opencl : add GEGLU, REGLU, SWIGLU (#14456)

* Conv2D: Add CPU version

* Half decent

* Tiled approach for F32

* remove file

* Fix tests

* Support F16 operations

* add assert about size

* Review: further formatting fixes, add assert and use CPU version of fp32->fp16

ggml/include/ggml.h

@@ -482,6 +482,7 @@ extern "C" {
         GGML_OP_CONV_TRANSPOSE_1D,
         GGML_OP_IM2COL,
         GGML_OP_IM2COL_BACK,
+        GGML_OP_CONV_2D,
         GGML_OP_CONV_2D_DW,
         GGML_OP_CONV_TRANSPOSE_2D,
         GGML_OP_POOL_1D,
@@ -1813,6 +1814,17 @@ extern "C" {
             struct ggml_tensor  * b,
             int                   stride);
 
+    GGML_API struct ggml_tensor * ggml_conv_2d_direct(
+            struct ggml_context * ctx,
+            struct ggml_tensor  * a,   // convolution kernel [KW, KH, IC, OC]
+            struct ggml_tensor  * b,   // input data [W, H, C, N]
+            int                   s0,  // stride dimension 0
+            int                   s1,  // stride dimension 1
+            int                   p0,  // padding dimension 0
+            int                   p1,  // padding dimension 1
+            int                   d0,  // dilation dimension 0
+            int                   d1); // dilation dimension 1
+
     enum ggml_op_pool {
         GGML_OP_POOL_MAX,
         GGML_OP_POOL_AVG,

ggml/src/ggml-cpu/CMakeLists.txt

@@ -589,4 +589,9 @@ function(ggml_add_cpu_backend_variant_impl tag_name)
     if (EMSCRIPTEN)
         set_target_properties(${GGML_CPU_NAME} PROPERTIES COMPILE_FLAGS "-msimd128")
     endif()
+
+    if (CMAKE_CXX_COMPILER_ID STREQUAL "IntelLLVM")
+        # The compiler automatically enables "-ffast-math" which can cause NaNs in tests due to "-fassociative-math"
+        target_compile_options(${GGML_CPU_NAME} PRIVATE "-fno-associative-math")
+    endif()
 endfunction()

ggml/src/ggml-cpu/ggml-cpu.c

@@ -1193,7 +1193,7 @@ static void ggml_compute_forward_mul_mat_one_chunk(
     }
 }
 
-static void ggml_compute_forward_mul_mat(
+void ggml_compute_forward_mul_mat(
         const struct ggml_compute_params * params,
               struct ggml_tensor * dst) {
 
@@ -1866,6 +1866,10 @@ static void ggml_compute_forward(struct ggml_compute_params * params, struct ggm
             {
                 ggml_compute_forward_im2col_back_f32(params, tensor);
             } break;
+        case GGML_OP_CONV_2D:
+            {
+                ggml_compute_forward_conv_2d(params, tensor);
+            } break;
         case GGML_OP_CONV_2D_DW:
             {
                 ggml_compute_forward_conv_2d_dw(params, tensor);
@@ -2228,6 +2232,7 @@ static int ggml_get_n_tasks(struct ggml_tensor * node, int n_threads) {
             } break;
         case GGML_OP_IM2COL:
         case GGML_OP_IM2COL_BACK:
+        case GGML_OP_CONV_2D:
         case GGML_OP_CONV_2D_DW:
         case GGML_OP_CONV_TRANSPOSE_1D:
         case GGML_OP_CONV_TRANSPOSE_2D:
@@ -2746,6 +2751,10 @@ struct ggml_cplan ggml_graph_plan(
                             GGML_ABORT("fatal error");
                         }
                     } break;
+                case GGML_OP_CONV_2D:
+                    {
+                        cur = GGML_IM2COL_WORK_SIZE;
+                    } break;
                 case GGML_OP_CONV_TRANSPOSE_2D:
                     {
                         const int64_t ne00 = node->src[0]->ne[0]; // W

ggml/src/ggml-cpu/ops.cpp

@@ -3,6 +3,7 @@
 #include "ggml-cpu.h"
 #include "ggml-impl.h"
 #include "binary-ops.h"
+#include "ggml.h"
 #include "unary-ops.h"
 #include "vec.h"
 
