Intel® FPGA SDK for OpenCL™ Pro Edition: Best Practices Guide

Download PDF
ID 683521
Date 12/19/2022
Public
Document Table of Contents
Document Table of Contents x
Product Discontinuance Notification 1. Introduction to Intel® FPGA SDK for OpenCL™ Pro Edition Best Practices Guide 2. Reviewing Your Kernel's report.html File 3. OpenCL Kernel Design Concepts 4. OpenCL Kernel Design Best Practices 5. Profiling Your Kernel to Identify Performance Bottlenecks 6. Strategies for Improving Single Work-Item Kernel Performance 7. Strategies for Improving NDRange Kernel Data Processing Efficiency 8. Strategies for Improving Memory Access Efficiency 9. Strategies for Optimizing FPGA Area Usage 10. Strategies for Optimizing Intel® Stratix® 10 OpenCL Designs 11. Strategies for Improving Performance in Your Host Application 12. Intel® FPGA SDK for OpenCL™ Pro Edition Best Practices Guide Archives A. Document Revision History for the Intel® FPGA SDK for OpenCL™ Pro Edition Best Practices Guide
1. Introduction to Intel® FPGA SDK for OpenCL™ Pro Edition Best Practices Guide x
1.1. FPGA Overview 1.2. Pipelines 1.3. Single Work-Item Kernel versus NDRange Kernel
2. Reviewing Your Kernel's report.html File x
2.1. High-Level Design Report Layout 2.2. Reviewing the Summary Report 2.3. Viewing Throughput Bottlenecks in the Design 2.4. Using Views 2.5. Analyzing Throughput 2.6. Reviewing Area Information 2.7. Optimizing an OpenCL Design Example Based on Information in the HTML Report 2.8. Accessing HLD FPGA Reports in JSON Format
2.4. Using Views x
2.4.1. Features of the System Viewer 2.4.2. Features of the Kernel Memory Viewer 2.4.3. Features of the Schedule Viewer
2.4.1. Features of the System Viewer x
2.4.1.1. Reviewing System Information 2.4.1.2. Reviewing Global Memory Information 2.4.1.3. Reviewing Block Information 2.4.1.4. Reviewing Cluster Information
2.5. Analyzing Throughput x
2.5.1. Reviewing Loop Information OpenCL Kernel Example
2.6. Reviewing Area Information x
2.6.1. Area Report Message for Board Interface 2.6.2. Area Report Message for Function Overhead 2.6.3. Area Report Message for State 2.6.4. Area Report Message for Feedback 2.6.5. Area Report Messages for Private Variable Storage
2.6.5. Area Report Messages for Private Variable Storage x
2.6.5.1. Area Report Message for Constant Memory
3. OpenCL Kernel Design Concepts x
3.1. Kernels 3.2. Global Memory Interconnect 3.3. Local Memory 3.4. Loops in a Single Work-Item Kernel 3.5. Channels 3.6. Load-Store Units
3.3. Local Memory x
3.3.1. Changing the Memory Access Pattern Example
3.4. Loops in a Single Work-Item Kernel x
3.4.1. Trade-Off Between Initiation Interval and Maximum Frequency 3.4.2. Loop-Carried Dependencies that Affect the Initiation Interval of a Loop 3.4.3. Nested Loops 3.4.4. Loop Speculation 3.4.5. Loop Fusion 3.4.6. Loop Bottlenecks
3.4.3. Nested Loops x
3.4.3.1. Reducing the Area Consumed by Nested Loops Using loop_coalesce
3.6. Load-Store Units x
3.6.1. Load-Store Unit Types 3.6.2. Load-Store Unit Modifiers 3.6.3. Controlling the Load-Store Units 3.6.4. When to Use Each LSU
4. OpenCL Kernel Design Best Practices x
4.1. Transferring Data Via Intel® FPGA SDK for OpenCL™ Channels or OpenCL Pipes 4.2. Unrolling Loops 4.3. Optimizing Floating-Point Operations 4.4. Allocating Aligned Memory 4.5. Aligning a Struct with or without Padding 4.6. Maintaining Similar Structures for Vector Type Elements 4.7. Avoiding Pointer Aliasing 4.8. Avoid Expensive Functions 4.9. Avoiding Work-Item ID-Dependent Backward Branching
4.1. Transferring Data Via Intel® FPGA SDK for OpenCL™ Channels or OpenCL Pipes x
4.1.1. Characteristics of Channels and Pipes 4.1.2. Execution Order for Channels and Pipes 4.1.3. Optimizing Buffer Inference for Channels or Pipes 4.1.4. Best Practices for Channels and Pipes
4.3. Optimizing Floating-Point Operations x
4.3.1. Floating-Point versus Fixed-Point Representations
5. Profiling Your Kernel to Identify Performance Bottlenecks x
5.1. Best Practices for Profiling Your Kernel 5.2. Instrumenting the Kernel Pipeline with Performance Counters (-profile) 5.3. Obtaining Profiling Data During Runtime 5.4. Reducing Area Resource Use While Profiling 5.5. Temporal Performance Collection 5.6. Performance Data Types 5.7. Interpreting the Profiling Information 5.8. Profiler Analyses of Example OpenCL Design Scenarios 5.9. Intel® FPGA Dynamic Profiler for OpenCL™ Limitations
5.3. Obtaining Profiling Data During Runtime x
5.3.1. Invoking the Profiler Runtime Wrapper 5.3.2. Viewing Profiling Data Using Intel® VTune™ Profiler
5.3.1. Invoking the Profiler Runtime Wrapper x
5.3.1.1. Splitting Execution and Data Post Processing
