#compiler-optimization

[goodanswerbiz]

How-to: Why does GCC generate such radically different assembly for nearly the same C code? #development #it #answer

How-to: Why does GCC generate such radically different assembly for nearly the same C code? #development #it #answer

Why does GCC generate such radically different assembly for nearly the same C code?

While writing an optimized ftol function I found some very odd behaviour in GCC 4.6.1. Let me show you the code first (for clarity I marked the differences):

fast_trunc_one, C:

int fast_trunc_one(int i) { int mantissa, exponent, sign, r; mantissa = (i & 0x07fffff) | 0x800000; exponent = 150 - ((i >> 23) & 0xff);…

View On WordPress

[goodanswerbiz]

Answer: What is &&& operation in C #computers #programming #development

Answer: What is &&& operation in C #computers #programming #development

What is &&& operation in C

#include <stdio.h> int main(void) { int i, c; for (i = 0; i < 3; i++) { c = i &&& i; printf("%d\n", c); } return 0; }

The output of the above program compiled using gcc is

0 1 1

With the -Wall or -Waddress option, gcc issues a warning:

warning: the address of ‘i’ will always evaluate as ‘true’ [-Waddress]

How is c being evaluated in the above program?

Answer [by Luch…

View On WordPress

[sevennet-blog]

Answer: Efficiency of premature return in a function #computers #dev #fix

Answer: Efficiency of premature return in a function #computers #dev #fix

Efficiency of premature return in a function

This is a situation I encounter frequently as an inexperienced programmer and am wondering about particularly for an ambitious, speed-intensive project of mine I’m trying to optimize. For the major C-like languages (C, objC, C++, Java, C#, etc) and their usual compilers, will these two functions run just as efficiently? Is there any difference in the…

View On WordPress

[sevennet-blog]

How to: Why can lambdas be better optimized by the compiler than plain functions?

How to: Why can lambdas be better optimized by the compiler than plain functions?

Why can lambdas be better optimized by the compiler than plain functions?

In his book The C++ Standard Library (Second Edition) Nicolai Josuttis states that lambdas can be better optimized by the compiler than plain functions.

In addition, C++ compilers optimize lambdas better than they do ordinary functions. (Page 213)

Why is that?

I thought when it comes to inlining there shouldn’t be any…

View On WordPress

[sevennet-blog]

How to: Using this pointer causes strange deoptimization in hot loop

How to: Using this pointer causes strange deoptimization in hot loop

Using this pointer causes strange deoptimization in hot loop

I recently came across a strange deoptimization (or rather missed optimization opportunity).

Consider this function for efficient unpacking of arrays of 3-bit integers to 8-bit integers. It unpacks 16 ints in each loop iteration:

void unpack3bit(uint8_t* target, char* source, int size) { while(size > 0){ uint64_t t =…

View On WordPress

[sevennet-blog]

How to: What is &&& operation in C

How to: What is &&& operation in C

What is &&& operation in C

#include <stdio.h> int main(void) { int i, c; for (i = 0; i < 3; i++) { c = i &&& i; printf("%d\n", c); } return 0; }

The output of the above program compiled using gcc is

0 1 1

With the -Wall or -Waddress option, gcc issues a warning:

warning: the address of ‘i’ will always evaluate as ‘true’ [-Waddress]

How is c being evaluated in the above program?

Answer: What is…

View On WordPress

[goodanswerbiz]

Solution: Why is one loop so much slower than two loops? #dev #it #computers

Solution: Why is one loop so much slower than two loops? #dev #it #computers

Why is one loop so much slower than two loops?

Suppose a1, b1, c1, and d1 point to heap memory and my numerical code has the following core loop.

const int n=100000 for(int j=0;j<n;j++){ a1[j] += b1[j]; c1[j] += d1[j]; }

This loop is executed 10,000 times via another outer for loop. To speed it up, I changed the code to:

for(int j=0;j<n;j++){ a1[j] += b1[j]; } for(int j=0;j<n;j++){ c1[j] +=…

View On WordPress

[sevennet-blog]

How to: Replacing a 32-bit loop count variable with 64-bit introduces crazy performance deviations

How to: Replacing a 32-bit loop count variable with 64-bit introduces crazy performance deviations

Replacing a 32-bit loop count variable with 64-bit introduces crazy performance deviations

I was looking for the fastest way to popcount large arrays of data. I encountered a very weird effect: Changing the loop variable from unsigned to uint64_t made the performance drop by 50% on my PC.

The Benchmark

#include #include #include int main(int argc, char* argv[]) { using namespace std; if (argc !=…

View On WordPress