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

Download PDF
ID 683176
Date 9/24/2018
Public
Document Table of Contents
Document Table of Contents x
1. Introduction to Standard Edition Best Practices Guide 2. Reviewing Your Kernel's report.html File 3. OpenCL Kernel Design Best Practices 4. Profiling Your Kernel to Identify Performance Bottlenecks 5. Strategies for Improving Single Work-Item Kernel Performance 6. Strategies for Improving NDRange Kernel Data Processing Efficiency 7. Strategies for Improving Memory Access Efficiency 8. Strategies for Optimizing FPGA Area Usage A. Additional Information
1. Introduction to Standard Edition Best Practices Guide x
1.1. FPGA Overview 1.2. Pipelines 1.3. Single Work-Item Kernel versus NDRange Kernel 1.4. Multi-Threaded Host Application
2. Reviewing Your Kernel's report.html File x
2.1. High Level Design Report Layout 2.2. Reviewing the Report Summary 2.3. Reviewing Loop Information 2.4. Reviewing Area Information 2.5. Verifying Information on Memory Replication and Stalls 2.6. Optimizing an OpenCL Design Example Based on Information in the HTML Report 2.7. HTML Report: Area Report Messages 2.8. HTML Report: Kernel Design Concepts
2.3. Reviewing Loop Information x
2.3.1. Loop Analysis Report of an OpenCL Design Example 2.3.2. Changing the Memory Access Pattern Example 2.3.3. Reducing the Area Consumed by Nested Loops Using loop_coalesce
2.4. Reviewing Area Information x
2.4.1. Area Analysis by Source 2.4.2. Area Analysis of System
2.5. Verifying Information on Memory Replication and Stalls x
2.5.1. Features of the System Viewer 2.5.2. Features of the Kernel Memory Viewer
2.7. HTML Report: Area Report Messages x
2.7.1. Area Report Message for Board Interface 2.7.2. Area Report Message for Function Overhead 2.7.3. Area Report Message for State 2.7.4. Area Report Message for Feedback 2.7.5. Area Report Message for Constant Memory 2.7.6. Area Report Messages for Private Variable Storage
2.8. HTML Report: Kernel Design Concepts x
2.8.1. Kernels 2.8.2. Global Memory Interconnect 2.8.3. Local Memory 2.8.4. Nested Loops 2.8.5. Loops in a Single Work-Item Kernel 2.8.6. Channels 2.8.7. Load-Store Units
3. OpenCL Kernel Design Best Practices x
3.1. Transferring Data Via Channels or OpenCL Pipes 3.2. Unrolling Loops 3.3. Optimizing Floating-Point Operations 3.4. Allocating Aligned Memory 3.5. Aligning a Struct with or without Padding 3.6. Maintaining Similar Structures for Vector Type Elements 3.7. Avoiding Pointer Aliasing 3.8. Avoid Expensive Functions 3.9. Avoiding Work-Item ID-Dependent Backward Branching
3.1. Transferring Data Via Channels or OpenCL Pipes x
3.1.1. Characteristics of Channels and Pipes 3.1.2. Execution Order for Channels and Pipes 3.1.3. Optimizing Buffer Inference for Channels or Pipes 3.1.4. Best Practices for Channels and Pipes
3.3. Optimizing Floating-Point Operations x
3.3.1. Floating-Point versus Fixed-Point Representations
4. Profiling Your Kernel to Identify Performance Bottlenecks x
4.1. Best Practices 4.2. GUI 4.3. Interpreting the Profiling Information 4.4. Limitations
4.2. GUI x
4.2.1. Source Code Tab 4.2.2. Kernel Execution Tab 4.2.3. Autorun Captures Tab
4.2.1. Source Code Tab x
4.2.1.1. Tool Tip Options
4.3. Interpreting the Profiling Information x
4.3.1. Stall, Occupancy, Bandwidth 4.3.2. Activity 4.3.3. Cache Hit 4.3.4. Profiler Analyses of Example OpenCL Design Scenarios 4.3.5. Autorun Profiler Data
4.3.1. Stall, Occupancy, Bandwidth x
4.3.1.1. Stalling Channels
4.3.4. Profiler Analyses of Example OpenCL Design Scenarios x
