From 5f8e7ef966c6057ef01f5bfb46a878ce20d1ad75 Mon Sep 17 00:00:00 2001
From: Praneet Rathi <prrathi10@gmail.com>
Date: Fri, 17 Jan 2025 16:58:27 -0600
Subject: [PATCH] cuda
---
hercules_cg/src/gpu.rs | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/hercules_cg/src/gpu.rs b/hercules_cg/src/gpu.rs
index a3a46d93..85ee7d90 100644
--- a/hercules_cg/src/gpu.rs
+++ b/hercules_cg/src/gpu.rs
@@ -631,7 +631,7 @@ extern \"C\" {} {}(", if ret_primitive { ret_type.clone() } else { "void".to_str
write!(w, "\tcudaMalloc((void**)&ret, sizeof({}));\n", ret_type)?;
write!(pass_args, ", ret")?;
}
- write!(w, "\t{}<<<{}_gpu, {}, {}>>>({});\n", self.function.name, num_blocks, num_threads, dynamic_shared_offset, pass_args)?;
+ write!(w, "\t{}_gpu<<<{}, {}, {}>>>({});\n", self.function.name, num_blocks, num_threads, dynamic_shared_offset, pass_args)?;
write!(w, "\tcudaDeviceSynchronize();\n")?;
if ret_primitive {
write!(w, "\t{} host_ret;\n", ret_type)?;
--
GitLab