@@ -6545,6 +6546,186 @@ void ggml_compute_forward_im2col_back_f32(
     }
 }
 
+static void ggml_call_mul_mat(ggml_type type, const ggml_compute_params * params, int64_t m, int64_t n, int64_t k,
+                              void * a, void * b, float * c) {
+    const ggml_type_traits * traits = ggml_get_type_traits(type);
+    struct ggml_tensor src1 = {};
+    src1.type  = type;
+    src1.ne[0] = k;
+    src1.ne[1] = m;
+    src1.ne[2] = 1;
+    src1.ne[3] = 1;
+    src1.nb[0] = traits->type_size;
+    src1.nb[1] = k * traits->type_size;
+    src1.nb[2] = src1.nb[1];
+    src1.nb[3] = src1.nb[2];
+    src1.data  = a;
+
+    struct ggml_tensor src0 = {};
+    src0.type  = type;
+    src0.ne[0] = k;
+    src0.ne[1] = n;
+    src0.ne[2] = 1;
+    src0.ne[3] = 1;
+    src0.nb[0] = traits->type_size;
+    src0.nb[1] = k * traits->type_size;
+    src0.nb[2] = src0.nb[1];
+    src0.nb[3] = src0.nb[2];
+    src0.data  = b;
+
+    struct ggml_tensor dst = {};
+    dst.ne[0] = n;
+    dst.ne[1] = m;
+    dst.ne[2] = 1;
+    dst.ne[3] = 1;
+    dst.nb[0] = sizeof(float);
+    dst.nb[1] = n * sizeof(float);
+    dst.nb[2] = dst.nb[1];
+    dst.nb[3] = dst.nb[2];
+    dst.data  = c;
+    dst.src[0] = &src0;
+    dst.src[1] = &src1;
+
+    ggml_compute_forward_mul_mat(params, &dst);
+}
+
+// ggml_compute_forward_conv_2d
+
+static void ggml_compute_forward_conv_2d_impl(const ggml_compute_params * params,
+                                              const ggml_tensor *         kernel,  // [KW, KH, IC, OC]
+                                              const ggml_tensor *         src,     // [W, H, C, N]
+                                              ggml_tensor *               dst,     // [OW, OH, OC, N]
+                                              ggml_type                   kernel_type) {
+
+    GGML_ASSERT(ggml_is_contiguous(kernel));
+    GGML_ASSERT(kernel_type == GGML_TYPE_F16 || kernel_type == GGML_TYPE_F32);
+    GGML_ASSERT(kernel->type == kernel_type);
+
+    const ggml_type_traits * traits = ggml_get_type_traits(kernel_type);
+
+    const int32_t stride_x   = dst->op_params[0];
+    const int32_t stride_y   = dst->op_params[1];
+    const int32_t pad_x      = dst->op_params[2];
+    const int32_t pad_y      = dst->op_params[3];
+    const int32_t dilation_x = dst->op_params[4];
+    const int32_t dilation_y = dst->op_params[5];
+
+    const int64_t c_in  = src->ne[2];
+    const int64_t c_out = kernel->ne[3];
+    GGML_ASSERT(c_in == kernel->ne[2]);
+
+    const int64_t src_w = src->ne[0];
+    const int64_t src_h = src->ne[1];
+    const int64_t knl_w = kernel->ne[0];
+    const int64_t knl_h = kernel->ne[1];
+    const int64_t dst_w = dst->ne[0];
+    const int64_t dst_h = dst->ne[1];
+
+    const float * src_data = (float *) src->data;
+    void  * knl_data       = kernel->data;
+    float * dst_data       = (float *) dst->data;
+
+    const int64_t knl_n           = knl_w * knl_h * c_in;
+    const int64_t patch_total     = dst->ne[3] * dst_w * dst_h;
+
+    const int64_t space_per_patch   = knl_n * traits->type_size + c_out * sizeof(float);
+    const int64_t batch_size        = params->wsize / space_per_patch;
+    const int64_t patches_per_batch = batch_size > 8 ? (batch_size / 8) * 8 : batch_size;
+    const int64_t batch_n           = (patch_total + patches_per_batch - 1) / patches_per_batch;
+
+    GGML_ASSERT(patches_per_batch > 0 && batch_size >= 1);
+
+    void * tmp = params->wdata;
+
+    for (int64_t batch_i = 0; batch_i < batch_n; ++batch_i) {
+
+        const int64_t patch_start_batch = batch_i * patches_per_batch;
+        const int64_t patch_end_batch   = std::min(patch_start_batch + patches_per_batch,
+                                              patch_total);
+        const int64_t patch_n           = patch_end_batch - patch_start_batch;
+
+        const int64_t patch_per_thread  = (patch_n + params->nth - 1) / params->nth;
+        const int64_t patch_start       = patch_start_batch + params->ith * patch_per_thread;
+        const int64_t patch_end         = std::min(patch_start + patch_per_thread, patch_end_batch);
+
+        //im2col for a patch
+        for (int64_t p = patch_start; p < patch_end; ++p) {
+            const int64_t  batch_n     =  p / (dst_w * dst_h);
+            const int64_t  src_x       = (p / dst_w) % dst_h;
+            const int64_t  src_y       =  p % dst_w;
+
+            const float * src_base = (const float *)((const char *)src_data + batch_n * src->nb[3]);
+            char *        dst_row  = (char *) tmp + (p % patches_per_batch) * knl_n * traits->type_size;
+
+            for (int64_t ic = 0; ic < c_in; ++ic) {
+                for (int64_t ky = 0; ky < knl_h; ++ky) {
+                    for (int64_t kx = 0; kx < knl_w; ++kx) {
+                        const int64_t sy = src_x * stride_y + ky * dilation_y - pad_y;
+                        const int64_t sx = src_y * stride_x + kx * dilation_x - pad_x;
+
+                        int64_t dst_idx = ic * (knl_h * knl_w) + ky * knl_w + kx;
+
+                        float src_val;
+                        if (sy < 0 || sy >= src_h || sx < 0 || sx >= src_w) {
+                            src_val = 0.0f;
+                        } else {
+                            const float * src_ptr = (const float *)((const char *)src_base + sx * src->nb[0] + sy * src->nb[1] + ic * src->nb[2]);
+                            src_val               = *src_ptr;
+                        }
+
+                        char * element_ptr = dst_row + dst_idx * traits->type_size;
+                        if (kernel_type == GGML_TYPE_F32) {
+                            *(float *) element_ptr = src_val;
+                        } else if (kernel_type == GGML_TYPE_F16) {
+                            *(ggml_fp16_t *) element_ptr = GGML_CPU_FP32_TO_FP16(src_val);
+                        }
+                    }
+                }
+            }
+        }   // patches handled by this thread
+
+        ggml_barrier(params->threadpool);
+
+        float * gemm_output = (float *) ((char *) tmp + patches_per_batch * knl_n * traits->type_size);
+
+        GGML_ASSERT(gemm_output + patch_n * c_out <= (float*)tmp + params->wsize);
+
+        // GEMM: patches[patch_n, knl_n] × kernel[knl_n, c_out] = output[patch_n, c_out]
+        ggml_call_mul_mat(kernel_type, params, patch_n, c_out, knl_n, tmp, knl_data, gemm_output);
+
+        ggml_barrier(params->threadpool);
+
+
+        //permute back [OC, N, OH, OW] to [N, OC, OH, OW]
+        const int64_t permute_per_thread = (patch_n + params->nth - 1) / params->nth;
+        const int64_t permute_start = params->ith * permute_per_thread;
+        const int64_t permute_end = std::min(permute_start + permute_per_thread, patch_n);
+
+        for (int64_t i = permute_start; i < permute_end; ++i) {
+            const int64_t p       = patch_start_batch + i;
+            const int64_t batch_n = p / (dst_w * dst_h);
+            const int64_t dst_y   = (p / dst_w) % dst_h;
+            const int64_t dst_x   = p % dst_w;
+
+            for (int64_t oc = 0; oc < c_out; ++oc) {
+                const float value = gemm_output[i * c_out + oc];
+                float * dst_ptr = (float *)((char *)dst_data + dst_x * dst->nb[0] + dst_y * dst->nb[1] + oc * dst->nb[2] + batch_n * dst->nb[3]);
+                *dst_ptr = value;
+            }
+        }
+    }
+}
+
+void ggml_compute_forward_conv_2d(
+        const ggml_compute_params * params,
+        ggml_tensor * dst) {
+
+    const ggml_tensor * src0 = dst->src[0];
+    const ggml_tensor * src1 = dst->src[1];
+
+    ggml_compute_forward_conv_2d_impl(params, src0, src1, dst, src0->type);
+}
+
 // ggml_compute_forward_conv_transpose_2d
 
