From a1d6df129bcd3d42cda38c09217d8d4ec4ea3bdd Mon Sep 17 00:00:00 2001
From: 0cc4m <picard12@live.de>
Date: Fri, 26 Jan 2024 23:07:32 +0100
Subject: Add OpenCL add kernel (#5151)

* Add OpenCL add kernel

* Put add kernel into different string to stay within MSVC string length limit, disable float16 support due to bad results
---
 ggml.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

(limited to 'ggml.c')

diff --git a/ggml.c b/ggml.c
index ef6fd8ca..8f57003e 100644
--- a/ggml.c
+++ b/ggml.c
@@ -7207,6 +7207,17 @@ static void ggml_compute_forward_add_f32(
     const int ith = params->ith;
     const int nth = params->nth;
 
+#ifdef GGML_USE_CLBLAST
+    if (src1->backend == GGML_BACKEND_GPU) {
+        // TODO: OpenCL kernel support full broadcast
+        GGML_ASSERT(ggml_can_repeat_rows(src1, src0));
+        if (ith == 0) {
+            ggml_cl_add(src0, src1, dst);
+        }
+        return;
+    }
+#endif
+
     const int nr  = ggml_nrows(src0);
 
     GGML_TENSOR_BINARY_OP_LOCALS
-- 
cgit v1.2.3