Update README and comment for new GpuProcess

README.md

@@ -17,7 +17,6 @@ The library exports five primary components:
 Below is a complete, self-contained example demonstrating how to initialize the GPU, load data, run a compute shader, and read the results back to the CPU:
 
 ```zig
-
 const std = @import("std");
 const gpu = @import("gpu");
 const GpuDevice = gpu.GpuDevice;
@@ -38,7 +37,15 @@ pub fn main(init: std.process.Init) !void {
     const gloc = grena.gpuAllocator();
 
     // 3. Load the WGSL compute pipeline
-    const add_process = try GpuProcess.init(device, @embedFile("shaders/add.wgsl"));
+    const add_process = try GpuProcess.init(
+        device,
+        @embedFile("shaders/add.wgsl"),
+        .{ .bindings = &.{
+            .{ .element_size = @sizeOf(f16) },
+            .{ .element_size = @sizeOf(f16) },
+            .{ .element_size = @sizeOf(f16) },
+        } },
+    );
     defer add_process.deinit();
 
     // 4. Setup CPU data
@@ -67,8 +74,7 @@ pub fn main(init: std.process.Init) !void {
     try buf_b.load(f16, data_b);
 
     // 7. Dispatch the Compute Process
-    // We pass the data type (f16) to allow GpuProcess to calculate chunks correctly
+    try add_process.run(gloc, .{ buf_a, buf_b, buf_out });
-    try add_process.run(gloc, f16, buf_a, buf_b, buf_out);
 
     // 8. Map and copy the resulting buffer back to the CPU
     const out = try buf_out.read(allocator, f16);
@@ -76,6 +82,7 @@ pub fn main(init: std.process.Init) !void {
 
     std.debug.print("Result: {any}\n", .{out});
 }
+
 ```
 
 ## Dependencies

examples/add.zig

@@ -21,13 +21,11 @@ pub fn main(init: std.process.Init) !void {
     const add_process = try GpuProcess.init(
         device,
         @embedFile("shaders/add.wgsl"),
-        .{
+        .{ .bindings = &.{
-            .bindings = &.{
+            .{ .element_size = @sizeOf(f16) },
-                .{ .element_size = @sizeOf(f16) },
+            .{ .element_size = @sizeOf(f16) },
-                .{ .element_size = @sizeOf(f16) },
+            .{ .element_size = @sizeOf(f16) },
-                .{ .element_size = @sizeOf(f16) },
+        } },
-            },
-        },
     );
     defer add_process.deinit();
 
@@ -44,7 +42,6 @@ pub fn main(init: std.process.Init) !void {
     }
 
     // 5. Initialize raw GPU Buffers
-    // We pass the EnumSet inline using `.initMany` since the Enum itself isn't exported
     const byte_size = len * @sizeOf(f16);
     const buf_a = try GpuBuffer.init(gloc, byte_size, .initMany(&.{ .Storage, .CopyDst, .CopySrc }));
     const buf_b = try GpuBuffer.init(gloc, byte_size, .initMany(&.{ .Storage, .CopyDst, .CopySrc }));
@@ -58,7 +55,6 @@ pub fn main(init: std.process.Init) !void {
     try buf_b.load(f16, data_b);
 
     // 7. Dispatch the Compute Process
-    // We pass the data type (f16) to allow GpuProcess to calculate chunks correctly
     try add_process.run(gloc, .{ buf_a, buf_b, buf_out });
 
     // 8. Map and copy the resulting buffer back to the CPU

src/GpuProcess.zig

@@ -48,8 +48,7 @@ pub fn deinit(self: @This()) void {
 }
 
 /// Execute the compute pass with arbitrary buffer bindings via a tuple.
-/// `override_elements_count` can be `null` to infer the dispatch count from the first checked buffer.
+/// Example: `try proc.run(gloc, .{ buf_a, buf_b, buf_out });`
-/// Example: `try proc.run(gloc, null, .{ buf_a, buf_b, buf_out });`
 pub fn run(
     self: @This(),
     gloc: GpuAllocator,