sycl: coalesce the ssm_conv window loads (#26612)

test-backend-ops perf -o SSM_CONV on an Arc Pro B70, interleaved A/B against
master, 6 reps, us/run:

  ne_a=[515,3328,1,1] ne_b=[4,3328,1,1]   n_t=512     97.68 -> 52.95   1.85x
  ne_a=[937,8192,1,1] ne_b=[4,8192,1,1]   n_t=934    516.16 -> 276.13  1.87x
  ne_a=[4,3328,1,1]   ne_b=[4,3328,1,1]   n_t=1        2.73 -> 2.71    flat

llama-bench on qwen35 27B Q4_K - Medium (48 of its 64 blocks run ssm_conv),
-ngl 99 -fa 1 -ctk f16 -ctv f16, interleaved passes of r=3:

  -b 2048 -ub 2048  pp2048  1045.1 / 1043.5 / 1043.7 -> 1069.5 / 1066.3 / 1065.9  +2.2%
  -b 2048 -ub 512   pp2048   771.8 /  772.7          ->  785.5 /  786.6           +1.8%
  -b 2048 -ub 512   tg128     23.81 /  23.88         ->   23.87 /  23.86          flat

diff --git a/ggml/src/ggml-sycl/ssm_conv.cpp b/ggml/src/ggml-sycl/ssm_conv.cpp
index e55223586a194d7cb8a767eb75dd5cbc8f8910d7..3eafa1a680d31590bb755326857c0a3050f500ec 100644 (file)
--- a/ggml/src/ggml-sycl/ssm_conv.cpp
+++ b/ggml/src/ggml-sycl/ssm_conv.cpp
@@ -36,9 +36,13 @@ static void kernel_ssm_conv(
                     return;
                 }
 
-                const int channel = static_cast<int>(idx % d_inner);
-                const int token   = static_cast<int>((idx / d_inner) % n_t);
-                const int seq     = static_cast<int>(idx / (static_cast<size_t>(d_inner) * static_cast<size_t>(n_t)));
+                // src has the tokens of one channel contiguous, dst has the channels of one
+                // token contiguous, so either the loads or the store must be strided. Indexing
+                // token-fastest coalesces the d_conv loads, which measured faster except for
+                // short, cache-resident rows.
+                const int token   = static_cast<int>(idx % n_t);
+                const int channel = static_cast<int>((idx / n_t) % d_inner);
+                const int seq     = static_cast<int>(idx / (static_cast<size_t>(n_t) * static_cast<size_t>(d_inner)));
 
                 const float *s = src_data
                     + static_cast<size_t>(seq) * static_cast<size_t>(src_stride_seq)