fuzzgpu 0.1.8__tar.gz → 0.3.0__tar.gz

{fuzzgpu-0.1.8 → fuzzgpu-0.3.0}/Cargo.lock

@@ -308,9 +308,9 @@ dependencies = [
 
 [[package]]
 name = "either"
-version = "1.17.0"
+version = "1.18.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9e5e8f6c15a24b9a3ee5efec809ccd006d3b30e8b3bb63c39af737c7f87daa1d"
+checksum = "252afb9ae5eaa683babdc6a068b3f5726eb19e05070c731f9b2a23a7c3e8ed34"
 
 [[package]]
 name = "equivalent"
@@ -372,7 +372,7 @@ dependencies = [
 
 [[package]]
 name = "fuzzgpu-core"
-version = "0.1.8"
+version = "0.3.0"
 dependencies = [
  "bytemuck",
  "criterion",
@@ -386,7 +386,7 @@ dependencies = [
 
 [[package]]
 name = "fuzzgpu-python"
-version = "0.1.8"
+version = "0.3.0"
 dependencies = [
  "fuzzgpu-core",
  "log",

{fuzzgpu-0.1.8 → fuzzgpu-0.3.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: fuzzgpu
-Version: 0.1.8
+Version: 0.3.0
 Classifier: Development Status :: 4 - Beta
 Classifier: Intended Audience :: Developers
 Classifier: License :: OSI Approved :: MIT License
@@ -37,7 +37,8 @@ Project-URL: Repository, https://github.com/kuntal-devrat/fuzzgpu
 
 *Cross-platform GPU compute via WebGPU (`wgpu`) & Multi-Core CPU parallelism with Rayon. Zero CUDA dependencies.*
 
-[![PyPI Version](https://img.shields.io/badge/pypi-v0.1.8-blue.svg?style=flat-square)](https://pypi.org/project/fuzzgpu/)
+[![PyPI 
+Version](https://img.shields.io/badge/pypi-v0.3.0-blue.svg?style=flat-square)](https://pypi.org/project/fuzzgpu/)
 [![License: MIT](https://img.shields.io/badge/License-MIT-green.svg?style=flat-square)](https://opensource.org/licenses/MIT)
 [![Rust](https://img.shields.io/badge/rust-1.87+-orange.svg?style=flat-square)](https://www.rust-lang.org)
 [![Cross Platform](https://img.shields.io/badge/platform-Windows%20%7C%20macOS%20%7C%20Linux%20%7C%20WASM-lightgrey.svg?style=flat-square)](https://github.com/kuntal-devrat/fuzzgpu)
@@ -60,7 +61,7 @@ No NVIDIA CUDA drivers or complex toolkits required.
 
 ---
 
-## What's New in v0.1.8
+## What's New in v0.3.0
 
 ### Production hardening
 - **Kernel `get()` panics eliminated** — all four GPU kernels (`GpuLevenshteinKernel`,
@@ -163,10 +164,17 @@ The full Python layer is now byte-identical to rapidfuzz 3.14.5 over a 169,744-p
 
 ## Benchmark Results
 
-*Hardware: Intel(R) Iris(R) Xe Graphics (Vulkan) + Intel Core i7 (Rayon uses all cores)*
-*Versions: fuzzgpu 0.1.8 · rapidfuzz 3.14.5 · python-Levenshtein 0.27.4*
+*Hardware: Intel(R) Iris(R) Xe Graphics — integrated GPU (Vulkan) + Intel Core i7 (Rayon, all cores)*
+*Versions: fuzzgpu 0.3.0 · rapidfuzz 3.14.5 · python-Levenshtein 0.27.4*
 *Median of 7 runs after warmup. Reproduce: `python benchmarks/bench_compare.py`*
 
