Developer Guide

FPGA Optimization Guide for Intel® oneAPI Toolkits

Download PDF
ID 767853
Date 12/16/2022
Public

A newer version of this document is available. Customers should click here to go to the newest version.

Document Table of Contents
Document Table of Contents x
FPGA Optimization Guide for Intel® oneAPI Toolkits
FPGA Optimization Guide for Intel® oneAPI Toolkits x
Introduction To FPGA Design Concepts Analyze Your Design Optimize Your Design FPGA Optimization Flags, Attributes, Pragmas, and Extensions Quick Reference Additional Information Document Revision History for the FPGA Optimization Guide for Intel® oneAPI Toolkits Notices and Disclaimers
Introduction To FPGA Design Concepts x
FPGA Architecture Overview Concepts of FPGA Hardware Design Methods of Hardware Design How Source Code Becomes a Custom Hardware Datapath Scheduling Mapping Parallelism Models to FPGA Hardware Memory Types
FPGA Architecture Overview x
Adaptive Logic Module (ALM) Lookup Table (LUT) Register Digital Signal Processing (DSP) Block Random Access Memory (RAM) Blocks
Concepts of FPGA Hardware Design x
Maximum Frequency (fMAX) Latency Pipelining Throughput Datapath Control Path Occupancy
How Source Code Becomes a Custom Hardware Datapath x
Mapping Source Code Instructions to Hardware Mapping Arrays and Their Accesses to Hardware
Scheduling x
Dynamic Scheduling Clustering the Datapath Handshaking Between Clusters
Mapping Parallelism Models to FPGA Hardware x
Data Parallelism Task Parallelism
Data Parallelism x
Executing Independent Operations Simultaneously Pipelining
Memory Types x
Kernel Memory Global Memory
Analyze Your Design x
Analyze the FPGA Early Image Analyze the FPGA Image
Analyze the FPGA Early Image x
Review the FPGA Optimization Report Access HLD FPGA Reports in JSON Format
Review the FPGA Optimization Report x
Loop Analysis Bottlenecks Viewer Area Estimates System Viewer Kernel Memory Viewer Schedule Viewer
Analyze the FPGA Image x
Quartus (Static) Summary Intel® FPGA Dynamic Profiler for DPC++ System-level Profiling Using the Intercept Layer for OpenCL* Applications
Quartus (Static) Summary x
Timing Failures
Intel® FPGA Dynamic Profiler for DPC++ x
Measure Kernel Performance Instrument the Kernel Pipeline with Performance Counters (<span class='codeph'>-Xsprofile</span>) Obtain Profiling Data During Runtime Reduce Area Resource Use While Profiling Profiler Analyses of Example SYCL* Design Scenarios Limitations
Obtain Profiling Data During Runtime x
Invoke the Profiler Runtime Wrapper to Obtain Profiling Data Use Intel® VTune™ Profiler
Use Intel® VTune™ Profiler x
Interpret Performance Counter Data
System-level Profiling Using the Intercept Layer for OpenCL* Applications x
Set Up the Intercept Layer for OpenCL* Applications
Optimize Your Design x
Throughput Resource Use
Throughput x
Single Work-item Kernels NDRange Kernels Memory Accesses Pipes Host
Single Work-item Kernels x
Single Work-item Kernel Design Guidelines Loops Single-Cycle Floating-Point Accumulator for Single Work-Item Kernels
Loops x
Refactor the Loop-Carried Data Dependency Relax Loop-Carried Dependency Transfer Loop-Carried Dependency to Local Memory Minimize the Memory Dependencies for Loop Pipelining Unroll Loops Fuse Loops to Reduce Overhead and Improve Performance Optimize Loops With Loop Speculation Remove Loop Bottlenecks Simple Loop Example Nested Loop Example Addressing Bottlenecks Shannonization to Improve FMAX/II Optimize Inner Loop Throughput Improve Loop Performance by Caching On-Chip Memory
Single-Cycle Floating-Point Accumulator for Single Work-Item Kernels x
Strategies for Inferring the Accumulator
Memory Accesses x
Load-Store Units Global Memory Accesses Optimization Perform Kernel Computations Using Local or Private Memory Local and Private Memory Accesses Optimization Annotating Unified Shared Memory Pointers Zero-Copy Memory Access Additional Recommendations
Load-Store Units x
Load-Store Unit Styles Load-Store Unit Modifiers Load-Store Unit Controls
Global Memory Accesses Optimization x
Global Memory Bandwidth Use Calculation Manual Partition of Global Memory Partitioning Buffers Across Different Memory Types (Heterogeneous Memory) Partitioning Buffers Across Memory Channels of the Same Memory Type Ignoring Dependencies Between Accessor Arguments Contiguous Memory Accesses Static Memory Coalescing
Host x
Multi-Threaded Host Application Utilizing Hardware Kernel Invocation Queue Double Buffering Host Utilizing Kernel Invocation Queue N-Way Buffering to Overlap Kernel Execution Prepinning Memory Simple Host-Device Streaming Buffered Host-Device Streaming
Double Buffering Host Utilizing Kernel Invocation Queue x
Applying Double-Buffering Using the Intercept Layer for OpenCL* Applications
Resource Use x
Data Types and Operations Kernel Variable Accesses
