Performance and profiling of OpenMP C++ code in VS107
I have a performance critical piece of C++ code running in Visual Studio 2017 that I've been profiling to look for potential bottlenecks. The profiler at a high level shows about 80% CPU usage across my eight cores executing this code. Having loaded in all the kernel symbols, the profiler shows that the busiest function is NTYieldExecution at 52% usage.
My guess is that this 52% is not correct, possibly 52% of one thread, but even then I'd be keen to know what's going on under the hood. I also have my own thread pool code which lead to 100% CPU usage on other code, so I'm wondering whether to move this code to an alternative multi-threading model. OpenMP is very convenient, but is it inefficient in Visual Studio 2017? More importantly, is it possible to isolate and remove any such inefficiencies?
The problem as it turned out was that part of the multi-threaded code in this case was inadvertently writing to a variable outside the scope of the OpenMP section which was in turn leading to the automatic insertion of a lock, as seen in the PartialBarrierN::Block. I resolved this by changing this to a more local variable which resulted in a significant speed up and 100% CPU usage.
- Why does 1.0/100.0 == 0.1/10.0 give True?
- How to organize the receive msg and user current input in C network such that it's clean
- Using inclusive scan syntax in OpenMP in the C language
- Unable to understand context in book "OOP in C" by Axel Schreiner
- How to dereference member from struct in which the definition is hid from user?
- variable-length array in struct with TI compiler in C (socket programming)
- A faster way to test 32bpp DDBs for a valid Alpha channel
- How can I compile the zephyr example-application as a freestanding application?
- Why does my forked process sometimes overwrite data in a file?
- Why in C can I initialize more values than the size of an array?
- _Generic in C needs typecasting?
- Declaring/defining an unused variable changes the output from an unrelated variable
- How to use gdb to explore the stack/heap?
- How can I read an input string of unknown length?
- Confused by difference between expression inside if and expression outside if
- Fast Arc Cos algorithm?
- Discrepancy of `unsigned long` size between llvm and gcc in riscv32
- GCC (C) - error: 'x' redeclared as different kind of symbol
- Why does GCC’s static analyser falsely warn that a pointer to an allocated memory block itself stored in an allocated memory block may leak?
- c language gcc compiler *.i file #3 "" 2 what is this?
- How to make clang compile to llvm IR
- Hashtable implementation in C
- EFI variables or config file on the EFI partition for EFI application?
- Pack high bit of every byte in ARM, for 64 bytes like AVX512 vpmovb2m?
- Calling an external C function (in a shared lib) from Perl with Inline::C does not work
- Can a C program detect if its own source code has been modified?
- Is this declaration UB?
- Eclipse C/C++ how to find variable belongs to which struct quickly
- Is this truly best way to delete last element in C?
- flint/arb.h: No such file or directory