest generation of the High Bandwidth Memory (HBM) that has become analogous to the Artificial Intelligence (AI) boom that is everywhere in today’s world. HBM is also increasingly being used in other applications like Data centers, autonomous driving systems, servers, cloud computing just to mention few domains where bandwidth and performance in a key requirement.

Designing the AI Factories: Unlocking Innovation with Intelligent IP

The rapid evolution of artificial intelligence (AI) is reshaping the technological landscape, driving unprecedented demands on computing infrastructure. At the heart of this transformation lie innovations in intellectual property (IP) that enable scalable, efficient, and performance-driven AI factories.

Frequently asked questions about GDDR Interface IP

What is GDDR6X Memory Model?

GDDR6X Memory Model is a GDDR IP core from SmartDV Technologies listed on Semi IP Hub.

How should engineers evaluate this GDDR?

Engineers should review the overview, key features, supported foundries and nodes, maturity, deliverables, and provider information before shortlisting this GDDR IP.

Can this semiconductor IP be compared with similar products?

Yes. Buyers can compare this product with similar semiconductor IP cores or IP families based on category, provider, process options, and structured technical specifications.

×
Semiconductor IP