You need to log in to make submissions.
Please read the general instructions for this exercise first. Here are the additional instructions specific to this task:
Implement a fast GPU solution using specialized SIMD instructions available on Turing.
This is a technique exercise, a valid solution must make use of the __dp4a intrinsic.
I will first run all kinds of tests to see that your code works correctly. You can try it out locally by running ./grading test, but please note that your code has to compile and work correctly not only on your own computer but also on our machines.
If all is fine, I will run the benchmarks. You can try it out on your own computer by running ./grading benchmark, but of course the precise running time on your own computer might be different from the performance on our grading hardware.
| Name | Parameters |
|---|---|
| benchmarks/1a | k = 1000, m = 1000, n = 1000 |
| multiply a 1000 × 1000 matrix with a 1000 × 1000 matrix for a 1000 × 1000 result. | |
| benchmarks/1b | k = 1003, m = 999, n = 1001 |
| multiply a 999 × 1003 matrix with a 1003 × 1001 matrix for a 999 × 1001 result. | |
| benchmarks/2a | k = 6000, m = 6000, n = 6000 |
| multiply a 6000 × 6000 matrix with a 6000 × 6000 matrix for a 6000 × 6000 result. | |
| benchmarks/2b | k = 15040, m = 15040, n = 15040 |
| multiply a 15040 × 15040 matrix with a 15040 × 15040 matrix for a 15040 × 15040 result. | |
| benchmarks/3 | k = 24000, m = 24000, n = 24000 |
| multiply a 24000 × 24000 matrix with a 24000 × 24000 matrix for a 24000 × 24000 result. | |
In this task your submission will be graded using benchmarks/3: multiply a 24000 × 24000 matrix with a 24000 × 24000 matrix for a 24000 × 24000 result..
The point thresholds are as follows. If you submit your solution no later than on Wednesday, 03 December 2025, at 23:59:59 (Helsinki), your score will be:
| Running time | Points |
|---|---|
| ≤ 4.000 sec | 1 |
| ≤ 3.000 sec | 2 |
| ≤ 2.000 sec | 3 |
| ≤ 1.500 sec | 4 |
If you submit your solution after the deadline, but before the course ends on Wednesday, 31 December 2025, at 23:59:59 (Helsinki), your score will be:
| Running time | Points |
|---|---|
| ≤ 4.000 sec | 1 |
| ≤ 3.000 sec | 2 |
| ≤ 2.000 sec | 3 |
| ≤ 1.500 sec | 4 |
Your submissions to this task will also automatically take part in the contest, and you can receive up to 2 additional points if your code is among the fastest solutions this year!
| Running time | Extra points |
|---|---|
| ≤ 1.20 × fastest | 1 |
| ≤ 1.05 × fastest | 2 |