whispercpp 1.3.4 → 1.3.5

data/ext/sources/ggml/src/ggml-sycl/count-equal.cpp

@@ -0,0 +1,79 @@
+#include "count-equal.hpp"
+
+#include <cstdint>
+
+template <typename T>
+static void count_equal(const T *__restrict__ x, const T *__restrict__ y,
+                        int64_t *__restrict__ dst, const int64_t dk,
+                        const int64_t k) {
+    auto item_ct1 = sycl::ext::oneapi::this_work_item::get_nd_item<3>();
+    const int64_t i0 = (int64_t)item_ct1.get_group(2) * dk;
+    const int64_t i1 = sycl::min(i0 + dk, k);
+
+    int nequal = 0;
+
+    for (int64_t i = i0 + item_ct1.get_local_id(2); i < i1; i += WARP_SIZE) {
+        const T xi = x[i];
+        const T yi = y[i];
+        nequal += xi == yi;
+    }
+
+    nequal = warp_reduce_sum(nequal);
+
+    if (item_ct1.get_local_id(2) != 0) {
+        return;
+    }
+
+    dpct::atomic_fetch_add<sycl::access::address_space::generic_space>(
+        (int *)dst, nequal);
+}
+
+void ggml_sycl_count_equal(ggml_backend_sycl_context &ctx, ggml_tensor *dst) {
+    scope_op_debug_print scope_dbg_print(__func__, dst, /*num_src=*/2);
+    const ggml_tensor * src0 = dst->src[0];
+    const ggml_tensor * src1 = dst->src[1];
+
+    GGML_ASSERT(src0->type == src1->type);
+    GGML_ASSERT( dst->type == GGML_TYPE_I64);
+
+    GGML_ASSERT(ggml_are_same_shape(src0, src1));
+    GGML_ASSERT(ggml_is_contiguous(src0));
+    GGML_ASSERT(ggml_is_contiguous(src1));
+    GGML_ASSERT(ggml_is_contiguous(dst));
+
+    int64_t * dst_d  = (int64_t *) dst->data;
+
+    dpct::queue_ptr stream = ctx.stream();
+    const int id       = get_current_device_id();
+    const int nsm = ggml_sycl_info().devices[id].nsm;
+
+    const int64_t ne = ggml_nelements(src0);
+    GGML_ASSERT(ne < (1 << 30) && "atomicAdd implementation only supports int");
+    const int64_t dne =
+        GGML_PAD((ne + 4 * nsm - 1) / (4 * nsm), SYCL_COUNT_EQUAL_CHUNK_SIZE);
+
+    SYCL_CHECK(CHECK_TRY_ERROR(stream->memset(dst_d, 0, ggml_nbytes(dst))));
+
+    const dpct::dim3 block_dims(WARP_SIZE, 1, 1);
+    const dpct::dim3 block_nums(
+        std::min((int64_t)4 * nsm, (ne + SYCL_COUNT_EQUAL_CHUNK_SIZE - 1) /
+                                       SYCL_COUNT_EQUAL_CHUNK_SIZE),
+        1, 1);
+
+    switch (src0->type) {
+    case GGML_TYPE_I32: {
+        const int *src0_d = (const int *)src0->data;
+        const int *src1_d = (const int *)src1->data;
+        stream->parallel_for(
+            sycl::nd_range<3>(block_nums * block_dims, block_dims),
+            [=](sycl::nd_item<3> item_ct1) {
+                count_equal(src0_d, src1_d, dst_d, dne, ne);
+                GGML_UNUSED(item_ct1);
+            });
+
+    } break;
+    default:
+        GGML_ASSERT(false);
+        break;
+    }
+}

data/ext/sources/ggml/src/ggml-sycl/count-equal.hpp

@@ -0,0 +1,9 @@
+#ifndef GGML_SYCL_COUNT_EQUAL_HPP
+#define GGML_SYCL_COUNT_EQUAL_HPP
+#include "common.hpp"
+
+#define SYCL_COUNT_EQUAL_CHUNK_SIZE 128
+
+void ggml_sycl_count_equal(ggml_backend_sycl_context & ctx, ggml_tensor * dst);
+
+#endif //GGML_SYCL_COUNT_EQUAL_HPP

data/ext/sources/ggml/src/ggml-sycl/cpy.cpp

@@ -515,9 +515,6 @@ void ggml_sycl_cpy(ggml_backend_sycl_context & ctx, const ggml_tensor * src0, co
     const int64_t ne = ggml_nelements(src0);
     GGML_ASSERT(ne == ggml_nelements(src1));
 
-    GGML_ASSERT(ggml_nbytes(src0) <= INT_MAX);
-    GGML_ASSERT(ggml_nbytes(src1) <= INT_MAX);
-
     GGML_TENSOR_BINARY_OP_LOCALS01;
 
     SYCL_CHECK(ggml_sycl_set_device(ctx.device));

data/ext/sources/ggml/src/ggml-sycl/dequantize.hpp

@@ -819,5 +819,23 @@ dequantize_block_iq4_xs(const void *__restrict__ vx, dst_t *__restrict__ yy,
     }
 }
 
