Developer Guide

Intel® oneAPI DPC++/C++ Compiler Handbook for FPGAs

Download PDF
ID 785441
Date 6/24/2024
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A newer version of this document is available.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
Intel oneAPI DPC++/C++ Compiler Handbook for FPGAs Overview Introduction To FPGA Design Concepts Intel oneAPI FPGA Development Getting Started with the Intel oneAPI DPC++/C++ Compiler for Intel FPGA Development Defining a Kernel for FPGAs Debugging and Verifying Your Design Analyzing Your Design Optimizing Your Kernel Optimizing Your Host Application Integrating Your Kernel into DSP Builder for Intel FPGAs Integrating Your RTL IP Core Into a System RTL IP Core Kernel Interfaces Loops Pipes Data Types and Arithmetic Operations Parallelism Memories and Memory Operations Libraries Additional FPGA Acceleration Flow Considerations FPGA Optimization Flags, Attributes, Pragmas, and Extensions Quick Reference Additional Information Document Revision History for the Intel oneAPI DPC++/C++ Compiler Handbook for Intel FPGAs Notices and Disclaimers
Introduction To FPGA Design Concepts x
FPGA Architecture Overview Concepts of FPGA Hardware Design How Source Code Becomes a Custom Hardware Datapath
How Source Code Becomes a Custom Hardware Datapath x
Mapping Source Code Instructions to Hardware Scheduling Mapping Parallelism Models to FPGA Hardware Memory Types
Intel oneAPI FPGA Development x
FPGA Flow Terminology Intel oneAPI FPGA Development Flow Types of SYCL* FPGA Compilation FPGA Compilation Flags FPGA Workflows in IDEs
Types of SYCL* FPGA Compilation x
Separating Device and Host Code Compilation
Getting Started with the Intel oneAPI DPC++/C++ Compiler for Intel FPGA Development x
Installing the Intel oneAPI FPGA Development Environment FPGA Development for Intel oneAPI Toolkits with Visual Studio* Code
Installing the Intel oneAPI FPGA Development Environment x
Simulation Prerequisites Installing the Questa*-Intel FPGA Edition Software Set Up the Simulation Environment
FPGA Development for Intel oneAPI Toolkits with Visual Studio* Code x
Set the Environment Variables and Launch Visual Studio* Code Create an FPGA Visual Studio* Code Project Enable Code Completion in a Visual Studio* Code Project Configure Running and Debugging in a Visual Studio* Code Project Debugging Your Kernel in Visual Studio* Code with a Native Debugger Generate and View the FPGA Optimization Report Build and Run the FPGA Hardware Image
Defining a Kernel for FPGAs x
Suggested Kernel Coding Styles Single Work-Item Kernels
Single Work-Item Kernels x
Single Work-item Kernel Design Guidelines Single-Cycle Floating-Point Accumulator for Single Work-Item Kernels
Single-Cycle Floating-Point Accumulator for Single Work-Item Kernels x
Strategies for Inferring the Accumulator
Debugging and Verifying Your Design x
Device Selectors for FPGA printf Command Restrictions Emulate and Debug Your Design Evaluate Your Kernel Through Simulation
Emulate and Debug Your Design x
Emulator Environment Variables Compile and Emulate Your Design Limitations of the Emulator Troubleshooting Discrepancies in Hardware and Emulator Results Emulator Known Issues
Evaluate Your Kernel Through Simulation x
Debug During Verification Compile a Kernel for Simulation Simulate Your Kernel Viewing Simulation Waveforms Troubleshooting Simulator Issues
Analyzing Your Design x
Review the FPGA Optimization Report Quartus (Static) Summary Intel® FPGA Dynamic Profiler for DPC++
Review the FPGA Optimization Report x
Loop Analysis Bottlenecks Viewer Area Estimates System Viewer Kernel Memory Viewer Schedule Viewer Access FPGA Optimization Reports in JSON Format
Quartus (Static) Summary x
Timing Failures
Intel® FPGA Dynamic Profiler for DPC++ x
Measure Kernel Performance Instrument the Kernel Pipeline with Performance Counters (-Xsprofile) Obtain Profiling Data During Run Time Reduce Area Resource Use While Profiling Profiler Analyses of Example SYCL* Design Scenarios Limitations
Obtain Profiling Data During Run Time x
Invoke the Profiler Runtime Wrapper to Obtain Profiling Data Use Intel® VTune™ Profiler
Use Intel® VTune™ Profiler x
Interpret Performance Counter Data
Optimizing Your Host Application x
Throughput Resource Use System-level Profiling Using the Intercept Layer for OpenCL™ Applications Multithreaded 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
System-level Profiling Using the Intercept Layer for OpenCL™ Applications x
Set Up the Intercept Layer for OpenCL™ Applications
Double Buffering Host Utilizing Kernel Invocation Queue x
Analyzing Buffering Using the Intercept Layer for OpenCL™ Applications
Integrating Your RTL IP Core Into a System x
Synthesize Your RTL IP Core with Quartus Prime Software Encrypting RTL IP Cores Add an RTL IP Core into a Platform Designer System Add an RTL IP Core into a Quartus Prime Project
Encrypting RTL IP Cores x
Encrypting RTL IP Cores Without Licensing Encrypting RTL IP Core With Licensing
RTL IP Core Kernel Interfaces x
Kernel Argument Interfaces Memory-Mapped (MM) Agent Kernel Invocation Interface Ready/Valid Handshaking Kernel Invocation Interface Memory-Mapped Host Interfaces Structs in RTL IP Core Interfaces IP core Reset Behavior
Memory-Mapped Host Interfaces x
Memory-Mapped Host Interfaces Using Unified Shared Memory Pointers and the annotated_arg Class Memory-Mapped Host Interfaces Using Accessors
Memory-Mapped Host Interfaces Using Unified Shared Memory Pointers and the annotated_arg Class x
Buffer Locations in Memory-Mapped Host Interfaces The annotated_arg Template Class
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 Improve fMAX/II with Shannonization Optimize Inner Loop Throughput Improve Loop Performance by Caching Data in On-Chip Memory