+> **GPU class note:** These numbers are from an **integrated GPU** (iGPU), which shares memory
+> bandwidth with the CPU and has a ~1 ms dispatch round-trip. On a **discrete GPU** (dGPU) the
+> GPU columns improve significantly — expect 3–10× better GPU throughput and GPU routing kicking
+> in at much smaller batch sizes (threshold drops from ~500 pairs to ~64 pairs automatically).
+> Concurrency gains (multiple Python threads, after the wgpu fix ships) add a further 2–4×
+> on top for server workloads regardless of GPU class.
+
 ### Levenshtein Batch (1 query × N candidates, 10-char strings)
 | Batch Size | `fuzzgpu` (GPU) | `fuzzgpu` (CPU) | `rapidfuzz` | vs RF (GPU) | vs RF (CPU) |
 | :--- | :---: | :---: | :---: | :---: | :---: |
@@ -222,7 +230,7 @@ pip install fuzzgpu
 ```toml
 # Rust
 [dependencies]
-fuzzgpu-core = "0.1.8"
+fuzzgpu-core = "0.3.0"
 ```
 
 ---
@@ -318,7 +326,7 @@ fuzzgpu.set_cpu_only(True)       # force CPU-only mode
 
 ```toml
 [dependencies]
-fuzzgpu-core = "0.1.8"                                        # GPU + CPU fallback
+fuzzgpu-core = "0.3.0"                                        # GPU + CPU fallback
 # fuzzgpu-core = { version = "0.1.7", default-features = false } # CPU-only
 ```
 
@@ -464,7 +472,7 @@ cargo test --workspace
 | `FUZZGPU_DEBUG` | Log GPU→CPU fallback decisions |
 | `FUZZGPU_SIMD` | Force ISA: `portable\|neon\|avx2\|avx512` |
 | `FUZZGPU_READBACK_TIMEOUT_MS` | GPU readback timeout (default 10000 ms) |
-| `FUZZGPU_SKIP_DISPATCH_LOCK` | Bypass serialization lock (repro only) |
+| `FUZZGPU_SKIP_DISPATCH_LOCK` | Opt-in GPU dispatch serialization (safety valve for the rare gfx-rs/wgpu#10085 crash class on Intel D3D12; dispatch is fully concurrent by default) |
 | `FUZZGPU_REQUIRE_GPU` | In tests: fail instead of skip when no GPU |
 | `WGPU_BACKEND` | Force wgpu backend: `vulkan\|metal\|dx12` |
 | `PROPTEST_CASES` | Override proptest case count |

{fuzzgpu-0.1.8 → fuzzgpu-0.3.0}/README.md

@@ -8,7 +8,8 @@
 
 *Cross-platform GPU compute via WebGPU (`wgpu`) & Multi-Core CPU parallelism with Rayon. Zero CUDA dependencies.*
 
-[![PyPI Version](https://img.shields.io/badge/pypi-v0.1.8-blue.svg?style=flat-square)](https://pypi.org/project/fuzzgpu/)
+[![PyPI 
+Version](https://img.shields.io/badge/pypi-v0.3.0-blue.svg?style=flat-square)](https://pypi.org/project/fuzzgpu/)
 [![License: MIT](https://img.shields.io/badge/License-MIT-green.svg?style=flat-square)](https://opensource.org/licenses/MIT)
 [![Rust](https://img.shields.io/badge/rust-1.87+-orange.svg?style=flat-square)](https://www.rust-lang.org)
 [![Cross Platform](https://img.shields.io/badge/platform-Windows%20%7C%20macOS%20%7C%20Linux%20%7C%20WASM-lightgrey.svg?style=flat-square)](https://github.com/kuntal-devrat/fuzzgpu)
@@ -31,7 +32,7 @@ No NVIDIA CUDA drivers or complex toolkits required.
 
