Intel® Agilex™ Variable Precision DSP Blocks User Guide

ID 683037
Date 11/17/2022
Public

A newer version of this document is available. Customers should click here to go to the newest version.

Document Table of Contents
Give Feedback

1.2.2. Floating-point Arithmetic

Table 3.  Supported Combinations of Operational Modes and Features
Variable-Precision DSP Block Resource Operation Mode Supported Operation Instance Chainin Support Chainout Support
1 variable precision DSP block FP32 multiplication mode 1 No Yes
FP32 addition or subtraction mode 1 No Yes
FP32 multiplication with addition or subtraction mode 1 Yes Yes
FP32 multiplication with accumulation mode 1 No Yes
FP32 vector one mode 1 Yes Yes
FP32 vector two mode 1 Yes Yes
Sum of two FP16 multiplication mode 1 No Yes
Sum of two FP16 multiplication with FP32 addition mode 1 Yes Yes
Sum of two FP16 multiplication with accumulation mode 1 No Yes
FP16 vector one mode 1 Yes Yes
FP16 vector two mode 1 Yes Yes
FP16 vector three 1 No Yes
4 Variable precision DSP blocks Floating-point complex multiplication 1 No No
Table 4.  Supported Combinations of Operational Modes and Dynamic Control Features
Variable-Precision DSP Block Resource Operation Mode Dynamic ACCUMULATE
1 variable precision DSP block FP32 multiplication mode No
FP32 adder or subtract mode No
FP32 multiplier adder or subtract mode No
FP32 multiplier accumulate mode Yes
FP32 vector one mode No
FP32 vector two mode No
Sum of two FP16 multiplication mode No
Sum of two FP16 multiplication with FP32 addition mode No
Sum of two FP16 multiplication with accumulation mode Yes
FP16 vector one mode No
FP16 vector two mode No
FP16 vector three Yes
4 Variable precision DSP blocks Floating-point complex multiplication No