Intel Agilex User Guide

•
fp32_adder_inexact
•
fp32_adder_overflow
•
fp32_adder_underflow
Figure 37. FP16 Vector Two Mode
fp32_chainout[31:0]
fp32_chainin[31:0]
fp32_adder_a[31:0]
fp16_mult_top_a[15:0]
fp32_result[31:0]
Input
Register
Bank
Top
Multiplier
Adder
*Pipeline
Register
*Pipeline
Register
*Pipeline
Register
*Pipeline
Register
*Pipeline
Register
Output
Register
Bank
*This block diagram shows the functional representation of the DSP block. The pipeline registers are embedded within the various circuits of the DSP block.
fp16_mult_top_b[15:0]
fp16_mult_bot_a[15:0]
Bottom
Multiplier
fp16_mult_bot_b[15:0]
*Pipeline
Register
Register
Adder
fp16_mult_top_invalid
fp16_mult_top_underflow
fp16_mult_top_overflow
fp32_adder_invalid
fp32_adder_inexact
fp32_adder_overflow
fp32_adder_underflow
fp16_mult_top_inexact
fp16_mult_bot_invalid
fp16_mult_bot_underflow
fp16_mult_bot_overflow
fp16_mult_bot_inexact
fp16_adder_invalid
fp16_adder_inexact
fp16_adder_overflow
fp16_adder_underflow
fp16_mult_top_infinite(extended format)
fp16_mult_top_zero(extended format)
fp16_mult_bot_infinite(extended format)
fp16_mult_bot_zero(extended format)
fp16_adder_infinite(extended format)
fp16_adder_zero(extended format)
3.2.2.7. FP16 Vector Three Mode
This mode performs a single-precision accumulation and a summation of two half-
precision multiplications.
Table 21. Equations Applied to Vector Three Mode
Accumulate Input Vector Three with Floating-Point
Addition
Vector Three with Floating-Point
Subtraction
Disable
fp32_result = fp32_adder_a
fp32_chainout = {fp16_mult_top_a
* fp16_mult_top_b} +
{fp16_mult_bot_a *
fp16_mult_bot_b}
fp32_result = fp32_adder_a
fp32_chainout = {fp16_mult_top_a
* fp16_mult_top_b} -
{fp16_mult_bot_a *
fp16_mult_bot_b}
Enable
fp32_result = fp32_adder_a +
fp32_result(t-1)
fp32_chainout = {fp16_mult_top_a
* fp16_mult_top_b} +
{fp16_mult_bot_a *
fp16_mult_bot_b}
fp32_result = fp32_adder_a -
fp32_result(t-1)
fp32_chainout = {fp16_mult_top_a
* fp16_mult_top_b} -
{fp16_mult_bot_a *
fp16_mult_bot_b}
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
3. Intel Agilex Variable Precision DSP Blocks Operational Modes
UG-20213 | 2019.04.02
Send Feedback
Intel
®
Agilex
™
Variable Precision DSP Blocks User Guide
53

Intel Agilex Specifications

General

Brand	Intel
Model	Agilex
Category	Microcontrollers
Language	English