 void ggml_compute_forward_conv_transpose_2d(

ggml/src/ggml-cpu/ops.h

@@ -20,6 +20,9 @@
 
 static const size_t CACHE_LINE_SIZE_F32 = CACHE_LINE_SIZE/sizeof(float);
 
+// Work buffer size for im2col operations in CONV2D
+#define GGML_IM2COL_WORK_SIZE (16 * 1024 * 1024)
+
 #ifdef __cplusplus
 extern "C" {
 #endif
@@ -65,6 +68,7 @@ void ggml_compute_forward_clamp(const struct ggml_compute_params * params, struc
 void ggml_compute_forward_conv_transpose_1d(const struct ggml_compute_params * params, struct ggml_tensor * dst);
 void ggml_compute_forward_im2col(const struct ggml_compute_params * params, struct ggml_tensor * dst);
 void ggml_compute_forward_im2col_back_f32(const struct ggml_compute_params * params, struct ggml_tensor * dst);
+void ggml_compute_forward_conv_2d(const struct ggml_compute_params * params, struct ggml_tensor * dst);
 void ggml_compute_forward_conv_transpose_2d(const struct ggml_compute_params * params, struct ggml_tensor * dst);
 void ggml_compute_forward_conv_2d_dw(const struct ggml_compute_params * params, struct ggml_tensor * dst);
 void ggml_compute_forward_pool_1d(const struct ggml_compute_params * params, struct ggml_tensor * dst);
@@ -107,6 +111,7 @@ void ggml_compute_forward_custom(const struct ggml_compute_params * params, stru
 void ggml_compute_forward_cross_entropy_loss(const struct ggml_compute_params * params, struct ggml_tensor * dst);
 void ggml_compute_forward_cross_entropy_loss_back(const struct ggml_compute_params * params, struct ggml_tensor * dst);
 void ggml_compute_forward_opt_step_adamw(const struct ggml_compute_params * params, struct ggml_tensor * dst);
+void ggml_compute_forward_mul_mat(const struct ggml_compute_params * params, struct ggml_tensor * dst);
 
 #ifdef __cplusplus
 }

ggml/src/ggml-metal/ggml-metal.metal

@@ -138,6 +138,7 @@ void quantize_q4_0(device const float * src, device block_q4_0 & dst) {
 }
 
 void quantize_q4_1(device const float * src, device block_q4_1 & dst) {
+#pragma METAL fp math_mode(safe)
     float min = FLT_MAX;
     float max = -FLT_MAX;
 