Data Types and Operations x
Optimize Floating-point Operation Avoid Expensive Functions Variable-Precision Integer and Floating-Point Support
Variable-Precision Integer and Floating-Point Support x
Advantages and Limitations of Arbitrary Precision Data Types Declare and Use the AC Data Types
Declare and Use the AC Data Types x
Declare the <span class='codeph'>ac_int</span> Data Type Declare the <span class='codeph'>ac_fixed</span> Data Type Declare the <span class='codeph'>ac_complex</span> Data Type Declare the <span class='codeph'>ap_float</span> Data Type
Declare the <span class='codeph'>ap_float</span> Data Type x
Conversion Rules for <span class='codeph'>ap_float</span> Operations with Explicit Precision Controls Comparison Operators Additional <span class='codeph'>ap_float</span> Functions Additional Data Types Provided by the <span class='codeph'>ap_float.hpp</span> Header File Quality of Results and the ap_float Data Type
FPGA Optimization Flags, Attributes, Pragmas, and Extensions x
Optimization Flags Kernel Attributes Kernel Controls Kernel Variables Memory Attributes Loop Directives Floating-Point Pragmas Latency Controls (Beta) System of Tasks Extension (<span class='codeph'>task_sequence</span>)
Optimization Flags x
Specify Schedule FMAX Target for Kernels (<span class='codeph'>-Xsclock=<clock target>) Disable Burst-Interleaving of Global Memory (<span class='codeph'>-Xsno-interleaving=<global_memory_type></span>) Force Ring Interconnect for Global Memory (<span class='codeph'>-Xsglobal-ring</span>) Force a Single Store Ring to Reduce Area (<span class='codeph'>-Xsforce-single-store-ring</span>) Force Fewer Read Data Reorder Units to Reduce Area (<span class='codeph'>-Xsnum-reorder</span>) Disable Hardware Kernel Invocation Queue (<span class='codeph'>-Xsno-hardware-kernel-invocation-queue</span>) Modify the Handshaking Protocol Between Clusters (<span class='codeph'>-Xshyper-optimized-handshaking</span>) Disable Automatic Fusion of Loops (<span class='codeph'>-Xsdisable-auto-loop-fusion</span>) Fuse Adjacent Loops With Unequal Trip Counts (<span class='codeph'>-Xsenable-unequal-tc-fusion</span>) Pipeline Loops in Non-task Kernels (<span class='codeph'>-Xsauto-pipeline</span>) Control Semantics of Floating-Point Operations (<span class='codeph'>-fp-model=<var><value></var> </span>) Modify the Rounding Mode of Floating-point Operations (<span class='codeph'>-Xsrounding=<rounding_type></span>) Global Control of Exit FIFO Latency of Stall-free Clusters (<span class='codeph'>-Xssfc-exit-fifo-type=<var><value></var> </span>) Enable the Read-Only Cache for Read-Only Accessors (<span class='codeph'>-Xsread-only-cache-size=<var><N></var>)</span> Control Hardware Implementation of the Supported Data Types and Math Operations (<span class='codeph'>-Xsdsp-mode=<var><option></var> </span>)
Kernel Attributes x
Specify Schedule FMAX Target for Kernels Specify a Workgroup Size Specify Number of SIMD WorkItems Omit Hardware that Generates and Dispatches Kernel IDs Omit Hardware to Support the <span class='codeph'>no_global_work_offset</span> Attribute in <span class='codeph'>parallel_for</span> Kernels Reduce Kernel Area and Latency
Kernel Controls x
Pipes Extension
Pipes Extension x
Key Properties of a Pipe Accessing Pipes The <span class='codeph'>pipe</span> Class and its Use I/O Pipes Characteristics of Pipes Restrictions of Pipes Guidelines for Designing Pipes Pipe and Atomic Fence
Loop Directives x
<span class='codeph'>disable_loop_pipelining</span> Attribute <span class='codeph'>initiation_interval</span> Attribute <span class='codeph'>ivdep</span> Attribute <span class='codeph'>loop_coalesce</span> Attribute <span class='codeph'>max_concurrency</span> Attribute <span class='codeph'>max_interleaving</span> Attribute <span class='codeph'>speculated_iterations</span> Attribute <span class='codeph'>unroll</span> Pragma Loop Fuse Functions and <span class='codeph'>nofusion</span> Attribute
System of Tasks Extension (<span class='codeph'>task_sequence</span>) x
Task Functions <span class='codeph'>task_sequence</span> Use Cases
Quick Reference x
Algorithmic C Data Types Floating Point Pragmas FPGA Accessor Properties FPGA Extensions FPGA Kernel Attributes FPGA Local Memory Function Latency Control Properties (Beta) FPGA LSU Controls FPGA Loop Directives FPGA Memory Attributes FPGA Optimization Flags Pipe API <span class='codeph'>task_sequence</span> Template Parameters and Function APIs
FPGA Optimization Guide for Intel® oneAPI Toolkits

Remove Loop Bottlenecks

Bottlenecks in a loop means that one or more loop carried dependencies caused the compiler to either reduce the number of data items to be processed concurrently (in the same clock cycle) or reduce fMAX. Bottlenecks occur only on single work-item kernels and are always created for loops.