4.3.4.1. High Stall Percentage 4.3.4.2. Low Occupancy Percentage 4.3.4.3. Low Bandwidth Efficiency 4.3.4.4. High Stall and High Occupancy Percentages 4.3.4.5. No Stalls, Low Occupancy Percentage, and Low Bandwidth Efficiency 4.3.4.6. No Stalls, High Occupancy Percentage, and Low Bandwidth Efficiency 4.3.4.7. Stalling Channels 4.3.4.8. High Stall and Low Occupancy Percentages
5. Strategies for Improving Single Work-Item Kernel Performance x
5.1. Addressing Single Work-Item Kernel Dependencies Based on Optimization Report Feedback 5.2. Removing Loop-Carried Dependencies Caused by Accesses to Memory Arrays 5.3. Good Design Practices for Single Work-Item Kernel
5.1. Addressing Single Work-Item Kernel Dependencies Based on Optimization Report Feedback x
5.1.1. Removing Loop-Carried Dependency 5.1.2. Relaxing Loop-Carried Dependency 5.1.3. Simplifying Loop-Carried Dependency 5.1.4. Transferring Loop-Carried Dependency to Local Memory 5.1.5. Removing Loop-Carried Dependency by Inferring Shift Registers
6. Strategies for Improving NDRange Kernel Data Processing Efficiency x
6.1. Specifying a Maximum Work-Group Size or a Required Work-Group Size 6.2. Kernel Vectorization 6.3. Multiple Compute Units 6.4. Combination of Compute Unit Replication and Kernel SIMD Vectorization 6.5. Reviewing Kernel Properties and Loop Unroll Status in the HTML Report
6.2. Kernel Vectorization x
6.2.1. Static Memory Coalescing
6.3. Multiple Compute Units x
6.3.1. Compute Unit Replication versus Kernel SIMD Vectorization
7. Strategies for Improving Memory Access Efficiency x
7.1. General Guidelines on Optimizing Memory Accesses 7.2. Optimize Global Memory Accesses 7.3. Performing Kernel Computations Using Constant, Local or Private Memory 7.4. Improving Kernel Performance by Banking the Local Memory 7.5. Optimizing Accesses to Local Memory by Controlling the Memory Replication Factor 7.6. Minimizing the Memory Dependencies for Loop Pipelining
7.2. Optimize Global Memory Accesses x
7.2.1. Contiguous Memory Accesses 7.2.2. Manual Partitioning of Global Memory
7.2.2. Manual Partitioning of Global Memory x
7.2.2.1. Heterogeneous Memory Buffers
7.3. Performing Kernel Computations Using Constant, Local or Private Memory x
7.3.1. Constant Cache Memory 7.3.2. Preloading Data to Local Memory 7.3.3. Storing Variables and Arrays in Private Memory
7.4. Improving Kernel Performance by Banking the Local Memory x
7.4.1. Optimizing the Geometric Configuration of Local Memory Banks Based on Array Index
8. Strategies for Optimizing FPGA Area Usage x
8.1. Compilation Considerations 8.2. Board Variant Selection Considerations 8.3. Memory Access Considerations 8.4. Arithmetic Operation Considerations 8.5. Data Type Selection Considerations
A. Additional Information x
A.1. Document Revision History for the Standard Edition Best Practices Guide
1. Introduction to Standard Edition Best Practices Guide
2. Reviewing Your Kernel's report.html File
3. OpenCL Kernel Design Best Practices
4. Profiling Your Kernel to Identify Performance Bottlenecks
5. Strategies for Improving Single Work-Item Kernel Performance
6. Strategies for Improving NDRange Kernel Data Processing Efficiency
7. Strategies for Improving Memory Access Efficiency
8. Strategies for Optimizing FPGA Area Usage
A. Additional Information

5.1.2. Relaxing Loop-Carried Dependency

Based on the feedback from the optimization report, you can relax a loop-carried dependency by increasing the dependence distance. Increase the dependence distance by increasing the number of loop iterations that occurs between the generation of a loop-carried value and its usage.

