[SYCL] Fix DMMV dequantization (#9279)

Fixed dmmv dequant for ncols== GGML_SYCL_DMMV_X
ggerganov · Sep 4, 2024 · 5910ea9 · 5910ea9
1 parent c8671ae
commit 5910ea9
Showing 1 changed file with 2 additions and 2 deletions.
diff --git a/ggml/src/ggml-sycl/dmmv.cpp b/ggml/src/ggml-sycl/dmmv.cpp
@@ -76,8 +76,8 @@ static void dequantize_mul_mat_vec(const void * __restrict__ vx, const dfloat *
     }
 
     // sum up partial sums and write back result
-#pragma unroll
-    for (int mask = WARP_SIZE / 2; mask > 0; mask >>= 1) {
+    const int mask_start = ncols > GGML_SYCL_DMMV_X ? WARP_SIZE >> 1 : WARP_SIZE >> 2;
+    for (int mask = mask_start; mask > 0; mask >>= 1) {
         tmp +=
             dpct::permute_sub_group_by_xor(item_ct1.get_sub_group(), tmp, mask);
     }