5.5. Temporal Performance Collection x
5.5.1. Profiling Autorun Kernels
5.7. Interpreting the Profiling Information x
5.7.1. Stall, Occupancy, Bandwidth 5.7.2. Stalling Channels 5.7.3. Channel Depths
5.8. Profiler Analyses of Example OpenCL Design Scenarios x
5.8.1. High Stall Percentage 5.8.2. Low Occupancy Percentage 5.8.3. High Stall and High Occupancy Percentages 5.8.4. No Stalls, Low Occupancy Percentage, and Low Bandwidth 5.8.5. No Stalls, High Occupancy Percentage, and Low Bandwidth 5.8.6. High Stall and Low Occupancy Percentages
6. Strategies for Improving Single Work-Item Kernel Performance x
6.1. Addressing Single Work-Item Kernel Dependencies Based on Optimization Report Feedback 6.2. Good Design Practices for Single Work-Item Kernel
6.1. Addressing Single Work-Item Kernel Dependencies Based on Optimization Report Feedback x
6.1.1. Removing Loop-Carried Dependency 6.1.2. Relaxing Loop-Carried Dependency 6.1.3. Transferring Loop-Carried Dependency to Local Memory 6.1.4. Relaxing Loop-Carried Dependency by Inferring Shift Registers 6.1.5. Removing Loop-Carried Dependencies Caused by Accesses to Memory Arrays
7. Strategies for Improving NDRange Kernel Data Processing Efficiency x
7.1. Specifying a Maximum Work-group Size or a Required Work-Group Size 7.2. Kernel Vectorization 7.3. Multiple Compute Units 7.4. Combination of Compute Unit Replication and Kernel SIMD Vectorization 7.5. Reviewing Kernel Properties and Loop Unroll Status in the HTML Report
7.3. Multiple Compute Units x
7.3.1. Compute Unit Replication versus Kernel SIMD Vectorization
8. Strategies for Improving Memory Access Efficiency x
8.1. General Guidelines on Optimizing Memory Accesses 8.2. Optimize Global Memory Accesses 8.3. Performing Kernel Computations Using Constant, Local or Private Memory 8.4. Improving Kernel Performance by Banking the Local Memory 8.5. Optimizing Accesses to Local Memory by Controlling the Memory Replication Factor 8.6. Minimizing the Memory Dependencies for Loop Pipelining 8.7. Static Memory Coalescing
8.2. Optimize Global Memory Accesses x
8.2.1. Contiguous Memory Accesses 8.2.2. Manual Partitioning of Global Memory 8.2.3. Optimizing for Two or More Banks of Global Memory
8.2.2. Manual Partitioning of Global Memory x
8.2.2.1. Heterogeneous Memory Buffers
8.3. Performing Kernel Computations Using Constant, Local or Private Memory x
8.3.1. Constant Cache Memory 8.3.2. Preloading Data to Local Memory 8.3.3. Storing Variables and Arrays in Private Memory
8.4. Improving Kernel Performance by Banking the Local Memory x
8.4.1. Optimizing the Geometric Configuration of Local Memory Banks Based on Array Index
9. Strategies for Optimizing FPGA Area Usage x
9.1. Compilation Considerations 9.2. Board Variant Selection Considerations 9.3. Memory Access Considerations 9.4. Arithmetic Operation Considerations 9.5. Data Type Selection Considerations
10. Strategies for Optimizing Intel® Stratix® 10 OpenCL Designs x
10.1. Reducing Channel Overhead 10.2. Optimizing Loop Control 10.3. Simplifying Memory Access to Local Memories 10.4. On-Chip Storage of Reused Data 10.5. Optimizing Data Path Control 10.6. Creating RTL Modules
10.1. Reducing Channel Overhead x
10.1.1. Reducing the Number of Kernels 10.1.2. Using a Single Kernel to Describe Systolic Arrays 10.1.3. Using Non-Blocking Channels
10.2. Optimizing Loop Control x
10.2.1. Simplifying Loop-Carried Dependencies in Intel® Stratix® 10 OpenCL Designs
10.6. Creating RTL Modules x
10.6.1. Reset Recommendations
11. Strategies for Improving Performance in Your Host Application x
11.1. Multi-Threaded Host Application 11.2. Utilizing Hardware Kernel Invocation Queue
11.2. Utilizing Hardware Kernel Invocation Queue x
11.2.1. Double Buffered Host Application Utilizing Kernel Invocation Queue
Product Discontinuance Notification
1. Introduction to Intel® FPGA SDK for OpenCL™ Pro Edition Best Practices Guide
2. Reviewing Your Kernel's report.html File
3. OpenCL Kernel Design Concepts
4. OpenCL Kernel Design Best Practices
5. Profiling Your Kernel to Identify Performance Bottlenecks
6. Strategies for Improving Single Work-Item Kernel Performance
7. Strategies for Improving NDRange Kernel Data Processing Efficiency
8. Strategies for Improving Memory Access Efficiency
9. Strategies for Optimizing FPGA Area Usage
10. Strategies for Optimizing Intel® Stratix® 10 OpenCL Designs
11. Strategies for Improving Performance in Your Host Application
12. Intel® FPGA SDK for OpenCL™ Pro Edition Best Practices Guide Archives
A. Document Revision History for the Intel® FPGA SDK for OpenCL™ Pro Edition Best Practices Guide

