Intel Agilex® 7 Variable Precision DSP Blocks User Guide

ID 683037
Date 10/02/2023
Public
Document Table of Contents

3.2.2.5. FP16 Vector One Mode

This mode performs a summation of two half-precision multiplications with the chainin input from the previous variable DSP Block. The output is a single-precision floating-point value which is fed into chainout.

Table 19.  Equations Applied to FP16 Vector One Mode
Chainin Parameter Vector One with Floating-point Addition Vector One with Floating-point Subtraction
Disable

fp32_result = (fp16_mult_top_a * fp16_mult_top_b) + (fp16_mult_bot_a * fp16_mult_bot_b)

fp32_chainout = fp32_adder_a

fp32_result = (fp16_mult_top_a * fp16_mult_top_b) - (fp16_mult_bot_a * fp16_mult_bot_b)

fp32_chainout = fp32_adder_a

Enable

fp32_result = (fp16_mult_top_a * fp16_mult_top_b) + (fp16_mult_bot_a * fp16_mult_bot_b) + fp32_chainin

fp32_chainout = fp32_adder_a

fp32_result = (fp16_mult_top_a * fp16_mult_top_b) - (fp16_mult_bot_a * fp16_mult_bot_b) - fp32_chainin

fp32_chainout = fp32_adder_a

The following are exception flags supported in flushed and bfloat16 formats:
  • fp16_mult_top_invalid
  • fp16_mult_top_inexact
  • fp16_mult_top_overflow
  • fp16_mult_top_underflow
  • fp16_mult_bot_invalid
  • fp16_mult_bot_inexact
  • fp16_mult_bot_overflow
  • fp16_mult_bot_underflow
  • fp16_adder_invalid
  • fp16_adder_inexact
  • fp16_adder_overflow
  • fp16_adder_underflow
  • fp32_adder_invalid
  • fp32_adder_inexact
  • fp32_adder_overflow
  • fp32_adder_underflow
The following are exception flags supported in extended format:
  • fp16_mult_top_invalid
  • fp16_mult_top_inexact
  • fp16_mult_top_infinite
  • fp16_mult_top_zero
  • fp16_mult_bot_invalid
  • fp16_mult_bot_inexact
  • fp16_mult_bot_infinite
  • fp16_mult_bot_zero
  • fp16_adder_invalid
  • fp16_adder_inexact
  • fp16_adder_infinite
  • fp16_adder_zero
  • fp32_adder_invalid
  • fp32_adder_inexact
  • fp32_adder_overflow
  • fp32_adder_underflow
Figure 36. FP16 Vector One Mode