llvm-project.git/libc/benchmarks/gpu/LibcGpuBenchmark.cpp, branch users/nico/python-1

[libc][gpu] Add Atan2 Benchmarks (#104708)

2024-08-18T17:50:30+00:00

This PR adds benchmarking for `atan2()`, `__nv_atan2()`, and
`__ocml_atan2_f64()` using the same setup as `sin()`. This PR also adds
support for throughout bencmarking for functions with 2 inputs.

[libc] [gpu] Fix Minor Benchmark UI Issues (#102529)

2024-08-08T20:32:20+00:00

Previously, `AmdgpuSinTwoPow_128` and others were too large for their
table cells. This PR shortens the name to `AmdSin...`

There were also some `-` missing in the separator. This PR instead
creates the separator string using the length of the headers.

[libc] [gpu] Change Time To Be Per Iteration (#101919)

2024-08-05T13:27:31+00:00

Previously, the time field was the total time take to run all iterations
of the benchmark. This PR changes the value displayed to be the average
time take by each iteration.

[libc] Add Generic and NVPTX Sin Benchmark (#99795)

2024-07-30T03:09:11+00:00

This PR adds sin benchmarking for a range of values and on a
pregenerated random distribution.

[libc] Add Minimum Time and Iterations, Reduce Epsilon (#100838)

2024-07-27T01:30:19+00:00

This PR adds minimums (50 iterations, 500 us, and epsilon of 0.0001) to
ensure that all benchmarks run at least a set number of times before
outputting a final measurement.

[libc] Fix invalid format specifier in benchmark

2024-07-22T16:21:22+00:00

Summary:
This value is a uint32_t but is printed as a uint64_t, leading to
invalid offsets when done on AMDGPU due to its packed format extending
past the buffer.

[libc] Add N Threads Benchmark Helper (#99834)

2024-07-22T02:56:40+00:00

This PR adds a `BENCHMARK_N_THREADS()` helper to register benchmarks
with a specific number of threads. This PR replaces the flags used
originally to allow any amount of threads.

[libc] Improve Benchmark UI (#99796)

2024-07-21T21:40:01+00:00

This PR changes the output to resemble Google Benchmark. e.g.

```
Running Suite: LlvmLibcIsAlNumGpuBenchmark
Benchmark            |  Cycles |     Min |     Max | Iterations |   Time (ns) |   Stddev |  Threads |
-----------------------------------------------------------------------------------------------------
IsAlnum              |      92 |      76 |     482 |         23 |       86500 |       76 |       64 |
IsAlnumSingleThread  |      87 |      76 |     302 |         20 |       72000 |       49 |        1 |
IsAlnumSingleWave    |      87 |      76 |     302 |         20 |       72000 |       49 |       32 |
IsAlnumCapital       |      89 |      76 |     299 |         17 |       78500 |       52 |       64 |
IsAlnumNotAlnum      |      87 |      76 |     303 |         20 |       76000 |       49 |       64 |
```

[libc] Add Multithreaded GPU Benchmarks (#98964)

2024-07-18T12:18:23+00:00

This PR runs benchmarks on a 32 threads (A single warp on NVPTX) by
default, adding the option for single threaded benchmarks. We can
specify that a benchmark should be run on a single thread using the
`SINGLE_THREADED_BENCHMARK()` macro.

I chose to use a flag here so that other options could be added in the
future.

[libc] Use Atomics in GPU Benchmarks (#98842)

2024-07-15T12:08:23+00:00

This PR replaces our old method of reducing the benchmark results by
using an array to using atomics instead. This should help us implement
single threaded benchmarks.