@@ -203,6 +204,7 @@ void quantize_q5_0(device const float * src, device block_q5_0 & dst) {
 }
 
 void quantize_q5_1(device const float * src, device block_q5_1 & dst) {
+#pragma METAL fp math_mode(safe)
     float max = src[0];
     float min = src[0];
 
@@ -239,6 +241,7 @@ void quantize_q5_1(device const float * src, device block_q5_1 & dst) {
 }
 
 void quantize_iq4_nl(device const float * src, device block_iq4_nl & dst) {
+#pragma METAL fp math_mode(safe)
     float amax = 0.0f; // absolute max
     float max  = 0.0f;
 

ggml/src/ggml-opencl/CMakeLists.txt

@@ -65,6 +65,7 @@ set(GGML_OPENCL_KERNELS
     gemv_noshuffle_general
     gemv_noshuffle
     get_rows
+    glu
     group_norm
     im2col_f32
     im2col_f16

ggml/src/ggml-opencl/ggml-opencl.cpp

@@ -351,6 +351,7 @@ struct ggml_backend_opencl_context {
     cl_program program_gemv_noshuffle_general;
     cl_program program_gemv_noshuffle;
     cl_program program_get_rows;
+    cl_program program_glu;
     cl_program program_im2col_f16;
     cl_program program_im2col_f32;
     cl_program program_mul_mat_Ab_Bi_8x4;
@@ -401,6 +402,8 @@ struct ggml_backend_opencl_context {
     cl_kernel kernel_relu;
     cl_kernel kernel_sigmoid_f32, kernel_sigmoid_f16;
     cl_kernel kernel_clamp;
+    cl_kernel kernel_geglu, kernel_reglu, kernel_swiglu,
+              kernel_geglu_f16, kernel_reglu_f16, kernel_swiglu_f16;
     cl_kernel kernel_norm;
     cl_kernel kernel_rms_norm;
     cl_kernel kernel_group_norm;
@@ -738,6 +741,27 @@ static void load_cl_kernels(ggml_backend_opencl_context *backend_ctx, ggml_cl_ve
         GGML_LOG_CONT(".");
     }
 
+    // glu
+    {
+#ifdef GGML_OPENCL_EMBED_KERNELS
+        const std::string kernel_src {
+            #include "glu.cl.h"
+        };
+#else
+        const std::string kernel_src = read_file("glu.cl");
+#endif
+        backend_ctx->program_glu =
+            build_program_from_source(backend_ctx->context, backend_ctx->device, kernel_src.c_str(), compile_opts);
+
+        CL_CHECK((backend_ctx->kernel_geglu      = clCreateKernel(backend_ctx->program_glu, "kernel_geglu", &err), err));
+        CL_CHECK((backend_ctx->kernel_reglu      = clCreateKernel(backend_ctx->program_glu, "kernel_reglu", &err), err));
+        CL_CHECK((backend_ctx->kernel_swiglu     = clCreateKernel(backend_ctx->program_glu, "kernel_swiglu", &err), err));
+        CL_CHECK((backend_ctx->kernel_geglu_f16  = clCreateKernel(backend_ctx->program_glu, "kernel_geglu_f16", &err), err));
+        CL_CHECK((backend_ctx->kernel_reglu_f16  = clCreateKernel(backend_ctx->program_glu, "kernel_reglu_f16", &err), err));
+        CL_CHECK((backend_ctx->kernel_swiglu_f16 = clCreateKernel(backend_ctx->program_glu, "kernel_swiglu_f16", &err), err));
+        GGML_LOG_CONT(".");
+    }
+
     // get_rows
     {
 #ifdef GGML_OPENCL_EMBED_KERNELS
@@ -2242,6 +2266,15 @@ static bool ggml_opencl_supports_op(ggml_backend_dev_t dev, const struct ggml_te
                 default:
                     return false;
             }
+        case GGML_OP_GLU:
+            switch (ggml_get_glu_op(op)) {
+                case GGML_GLU_OP_GEGLU:
+                case GGML_GLU_OP_REGLU:
+                case GGML_GLU_OP_SWIGLU:
+                    return ggml_is_contiguous_1(op->src[0]) && (op->type == GGML_TYPE_F32 || op->type == GGML_TYPE_F16);
+                default:
+                    return false;
+            }
         case GGML_OP_CLAMP:
             return op->src[0]->type == GGML_TYPE_F32;
         case GGML_OP_SOFT_MAX:
@@ -6143,6 +6176,91 @@ static void ggml_cl_sum_rows(ggml_backend_t backend, const ggml_tensor * src0, c
     backend_ctx->enqueue_ndrange_kernel(kernel, 3, global_work_size, local_work_size, dst);
 }
 
