add OP sigmoid (#12056)

Co-authored-by: Judd <redacted>

diff --git a/ggml/src/ggml-vulkan/ggml-vulkan.cpp b/ggml/src/ggml-vulkan/ggml-vulkan.cpp
index daef8b89d451e9ef886df19f17f2fd6d8da42b66..5864e9819d9c6a68c6228c886a7ed9c943f4135e 100644 (file)
--- a/ggml/src/ggml-vulkan/ggml-vulkan.cpp
+++ b/ggml/src/ggml-vulkan/ggml-vulkan.cpp
@@ -249,6 +249,7 @@ struct vk_device_struct {
     vk_pipeline pipeline_relu_f32;
     vk_pipeline pipeline_leaky_relu_f32;
     vk_pipeline pipeline_tanh_f32;
+    vk_pipeline pipeline_sigmoid_f32;
     vk_pipeline pipeline_diag_mask_inf_f32;
     vk_pipeline pipeline_soft_max_f32, pipeline_soft_max_f32_f16;
     vk_pipeline pipeline_soft_max_f32_wg512, pipeline_soft_max_f32_f16_wg512;
@@ -2189,6 +2190,7 @@ static void ggml_vk_load_shaders(vk_device& device) {
     ggml_vk_create_pipeline(device, device->pipeline_relu_f32, "relu_f32", relu_f32_len, relu_f32_data, "main", 2, sizeof(vk_op_push_constants), {512, 1, 1}, {}, 1);
     ggml_vk_create_pipeline(device, device->pipeline_leaky_relu_f32, "leaky_relu_f32", leaky_relu_f32_len, leaky_relu_f32_data, "main", 2, sizeof(vk_op_push_constants), {512, 1, 1}, {}, 1);
     ggml_vk_create_pipeline(device, device->pipeline_tanh_f32, "tanh_f32", tanh_f32_len, tanh_f32_data, "main", 2, sizeof(vk_op_push_constants), {512, 1, 1}, {}, 1);
+    ggml_vk_create_pipeline(device, device->pipeline_sigmoid_f32, "sigmoid_f32", sigmoid_f32_len, sigmoid_f32_data, "main", 2, sizeof(vk_op_push_constants), {512, 1, 1}, {}, 1);
 
     ggml_vk_create_pipeline(device, device->pipeline_diag_mask_inf_f32, "diag_mask_inf_f32", diag_mask_inf_f32_len, diag_mask_inf_f32_data, "main", 2, sizeof(vk_op_diag_mask_push_constants), {1, 512, 1}, {}, 1, true);
 
