Implement vload_half{,n} and vload(half)
v2: add vload(half) as well
make helpers amdgpu specific (NVPTX uses different private AS numbering)
use clang builtin on clang >= 6
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
Reviewed-by: Tom Stellard <tstellar@redhat.com>
llvm-svn: 312839
diff --git a/libclc/amdgpu/lib/shared/vload_half_helpers.ll b/libclc/amdgpu/lib/shared/vload_half_helpers.ll
new file mode 100644
index 0000000..b8c905a
--- /dev/null
+++ b/libclc/amdgpu/lib/shared/vload_half_helpers.ll
@@ -0,0 +1,23 @@
+define float @__clc_vload_half_float_helper__private(half addrspace(0)* nocapture %ptr) nounwind alwaysinline {
+ %data = load half, half addrspace(0)* %ptr
+ %res = fpext half %data to float
+ ret float %res
+}
+
+define float @__clc_vload_half_float_helper__global(half addrspace(1)* nocapture %ptr) nounwind alwaysinline {
+ %data = load half, half addrspace(1)* %ptr
+ %res = fpext half %data to float
+ ret float %res
+}
+
+define float @__clc_vload_half_float_helper__local(half addrspace(3)* nocapture %ptr) nounwind alwaysinline {
+ %data = load half, half addrspace(3)* %ptr
+ %res = fpext half %data to float
+ ret float %res
+}
+
+define float @__clc_vload_half_float_helper__constant(half addrspace(2)* nocapture %ptr) nounwind alwaysinline {
+ %data = load half, half addrspace(2)* %ptr
+ %res = fpext half %data to float
+ ret float %res
+}