Intel Agilex User Manual page 56

•
fp32_adder_inexact
•
fp32_adder_overflow
•
fp32_adder_underflow
Figure 39. Multiply-Add or Multiply-Subtract Mode for Intel Agilex Devices
fp32_chainin[31:0]
accumulate
fp32_adder_a[31:0]
fp32_adder_b[31:0]
fp32_mult_a[31:0]
fp32_mult_b[31:0]
3.2.3.2. Direct Vector Dot Product
The following figures shows the combination of DSP blocks to create direct vector dot
product. For FP32 single-precision floating-point arithmetic, the direct vector dot
product consists of:
• Multiply-add and subtract mode with chainin parameter turned on
• Vector one
• Vector two
® ™
Intel Agilex Variable Precision DSP Blocks User Guide
56
3. Intel Agilex Variable Precision DSP Blocks Operational Modes
Input
Register
Bank
*Pipeline *Pipeline
Register Register
Bank Bank
Multiplier
*This block diagram shows the functional representation of the DSP block.
The pipeline registers are embedded within the various circuits of the DSP block.
*Pipeline *Pipeline
Register Register
*Pipeline
Bank Bank
Adder
Register
Bank
fp32_chainout[31:0]
UG-20213 | 2019.04.02
Output
fp32_result[31:0]
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
Send Feedback