 ---
 
-## What's New in v0.1.8
+## What's New in v0.3.0
 
 ### Production hardening
 - **Kernel `get()` panics eliminated** — all four GPU kernels (`GpuLevenshteinKernel`,
@@ -134,10 +135,17 @@ The full Python layer is now byte-identical to rapidfuzz 3.14.5 over a 169,744-p
 
 ## Benchmark Results
 
-*Hardware: Intel(R) Iris(R) Xe Graphics (Vulkan) + Intel Core i7 (Rayon uses all cores)*
-*Versions: fuzzgpu 0.1.8 · rapidfuzz 3.14.5 · python-Levenshtein 0.27.4*
+*Hardware: Intel(R) Iris(R) Xe Graphics — integrated GPU (Vulkan) + Intel Core i7 (Rayon, all cores)*
+*Versions: fuzzgpu 0.3.0 · rapidfuzz 3.14.5 · python-Levenshtein 0.27.4*
 *Median of 7 runs after warmup. Reproduce: `python benchmarks/bench_compare.py`*
 
+> **GPU class note:** These numbers are from an **integrated GPU** (iGPU), which shares memory
+> bandwidth with the CPU and has a ~1 ms dispatch round-trip. On a **discrete GPU** (dGPU) the
+> GPU columns improve significantly — expect 3–10× better GPU throughput and GPU routing kicking
+> in at much smaller batch sizes (threshold drops from ~500 pairs to ~64 pairs automatically).
+> Concurrency gains (multiple Python threads, after the wgpu fix ships) add a further 2–4×
+> on top for server workloads regardless of GPU class.
+
 ### Levenshtein Batch (1 query × N candidates, 10-char strings)
 | Batch Size | `fuzzgpu` (GPU) | `fuzzgpu` (CPU) | `rapidfuzz` | vs RF (GPU) | vs RF (CPU) |
 | :--- | :---: | :---: | :---: | :---: | :---: |
@@ -193,7 +201,7 @@ pip install fuzzgpu
 ```toml
 # Rust
 [dependencies]
-fuzzgpu-core = "0.1.8"
+fuzzgpu-core = "0.3.0"
 ```
 
 ---
@@ -289,7 +297,7 @@ fuzzgpu.set_cpu_only(True)       # force CPU-only mode
 
 ```toml
 [dependencies]
-fuzzgpu-core = "0.1.8"                                        # GPU + CPU fallback
+fuzzgpu-core = "0.3.0"                                        # GPU + CPU fallback
 # fuzzgpu-core = { version = "0.1.7", default-features = false } # CPU-only
 ```
 
@@ -435,7 +443,7 @@ cargo test --workspace
 | `FUZZGPU_DEBUG` | Log GPU→CPU fallback decisions |
 | `FUZZGPU_SIMD` | Force ISA: `portable\|neon\|avx2\|avx512` |
 | `FUZZGPU_READBACK_TIMEOUT_MS` | GPU readback timeout (default 10000 ms) |
-| `FUZZGPU_SKIP_DISPATCH_LOCK` | Bypass serialization lock (repro only) |
+| `FUZZGPU_SKIP_DISPATCH_LOCK` | Opt-in GPU dispatch serialization (safety valve for the rare gfx-rs/wgpu#10085 crash class on Intel D3D12; dispatch is fully concurrent by default) |
 | `FUZZGPU_REQUIRE_GPU` | In tests: fail instead of skip when no GPU |
 | `WGPU_BACKEND` | Force wgpu backend: `vulkan\|metal\|dx12` |
 | `PROPTEST_CASES` | Override proptest case count |

{fuzzgpu-0.1.8 → fuzzgpu-0.3.0}/crates/fuzzgpu-core/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "fuzzgpu-core"
-version = "0.1.8"
+version = "0.3.0"
 edition = "2021"
 description = "GPU-accelerated fuzzy string matching engine"
 license = "MIT"

{fuzzgpu-0.1.8 → fuzzgpu-0.3.0}/crates/fuzzgpu-core/benches/bench.rs

@@ -13,7 +13,9 @@ use criterion::{black_box, criterion_group, criterion_main, Criterion};
 use fuzzgpu_core::damerau::damerau_levenshtein_batch;
 use fuzzgpu_core::fuzz::ratio;
 use fuzzgpu_core::jaro::{jaro_winkler, jaro_winkler_batch};
-use fuzzgpu_core::levenshtein::{levenshtein_cdist_cpu, levenshtein_distance_raw, LevenshteinKernel};
+use fuzzgpu_core::levenshtein::{
+    levenshtein_cdist_cpu, levenshtein_distance_raw, LevenshteinKernel,
+};
 use fuzzgpu_core::needleman::{needleman_wunsch_affine, needleman_wunsch_affine_batch};
 use fuzzgpu_core::simd::levenshtein_myers;
 