Pipes x
Host Pipes Pipes Extension
Host Pipes x
Host Pipe Declaration Host Pipe API Host Pipes RTL Interfaces
Pipes Extension x
Key Properties of a Pipe Accessing Pipes The pipe Class and its Use I/O Pipes Characteristics of Pipes Restrictions of Pipes Guidelines for Designing Pipes The atomic_fence Function and Pipes
I/O Pipes x
Emulate Applications with a Pipe That Reads or Writes to an I/O Pipe
Data Types and Arithmetic Operations x
Optimize Floating-point Operation Minimize the Use of Expensive Functions Variable-Precision Data Type Support
Variable-Precision Data Type Support x
Advantages and Limitations of Variable Precision Data Types Declare and Use the AC Data Types
Declare and Use the AC Data Types x
Declare the ac_int Data Type Declare the ac_fixed Data Type Declare the ac_complex Data Type Declare the ap_float Data Type
Declare the ap_float Data Type x
Conversion Rules for the ap_float Data Type Operations with Explicit Precision Controls Comparison Operators Additional ap_float Functions Additional Data Types Provided by the ap_float.hpp Header File Quality of Results and the ap_float Data Type
Parallelism x
Pipelined Kernels NDRange Kernels Asynchronous Parallelism Within Kernels (task_sequence)
Pipelined Kernels x
Stable Arguments
Asynchronous Parallelism Within Kernels (task_sequence) x
Task Functions task_sequence Use Cases
Memories and Memory Operations x
The device_global Extension (Beta) The annotated_ptr Template Class (Beta) Memory Accesses Kernel Variable Accesses
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
Libraries x
Use SYCL Shared Library With Third-Party Applications Use of RTL Libraries for FPGA Object Manifest File Syntax of an RTL Library Restrictions and Limitations in RTL Support Agilex 7 and Stratix 10 Design-Specific Reset Requirements for Stall-Free and Stallable RTL Libraries Stall-Free RTL
Additional FPGA Acceleration Flow Considerations x
FPGA-CPU Interaction FPGA Boards and Board Support Packages (BSPs) Targeting Multiple Identical FPGA Devices Targeting Multiple Platforms Split Kernel into Multiple FPGA Images (Linux only)
FPGA Boards and Board Support Packages (BSPs) x
The FPGA Board Utility Commands Managing an FPGA Board Advanced Board Management The OpenCL™ Installable Client Driver (ICD)
Advanced Board Management x
Extracting the FPGA Device Image (.aocx) File from a Multiarchitecture Binary File
FPGA Optimization Flags, Attributes, Pragmas, and Extensions x
Optimization Flags Optimization Targets Kernel Variables Kernel Attributes Memory Attributes Loop Directives Floating-Point Pragmas Latency Controls (Beta)
Optimization Flags x
Specify Schedule fMAX Target for Kernels (-Xsclock=<clock target>) Create a 2xclock Interface (-Xsuse-2xclock) Disable Burst-Interleaving of Global Memory (-Xsno-interleaving) Force Ring Interconnect for Global Memory (-Xsglobal-ring) Force a Single Store Ring to Reduce Area (-Xsforce-single-store-ring) Force Fewer Read Data Reorder Units to Reduce Area (-Xsnum-reorder) Disable Hardware Kernel Invocation Queue (-Xsno-hardware-kernel-invocation-queue) Modify the Handshaking Protocol Between Clusters (-Xshyper-optimized-handshaking) Disable Automatic Fusion of Loops (-Xsdisable-auto-loop-fusion) Fuse Adjacent Loops With Unequal Trip Counts (-Xsenable-unequal-tc-fusion) Pipeline Loops in Non-task Kernels (-Xsauto-pipeline) Control Semantics of Floating-Point Operations (-fp-model=<value>) Modify the Rounding Mode of Floating-point Operations (-Xsrounding=<rounding_type>) Global Control of Exit FIFO Latency of Stall-free Clusters (-Xssfc-exit-fifo-type=<value>) Enable the Read-Only Cache for Read-Only Accessors (-Xsread-only-cache-size=<N>) Control Hardware Implementation of the Supported Data Types and Math Operations (-Xsdsp-mode=<option>) Generate Register Map Wrapper (-Xsregister-map-wrapper-type) Allow Wide Memory Initialization (-Xsallow-wide-device-globals)
Optimization Targets x
Minimum Latency Flow Minimum Area Flow Balanced Throughput-Area Trade-Offs Flow
Kernel Attributes x
Specify Schedule fMAX Target for Kernels (scheduler_target_fmax_mhz) Specify a Workgroup Size (max_work_group_size/reqd_work_group_size) Specify Number of SIMD Work Items (num_simd_work_items) Omit Hardware that Generates and Dispatches Kernel IDs (max_global_work_dim) Omit Hardware that Supports Global Work Offsets (no_global_work_offset) Reduce Kernel Area and Latency (use_stall_enable_clusters)
Loop Directives x
disable_loop_pipelining Attribute initiation_interval Attribute ivdep Attribute loop_coalesce Attribute max_concurrency Attribute max_interleaving Attribute speculated_iterations Attribute unroll Pragma Loop Fuse Functions and nofusion Attribute max_reinvocation_delay Attribute (Beta)
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
Intel oneAPI DPC++/C++ Compiler Handbook for FPGAs Overview
Introduction To FPGA Design Concepts
Intel oneAPI FPGA Development
Getting Started with the Intel oneAPI DPC++/C++ Compiler for Intel FPGA Development
Defining a Kernel for FPGAs
Debugging and Verifying Your Design
Analyzing Your Design
Optimizing Your Kernel
Optimizing Your Host Application
Integrating Your Kernel into DSP Builder for Intel FPGAs
Integrating Your RTL IP Core Into a System
RTL IP Core Kernel Interfaces
Loops
Pipes
Data Types and Arithmetic Operations
Parallelism
Memories and Memory Operations
Libraries
Additional FPGA Acceleration Flow Considerations
FPGA Optimization Flags, Attributes, Pragmas, and Extensions
Quick Reference
Additional Information
Document Revision History for the Intel oneAPI DPC++/C++ Compiler Handbook for Intel FPGAs
Notices and Disclaimers

