vulkan: tiled transpose for 0<->2 permuted CONT (llama/26585)

* vulkan: tiled transpose for 0<->2 permuted CONT

-ggml_vk_get_cpy_pipeline only routed to the tiled shared-memory transpose
shader when dim1 was the innermost dimension, i.e. ggml_transpose (a 0<->1
swap). A 0<->2 swap -- ggml_cont(ggml_permute(x, 2, 1, 0, 3)) -- fell back to
the generic per-element strided copy, whose source reads stride by ne0*ne1
elements: one cache line per lane.

-DeepSeek-V4's lightning indexer performs exactly that permute on a
[n_kv, n_tokens, n_head] tensor. On Vulkan/RADV gfx1151 it ran at ~1-9 GB/s of
a ~200 GB/s part and accounted for 43% of total prefill time.

-Add copy_transpose_02.comp, mirroring copy_transpose.comp but tiling over dst
dims (0, 2) with dims 1 and 3 as the batch, so reads walk src dim2 and writes
walk dst dim0 -- both contiguous. The selection condition additionally requires
a non-contiguous source and a contiguous destination so it cannot take cases
the contiguous-copy shader already handles.

-test-backend-ops only exercised ggml_transpose for CONT, so the strided path
was untested. Add test_cont_permute covering (2,1,0,3), (1,2,0,3) and (0,2,1,3)
over f32/f16 at tile-aligned, tile-unaligned and large shapes. The large shapes
are in the eval set rather than only in perf because perf mode does not verify
results.

-Measured on gfx1151, ne=[n_kv,64,64,1], perm=(2,1,0,3), f32:

  n_kv=1024:   9.08 ->  579.85 GB/s
  n_kv=1280:  20.03 ->  153.71 GB/s
  n_kv=2048:   7.11 ->   91.68 GB/s
  n_kv=2304:  16.24 ->   86.49 GB/s

-The ~2.2x penalty previously seen at power-of-two n_kv (destination-stride
aliasing) is gone. End to end, DeepSeek-V4-Flash IQ3_XXS prefill on a 9k-token
prompt goes from 56.33 t/s to 103.74 t/s (+84%).

-Note: at n_tokens=512 a single slow-path dispatch takes ~273 ms and looping it
in perf mode can trip the GPU watchdog, so the perf cases use n_tokens=64.

* tests: fold test_cont_permute into test_cont, add L2-exceeding perf shapes

Review feedback: test_cont gains a permute parameter ({0,0,0,0} = none),
matching test_mul_mat's pattern, and the separate struct is gone. Perf
adds [n_kv, 512, 64, 1] variants (~0.5 GB per run) that exceed GPU L2,
since the 64-token shapes fit in cache on large parts and read above
memory bandwidth.

* tests: trim perf-case comment to the two-line summary

* vulkan: trim comments on the 0<->2 transpose path

Drop the shader file header, the read/write block comments and the
rationale prose in the CONT test cases. Keep the tile-shape and
bank-conflict notes and the permute parameter documentation.

---------

Co-authored-by: Kevin Hopper <no-reply@maestro.press>

ggml/src/ggml-vulkan/ggml-vulkan.cpp

@@ -962,6 +962,7 @@ struct vk_device_struct {
     vk_pipeline pipeline_cpy_f32_quant[GGML_TYPE_COUNT];
     vk_pipeline pipeline_cpy_quant_f32[GGML_TYPE_COUNT];
     vk_pipeline pipeline_cpy_transpose_16, pipeline_cpy_transpose_32;
+    vk_pipeline pipeline_cpy_transpose_02_16, pipeline_cpy_transpose_02_32;
     // [src0 0=fp32,1=fp16][dst]
     vk_pipeline pipeline_set_rows_i32[2][GGML_TYPE_COUNT];
     vk_pipeline pipeline_set_rows_i64[2][GGML_TYPE_COUNT];
@@ -5525,6 +5526,8 @@ static void ggml_vk_load_shaders(vk_device& device, vk_pipeline requested) {
 