@@ -24,7 +26,9 @@ fn gen_strings(count: usize, len: usize, seed: u64) -> Vec<String> {
     for _ in 0..count {
         let mut s = String::with_capacity(len);
         for _ in 0..len {
-            state = state.wrapping_mul(6364136223846793005).wrapping_add(1442695040888963407);
+            state = state
+                .wrapping_mul(6364136223846793005)
+                .wrapping_add(1442695040888963407);
             s.push((b'a' + ((state >> 33) as u8 % 26)) as char);
         }
         out.push(s);
@@ -47,7 +51,11 @@ fn cpu_benches(c: &mut Criterion) {
     let long = gen_strings(2, 256, 3);
 
     let mut g = c.benchmark_group("scalar");
-    for (name, s) in [("short_8", &short), ("medium_64", &medium), ("long_256", &long)] {
+    for (name, s) in [
+        ("short_8", &short),
+        ("medium_64", &medium),
+        ("long_256", &long),
+    ] {
         let (s1, s2) = (&s[0], &s[1]);
         g.bench_function(format!("levenshtein/{name}"), |b| {
             b.iter(|| black_box(levenshtein_distance_raw(s1, s2)))
@@ -62,7 +70,11 @@ fn cpu_benches(c: &mut Criterion) {
             b.iter(|| black_box(ratio(s1, s2)))
         });
         g.bench_function(format!("needleman_affine/{name}"), |b| {
-            b.iter(|| black_box(needleman_wunsch_affine(s1, s2, MATCH, MISMATCH, GAP_OPEN, GAP_EXTEND)))
+            b.iter(|| {
+                black_box(needleman_wunsch_affine(
+                    s1, s2, MATCH, MISMATCH, GAP_OPEN, GAP_EXTEND,
+                ))
+            })
         });
         g.bench_function(format!("damerau/{name}"), |b| {
             b.iter(|| black_box(fuzzgpu_core::damerau::damerau_levenshtein_distance(s1, s2)))
@@ -89,14 +101,27 @@ fn cpu_benches(c: &mut Criterion) {
         b.iter(|| black_box(jaro_winkler_batch(query, &cand_refs, 0.1)))
     });
     g.bench_function("needleman_affine_batch_1000", |b| {
-        b.iter(|| black_box(needleman_wunsch_affine_batch(query, &cand_refs, MATCH, MISMATCH, GAP_OPEN, GAP_EXTEND)))
+        b.iter(|| {
+            black_box(needleman_wunsch_affine_batch(
+                query, &cand_refs, MATCH, MISMATCH, GAP_OPEN, GAP_EXTEND,
+            ))
+        })
     });
     // Long-string needleman (80 chars): the anti-diagonal wavefront GPU path's
     // target workload; Rayon CPU is the comparison baseline.
     let cands_nw80 = gen_strings(1000, 80, 0xAB);
     let cand_refs_nw80: Vec<&str> = cands_nw80.iter().map(|s| s.as_str()).collect();
     g.bench_function("needleman_affine_batch_1000_long80_large", |b| {
-        b.iter(|| black_box(needleman_wunsch_affine_batch(query, &cand_refs_nw80, MATCH, MISMATCH, GAP_OPEN, GAP_EXTEND)))
+        b.iter(|| {
+            black_box(needleman_wunsch_affine_batch(
+                query,
+                &cand_refs_nw80,
+                MATCH,
+                MISMATCH,
+                GAP_OPEN,
+                GAP_EXTEND,
+            ))
+        })
     });
     g.bench_function("damerau_batch_1000", |b| {
         b.iter(|| black_box(damerau_levenshtein_batch(query, &cand_refs)))
@@ -128,8 +153,9 @@ fn cpu_benches(c: &mut Criterion) {
         b.iter(|| black_box(levenshtein_cdist_cpu(&refs_a_1k, &refs_b_1k)))
     });
     // Sequential 10 x 1000 pairs: the CPU baseline for the batched-GPU bench.
-    let cands10: Vec<Vec<String>> =
-        (0..10).map(|i| gen_strings(1000, 16, 0x100 + i as u64)).collect();
+    let cands10: Vec<Vec<String>> = (0..10)
