Raise layer_norm scalar threshold from 256 to 1024

Summary:
Raise kSmallNThreshold from 256 to 1024 in the optimized native_layer_norm kernel. The previous threshold of 256 (D98795281) was tuned for trackpad models with N=26-144, but newer EMG models use larger normalized dimensions where SIMD vectorization setup/tail overhead still exceeds the benefit.

#### Why 1024

Inspecting two production EMG models reveals that all layer_norm calls have N <= 512, well below where SIMD (RowwiseMoments + vec::map3) becomes beneficial:

**Laserpointer model** (laserpointer-e985727590-FP32.pte) — 24 layer_norm calls:
- N=324: 20x, N=512: 4x
- All calls have weight=None, bias=None, so the vec::map3 SIMD normalization path is never used — all fall into the scalar gamma/beta loop anyway
- With threshold=256: all 24 calls take the SIMD path (regression)
- With threshold=1024: all 24 calls take the scalar path (fix)

**Trackpad V4 model** (trackpad-V4-FP32.pte) — 37 layer_norm calls:
- N=32: 6x, N=64: 2x, N=128: 8x, N=256: 16x, N=512: 5x
- With threshold=256: 16 calls at N=32-128 use scalar, but 21 calls at N=256-512 use SIMD (regression)
- With threshold=1024: all 37 calls use scalar path (fix)

Large-tensor models (LLM, ASR, TTS) with N >= 1024 are unaffected and continue to use the SIMD path.

#### Benchmark results (x86_64 devserver, median latency in us)

Laserpointer model:

| Threads | Portable | Optimized (N<256) | Optimized (N<1024) | Change |
|---------|----------|-------------------|--------------------|--------|
| 1       | 3,916    | 4,801             | 3,390              | 1.42x faster |
| 2       | 3,231    | 4,959             | 3,278              | 1.51x faster |
| 4       | 4,127    | 5,375             | 4,085              | 1.32x faster |

Trackpad V4 model:

| Threads | Portable | Optimized (N<256) | Optimized (N<1024) | Change |
|---------|----------|-------------------|--------------------|--------|
| 1       | 5,742    | 6,146             | 5,866              | 1.05x faster |
| 2       | 6,010    | 6,379             | 6,137              | 1.04x faster |
| 4       | 7,428    | 8,010             | 7,699              | 1.04x faster |

With threshold=256, the optimized kernel was 1.07-1.53x slower than portable for these models. With threshold=1024, the regression is eliminated — optimized is now on par or faster than portable.

This diff was authored with Claude Code.

Differential Revision: D101050373

Author: xiaodong705

kernels/optimized/cpu/op_native_layer_norm.cpp

@@ -75,7 +75,7 @@ void layer_norm(
   // For small normalized dimensions, fall back to the portable scalar
   // implementation since SIMD vectorization setup/tail-handling overhead
   // exceeds the benefit for small N.
-  constexpr size_t kSmallNThreshold = 256;
+  constexpr size_t kSmallNThreshold = 1024;
   if (N < kSmallNThreshold) {
     layer_norm_scalar<CTYPE>(
         input_data,