+static void ggml_cl_glu(ggml_backend_t backend, const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst) {
+    GGML_ASSERT(src0);
+    GGML_ASSERT(src0->extra);
+    GGML_ASSERT(dst);
+    GGML_ASSERT(dst->extra);
+
+    GGML_ASSERT(ggml_is_contiguous_1(src0));
+
+    if (src1) {
+        GGML_ASSERT(src1);
+        GGML_ASSERT(src1->extra);
+        GGML_ASSERT(ggml_are_same_shape(src0, src1));
+    }
+
+    ggml_backend_opencl_context *backend_ctx = (ggml_backend_opencl_context *)backend->context;
+
+    cl_kernel kernel;
+    switch (ggml_get_glu_op(dst)) {
+        case GGML_GLU_OP_GEGLU:
+            if (dst->type == GGML_TYPE_F32) {
+                kernel = backend_ctx->kernel_geglu;
+            } else {
+                kernel = backend_ctx->kernel_geglu_f16;
+            }
+            break;
+        case GGML_GLU_OP_REGLU:
+            if (dst->type == GGML_TYPE_F32) {
+                kernel = backend_ctx->kernel_reglu;
+            } else {
+                kernel = backend_ctx->kernel_reglu_f16;
+            }
+            break;
+        case GGML_GLU_OP_SWIGLU:
+            if (dst->type == GGML_TYPE_F32) {
+                kernel = backend_ctx->kernel_swiglu;
+            } else {
+                kernel = backend_ctx->kernel_swiglu_f16;
+            }
+            break;
+        default:
+            GGML_ABORT("Unsupported glu op");
+    }
+
+    ggml_tensor_extra_cl * extra0 = (ggml_tensor_extra_cl *)src0->extra;
+    ggml_tensor_extra_cl * extrad = (ggml_tensor_extra_cl *)dst->extra;
+
+    ggml_tensor_extra_cl * extra1 = src1 ? (ggml_tensor_extra_cl *)src1->extra : nullptr;
+
+    cl_ulong offset0 = extra0->offset + src0->view_offs;
+    cl_ulong offsetd = extrad->offset + dst->view_offs;
+
+    cl_ulong offset1 = extra1 ? extra1->offset + src1->view_offs : offset0;
+
+    const int ne0       = dst->ne[0];
+
+    const cl_ulong nb01 = src0->nb[1];
+    const cl_ulong nb11 = src1 ? src1->nb[1] : nb01;
+
+    const cl_ulong nb1  = dst->nb[1];
+
+    const int swp = ((const int32_t *) dst->op_params)[1];
+    const int ne00_off = src1 ? 0 : (swp ? ne0 : 0);
+    const int ne10_off = src1 ? 0 : (swp ? 0 : ne0);
+
+    CL_CHECK(clSetKernelArg(kernel,  0, sizeof(cl_mem),   &extra0->data_device));
+    CL_CHECK(clSetKernelArg(kernel,  1, sizeof(cl_ulong), &offset0));
+    CL_CHECK(clSetKernelArg(kernel,  2, sizeof(cl_mem),   src1 ? &extra1->data_device : &extra0->data_device));
+    CL_CHECK(clSetKernelArg(kernel,  3, sizeof(cl_ulong), &offset1));
+    CL_CHECK(clSetKernelArg(kernel,  4, sizeof(cl_mem),   &extrad->data_device));
+    CL_CHECK(clSetKernelArg(kernel,  5, sizeof(cl_ulong), &offsetd));
+    CL_CHECK(clSetKernelArg(kernel,  6, sizeof(cl_ulong), &nb01));
+    CL_CHECK(clSetKernelArg(kernel,  7, sizeof(cl_ulong), &nb11));
+    CL_CHECK(clSetKernelArg(kernel,  8, sizeof(int),      &ne0));
+    CL_CHECK(clSetKernelArg(kernel,  9, sizeof(cl_ulong), &nb1));
+    CL_CHECK(clSetKernelArg(kernel, 10, sizeof(int),      &ne00_off));
+    CL_CHECK(clSetKernelArg(kernel, 11, sizeof(int),      &ne10_off));
+
+    const size_t nrows = ggml_nrows(src0);
+    size_t nth = 512;
+    size_t global_work_size[] = {nrows*nth, 1, 1};
+    size_t local_work_size[] = {nth, 1, 1};
+
+    backend_ctx->enqueue_ndrange_kernel(kernel, 3, global_work_size, local_work_size, dst);
+}
+
 //------------------------------------------------------------------------------
 // Op offloading
 //------------------------------------------------------------------------------
@@ -6244,6 +6362,12 @@ bool ggml_cl_compute_forward(ggml_backend_t backend, struct ggml_tensor * tensor
                 default:
                     return false;
             } break;
+        case GGML_OP_GLU:
+            if (!any_on_device) {
+                return false;
+            }
+            func = ggml_cl_glu;
+            break;
         case GGML_OP_CLAMP:
             if (!any_on_device) {
                 return false;

