Loop unrolling is a loop optimization strategy.
Questions tagged [loop-unrolling]
164 questions
1
vote
1 answer
cuda - loop unrolling issue
I have a kernel with a #pragma unroll 80 and I'm running it with NVIDIA GT 285, compute capability 1.3,
with grid architecture: dim3 thread_block( 16, 16 ) and dim3 grid( 40 , 30 ) and it works fine.
When I tried running it with NVIDIA GT 580,…
user1280671
- 69
- 2
- 15
1
vote
3 answers
(c++) any way to optimize this loop? can't use function pointer as its inside a class
Trying to optimize the fun_a1() function. The variable j does not change in the scope of fun_a1(). So, checking j==1 or 2 or 3 for each 'i' iteration is obviously a waste of CPU cycles. But if I try to bring the condition evaluation outside the…
Anon Y.
- 99
- 1
- 7
1
vote
1 answer
looping on flattened fortran matrices
I have a bit of code that looks like this:
DO I=0,500
arg1((I*54+1):(I*54+54)) = premultz*sinphi(I+1)
ENDDO
In short, I have an array premultz of dimension 54. I have an array sinphi of dimension 501. I want to take the first value of of…
user1997417
- 13
- 3
1
vote
1 answer
Why does gcc4 not unroll this loop?
In the gcc 4.4.6 docs it is stated:
-funroll-all-loops:
Unroll all loops, even if their number of iterations is uncertain
when the loop isentered.
I am compiling this code:
int unroll(){
int i = 0;
int array[1000];
do {
…
franka
- 1,867
- 3
- 17
- 31
1
vote
1 answer
Loop unrolling and its effects on pipelining and CPE (have the solution, but don't understand it)
Below the line is a question on a practice test. The table actually has all the solutions filled in. However, I need clarification upon why the solutions are what they are. (Read the question below the horizontal line).
For example, I would really…
Kyra Westwood
- 137
- 7
1
vote
2 answers
How to be sure that a parameter will be treated as a constant during the compilation in C++?
I wonder if the two following implementations will produce exactly the same thing with the same performances whatever the compiler I use :
template MyClass1
{
static const unsigned int size_const = 0;
public:
…
Vincent
- 57,703
- 61
- 205
- 388
1
vote
1 answer
Why does memcmp have duplicated lines in bionic?
I found memcmp.c in bionic is like this:
30 int memcmp(const void *s1, const void *s2, size_t n)
31 {
32 const unsigned char* p1 = s1;
33 const unsigned char* end1 = p1 + n;
34 const unsigned char* p2 = s2;
35 int …
Victor S
- 4,021
- 15
- 43
- 54
1
vote
1 answer
Effects of Loop unrolling on memory bound data
I have been working with a piece of code which is intensively memory bound. I am trying to optimize it within a single core by manually implementing cache blocking, sw prefetching, loop unrolling etc. Even though cache blocking gives significant…
Anusuya
- 11
- 1
0
votes
1 answer
Loop unrolling to achieve parallelism
During a lecture my professor gave us the following loop:
for (int i = 0; i < 100; i++) {
a[i] = a[i] + b[i];
b[i + 1] = c[i] + d[i];
}
He pointed out the dependency between iterations of the loop because line three sets a value that is…
Joe P
- 1
0
votes
3 answers
optimization tool
I wonder there are any tool to optimize my program in term of loop unrolling, and how can I use it?
I have the following python code:
for i in range(0, 1000):
a = a * 10 + a%4 + i
for j in range(0, 1000):
j = j + a
for b in range(0,…
user1041338
0
votes
1 answer
Unrolling loops in one file
I'm writing Objective-C code with LLVM. I have one file full of very performance-critical code. Is it possible to turn on compiler optimizations (specifically, loop unrolling) for just this one file, without setting a project-wide value?
Bill
- 44,502
- 24
- 122
- 213
0
votes
0 answers
Is there some kind of data structure in a fragment shader where I can store processed data that will not cause loops to unroll?
Basically I am trying to create an SDF shader that runs entirely off a data stream. The problem is the inside the mapping function is a loop to process and unify the data from the various shapes. However the results from each shape need to be stored…
Simon
- 1
- 1
0
votes
1 answer
How do I force the GCC compiler to unroll loops?
I'm writing a C program and want a loop unrolled. I need to force the compiler to unroll a loop where the number of iterations is known at compile time.
I've tried compiling using "-O0 -funroll-all-loops". I've tried using #pragma GCC unroll, I've…
alon
- 1
- 1
0
votes
0 answers
Optimize Horner Method to Reduce CPE (CSAPP)
Using loop unrolling to reduce the CPE of Horner Method enter image description here
I have to optimize a question using Horner Method.
Its original solution was:
void poly(const double a[], double x, long degree, double *result) {
long i;
…
Cius
- 1
- 1
0
votes
2 answers
Optimization Loop unrolling to find the inverse of a matrix by the gauss jordan method
I am trying to apply the loop unrolling to find the inverse of a matrix by the Gauss Jorda method, to reduce the number of memory accesses (bottleneck) when the size of the matrices is very large and does not fit in the caches.
I get it to go…
subject25
- 1
- 2