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A newer version of this document is available.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 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 Examples <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

<span class='codeph'>ivdep</span> Attribute

Include the ivdep attribute in your single task kernel to direct the Intel® oneAPI DPC++/C++ Compiler to ignore memory dependencies carried by the loop that the attribute is applied to. This attribute applies only to the loop it is applied to, and not to any of the future loops that might appear as a result of the [[intel::loop_coalesce(N)]] attribute.

Syntax

[[intel::ivdep]]
[[intel::ivdep(safelen)]]
[[intel::ivdep(array)]]
[[intel::ivdep(array, safelen)]]
[[intel::ivdep(safelen, array)]]
CAUTION:

Applying the ivdep attribute incorrectly results in functionally incorrect hardware and potential functional differences between the hardware run and emulation. The ivdep attribute is in fact ignored in emulation.

During compilation, the Intel® oneAPI DPC++/C++ Compiler creates hardware that ensures load and store instructions operate within dependency constraints. An example of a dependency constraint is that dependent load and store instructions must execute in order. The presence of the ivdep attribute instructs the Intel® oneAPI DPC++/C++ Compiler to remove the extra hardware between load and store instructions in the loop that immediately follows the attribute declaration in the kernel code. Removing the extra hardware may reduce logic utilization and lower the II value.

You can provide more information about loop dependencies by specifying a safelen parameter to the attribute by adding an integer type C++ constant expression argument to the attribute. The safelen parameter specifies the maximum number of consecutive loop iterations without loop-carried dependencies. For example, [[intel::ivdep(32)]] indicates to the compiler that there are at least 32 iterations of the loop before loop-carried dependencies is introduced. That is, while the [[intel::ivdep]] attribute guarantees to the compiler that there are no implicit memory dependencies between any iteration of this loop, [[intel::ivdep(32)]] guarantees that there does not exist a loop-carried dependence with a dependence distance less than 32. For example, if an iteration reads from memory, the preceding 31 iterations and succeeding 31 iterations are guaranteed not to write to the same memory location.

NOTE:
A safelen setting of 1 or 0 is allowed as a convenience, but it has no effect on the loop and the compiler generates a warning.

To specify that accesses to a particular memory array inside a loop do not cause loop-carried dependencies, add the array parameter to the attribute by specifying the array variable name as an argument to the attribute. The array specified by the ivdep attribute must be a local or private memory array, or a pointer variable that points to a global, local, or private memory storage. The array specified by the ivdep attribute can also be an array or a pointer member of a struct.

Examples

// No loop-carried dependencies for accesses to arrays A and B
[[intel::ivdep]]
for (int i = 0; i < N; i++) {
  A[i] = A[i - X[i]];
  B[i] = B[i - Y[i]];
}

// No loop-carried dependencies for accesses to array A
// Compiler inserts hardware that reinforces dependency constraints for B
[[intel::ivdep(A)]]
for (int i = 0; i < N; i++) {
  A[i] = A[i - X[i]];
  B[i] = B[i - Y[i]];
}
// No loop-carried dependencies for array A inside struct
[[intel::ivdep(S.A)]]
for (int i = 0; i < N; i++) {
  S.A[i] = S.A[i - X[i]];
}
// No loop-carried dependencies for array A inside the struct pointed by S
[[intel::ivdep(S->X[2][3].A)]]
for (int i = 0; i < N; i++) {
  S->X[2][3].A[i] = S.A[i - X[i]];
}
CAUTION:

When specifying the array name an ivdep attribute must apply to, the compiler still claims there is a memory dependency on that array. Consider the following example code: 

[[intel::ivdep( kSafeLen, histogram.data_ )]] 
for( uint32_t n = 0; n < kInitNumInputs; ++n ) {
  // Compute the Histogram index to increment
  uint32_t hist_group = input[n] % kNumOutputs;
  auto hist_count = histogram.read( hist_group );
  hist_count++;
  histogram.write( hist_group, hist_count );
}

This for loop returns an II of 2 and reports memory dependency on the histogram.data_ array, to which the compiler must apply the ivdep attribute. histogram.data_ is accessed in the histogram.write() and histogram.read() function calls, which prevents the ivdep directive from working.





You can apply [[intel::ivdep(safelen, array)]] only to accesses of that specific array by name in the code that is lexicographically in the loop, which means the array is not traced through function calls.

NOTE:

For additional information, refer to the FPGA tutorial sample "Loop IVDEP" listed in the Intel® oneAPI Samples Browser on Linux* or Windows*, or access the code sample on GitHub.

Parent topic: Loop Directives
Level Two Title