initial stream-k implementation with example (#699)

* initial stream-k implementation with example * fix unexpected change in err * improve a little bit performance by reorganize pipeline. * improve perf a little bit by swizzle block idx * add profiler * update example * fix spelling * shrink karg for streamk * support dynamic buffer using memory coherence glc_slc bit from template * control memory coherence while construct dynamic buffer * update reduction for streamk(not ready yet) * Add template parameter to make_dynamic_buffer to support amd_buffer coherence setting * fix build issue * fix several bug * now result is correct, everything works (but has scratch) * remove scratch by manually reset coordinate * update device code * fix a bug in final reduce * fix something in example * update async memset * fix enum as camel case * modify coherence enum name * clean code and use atomic streamk by default * remove unused var * throw exception if have empty pointer * fix format * fix CI warning * fix type in init * modify CI error * filter out on gfx10+ * restore changed example code --------- Co-authored-by: Qianfeng Zhang <Qianfeng.Zhang@amd.com>
2026-04-19 22:39:03 +00:00 · 2023-07-27 03:18:15 +08:00
parent 9195435c77
commit e7dca79d27
28 changed files with 4234 additions and 36 deletions
--- a/include/ck/host_utility/kernel_launch.hpp
+++ b/include/ck/host_utility/kernel_launch.hpp
@@ -73,3 +73,72 @@ float launch_and_time_kernel(const StreamConfig& stream_config,
    return 0;
 #endif
 }
+
+template <typename... Args, typename F, typename PreProcessFunc>
+float launch_and_time_kernel_with_preprocess(const StreamConfig& stream_config,
+                                             PreProcessFunc preprocess,
+                                             F kernel,
+                                             dim3 grid_dim,
+                                             dim3 block_dim,
+                                             std::size_t lds_byte,
+                                             Args... args)
+{
+#if CK_TIME_KERNEL
+    if(stream_config.time_kernel_)
+    {
+#if DEBUG_LOG
+        printf("%s: grid_dim {%d, %d, %d}, block_dim {%d, %d, %d} \n",
+               __func__,
+               grid_dim.x,
+               grid_dim.y,
+               grid_dim.z,
+               block_dim.x,
+               block_dim.y,
+               block_dim.z);
+
+        printf("Warm up 1 time\n");
+#endif
+        // warm up
+        preprocess();
+        kernel<<<grid_dim, block_dim, lds_byte, stream_config.stream_id_>>>(args...);
+
+        const int nrepeat = 10;
+#if DEBUG_LOG
+        printf("Start running %d times...\n", nrepeat);
+#endif
+        hipEvent_t start, stop;
+
+        hip_check_error(hipEventCreate(&start));
+        hip_check_error(hipEventCreate(&stop));
+
+        hip_check_error(hipDeviceSynchronize());
+        hip_check_error(hipEventRecord(start, stream_config.stream_id_));
+
+        for(int i = 0; i < nrepeat; ++i)
+        {
+            preprocess();
+            kernel<<<grid_dim, block_dim, lds_byte, stream_config.stream_id_>>>(args...);
+        }
+
+        hip_check_error(hipEventRecord(stop, stream_config.stream_id_));
+        hip_check_error(hipEventSynchronize(stop));
+
+        float total_time = 0;
+
+        hip_check_error(hipEventElapsedTime(&total_time, start, stop));
+
+        return total_time / nrepeat;
+    }
+    else
+    {
+        preprocess();
+        kernel<<<grid_dim, block_dim, lds_byte, stream_config.stream_id_>>>(args...);
+
+        return 0;
+    }
+#else
+    kernel<<<grid_dim, block_dim, lds_byte, stream_config.stream_id_>>>(args...);
+
+    return 0;
+#endif
+}