embblk.latency.systolicQRBlockTiming

Compute throughput and latency of Systolic QR Decomposition block

Since R2024a

Syntax

[throughput,latency] = embblk.latency.systolicQRBlockTiming(A,B)

Description

[throughput,latency] = embblk.latency.systolicQRBlockTiming(A,B) returns the throughput and latency of the Systolic QR Decomposition block. This computation depends on the data type, complexity, and dimension of the input matrices A,B.

Examples

collapse all

Compute Throughput and Latency for Systolic QR Decomposition Block

Define input matrices A and B. Compute the latency and throughput of the Systolic QR Decomposition block for these inputs.

A = fi(complex(randn(4,4),randn(4,4)),1,17,10)
B = fi(complex(randn(4,1),randn(4,1)),1,17,10)
[throughput,latency] = embblk.latency.systolicQRBlockTiming(A,B)

throughput =

    20


latency =

   152

Input Arguments

collapse all

`A,B` — Input matrices A and B
matrices

Input matrices A and B to the Systolic Matrix Solve Using QR Decomposition block, specified as matrices.

Data Types: single | double | fi
Complex Number Support: Yes

Output Arguments

collapse all

`throughput` — Throughput
scalar

Throughput of the Systolic Matrix Solve Using QR Decomposition block, returned as a scalar. Throughput is defined as the number of clock cycles between adjacent ready signals.

`latency` — Latency
scalar

Latency of the Systolic Matrix Solve Using QR Decomposition block, returned as a scalar. Latency is defined as the number of clock cycles between the input and the corresponding output.