[Libclc-dev] [PATCH 3/3] Implement async_work_group_copy builtin v3

[Tom Stellard]

This is a simple implementation which just copies data synchronously.

v2:
  - Use size_t.

v3:
  - Fix possible race condition by splitting the copy among multiple
    work items.
---
 generic/include/clc/async/async_work_group_copy.h   | 15 +++++++++++++++
 generic/include/clc/async/async_work_group_copy.inc |  5 +++++
 generic/include/clc/clc.h                           |  1 +
 generic/lib/SOURCES                                 |  1 +
 generic/lib/async/async_work_group_copy.cl          |  9 +++++++++
 generic/lib/async/async_work_group_copy.inc         | 17 +++++++++++++++++
 6 files changed, 48 insertions(+)
 create mode 100644 generic/include/clc/async/async_work_group_copy.h
 create mode 100644 generic/include/clc/async/async_work_group_copy.inc
 create mode 100644 generic/lib/async/async_work_group_copy.cl
 create mode 100644 generic/lib/async/async_work_group_copy.inc

diff --git a/generic/include/clc/async/async_work_group_copy.h b/generic/include/clc/async/async_work_group_copy.h
new file mode 100644
index 0000000..39c637b
--- /dev/null
+++ b/generic/include/clc/async/async_work_group_copy.h
@@ -0,0 +1,15 @@
+#define __CLC_DST_ADDR_SPACE local
+#define __CLC_SRC_ADDR_SPACE global
+#define __CLC_BODY <clc/async/async_work_group_copy.inc>
+#include <clc/async/gentype.inc>
+#undef __CLC_DST_ADDR_SPACE
+#undef __CLC_SRC_ADDR_SPACE
+#undef __CLC_BODY
+
+#define __CLC_DST_ADDR_SPACE global
+#define __CLC_SRC_ADDR_SPACE local
+#define __CLC_BODY <clc/async/async_work_group_copy.inc>
+#include <clc/async/gentype.inc>
+#undef __CLC_DST_ADDR_SPACE
+#undef __CLC_SRC_ADDR_SPACE
+#undef __CLC_BODY
diff --git a/generic/include/clc/async/async_work_group_copy.inc b/generic/include/clc/async/async_work_group_copy.inc
new file mode 100644
index 0000000..d85df6c
--- /dev/null
+++ b/generic/include/clc/async/async_work_group_copy.inc
@@ -0,0 +1,5 @@
+_CLC_OVERLOAD _CLC_DECL event_t async_work_group_copy(
+  __CLC_DST_ADDR_SPACE __CLC_GENTYPE *dst,
+  const __CLC_SRC_ADDR_SPACE __CLC_GENTYPE *src,
+  size_t num_gentypes,
+  event_t event);
diff --git a/generic/include/clc/clc.h b/generic/include/clc/clc.h
index 0160e18..f5e9798 100644
--- a/generic/include/clc/clc.h
+++ b/generic/include/clc/clc.h
@@ -137,6 +137,7 @@
 #include <clc/synchronization/barrier.h>
 
 /* 6.11.10 Async Copy and Prefetch Functions */
+#include <clc/async/async_work_group_copy.h>
 #include <clc/async/async_work_group_strided_copy.h>
 #include <clc/async/prefetch.h>
 #include <clc/async/wait_group_events.h>
diff --git a/generic/lib/SOURCES b/generic/lib/SOURCES
index beca288..f13e5ad 100644
--- a/generic/lib/SOURCES
+++ b/generic/lib/SOURCES
@@ -1,3 +1,4 @@
+async/async_work_group_copy.cl
 async/async_work_group_strided_copy.cl
 async/prefetch.cl
 async/wait_group_events.cl
diff --git a/generic/lib/async/async_work_group_copy.cl b/generic/lib/async/async_work_group_copy.cl
new file mode 100644
index 0000000..fe20ecf
--- /dev/null
+++ b/generic/lib/async/async_work_group_copy.cl
@@ -0,0 +1,9 @@
+#include <clc/clc.h>
+
+#ifdef cl_khr_fp64
+#pragma OPENCL EXTENSION cl_khr_fp64 : enable
+#endif
+
+#define __CLC_BODY <async_work_group_copy.inc>
+#include <clc/async/gentype.inc>
+#undef __CLC_BODY
diff --git a/generic/lib/async/async_work_group_copy.inc b/generic/lib/async/async_work_group_copy.inc
new file mode 100644
index 0000000..a143ddf
--- /dev/null
+++ b/generic/lib/async/async_work_group_copy.inc
@@ -0,0 +1,17 @@
+_CLC_OVERLOAD _CLC_DEF event_t async_work_group_copy(
+    local __CLC_GENTYPE *dst,
+    const global __CLC_GENTYPE *src,
+    size_t num_gentypes,
+    event_t event) {
+
+  return async_work_group_strided_copy(dst, src, num_gentypes, 1, event);
+}
+
+_CLC_OVERLOAD _CLC_DEF event_t async_work_group_copy(
+    global __CLC_GENTYPE *dst,
+    const local __CLC_GENTYPE *src,
+    size_t num_gentypes,
+    event_t event) {
+
+  return async_work_group_strided_copy(dst, src, num_gentypes, 1, event);
+}
-- 
1.8.5.5