Intel Agilex User Guide

Figure 44. Complex Multiplication with Result Real Using FP32 Single-Precision Floating-
Point Arithmetic
b
d
a
c
Result Real
Multiply-Subtract Mode
*This block diagram shows the functional representation of the DSP block.
The pipeline registers are embedded within the various circuits of the DSP block.
Multiplication Mode
fp32_chainout[31:0]
fp32_chainin[31:0]
accumulate
fp32_adder_a[31:0]
fp32_mult_b[31:0]
fp32_mult_b31:0]
Output
Register
Bank
fp32_result[31:0]
Input
Register
Bank
Multiplier
Adder
*Pipeline
Register
Bank
*Pipeline
Register
Bank
Register
Bank
*Pipeline
Register
Bank
*Pipeline
Register
Bank
fp32_mult_invalid
fp32_mult_inexact
fp32_mult_overflow
fp32_mult_underflow
*Pipeline
fp32_adder_b[31:0]
fp32_chainout[31:0]
fp32_chainin[31:0]
accumulate
fp32_adder_a[31:0]
fp32_result[31:0]
Multiplier
Subtract
*Pipeline
Register
Bank
*Pipeline
Register
Bank
Register
Bank
*Pipeline
Register
Bank
*Pipeline
Register
Bank
fp32_mult_invalid
fp32_mult_inexact
fp32_mult_overflow
fp32_mult_underflow
fp32_adder_invalid
fp32_adder_inexact
fp32_dder_overflow
fp32_adder_underflow
*Pipeline
Output
Register
Bank
Input
Register
Bank
fp32_adder_b[31:0]
fp32_mult_a[31:0]
fp32_mult_b[31:0]
Figure 45. Complex Multiplication with Imaginary Result Using FP16 Half-Precision
Floating-Point Arithmetic
a
d
b
c
Result Imaginary
*This block diagram shows the functional representation of the DSP block.
The pipeline registers are embedded within the various circuits of the DSP block.
fp32_chainout[31:0]
fp32_chainout[31:0]
fp16_mult_top_a[15:0]
fp32_result[31:0]
Input
Register
Bank
Top
Multiplier
*Pipeline
Register
fp16_mult_top_invalid
fp16_mult_top_underflow
fp16_mult_top_overflow
fp16_adder_invalid
fp16_adder_inexact
*Pipeline
Register
Output
Register
Bank
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_inexact
fp16_mult_bot_invalid
fp16_mult_bot_underflow
fp16_mult_bot_overflow
fp16_mult_bot_inexact
fp16_mult_top_infinite(extended mode)
fp16_mult_top_zero(extended mode)
fp16_mult_bot_infinite(extended mode)
fp16_mult_bot_zero(extended mode)
3. Intel Agilex Variable Precision DSP Blocks Operational Modes
UG-20213 | 2019.04.02
Intel
®
Agilex
™
Variable Precision DSP Blocks User Guide
Send Feedback
60

Intel Agilex Specifications

General

Brand	Intel
Model	Agilex
Category	Microcontrollers
Language	English