ggml/src/ggml-opencl/kernels/glu.cl

@@ -0,0 +1,201 @@
+#pragma OPENCL EXTENSION cl_khr_fp16 : enable
+
+#define GELU_COEF_A     0.044715f
+#define SQRT_2_OVER_PI  0.79788456080286535587989211986876f
+
+//------------------------------------------------------------------------------
+// geglu
+//------------------------------------------------------------------------------
+kernel void kernel_geglu(
+    global char * src0,
+    ulong  offset0,
+    global char * src1,
+    ulong  offset1,
+    global char * dst,
+    ulong  offsetd,
+    ulong nb01,
+    ulong nb11,
+    int ne0,
+    ulong nb1,
+    int ne00_off,
+    int ne10_off
+) {
+    src0 = (global char*)((global char*)src0 + offset0);
+    src1 = (global char*)((global char*)src1 + offset1);
+    dst  = (global char*)((global char*)dst  + offsetd);
+
+    global float * src0_row = (global float *) ((global char *) src0 + get_group_id(0)*nb01) + ne00_off;
+    global float * src1_row = (global float *) ((global char *) src1 + get_group_id(0)*nb11) + ne10_off;
+    global float * dst_row  = (global float *) ((global char *) dst  + get_group_id(0)*nb1);
+
+    for (int i0 = get_local_id(0); i0 < ne0; i0 += get_local_size(0)) {
+        const float x0 = src0_row[i0];
+        const float x1 = src1_row[i0];
+
+        const float gelu = 0.5f*x0*(1.0f + tanh(SQRT_2_OVER_PI*x0*(1.0f + GELU_COEF_A*x0*x0)));
+
+        dst_row[i0] = gelu*x1;
+    }
+}
+
+kernel void kernel_geglu_f16(
+    global char * src0,
+    ulong  offset0,
+    global char * src1,
+    ulong  offset1,
+    global char * dst,
+    ulong  offsetd,
+    ulong nb01,
+    ulong nb11,
+    int ne0,
+    ulong nb1,
+    int ne00_off,
+    int ne10_off
+) {
+    src0 = (global char*)((global char*)src0 + offset0);
+    src1 = (global char*)((global char*)src1 + offset1);
+    dst  = (global char*)((global char*)dst  + offsetd);
+
+    global half * src0_row = (global half *) ((global char *) src0 + get_group_id(0)*nb01) + ne00_off;
+    global half * src1_row = (global half *) ((global char *) src1 + get_group_id(0)*nb11) + ne10_off;
+    global half * dst_row  = (global half *) ((global char *) dst  + get_group_id(0)*nb1);
+
+    for (int i0 = get_local_id(0); i0 < ne0; i0 += get_local_size(0)) {
+        const half x0 = src0_row[i0];
+        const half x1 = src1_row[i0];
+
+        const half gelu = 0.5f*x0*(1.0f + tanh(SQRT_2_OVER_PI*x0*(1.0f + GELU_COEF_A*x0*x0)));
+
+        dst_row[i0] = gelu*x1;
+    }
+}
+
+//------------------------------------------------------------------------------
+// reglu
+//------------------------------------------------------------------------------
+kernel void kernel_reglu(
+    global char * src0,
+    ulong  offset0,
+    global char * src1,
+    ulong  offset1,
+    global char * dst,
+    ulong  offsetd,
+    ulong nb01,
+    ulong nb11,
+    int ne0,
+    ulong nb1,
+    int ne00_off,
+    int ne10_off
+) {
+    src0 = (global char*)((global char*)src0 + offset0);
+    src1 = (global char*)((global char*)src1 + offset1);
+    dst  = (global char*)((global char*)dst  + offsetd);
+
+    global float * src0_row = (global float *) ((global char *) src0 + get_group_id(0)*nb01) + ne00_off;
+    global float * src1_row = (global float *) ((global char *) src1 + get_group_id(0)*nb11) + ne10_off;
+    global float * dst_row  = (global float *) ((global char *) dst  + get_group_id(0)*nb1);
+
+    for (int i0 = get_local_id(0); i0 < ne0; i0 += get_local_size(0)) {
+        const float x0 = src0_row[i0];
+        const float x1 = src1_row[i0];
+
+        dst_row[i0] = x0*x1*(x0 > 0.0f);
+    }
+}
+
+kernel void kernel_reglu_f16(
+    global char * src0,
+    ulong  offset0,
+    global char * src1,
+    ulong  offset1,
+    global char * dst,
+    ulong  offsetd,
+    ulong nb01,
+    ulong nb11,
+    int ne0,
+    ulong nb1,
+    int ne00_off,
+    int ne10_off
+) {
+    src0 = (global char*)((global char*)src0 + offset0);
+    src1 = (global char*)((global char*)src1 + offset1);
+    dst  = (global char*)((global char*)dst  + offsetd);
+
+    global half * src0_row = (global half *) ((global char *) src0 + get_group_id(0)*nb01) + ne00_off;
+    global half * src1_row = (global half *) ((global char *) src1 + get_group_id(0)*nb11) + ne10_off;
+    global half * dst_row  = (global half *) ((global char *) dst  + get_group_id(0)*nb1);
+
+    for (int i0 = get_local_id(0); i0 < ne0; i0 += get_local_size(0)) {
+        const half x0 = src0_row[i0];
+        const half x1 = src1_row[i0];
+
+        dst_row[i0] = x0*x1*(x0 > 0.0f);
+    }
+}
+
+//------------------------------------------------------------------------------
+// swiglu
+//------------------------------------------------------------------------------
+kernel void kernel_swiglu(
+    global char * src0,
+    ulong  offset0,
+    global char * src1,
+    ulong  offset1,
+    global char * dst,
+    ulong  offsetd,
+    ulong nb01,
+    ulong nb11,
+    int ne0,
+    ulong nb1,
+    int ne00_off,
+    int ne10_off
+) {
+    src0 = (global char*)((global char*)src0 + offset0);
+    src1 = (global char*)((global char*)src1 + offset1);
+    dst  = (global char*)((global char*)dst  + offsetd);
+
+    global float * src0_row = (global float *) ((global char *) src0 + get_group_id(0)*nb01) + ne00_off;
+    global float * src1_row = (global float *) ((global char *) src1 + get_group_id(0)*nb11) + ne10_off;
+    global float * dst_row  = (global float *) ((global char *) dst  + get_group_id(0)*nb1);
+
+    for (int i0 = get_local_id(0); i0 < ne0; i0 += get_local_size(0)) {
+        const float x0 = src0_row[i0];
+        const float x1 = src1_row[i0];
+
+        const float silu = x0 / (1.0f + exp(-x0));
+
+        dst_row[i0] = silu*x1;
+    }
+}
+
+kernel void kernel_swiglu_f16(
+    global char * src0,
+    ulong  offset0,
+    global char * src1,
+    ulong  offset1,
+    global char * dst,
+    ulong  offsetd,
+    ulong nb01,
+    ulong nb11,
+    int ne0,
+    ulong nb1,
+    int ne00_off,
+    int ne10_off
+) {
+    src0 = (global char*)((global char*)src0 + offset0);
+    src1 = (global char*)((global char*)src1 + offset1);
+    dst  = (global char*)((global char*)dst  + offsetd);
+
+    global half * src0_row = (global half *) ((global char *) src0 + get_group_id(0)*nb01) + ne00_off;
+    global half * src1_row = (global half *) ((global char *) src1 + get_group_id(0)*nb11) + ne10_off;
+    global half * dst_row  = (global half *) ((global char *) dst  + get_group_id(0)*nb1);
+
+    for (int i0 = get_local_id(0); i0 < ne0; i0 += get_local_size(0)) {
+        const half x0 = src0_row[i0];
+        const half x1 = src1_row[i0];
+
+        const half silu = x0 / (1.0f + exp(-x0));
+
+        dst_row[i0] = silu*x1;
+    }
+}