ivdep Attribute

Include the ivdep attribute in your single task kernel to direct the Intel® oneAPI DPC++/C++ Compiler to ignore memory aliasing 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 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.

IMPORTANT:

The ivdep attribute applies to memory aliasing dependencies and not memory ordering dependencies.

For example, the ivdep attribute in the following code does not cause the compiler to ignore dependencies.

atomic_ref<int, memory_order::acquire, memory_scope_device> B_ref(B);
atomic_ref<int, memory_order::release, memory_scope_device> A_ref(A);
[[intel::ivdep]]
for (int i = 0; i < N; ++i) {
  // Assume A and B don't alias
  A_ref[i] = ...;
  ... = B_ref[i];
}

Because the atomic store to A has release semantics (that is, the store must happen after any memory operation that comes before it), and the atomic load from B has acquire semantics (that is, the load must happen before any memory operation that comes after it) then the ivdep attribute will not cause the compiler to ignore the dependence between the load on iteration i and the store on iteration i+1.

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]];
}

RESTRICTION:
Do not apply the ivdep attribute to a variable that is used in a lambda function or a variable that is passed as a function argument. The ivdep attribute is not propagated to the lambda function or function argument. Because the attribute is not propagated, its effects are ignored and can result in functional failures in your kernel. 
// The ivdep directive will not be applied to usages of accessorA inside the lambda foo or the function bar
[[intel::ivdep(accessorA, safelen)]]
for (;;){
  auto foo = [=](){ ...; // Uses of accessorA }
  bar(accessorA, ...);
}

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.

CAUTION:

if a loop with the [[intel::ivdep]] or [[intel::ivdep(safelen)]] attributes has an array declared within the scope of the loop itself, the effects of the ivdep apply to the loads and stores of that array.

It is currently undefined behavior to add an ivdep attribute to a loop that includes a locally-defined array if the same indices of that array are accessed in consecutive loop iterations. Even though such a program does not technically have loop-carried dependencies, this is a current limitation of the compiler.

Consider the following example:

[[intel::ivdep]]
for (int i = 0; i < N; ++i) {
  int A[2];
  A[0] = i;
  A[1] = i+1;
  ...
  B[idx[i]] = A[i%2];
}

Although A is local to the loop, because we generate one physical memory for A, we need to make sure that the writes to A in iteration i happen after the read from A in iteration i-1. Removing that dependence may lead to undefined behavior.

For this example, if the accesses to B do not have loop-carried dependencies, it would be legal to replace [[intel::ivdep]] with [[intel::ivdep(B)]].

For additional information, refer to "Loop ivdep Sample" on GitHub.

Parent topic: Loop Directives
Level Two Title