2.5.1. Reviewing Loop Information

The Loops Analysis report contains information about all the loops (coalesced, unrolled, and fused loops) in your design and their unroll statuses. This report helps you examine whether the Intel® FPGA SDK for OpenCL™ Offline Compiler can maximize the throughput of your kernel.

Note: The fMAX II report is now deprecated and its information is merged with the Loop Analysis report.

To view detailed information about the throughput bottlenecks, use the Bottlenecks viewer.

To access the report, click Throughput Analysis > Loop Analysis. The left-hand Loops List pane displays the following types of loops:

  • Fused loops
  • Fused subloops
  • Coalesced loops
  • Fully unrolled loops
  • Partial unrolled loops
  • Regular loops

The Loops Analysis report captures the following key performance metrics on all blocks:

  • Source Location: Indicates the loop location in the source code.
  • Pipelined: Indicates whether the body of a loop is pipelined. Pipelining allows for many data items to get processed concurrently (in the same clock cycle) while making efficient use of the hardware in the datapath by keeping it occupied.
  • II: Shows the sustainable initiation interval (II) of the loop. Processing data in loops is an additional source of pipeline parallelism. When you pipeline a loop, the next iteration of the loop begins before previous iterations complete.

    You can determine the number of clock cycles between iterations by the number of clock cycles you require to resolve any dependencies between iterations. You can refer to this number as the initiation interval (II) of the loop.

    The Intel® FPGA SDK for OpenCL™ Offline Compiler automatically identifies these dependencies and builds hardware to resolve these dependencies while minimizing the II. For additional information, refer to Specifying a loop initiation interval (II).

  • Scheduled f MAX : Shows the scheduled maximum clock frequency at which the loop operates. The fMAX is the maximum rate at which the outputs of registers are updated.

