[Libclc-dev] [PATCH 3/3] amdgcn, popcount: Workaround broken llvm.ctpop intrinsic on some GCN ASICs

[Jan Vesely via Libclc-dev]

This is only really needed for VI+ ASICs. However, llvm would cast the value to
i32 for older asics anyway. The proper fix is in LLVM-7 (r326535).
Fixes CTS popcount on carrizo.

Signed-off-by: Jan Vesely <jan.vesely at rutgers.edu>
---
 amdgcn/lib/SOURCES              |  1 +
 amdgcn/lib/integer/popcount.cl  |  6 ++++++
 amdgcn/lib/integer/popcount.inc | 17 +++++++++++++++++
 3 files changed, 24 insertions(+)
 create mode 100644 amdgcn/lib/integer/popcount.cl
 create mode 100644 amdgcn/lib/integer/popcount.inc

diff --git a/amdgcn/lib/SOURCES b/amdgcn/lib/SOURCES
index 8e14ce2..6a5ce00 100644
--- a/amdgcn/lib/SOURCES
+++ b/amdgcn/lib/SOURCES
@@ -1,4 +1,5 @@
 cl_khr_int64_extended_atomics/minmax_helpers.ll
+integer/popcount.cl
 math/ldexp.cl
 mem_fence/fence.cl
 synchronization/barrier.cl
diff --git a/amdgcn/lib/integer/popcount.cl b/amdgcn/lib/integer/popcount.cl
new file mode 100644
index 0000000..ebd167d
--- /dev/null
+++ b/amdgcn/lib/integer/popcount.cl
@@ -0,0 +1,6 @@
+#include <clc/clc.h>
+#include <utils.h>
+#include <integer/popcount.h>
+
+#define __CLC_BODY "popcount.inc"
+#include <clc/integer/gentype.inc>
diff --git a/amdgcn/lib/integer/popcount.inc b/amdgcn/lib/integer/popcount.inc
new file mode 100644
index 0000000..402ddb7
--- /dev/null
+++ b/amdgcn/lib/integer/popcount.inc
@@ -0,0 +1,17 @@
+_CLC_OVERLOAD _CLC_DEF __CLC_GENTYPE popcount(__CLC_GENTYPE x) {
+/* LLVM-4+ implements i16 ops for VI+ ASICs. However, ctpop implementation
+ * is missing until r326535. Therefore we have to convert sub i32 types to uint
+ * as a workaround. */
+#if __clang_major__ < 7 && __clang_major__ > 3 && __CLC_GENSIZE < 32
+	/* Prevent sign extension on uint conversion */
+	const __CLC_U_GENTYPE y = __CLC_XCONCAT(as_, __CLC_U_GENTYPE)(x);
+	/* Convert to uintX */
+	const __CLC_XCONCAT(uint, __CLC_VECSIZE) z = __CLC_XCONCAT(convert_uint, __CLC_VECSIZE)(y);
+	/* Call popcount on uintX type */
+	const __CLC_XCONCAT(uint, __CLC_VECSIZE) res = __clc_native_popcount(z);
+	/* Convert the result back to gentype. */
+	return __CLC_XCONCAT(convert_, __CLC_GENTYPE)(res);
+#else
+	return __clc_native_popcount(x);
+#endif
+}
-- 
2.14.3