From 1e6b5bf111109f4ea87144d38f578c5e53332f18 Mon Sep 17 00:00:00 2001
From: xaedes <xaedes@gmail.com>
Date: Sun, 14 May 2023 17:00:19 +0200
Subject: [PATCH] fix race condition bug in non-inplace
 ggml_compute_forward_diag_mask_f32

memcpy needs to be synchronized across threads to avoid race conditions.
=> do it in INIT phase
---
 ggml.c | 19 +++++++++++++------
 1 file changed, 13 insertions(+), 6 deletions(-)

diff --git a/ggml.c b/ggml.c
index 8ef1bb244..cb7b5695a 100644
--- a/ggml.c
+++ b/ggml.c
@@ -10450,20 +10450,27 @@ static void ggml_compute_forward_diag_mask_f32(
     assert(src1->type == GGML_TYPE_I32);
     assert(ggml_nelements(src1) == 2);
 
-    if (params->type == GGML_TASK_INIT || params->type == GGML_TASK_FINALIZE) {
-        return;
-    }
-
     const int ith = params->ith;
     const int nth = params->nth;
 
     const int  n_past  =       ((int32_t *) src1->data)[0];
     const bool inplace = (bool)((int32_t *) src1->data)[1];
 
-    if (!inplace) {
-        ggml_compute_forward_dup_same_cont(params, src0, dst);
+    if (!inplace && (params->type == GGML_TASK_INIT)) {
+        // memcpy needs to be synchronized across threads to avoid race conditions.
+        // => do it in INIT phase
+        GGML_ASSERT(ggml_nelements(dst) == ggml_nelements(src0));
+        GGML_ASSERT(ggml_is_contiguous(dst) && ggml_is_contiguous(src0));
+        memcpy(
+            ((char *)  dst->data),
+            ((char *) src0->data),
+            ggml_nbytes(dst));
     }
 
+    if (params->type == GGML_TASK_INIT || params->type == GGML_TASK_FINALIZE) {
+        return;
+    }
+    
     // TODO: handle transposed/permuted matrices
 
     const int n  = ggml_nrows(src0);