Ttykuu

Why is this estimator biased?

Quoting Keynes in a lecture

This is why we puzzle

What happens if you are holding an Iron Flask with a demon inside and walk into an Antimagic Field?

How to cover method return statement in Apex Class?

Why does AES have exactly 10 rounds for a 128-bit key, 12 for 192 bits and 14 for a 256-bit key size?

Why should universal income be universal?

What does "Scientists rise up against statistical significance" mean? (Comment in Nature)

What is Cash Advance APR?

Angel of Condemnation - Exile creature with second ability

Unexpected behavior of the procedure `Area` on the object 'Polygon'

putting logo on same line but after title, latex

Temporarily disable WLAN internet access for children, but allow it for adults

How do apertures which seem too large to physically fit work?

What if a revenant (monster) gains fire resistance?

How do I delete all blank lines in a buffer?

Can disgust be a key component of horror?

How can mimic phobia be cured?

How do you respond to a colleague from another team when they're wrongly expecting that you'll help them?

Can I say "fingers" when referring to toes?

Does the UK parliament need to pass secondary legislation to accept the Article 50 extension

Calculate sum of polynomial roots

Store Credit Card Information in Password Manager?

It grows, but water kills it

Generating random number from a binomial distribution

Generating 1000 random numbersGenerating a random number of progress barsEqualized PRNG number distributionGenerating random XML documentsGenerating new random items from a listRandom distribution in RubyRandom string generating functionSimple game outcome simulatorRandom number distribution programGenerating random N-dimensional arrays

0

$begingroup$

In my application of Monte Carlo simulation, the crucial part is to generate a random number from a binomial distribution with parameters n = size and p = 0.5. Here is my current implementation

#include <stdio.h>
#include <stdint.h>
#include <x86intrin.h>

int64_t rbinom(int64_t size) 
 if (!size) 
 return 0;
 

 int64_t result = 0;
 while (size >= 64) 
 uint64_t random64;
 while (!_rdrand64_step(&random64)) 
 fprintf(stderr, "HW_RND_GEN not readyn");
 
 result += _popcnt64(random64);
 size -= 64;
 

 uint64_t random64;
 while (!_rdrand64_step(&random64)) 
 fprintf(stderr, "HW_RND_GEN not readyn");
 
 result += _popcnt64(random64 & ~(UINT64_MAX << size));

 return result;

However, the result of benchmarking terrifies me:

I'm spending 99.68% of the runtime on this function! How can I optimize it?

The result doesn't need to be cryptographically secure, as long as it's good enough for Monte Carlo simulations.

performance c random statistics x86

share

asked 9 mins ago

nalzoknalzok

311212

$endgroup$

add a comment | 

0

$begingroup$

In my application of Monte Carlo simulation, the crucial part is to generate a random number from a binomial distribution with parameters n = size and p = 0.5. Here is my current implementation

#include <stdio.h>
#include <stdint.h>
#include <x86intrin.h>

int64_t rbinom(int64_t size) 
 if (!size) 
 return 0;
 

 int64_t result = 0;
 while (size >= 64) 
 uint64_t random64;
 while (!_rdrand64_step(&random64)) 
 fprintf(stderr, "HW_RND_GEN not readyn");
 
 result += _popcnt64(random64);
 size -= 64;
 

 uint64_t random64;
 while (!_rdrand64_step(&random64)) 
 fprintf(stderr, "HW_RND_GEN not readyn");
 
 result += _popcnt64(random64 & ~(UINT64_MAX << size));

 return result;

However, the result of benchmarking terrifies me:

I'm spending 99.68% of the runtime on this function! How can I optimize it?

The result doesn't need to be cryptographically secure, as long as it's good enough for Monte Carlo simulations.

performance c random statistics x86

share

asked 9 mins ago

nalzoknalzok

311212

$endgroup$

add a comment | 

$begingroup$

In my application of Monte Carlo simulation, the crucial part is to generate a random number from a binomial distribution with parameters n = size and p = 0.5. Here is my current implementation

#include <stdio.h>
#include <stdint.h>
#include <x86intrin.h>

int64_t rbinom(int64_t size) 
 if (!size) 
 return 0;
 

 int64_t result = 0;
 while (size >= 64) 
 uint64_t random64;
 while (!_rdrand64_step(&random64)) 
 fprintf(stderr, "HW_RND_GEN not readyn");
 
 result += _popcnt64(random64);
 size -= 64;
 

 uint64_t random64;
 while (!_rdrand64_step(&random64)) 
 fprintf(stderr, "HW_RND_GEN not readyn");
 
 result += _popcnt64(random64 & ~(UINT64_MAX << size));

 return result;

However, the result of benchmarking terrifies me:

I'm spending 99.68% of the runtime on this function! How can I optimize it?

The result doesn't need to be cryptographically secure, as long as it's good enough for Monte Carlo simulations.

performance c random statistics x86

share

asked 9 mins ago

nalzoknalzok

311212

$endgroup$

#include <stdio.h>
#include <stdint.h>
#include <x86intrin.h>

int64_t rbinom(int64_t size) 
 if (!size) 
 return 0;
 

 int64_t result = 0;
 while (size >= 64) 
 uint64_t random64;
 while (!_rdrand64_step(&random64)) 
 fprintf(stderr, "HW_RND_GEN not readyn");
 
 result += _popcnt64(random64);
 size -= 64;
 

 uint64_t random64;
 while (!_rdrand64_step(&random64)) 
 fprintf(stderr, "HW_RND_GEN not readyn");
 
 result += _popcnt64(random64 & ~(UINT64_MAX << size));

 return result;

share

asked 9 mins ago

nalzoknalzok

311212

share

asked 9 mins ago

nalzoknalzok

311212

asked 9 mins ago

nalzoknalzok

311212

asked 9 mins ago

nalzoknalzok

311212