w host

hercules_cg/src/device.rs

@@ -9,6 +9,8 @@ pub fn device_placement(functions: &Vec<Function>, callgraph: &CallGraph) -> Vec
     let mut devices = vec![];
 
     for (idx, function) in functions.into_iter().enumerate() {
+        devices.push(Device::CUDA);
+        continue;
         if let Some(device) = function.device {
             devices.push(device);
         } else if function.entry || callgraph.num_callees(FunctionID::new(idx)) != 0 {

hercules_opt/src/pass.rs

@@ -970,6 +970,7 @@ impl PassManager {
                             _ => todo!(),
                         }
                     }
+                    println!("{}", cuda_ir);
                     println!("{}", llvm_ir);
                     println!("{}", rust_rt);
 

hercules_samples/matmul/src/matmul.hir

-fn matmul<3>(a: array(i32, #0, #1), b: array(i32, #1, #2)) -> array(i32, #0, #2)
-  c = constant(array(i32, #0, #2), [])
-  i_j_ctrl = fork(start, #0, #2)
+fn matmul(a: array(i32, 16, 64), b: array(i32, 64, 32)) -> array(i32, 16, 32)
+  c = constant(array(i32, 16, 32), [])
+  i_j_ctrl = fork(start, 16, 32)
   i_idx = thread_id(i_j_ctrl, 0)
   j_idx = thread_id(i_j_ctrl, 1)
-  k_ctrl = fork(i_j_ctrl, #1)
+  k_ctrl = fork(i_j_ctrl, 64)
   k_idx = thread_id(k_ctrl, 0)
   k_join_ctrl = join(k_ctrl)
   i_j_join_ctrl = join(k_join_ctrl)

juno_samples/test2.jn

+#[entry]
+fn main<m, n : usize>() -> i32[m, n, 64, 64] {
+    let res : i32[m, n, 64, 64];
+    for bi = 0 to m {
+        for bj = 0 to n {
+            let tile : i32[64, 64];
+            for ti = 0 to 64 {
+                for tj = 0 to 64 {
+                    tile[ti, tj] = (ti as i32) + (tj as i32) + (bi as i32) + (bj as i32);
+                }
+            }
+            for si = 1 to 63 {
+                for sj = 1 to 63 {
+                    tile[si, sj] = tile[si-1, sj-1] + tile[si+1, sj+1];
+                }
+            }
+            for ri = 0 to 64 {
+                for rj = 0 to 64 {
+                    res[bi, bj, ri, rj] = tile[ri, rj];
+                }
+            }
+        }
+    }
+    return res;
+}