     ggml_vk_create_pipeline(device, device->pipeline_cpy_transpose_32, "cpy_transpose_32", cpy_transpose_32_len, cpy_transpose_32_data, "main", 2, sizeof(vk_op_unary_push_constants), {1, 1, 1}, {}, 1);
     ggml_vk_create_pipeline(device, device->pipeline_cpy_transpose_16, "cpy_transpose_16", cpy_transpose_16_len, cpy_transpose_16_data, "main", 2, sizeof(vk_op_unary_push_constants), {1, 1, 1}, {}, 1);
+    ggml_vk_create_pipeline(device, device->pipeline_cpy_transpose_02_32, "cpy_transpose_02_32", cpy_transpose_02_32_len, cpy_transpose_02_32_data, "main", 2, sizeof(vk_op_unary_push_constants), {1, 1, 1}, {}, 1);
+    ggml_vk_create_pipeline(device, device->pipeline_cpy_transpose_02_16, "cpy_transpose_02_16", cpy_transpose_02_16_len, cpy_transpose_02_16_data, "main", 2, sizeof(vk_op_unary_push_constants), {1, 1, 1}, {}, 1);
 
     ggml_vk_create_pipeline(device, device->pipeline_cpy_f32_quant[GGML_TYPE_Q1_0], "cpy_f32_q1_0", cpy_f32_q1_0_len, cpy_f32_q1_0_data, "main", 2, sizeof(vk_op_unary_push_constants), {32, 1, 1}, {}, 1);
     ggml_vk_create_pipeline(device, device->pipeline_cpy_f32_quant[GGML_TYPE_Q2_0], "cpy_f32_q2_0", cpy_f32_q2_0_len, cpy_f32_q2_0_data, "main", 2, sizeof(vk_op_unary_push_constants), {32, 1, 1}, {}, 1);
@@ -8931,6 +8934,18 @@ static vk_pipeline ggml_vk_get_cpy_pipeline(ggml_backend_vk_context * ctx, const
         }
     }
 
+    // Same, for a 0<->2 swap: src dim2 is the innermost dimension.
+    bool transpose02 = dst && !contig && src->nb[2] == ggml_type_size(to) &&
+                       ggml_is_contiguous(dst) && ggml_are_same_shape(dst, src);
+
+    if (transpose02 && src->type == to) {
+        if (ggml_type_size(to) == 4) {
+            return ctx->device->pipeline_cpy_transpose_02_32;
+        } else if (ggml_type_size(to) == 2) {
+            return ctx->device->pipeline_cpy_transpose_02_16;
+        }
+    }
+
     if (src->type == GGML_TYPE_F32 && to == GGML_TYPE_F32) {
         if (contig) {
             return ctx->device->pipeline_contig_cpy_f32_f32;
@@ -12192,7 +12207,16 @@ static void ggml_vk_op_f32(ggml_backend_vk_context * ctx, vk_context& subctx, co
                 elements = { ne, 1, 1 };
             }
 
-            if (pipeline == ctx->device->pipeline_cpy_transpose_32 ||
+            if (pipeline == ctx->device->pipeline_cpy_transpose_02_32 ||
+                pipeline == ctx->device->pipeline_cpy_transpose_02_16) {
+                // 32x32 tiles over dims 0 and 2; dim1 and dim3 are the batch
+                elements[0] = (uint32_t)CEIL_DIV(dst->ne[0], 32);
+                elements[1] = (uint32_t)CEIL_DIV(dst->ne[2], 32);
+                elements[2] = (uint32_t)(dst->ne[1]*dst->ne[3]);
+                elements[0] = std::min(elements[0], ctx->device->properties.limits.maxComputeWorkGroupCount[0]);
+                elements[1] = std::min(elements[1], ctx->device->properties.limits.maxComputeWorkGroupCount[1]);
+                elements[2] = std::min(elements[2], ctx->device->properties.limits.maxComputeWorkGroupCount[2]);
+            } else if (pipeline == ctx->device->pipeline_cpy_transpose_32 ||
                 pipeline == ctx->device->pipeline_cpy_transpose_16) {
                 // 32x32 tiles
                 elements[0] = (uint32_t)CEIL_DIV(dst->ne[0], 32);