+template<typename dst_t>
+static void dequantize_block_mxfp4(const void * __restrict__ vx, dst_t * __restrict__ yy,
+                                   const sycl::nd_item<3> &item_ct1) {
+    // auto                item_ct1 = sycl::ext::oneapi::this_work_item::get_nd_item<3>();
+    const int64_t       i        = item_ct1.get_group(2);
+    const block_mxfp4 * x = (const block_mxfp4 *) vx + i*(QK_K/QK_MXFP4);
+
+    const int64_t    tid = item_ct1.get_local_id(2);
+    const int64_t il = tid/8; // 0...3
+    const int64_t ib = tid%8; // 0...7
+    dst_t * y = yy + i*QK_K + 32*ib + 4*il;
+    const uint8_t  * q4 = x[ib].qs + 4*il;
+    const float d = ggml_sycl_e8m0_to_fp32(x[ib].e);
+    for (int j = 0; j < 4; ++j) {
+        y[j+ 0] = d * kvalues_mxfp4[q4[j] & 0xf]*0.5f;
+        y[j+16] = d * kvalues_mxfp4[q4[j] >>  4]*0.5f;
+    }
+}
 
 #endif // GGML_SYCL_DEQUANTIZE_HPP

data/ext/sources/ggml/src/ggml-sycl/dpct/helper.hpp

@@ -277,6 +277,26 @@ namespace dpct
 
     } // namespace detail
 
+    // COPY from DPCT head files
+    /// dim3 is used to store 3 component dimensions.
+    class dim3 {
+        public:
+        unsigned x, y, z;
+
+        constexpr dim3(unsigned x = 1, unsigned y = 1, unsigned z = 1)
+            : x(x), y(y), z(z) {}
+
+        dim3(const sycl::id<3> &r) : dim3(r[2], r[1], r[0]) {}
+
+        operator sycl::range<3>() const { return sycl::range<3>(z, y, x); }
+    }; // namespace dim3
+
+    inline dim3 operator*(const dim3 &a, const dim3 &b) {
+    return dim3{a.x * b.x, a.y * b.y, a.z * b.z};
+    }
+    // COPY from DPCT head files
+
+
     /// Pitched 2D/3D memory data.
     class pitched_data
     {
@@ -1840,10 +1860,31 @@ namespace dpct
                                            : id);
     }
 
+    template <typename T1, typename T2>
+    using dot_product_acc_t = std::conditional_t<
+        std::is_unsigned_v<T1> && std::is_unsigned_v<T2>,
+        uint32_t,
+        int32_t>;
+
+    template <typename T>
+    sycl::vec<T, 4> extract_and_sign_or_zero_extend4(T val) {
+      return sycl::vec<T, 1>(val)
+          .template as<sycl::vec<
+              std::conditional_t<std::is_signed_v<T>, int8_t, uint8_t>,
+              4>>()
+          .template convert<T>();
+    }
+
     template <typename T1, typename T2, typename T3>
-    inline auto dp4a(T1 a, T2 b, T3 c)
-    {
-        return syclcompat::dp4a(a, b, c);
+    inline auto dp4a(T1 a, T2 b, T3 c) {
+      dot_product_acc_t<T1, T2> res = c;
+      auto va = extract_and_sign_or_zero_extend4(a);
+      auto vb = extract_and_sign_or_zero_extend4(b);
+      res += va[0] * vb[0];
+      res += va[1] * vb[1];
+      res += va[2] * vb[2];
+      res += va[3] * vb[3];
+      return res;
     }
 
     struct sub_sat
@@ -2952,6 +2993,38 @@ namespace dpct
     atomic_fetch_add<T1, addressSpace>(addr, operand, memoryOrder);
     }
 
+    inline unsigned int byte_level_permute(
+        unsigned int a, unsigned int b, unsigned int s) {
+      unsigned int ret;
+      ret = ((((std::uint64_t)b << 32 | a) >> (s & 0x7) * 8) & 0xff) |
+            (((((std::uint64_t)b << 32 | a) >> ((s >> 4) & 0x7) * 8) & 0xff)
+             << 8) |
+            (((((std::uint64_t)b << 32 | a) >> ((s >> 8) & 0x7) * 8) & 0xff)
+             << 16) |
+            (((((std::uint64_t)b << 32 | a) >> ((s >> 12) & 0x7) * 8) & 0xff)
+             << 24);
+      return ret;
+    }
+
+    inline uint32_t byte_level_permute_custom(
+        uint32_t low32, uint32_t high32, uint32_t sel, int mode = 0) {
+      constexpr uint16_t lookup[6][4] = {
+          {0x3210, 0x4321, 0x5432, 0x6543},  // Forward 4-byte extract
+          {0x5670, 0x6701, 0x7012, 0x0123},  // Backward 4-byte extract
+          {0x0000, 0x1111, 0x2222, 0x3333},  // Replicate 8-bit values
+          {0x3210, 0x3211, 0x3222, 0x3333},  // Edge clamp left
+          {0x0000, 0x1110, 0x2210, 0x3210},  // Edge clamp right
+          {0x1010, 0x3232, 0x1010, 0x3232}   // Replicate 16-bit values
+      };
+
+      if (mode >= 1 && mode <= 6) {
+        return byte_level_permute(low32, high32, lookup[mode - 1][sel & 0x3]);
+      } else if (!mode) {
+        return byte_level_permute(low32, high32, sel);
+      }
+      return 0;
+    }
+
 } // COPY from DPCT head files
 
 #endif // GGML_SYCL_DPCT_HELPER_HPP