by naveed125 on 3/18/25, 4:32 AM with 4 comments
by naveed125 on 3/18/25, 4:32 AM
by jmillikin on 3/18/25, 6:04 AM
---
The numbers in the table for C vs Rust don't make sense, and I wasn't able to reproduce them locally. For a benchmark like this I would expect to see nearly identical performance for those two languages.
Benchmark sources:
https://github.com/naveed125/rust-vs/blob/6db90fec706c875300...
https://github.com/naveed125/rust-vs/blob/6db90fec706c875300...
Benchmark process and results:
$ gcc --version
gcc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0
$ gcc -O2 -static -o bench-c-gcc benchmark.c
$ clang --version
Ubuntu clang version 14.0.0-1ubuntu1.1
$ clang -O2 -static -o bench-c-clang benchmark.c
$ rustc --version
rustc 1.81.0 (eeb90cda1 2024-09-04)
$ rustc -C opt-level=2 --target x86_64-unknown-linux-musl -o bench-rs benchmark.rs
$ taskset -c 1 hyperfine --warmup 1000 ./bench-c-gcc
Benchmark 1: ./bench-c-gcc
Time (mean ± σ): 3.2 ms ± 0.1 ms [User: 2.7 ms, System: 0.6 ms]
Range (min … max): 3.2 ms … 4.1 ms 770 runs
$ taskset -c 1 hyperfine --warmup 1000 ./bench-c-clang
Benchmark 1: ./bench-c-clang
Time (mean ± σ): 3.5 ms ± 0.1 ms [User: 3.0 ms, System: 0.6 ms]
Range (min … max): 3.4 ms … 4.8 ms 721 runs
$ taskset -c 1 hyperfine --warmup 1000 ./bench-rs
Benchmark 1: ./bench-rs
Time (mean ± σ): 5.1 ms ± 0.1 ms [User: 2.9 ms, System: 2.2 ms]
Range (min … max): 5.0 ms … 7.1 ms 507 runs
Oh, it's because benchmark.rs is performing a dynamic memory allocation for each key. The C version uses a buffer on the stack, with fixed-width keys. Let's try doing the same in the Rust version:
--- benchmark.rs
+++ benchmark.rs
@@ -38,22 +38,22 @@
}
// Generates a random 8-character string
-fn generate_random_string(rng: &mut Xorshift) -> String {
+fn generate_random_string(rng: &mut Xorshift) -> [u8; 8] {
const CHARSET: &[u8] = b"0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ";
- let mut result = String::with_capacity(8);
+ let mut result = [0u8; 8];
- for _ in 0..8 {
+ for ii in 0..8 {
let rand_index = (rng.next() % 62) as usize;
- result.push(CHARSET[rand_index] as char);
+ result[ii] = CHARSET[rand_index];
}
result
}
// Generates `count` random strings and tracks their occurrences
-fn generate_random_strings(count: usize) -> HashMap<String, u32> {
+fn generate_random_strings(count: usize) -> HashMap<[u8; 8], u32> {
let mut rng = Xorshift::new();
- let mut string_counts: HashMap<String, u32> = HashMap::new();
+ let mut string_counts: HashMap<[u8; 8], u32> = HashMap::with_capacity(count);
for _ in 0..count {
let random_string = generate_random_string(&mut rng);
$ taskset -c 1 hyperfine --warmup 1000 ./bench-rs
Benchmark 1: ./bench-rs
Time (mean ± σ): 1.5 ms ± 0.1 ms [User: 1.3 ms, System: 0.2 ms]
Range (min … max): 1.4 ms … 3.2 ms 1426 runs
---
I go to look in benchmark.c, and my eyes are immediately drawn to this weird bullshit:
// Xorshift+ state variables (64-bit)
uint64_t state0, state1;
// Xorshift+ function for generating pseudo-random 64-bit numbers
uint64_t xorshift_plus() {
uint64_t s1 = state0;
uint64_t s0 = state1;
state0 = s0;
s1 ^= s1 << 23;
s1 ^= s1 >> 18;
s1 ^= s0;
s1 ^= s0 >> 5;
state1 = s1;
return state1 + s0;
}
A rough patch to put the state into something the compiler has a hope of optimizing:
--- benchmark.c
+++ benchmark.c
@@ -18,25 +18,35 @@
StringNode *hashTable[HASH_TABLE_SIZE]; // Hash table for storing unique strings
// Xorshift+ state variables (64-bit)
-uint64_t state0, state1;
+struct xorshift_state {
+ uint64_t state0, state1;
+};
// Xorshift+ function for generating pseudo-random 64-bit numbers
-uint64_t xorshift_plus() {
- uint64_t s1 = state0;
- uint64_t s0 = state1;
- state0 = s0;
+uint64_t xorshift_plus(struct xorshift_state *st) {
+ uint64_t s1 = st->state0;
+ uint64_t s0 = st->state1;
+ st->state0 = s0;
s1 ^= s1 << 23;
s1 ^= s1 >> 18;
s1 ^= s0;
s1 ^= s0 >> 5;
- state1 = s1;
- return state1 + s0;
+ st->state1 = s1;
+ return s1 + s0;
}
// Function to generate an 8-character random string
void generate_random_string(char *buffer) {
+ uint64_t timestamp = (uint64_t)time(NULL) * 1000;
+ uint64_t state0 = timestamp ^ 0xDEADBEEF;
+ uint64_t state1 = (timestamp << 21) ^ 0x95419C24A637B12F;
+ struct xorshift_state st = {
+ .state0 = state0,
+ .state1 = state1,
+ };
+
for (int i = 0; i < STRING_LENGTH; i++) {
- uint64_t rand_value = xorshift_plus() % 62;
+ uint64_t rand_value = xorshift_plus(&st) % 62;
if (rand_value < 10) { // 0-9
buffer[i] = '0' + rand_value;
@@ -113,11 +123,6 @@
}
int main() {
- // Initialize random seed
- uint64_t timestamp = (uint64_t)time(NULL) * 1000;
- state0 = timestamp ^ 0xDEADBEEF; // Arbitrary constant
- state1 = (timestamp << 21) ^ 0x95419C24A637B12F; // Arbitrary constant
-
double total_time = 0.0;
// Run 3 times and measure execution time
$ taskset -c 1 hyperfine --warmup 1000 ./bench-c-gcc
Benchmark 1: ./bench-c-gcc
Time (mean ± σ): 1.1 ms ± 0.1 ms [User: 1.1 ms, System: 0.1 ms]
Range (min … max): 1.0 ms … 1.8 ms 1725 runs
$ taskset -c 1 hyperfine --warmup 1000 ./bench-c-clang
Benchmark 1: ./bench-c-clang
Time (mean ± σ): 1.0 ms ± 0.1 ms [User: 0.9 ms, System: 0.1 ms]
Range (min … max): 0.9 ms … 1.4 ms 1863 runs
> Yes, I absolutely used ChatGPT to polish my code. If you’re judging me for this,
> I’m going to assume you still churn butter by hand and refuse to use calculators.
> [...]
> I then embarked on the linguistic equivalent of “Google Translate for code,”