+        .map(|i| gen_strings(1000, 16, 0x100 + i as u64))
+        .collect();
     let ops10: Vec<Vec<(&str, &str)>> = cands10.iter().map(|c| make_pairs(query, c)).collect();
     g.bench_function("levenshtein_10x1000_seq_cpu", |b| {
         b.iter(|| {
@@ -190,13 +216,23 @@ fn gpu_benches(c: &mut Criterion) {
     match GpuNeedlemanAffineKernel::get() {
         Ok(kernel) => {
             g.bench_function("needleman_affine_batch_1000", |b| {
-                b.iter(|| black_box(kernel.compute_batch(&pairs, MATCH, MISMATCH, GAP_OPEN, GAP_EXTEND)))
+                b.iter(|| {
+                    black_box(kernel.compute_batch(&pairs, MATCH, MISMATCH, GAP_OPEN, GAP_EXTEND))
+                })
             });
             // 80-char pairs: routes to the anti-diagonal wavefront kernel.
             let cands_nw80 = gen_strings(1000, 80, 0xAB);
             let pairs_nw80 = make_pairs(query, &cands_nw80);
             g.bench_function("needleman_affine_batch_1000_long80_large", |b| {
-                b.iter(|| black_box(kernel.compute_batch(&pairs_nw80, MATCH, MISMATCH, GAP_OPEN, GAP_EXTEND)))
+                b.iter(|| {
+                    black_box(kernel.compute_batch(
+                        &pairs_nw80,
+                        MATCH,
+                        MISMATCH,
+                        GAP_OPEN,
+                        GAP_EXTEND,
+                    ))
+                })
             });
         }
         Err(e) => {
@@ -247,9 +283,11 @@ fn gpu_benches(c: &mut Criterion) {
             });
             // 10 x 1000 pairs: one batched dispatch+readback vs 10 sequential
             // sync-round-trips. Same total work as cpu_batch/..._seq_cpu.
-            let cands10: Vec<Vec<String>> =
-                (0..10).map(|i| gen_strings(1000, 16, 0x100 + i as u64)).collect();
-            let ops10: Vec<Vec<(&str, &str)>> = cands10.iter().map(|c| make_pairs(query, c)).collect();
+            let cands10: Vec<Vec<String>> = (0..10)
+                .map(|i| gen_strings(1000, 16, 0x100 + i as u64))
+                .collect();
+            let ops10: Vec<Vec<(&str, &str)>> =
+                cands10.iter().map(|c| make_pairs(query, c)).collect();
             g.bench_function("levenshtein_10x1000_seq", |b| {
                 b.iter(|| {
                     for op in &ops10 {
@@ -268,10 +306,16 @@ fn gpu_benches(c: &mut Criterion) {
             });
         }
         Err(e) => {
-            eprintln!("WARN: no GPU device, skipping large-scale GpuLevenshteinKernel benches: {e}");
+            eprintln!(
+                "WARN: no GPU device, skipping large-scale GpuLevenshteinKernel benches: {e}"
+            );
             g.bench_function("levenshtein_batch_100k_large", |b| b.iter(|| black_box(0)));
-            g.bench_function("levenshtein_batch_1000_long256_large", |b| b.iter(|| black_box(0)));
-            g.bench_function("levenshtein_cdist_1000x1000_large", |b| b.iter(|| black_box(0)));
+            g.bench_function("levenshtein_batch_1000_long256_large", |b| {
+                b.iter(|| black_box(0))
+            });
+            g.bench_function("levenshtein_cdist_1000x1000_large", |b| {
+                b.iter(|| black_box(0))
+            });
             g.bench_function("levenshtein_10x1000_seq", |b| b.iter(|| black_box(0)));
             g.bench_function("levenshtein_10x1000_batched", |b| b.iter(|| black_box(0)));
         }