ggml/src/ggml-sycl/ggml-sycl.cpp

@@ -4215,6 +4215,7 @@ static bool ggml_backend_sycl_device_supports_op(ggml_backend_dev_t dev, const g
                 case GGML_UNARY_OP_GELU_QUICK:
                 case GGML_UNARY_OP_GELU_ERF:
                 case GGML_UNARY_OP_TANH:
+                case GGML_UNARY_OP_EXP:
                 case GGML_UNARY_OP_SGN:
                 case GGML_UNARY_OP_ABS:
                 case GGML_UNARY_OP_ELU:
@@ -4223,9 +4224,6 @@ static bool ggml_backend_sycl_device_supports_op(ggml_backend_dev_t dev, const g
 #else
                     return ggml_is_contiguous(op->src[0]) && (op->src[0]->type == GGML_TYPE_F32 && op->type == GGML_TYPE_F32) && (op->type == op->src[0]->type);
 #endif
-                case GGML_UNARY_OP_EXP:
-                     // Disable FP16 until we find out the root cause of failing fp16 sycl::exp
-                    return ggml_is_contiguous(op->src[0]) && (op->type == op->src[0]->type) && op->src[0]->type == GGML_TYPE_F32;
                 default:
                     return false;
             }

ggml/src/ggml.c

@@ -945,6 +945,7 @@ static const char * GGML_OP_NAME[GGML_OP_COUNT] = {
     "CONV_TRANSPOSE_1D",
     "IM2COL",
     "IM2COL_BACK",
+    "CONV_2D",
     "CONV_2D_DW",
     "CONV_TRANSPOSE_2D",
     "POOL_1D",
@@ -986,7 +987,7 @@ static const char * GGML_OP_NAME[GGML_OP_COUNT] = {
     "GLU",
 };
 
-static_assert(GGML_OP_COUNT == 85, "GGML_OP_COUNT != 85");
+static_assert(GGML_OP_COUNT == 86, "GGML_OP_COUNT != 86");
 
 static const char * GGML_OP_SYMBOL[GGML_OP_COUNT] = {
     "none",
@@ -1044,6 +1045,7 @@ static const char * GGML_OP_SYMBOL[GGML_OP_COUNT] = {
     "conv_transpose_1d(x)",
     "im2col(x)",
     "im2col_back(x)",
+    "conv_2d(x)",
     "conv_2d_dw(x)",
     "conv_transpose_2d(x)",
     "pool_1d(x)",
@@ -1085,7 +1087,7 @@ static const char * GGML_OP_SYMBOL[GGML_OP_COUNT] = {
     "glu(x)",
 };
 
-static_assert(GGML_OP_COUNT == 85, "GGML_OP_COUNT != 85");
+static_assert(GGML_OP_COUNT == 86, "GGML_OP_COUNT != 86");
 
 static_assert(GGML_OP_POOL_COUNT == 2, "GGML_OP_POOL_COUNT != 2");
 