Consider the following code example:

 1 #define N 128
 2 
 3 __kernel void unoptimized (__global float * restrict A,
 4                            __global float * restrict result)
 5 {
 6   float mul = 1.0f;
 7 
 8   for (unsigned i = 0; i < N; i++)
 9     mul *= A[i];
10 
11   * result = mul;
12 }
 
==================================================================================
Kernel: unoptimized
==================================================================================
The kernel is compiled for single work-item execution.

Loop Report:

 + Loop "Block1" (file unoptimized.cl line 8)
   Pipelined with successive iterations launched every 6 cycles due to:

       Data dependency on variable mul  (file unoptimized.cl line 9)
       Largest Critical Path Contributor:
           100%: Fmul Operation  (file unoptimized.cl line 9)


===================================================================================

The optimization report above shows that the infers pipelined execution for the loop successfully. However, the loop-carried dependency on the variable mul causes loop iterations to launch every six cycles. In this case, the floating-point multiplication operation on line 9 (that is, mul *= A[i]) contributes the largest delay to the computation of the variable mul.

To relax the loop-carried data dependency, instead of using a single variable to store the multiplication results, operate on M copies of the variable and use one copy every M iterations:

  1. Declare multiple copies of the variable mul (for example, in an array called mul_copies).
  2. Initialize all the copies of mul_copies.
  3. Use the last copy in the array in the multiplication operation.
  4. Perform a shift operation to pass the last value of the array back to the beginning of the shift register.
  5. Reduce all the copies to mul and write the final value to result.
Below is the restructured kernel: 
 1 #define N 128
 2 #define M 8
 3 
 4 __kernel void optimized (__global float * restrict A,
 5                          __global float * restrict result)
 6 {
 7   float mul = 1.0f;
 8 
 9   // Step 1: Declare multiple copies of variable mul
10   float mul_copies[M];
11 
12   // Step 2: Initialize all copies
13   for (unsigned i = 0; i < M; i++)
14     mul_copies[i] = 1.0f;
15 
16   for (unsigned i = 0; i < N; i++) {
17     // Step 3: Perform multiplication on the last copy
18     float cur = mul_copies[M-1] * A[i];
19 
20     // Step 4a: Shift copies
21     #pragma unroll 
22     for (unsigned j = M-1; j > 0; j--)
23       mul_copies[j] = mul_copies[j-1];
24 
25     // Step 4b: Insert updated copy at the beginning
26     mul_copies[0] = cur;
27   }
28 
29   // Step 5: Perform reduction on copies
30   #pragma unroll 
31   for (unsigned i = 0; i < M; i++)
32     mul *= mul_copies[i];
33 
34   * result = mul;
35 }

An optimization report similar to the one below indicates the successful relaxation of the loop-carried dependency on the variable mul: 

==================================================================================
Kernel: optimized
==================================================================================
The kernel is compiled for single work-item execution.

Loop Report:

 + Fully unrolled loop (file optimized2.cl line 13)
   Loop was automatically and fully unrolled.
   Add "#pragma unroll 1" to prevent automatic unrolling.


 + Loop "Block1" (file optimized2.cl line 16)
 | Pipelined well. Successive iterations are launched every cycle.
 |
 |
 |-+ Fully unrolled loop (file optimized2.cl line 22)
     Loop was fully unrolled due to "#pragma unroll" annotation.


 + Fully unrolled loop (file optimized2.cl line 31)
   Loop was fully unrolled due to "#pragma unroll" annotation.
Level Two Title