Vulkan: halve the pointwise conv spatial tile

conv2d_pw_tiled is generated only at TILE_M=4. TILE_M=2 is faster on every
model and both GPU vendors measured, and the tile size is otherwise
unchanged, so this just moves the generated variant.

Mali-G76 (Galaxy S10+), conv2d_pw / whole-graph GPU, median of interleaved
rounds: lraspp-mobilenet-v3-large fp16 @520 71.5 -> 43.8 ms (1.63x) and
99.3 -> 71.7 ms (1.38x); selfie-segmentation fp16 @256 4.21 -> 2.32 ms
(1.82x) and 8.46 -> 6.54 ms (1.29x).

Adreno 840 (Galaxy S26 Ultra): lraspp 5.35 -> 5.00 ms (1.07x) and
10.95 -> 10.59 ms (1.03x); selfie 0.530 -> 0.435 ms (1.22x) and
1.050 -> 0.956 ms (1.10x); PP-OCRv6 fp16 neutral at 1.00x / 0.99x.

Going the other way is much worse, which is what makes 2 the optimum
rather than a local accident: TILE_M=1 is 0.97x, TILE_M=8 0.24x,
TILE_N4=2 0.16x and TILE_N4=4 0.06x on Mali.

Output is bit identical at every tile size tested.

Author: msluszniak

backends/vulkan/runtime/graph/ops/glsl/conv2d_pw_tiled.yaml

@@ -11,7 +11,7 @@ conv2d_pw_tiled:
     TILE_M4: 1
     TILE_K4: 1
     TILE_N4: 1
-    TILE_M: 4
+    TILE_M: 2
   generate_variant_forall:
     DTYPE:
       - VALUE: float

backends/vulkan/runtime/graph/ops/impl/Conv2dPW.cpp

@@ -79,8 +79,8 @@ GlobalWorkGrid pick_conv2d_pw_tiled_gwg(
   uint32_t C_out = graph->size_at<uint32_t>(-3, out);
   uint32_t M = H * W;
   uint32_t N4 = utils::div_up_4(C_out);
-  // TILE_N4=1, TILE_M=4
-  return GlobalWorkGrid({N4, utils::div_up(M, 4u), 1u}, kTiledWorkGrid);
+  // TILE_N4=1, TILE_M=2. Must match conv2d_pw_tiled.yaml.
+  return GlobalWorkGrid({N4, utils::div_up(M, 2u), 1u}, kTiledWorkGrid);
 }
 
 //