ggml/src/ggml-vulkan/vulkan-shaders/copy_transpose_02.comp

@@ -0,0 +1,61 @@
+#version 450
+
+#include "types.glsl"
+#include "generic_unary_head.glsl"
+
+// workgroup does 32x32 tile, but uses 32x8 threads
+#define TILE_DIM 32
+layout(local_size_x = 32, local_size_y = 8, local_size_z = 1) in;
+
+// +1 padding avoids shared-memory bank conflicts on the transposed read
+shared uint sh[TILE_DIM][TILE_DIM + 1];
+
+void iter(uvec3 wg_id) {
+    const uint tile_i0 = wg_id.x;   // tiles dst ne10 (== src ne00)
+    const uint tile_i2 = wg_id.y;   // tiles dst ne12 (== src ne02)
+
+    const uint tid_col = gl_LocalInvocationID.x;
+    const uint tid_row = gl_LocalInvocationID.y;
+
+    const uint i1 = wg_id.z % p.ne11;
+    const uint i3 = wg_id.z / p.ne11;
+    const uint i01 = i1;
+    const uint i03 = i3;
+
+    [[unroll]] for (uint y = 0; y < 4; ++y) {
+        const uint i00 = tile_i0 * TILE_DIM + tid_row + 8 * y;
+        const uint i02 = tile_i2 * TILE_DIM + tid_col;
+        if (i00 < p.ne00 && i01 < p.ne01 && i02 < p.ne02 && i03 < p.ne03) {
+            const uint src_idx = i00 * p.nb00 + i01 * p.nb01 + i02 * p.nb02 + i03 * p.nb03;
+            sh[tid_row + 8 * y][tid_col] = uint(data_a[get_aoffset() + src_idx]);
+        }
+    }
+
+    barrier();
+
+    [[unroll]] for (uint y = 0; y < 4; ++y) {
+        const uint i0 = tile_i0 * TILE_DIM + tid_col;
+        const uint i2 = tile_i2 * TILE_DIM + tid_row + 8 * y;
+        if (i0 < p.ne10 && i1 < p.ne11 && i2 < p.ne12 && i3 < p.ne13) {
+            const uint dst_idx = i0 * p.nb10 + i1 * p.nb11 + i2 * p.nb12 + i3 * p.nb13;
+            data_d[get_doffset() + dst_idx] = D_TYPE(sh[tid_col][tid_row + 8 * y]);
+        }
+    }
+}
+
+#define CEIL_DIV(a, b) (((a) + (b) - 1) / (b))
+
+void main() {
+    bool need_barrier = false;
+    for (uint z = gl_WorkGroupID.z; z < p.ne11 * p.ne13; z += gl_NumWorkGroups.z) {
+        for (uint y = gl_WorkGroupID.y; y < CEIL_DIV(p.ne12, TILE_DIM); y += gl_NumWorkGroups.y) {
+            for (uint x = gl_WorkGroupID.x; x < CEIL_DIV(p.ne10, TILE_DIM); x += gl_NumWorkGroups.x) {
+                if (need_barrier) {
+                    barrier();
+                }
+                need_barrier = true;
+                iter(uvec3(x, y, z));
+            }
+        }
+    }
+}

ggml/src/ggml-vulkan/vulkan-shaders/vulkan-shaders-gen.cpp

@@ -826,6 +826,8 @@ void process_shaders() {
 
     string_to_spv("cpy_transpose_16", "copy_transpose.comp", {{"A_TYPE", "uint16_t"}, {"D_TYPE", "uint16_t"}});
     string_to_spv("cpy_transpose_32", "copy_transpose.comp", {{"A_TYPE", "uint"}, {"D_TYPE", "uint"}});
+    string_to_spv("cpy_transpose_02_16", "copy_transpose_02.comp", {{"A_TYPE", "uint16_t"}, {"D_TYPE", "uint16_t"}});
+    string_to_spv("cpy_transpose_02_32", "copy_transpose_02.comp", {{"A_TYPE", "uint"}, {"D_TYPE", "uint"}});
 
     for (std::string t : {"q1_0", "q2_0", "q4_0", "q4_1", "q5_0", "q5_1", "q8_0", "iq4_nl"}) {
         string_to_spv("cpy_f32_" + t, "copy_to_quant.comp", {{"DATA_A_" + to_uppercase(t), "1"}, {"S_TYPE", "float"}, {"D_TYPE", "float"}, {"FLOAT_TYPE", "float"}});