Before analyzing the throughput of a simple loop, it is important to understand the concept of dynamic initiation interval. The initiation interval (II) is the statically determined number of cycles between successive iteration launches of a given loop invocation. However, the statically scheduled II may differ from the actual realized dynamic II when considering interleaving.

NOTE:

Interleaving allows the iterations of more than one invocation of a loop to execute in parallel, provided that the static II of that loop is greater than 1. By default, the maximum amount of interleaving for a loop is equal to the static II of that loop.

In the presence of interleaving, the dynamic II of a loop can be approximated by the static II of the loop divided by the degree of interleaving, that is, by the number of concurrent invocations of the loop that are in flight.

Simple Loop Example

In a simple loop, the maximum number of data items that can be processed concurrently (also known as maximum concurrency) can be expressed as:

ConcurrencyMAX = (Block latency × Maximum interleaving iterations) / Initiation Interval

Consider a simple loop with memory dependency from the Triangular Loops example: 

for (int y = x + 1; y < n; y++) {            
  local_buf[y] = local_buf[y] + SomethingComplicated(local_buf[x]);          
}

The Loop Analysis report displays the following for the simple loop:


The for loop on line 77 has a latency of 36, maximum interleaving iterations of 1, and initiation interval of 30. So, the maximum concurrency is ~1 ((Latency of 36 x Maximum interleaving iteration of 1) / II of 30). The bottleneck causing this low maximum concurrency results from a loop carried dependency caused by a memory dependency. This is reported in the Bottlenecks Viewer as shown in the following image:


Another type of loop carried dependency is a data dependency, as shown in the following example: 

int res = N;
for (int i = 0; i < N; i++) {
  res += 1;
  res ^= i;
}

Nested Loop Example

In a nested loop, the maximum concurrency is more difficult to compute. For example, the loop carried dependency in a nested loop does not necessarily affect the initiation interval of the outer loop. Additionally, a nested loop often requires the knowledge of the inner loop's trip count. Consider the Triangular Loops example: 

void TriangularLoop(std::unique_ptr<queue>& q, buffer<uint32_t>& input_buf,
                    buffer<uint32_t>& output_buf, uint32_t n, event& e,
                    bool optimize) {

  e = q->submit([&](handler& h) {
   
    accessor input(input_buf, h, read_only);
    accessor output(output_buf, h, write_only, no_init);

    h.single_task<Task>([=]() [[intel::kernel_args_restrict]] {
     
      const int real_iterations = (n * (n + 1) / 2 - 1);
      const int extra_dummy_iterations = (kM - 2) * (kM - 1) / 2;
      const int loop_bound = real_iterations + extra_dummy_iterations;

      uint32_t local_buf[kSize];

      for (uint32_t i = 0; i < kSize; i++) {
        local_buf[i] = input[i];
      }

      if (!optimize) {  // Unoptimized loop.

        for (int x = 0; x < n; x++) {
          for (int y = x + 1; y < n; y++) {
            local_buf[y] = local_buf[y] + SomethingComplicated(local_buf[x]);
          }
        }

In this example, the bottleneck is resulted from a loop carried dependency caused by a memory dependency on the variable local_buf. The local_buf variable must finish loading in the loop on line 27 before the next outer loop (line 24) iteration is launched. Therefore, the maximum concurrency of the outer loop is 1. This information is reported in the details sections of the Loop Analysis and Schedule Viewer reports.

Addressing Bottlenecks

To address bottlenecks, primarily consider restructuring your design code.

After restructuring, consider applying the following loop attributes on arrays:

Consider the previous Simple Loop Example where the concurrency is 1 and the initiation interval is 30. Applying the [[intel::ivdep(M)]] attribute, as shown in the following code snippet, comes at an expense of lowered predicted fMAX from 240 MHz to 194.4 MHz. The original nested loop is manually coalesced or merged into a single loop. Since the loop is restructured to ensure that a minimum of M iterations is executed, the [[intel::ivdep(M)]] is used to inform the compiler that at least M iterations always separate any pair of dependent iterations. This new modified loop now has a maximum concurrency of 35 ((Latency of 35 x Maximum interleaving iteration of 1) / II of 1) and an initiation interval of 1. 

// Indices to track the execution in the merged loop
int x = 0, y = 1;

// Total iterations of the merged loop
const int loop_bound = TotalIterations(M, n);

[[intel::ivdep(M)]] 
for (int i = 0; i < loop_bound; i++) {

  // Determine if this is a real or dummy iteration
  bool compute = y > x;
  if (compute) {
    local_buf[y] = local_buf[y] + SomethingComplicated(local_buf[x]);
  }
  
  y++;
  if (y == n) {
    x++;
    y = Min(n - M, x + 1);
  }
}
Parent topic: Loops
Level Two Title