@@ -4291,6 +4293,44 @@ struct ggml_tensor * ggml_conv_2d_dw_direct(
     return result;
 }
 
+// ggml_conv_2d_direct
+
+struct ggml_tensor * ggml_conv_2d_direct(
+        struct ggml_context * ctx,
+        struct ggml_tensor  * a,   // convolution kernel [KW, KH, IC, OC]
+        struct ggml_tensor  * b,   // input data [W, H, C, N]
+        int                   s0,  // stride dimension 0
+        int                   s1,  // stride dimension 1
+        int                   p0,  // padding dimension 0
+        int                   p1,  // padding dimension 1
+        int                   d0,  // dilation dimension 0
+        int                   d1) {// dilation dimension 1
+
+    GGML_ASSERT(a->ne[2] == b->ne[2]);
+    //GGML_ASSERT(a->type == b->type);
+
+    int64_t ne[4];
+    ne[0] = ggml_calc_conv_output_size(b->ne[0], a->ne[0], s0, p0, d0);
+    ne[1] = ggml_calc_conv_output_size(b->ne[1], a->ne[1], s1, p1, d1);
+    ne[2] = a->ne[3];
+    ne[3] = b->ne[3];
+
+    struct ggml_tensor * result = ggml_new_tensor(ctx, b->type, 4, ne);
+
+    ggml_set_op_params_i32(result, 0, s0);
+    ggml_set_op_params_i32(result, 1, s1);
+    ggml_set_op_params_i32(result, 2, p0);
+    ggml_set_op_params_i32(result, 3, p1);
+    ggml_set_op_params_i32(result, 4, d0);
+    ggml_set_op_params_i32(result, 5, d1);
+
+    result->op = GGML_OP_CONV_2D;
+    result->src[0] = a;
+    result->src[1] = b;
+
+    return result;
+}
+
 // ggml_conv_transpose_2d_p0
 
 static int64_t ggml_calc_conv_transpose_output_size(int64_t ins, int64_t ks, int s, int p) {

src/llama-kv-cache-unified-iswa.cpp

@@ -246,7 +246,7 @@ bool llama_kv_cache_unified_iswa_context::next() {
 }
 
 bool llama_kv_cache_unified_iswa_context::apply() {
-    assert(status == LLAMA_MEMORY_STATUS_SUCCESS);
+    assert(!llama_memory_status_is_fail(status));
 
     bool res = true;
 

src/llama-kv-cache-unified.cpp

@@ -1776,7 +1776,7 @@ bool llama_kv_cache_unified_context::next() {
 }
 
 bool llama_kv_cache_unified_context::apply() {
-    assert(status == LLAMA_MEMORY_STATUS_SUCCESS);
+    assert(!llama_memory_status_is_fail(status));
 
     // no ubatches -> this is a KV cache update
     if (ubatches.empty()) {

src/llama-memory-hybrid.cpp

@@ -218,7 +218,7 @@ bool llama_memory_hybrid_context::next() {
 }
 
 bool llama_memory_hybrid_context::apply() {
-    assert(status == LLAMA_MEMORY_STATUS_SUCCESS);
+    assert(!llama_memory_status_is_fail(status));
 
     bool res = true;
 

src/llama-memory-recurrent.cpp

@@ -1071,7 +1071,15 @@ bool llama_memory_recurrent_context::next() {
 }
 
 bool llama_memory_recurrent_context::apply() {
-    assert(status == LLAMA_MEMORY_STATUS_SUCCESS);
+    assert(!llama_memory_status_is_fail(status));
+
+    // no ubatches -> this is an update
+    if (ubatches.empty()) {
+        // recurrent cache never performs updates
+        assert(status == LLAMA_MEMORY_STATUS_NO_UPDATE);
+
+        return true;
+    }
 
     mem->find_slot(ubatches[i_next]);
 

src/llama-memory.cpp

@@ -40,3 +40,20 @@ llama_memory_status llama_memory_status_combine(llama_memory_status s0, llama_me
     // if either status has an update, then the combined status has an update
     return has_update ? LLAMA_MEMORY_STATUS_SUCCESS : LLAMA_MEMORY_STATUS_NO_UPDATE;
 }
+
+bool llama_memory_status_is_fail(llama_memory_status status) {
+    switch (status) {
+        case LLAMA_MEMORY_STATUS_SUCCESS:
+        case LLAMA_MEMORY_STATUS_NO_UPDATE:
+            {
+                return false;
+            }
+        case LLAMA_MEMORY_STATUS_FAILED_PREPARE:
+        case LLAMA_MEMORY_STATUS_FAILED_COMPUTE:
+            {
+                return true;
+            }
+    }
+
+    return false;
+}

src/llama-memory.h

@@ -31,6 +31,9 @@ enum llama_memory_status {
 // useful for implementing hybrid memory types (e.g. iSWA)
 llama_memory_status llama_memory_status_combine(llama_memory_status s0, llama_memory_status s1);
 
+// helper function for checking if a memory status indicates a failure
+bool llama_memory_status_is_fail(llama_memory_status status);
+
 // the interface for managing the memory context during batch processing
 // this interface is implemented per memory type. see:
 //   - llama_kv_cache_unified_context