@@ -5342,6 +5344,11 @@ static vk_pipeline ggml_vk_op_get_pipeline(ggml_backend_vk_context * ctx, const
                     return ctx->device->pipeline_tanh_f32;
                 }
                 break;
+            case GGML_UNARY_OP_SIGMOID:
+                if (src0->type == GGML_TYPE_F32 && dst->type == GGML_TYPE_F32) {
+                    return ctx->device->pipeline_sigmoid_f32;
+                }
+                break;
             default:
                 break;
         }
@@ -7335,6 +7342,7 @@ static bool ggml_vk_build_graph(ggml_backend_vk_context * ctx, ggml_tensor * nod
         case GGML_UNARY_OP_GELU_QUICK:
         case GGML_UNARY_OP_RELU:
         case GGML_UNARY_OP_TANH:
+        case GGML_UNARY_OP_SIGMOID:
             break;
         default:
             return false;
@@ -7551,6 +7559,7 @@ static bool ggml_vk_build_graph(ggml_backend_vk_context * ctx, ggml_tensor * nod
         case GGML_UNARY_OP_GELU_QUICK:
         case GGML_UNARY_OP_RELU:
         case GGML_UNARY_OP_TANH:
+        case GGML_UNARY_OP_SIGMOID:
             ggml_vk_unary(ctx, compute_ctx, src0, node, dryrun);
             break;
         default:
@@ -7738,6 +7747,7 @@ static bool ggml_vk_compute_forward(ggml_backend_vk_context * ctx, ggml_tensor *
         case GGML_UNARY_OP_GELU_QUICK:
         case GGML_UNARY_OP_RELU:
         case GGML_UNARY_OP_TANH:
+        case GGML_UNARY_OP_SIGMOID:
             buf = tensor->buffer;
             break;
         default:
@@ -8439,6 +8449,7 @@ static bool ggml_backend_vk_device_supports_op(ggml_backend_dev_t dev, const ggm
                 case GGML_UNARY_OP_SILU:
                 case GGML_UNARY_OP_RELU:
                 case GGML_UNARY_OP_TANH:
+                case GGML_UNARY_OP_SIGMOID:
                     return ggml_is_contiguous(op->src[0]);
                 default:
                     return false;
@@ -9105,6 +9116,9 @@ static void ggml_vk_check_results_0(ggml_tensor * tensor) {
         case GGML_UNARY_OP_TANH:
             tensor_clone = ggml_tanh(ggml_ctx, src_clone[0]);
             break;
+        case GGML_UNARY_OP_SIGMOID:
+            tensor_clone = ggml_sigmoid(ggml_ctx, src_clone[0]);
+            break;
         default:
             std::cerr << "Missing vk_check_results OP: " << ggml_op_name(tensor->op) << std::endl;
             GGML_ABORT("fatal error");

diff --git a/ggml/src/ggml-vulkan/vulkan-shaders/sigmoid.comp b/ggml/src/ggml-vulkan/vulkan-shaders/sigmoid.comp
new file mode 100644 (file)
index 0000000..776581e
--- /dev/null
+++ b/ggml/src/ggml-vulkan/vulkan-shaders/sigmoid.comp
@@ -0,0 +1,20 @@
+#version 450
+
+#include "generic_head.comp"
+#include "types.comp"
+
+#extension GL_EXT_control_flow_attributes : enable
+
+layout(local_size_x = 512, local_size_y = 1, local_size_z = 1) in;
+
+layout (binding = 0) readonly buffer X {A_TYPE data_a[];};
+layout (binding = 1) writeonly buffer D {D_TYPE data_d[];};
+
+void main() {
+    const uint i = gl_GlobalInvocationID.z * 262144 + gl_GlobalInvocationID.y * 512 + gl_GlobalInvocationID.x;
+
+    if (i >= p.KX) {
+        return;
+    }
+    data_d[i] = D_TYPE(1. / (1 + exp(-1. *data_a[i])));
+}

diff --git a/ggml/src/ggml-vulkan/vulkan-shaders/vulkan-shaders-gen.cpp b/ggml/src/ggml-vulkan/vulkan-shaders/vulkan-shaders-gen.cpp
index fc8bbb9460ad28028fe12f6bb0c12a4fa6a14b5f..c5e0bba82b26040c2119eacbbe4809daee70837b 100644 (file)
--- a/ggml/src/ggml-vulkan/vulkan-shaders/vulkan-shaders-gen.cpp
+++ b/ggml/src/ggml-vulkan/vulkan-shaders/vulkan-shaders-gen.cpp
@@ -482,6 +482,7 @@ void process_shaders() {
     string_to_spv("relu_f32", "relu.comp", {{"A_TYPE", "float"}, {"D_TYPE", "float"}});
     string_to_spv("leaky_relu_f32", "leaky_relu.comp", {{"A_TYPE", "float"}, {"D_TYPE", "float"}});
     string_to_spv("tanh_f32", "tanh.comp", {{"A_TYPE", "float"}, {"D_TYPE", "float"}});
+    string_to_spv("sigmoid_f32", "sigmoid.comp", {{"A_TYPE", "float"}, {"D_TYPE", "float"}});
 
     string_to_spv("diag_mask_inf_f32", "diag_mask_inf.comp", {{"A_TYPE", "float"}, {"D_TYPE", "float"}});