    The physical propagation delay of the signal between two consecutive registers limits the clock speed. This propagation delay is a function of the complexity of the Boolean logic in the path. The path with the most logic (and the highest delay) limits the speed of the entire circuit, and you can refer to this path as the critical path.

    The fMAX is calculated as the inverse of the critical path delay. High fMAX is desirable because it correlates directly with high performance in the absence of other bottlenecks. The offline compiler attempts to optimize the kernel for different objectives for the scheduled fMAX depending on whether the fMAX target is set and whether the #pragma II is set for each of the loops. The fMAX target is a strong suggestion and the compiler does not error out if it is not able to achieve this fMAX, whereas the #pragma II triggers an error if the compiler cannot achieve the requested II. The fMAX achieved for each block of code is shown in the Loops report.

    The following table outlines the behavior of the scheduler in the Intel® FPGA SDK for OpenCL™ Offline Compiler:

    Explicitly Specify fMAX? Explicitly Specify II? Compiler Behavior
    No No Use heuristic to achieve best fMAX/II trade-off.
    No Yes Best effort to achieve the II for the corresponding loop (may not achieve the best possible fMAX).
    Yes No Best effort to achieve fMAX specified (may not achieve the best possible II).
    Yes Yes Best effort to achieve the fMAX specified at the given II. The compiler errors out if it cannot achieve the requested II.
    Note: If you are using an fMAX target in the command line or for a kernel, use #pragma II = <N> for performance-critical loops in your design.
  • Latency: Shows the number of clock cycles a loop takes to complete one or more instructions. Typically, you want to have low latency. However, lowering latency often results in decreased fMAX.
  • Speculated Iterations: Shows the loop speculation. Loop speculation is an optimization technique that enables more efficient loop pipelining by allowing future iterations to get initiated before determining whether the loop exited already. For more information, refer to Loop Speculation.
  • Max Interleaving Iterations: Indicates the number of interleaved invocations of an inner loop that can be executed simultaneously. For more information, refer to Loop Interleaving Control.

You can use the Loops Analysis report to determine where to deploy one or more pragmas on your loops. Refer to the following pragma documentation in the Intel FPGA SDK for OpenCL Programming Guide:

Table 3.  Loop Pragmas
Pragma Reference
#pragma unroll Unrolling a Loop
#pragma loop_coalesce Coalescing Nested Loops
#pragma ii Specifying a loop initiation interval (II)
#pragma speculated_iterations Loop Speculation
#pragma max_concurrency Loop Concurrency
#pragma max_interleaving Loop Interleaving Control
#pragma disable_loop_pipelining Disabling Pipelining of a Loop
#pragma loop_fuse Fusing Adjacent Loops
#pragma nofusion Marking Loops to Prevent Automatic Fusion

OpenCL Kernel Example

The following is an OpenCL kernel example that includes four loops: 

 1  // ND-Range kernel with unrolled loops
 2  __attribute((reqd_work_group_size(1024,1,1)))
 3  kernel void t (global int * out, int N) {
 4    int i = get_global_id(0);
 5    int j = 1;
 6    for (int k = 0; k < 4; k++) {
 7      #pragma unroll
 8      for (int n = 0; n < 4; n++) {
 9        j += out[k+n];
10      }
11    }
12    out[i] = j;
13
14    int m = 0;
15    #pragma unroll 1
16    for (int k = 0; k < N; k++) {
17      m += out[k/3];
18    }
19    #pragma unroll
20    for (int k = 0; k < 6; k++) {
21      m += out[k];
22    }
23    #pragma unroll 2
24    for (int k = 0; k < 6; k++) {
25      m += out[k];
26    }
27    out[2] = m;
28  }

The loop analysis report of this design example highlights the unrolling strategy for the different kinds of loops defined in the code.

The Intel® FPGA SDK for OpenCL™ Offline Compiler executes the following loop unrolling strategies based on the source code:

  • Fully unrolls the inner loop (line 8) within the first loop because of the #pragma unroll specification
  • Does not unroll the second outer loop, Block4 (line 16), because of the #pragma unroll 1 specification
  • Fully unrolls the third outer loop (line 20) because of the #pragma unroll specification
  • Unrolls the fourth outer loop, Block5 (line 24), twice because of the #pragma unroll 2 specification
Level Two Title