================
@@ -18,9 +39,45 @@ struct __attribute__((device_builtin_texture_type)) texture
: public textureReference {};
texture<float, 2, NormalizedFloat> tex;
+texture<float, 1, ElementType> tex_element;
+
+//===----------------------------------------------------------------------===//
+// Device-side checks
+//===----------------------------------------------------------------------===//
// CIR-DEVICE: cir.global external target_address_space(1) @tex = #cir.undef :
!cir.cuda_texture
+// CIR-DEVICE: cir.global external target_address_space(1) @tex_element =
#cir.undef : !cir.cuda_texture
// CIR now matches OG CodeGen and emits undef for CUDA shadow variables.
// LLVM-DEVICE: @tex ={{.*}} addrspace(1) externally_initialized global i64
undef
+// LLVM-DEVICE: @tex_element ={{.*}} addrspace(1) externally_initialized
global i64 undef
+
// OGCG-DEVICE: @tex ={{.*}} addrspace(1) externally_initialized global i64
undef
+// OGCG-DEVICE: @tex_element ={{.*}} addrspace(1) externally_initialized
global i64 undef
+
+//===----------------------------------------------------------------------===//
+// Host-side checks
+//===----------------------------------------------------------------------===//
+
+// Check the CUDA texture registration runtime declaration.
+// CIR-HOST: cir.func private
@__cudaRegisterTexture(!cir.ptr<!cir.ptr<!void>>, !cir.ptr<!void>,
!cir.ptr<!void>, !cir.ptr<!void>, !s32i, !s32i, !s32i)
+
+// Check texture registration metadata.
+// CIR-HOST-DAG: @tex = {{.*}}cu.var_registration =
#cir.cu.var_registration<tex, Texture, texture_type = 2, normalized>
+// CIR-HOST-DAG: @tex_element = {{.*}}cu.var_registration =
#cir.cu.var_registration<tex_element, Texture, texture_type = 1>
+
+// Check that the host-side shadow variables are internalized.
+// LLVM-HOST-DAG: @tex = internal global
+// LLVM-HOST-DAG: @tex_element = internal global
+
+// Check the CIR-lowered LLVM registration calls.
+// LLVM-HOST-LABEL: define internal void @__cuda_register_globals
+// LLVM-HOST-SAME: (ptr %[[FATBIN:.*]])
+// LLVM-HOST: call void @__cudaRegisterTexture(ptr %[[FATBIN]], ptr @tex, ptr
@[[TEX_NAME:.*]], ptr @[[TEX_NAME]], i32 2, i32 1, i32 0)
+// LLVM-HOST: call void @__cudaRegisterTexture(ptr %[[FATBIN]], ptr
@tex_element, ptr @[[ELEMENT_NAME:.*]], ptr @[[ELEMENT_NAME]], i32 1, i32 0,
i32 0)
+
+// Check original Clang CodeGen registration calls.
+// OGCG-HOST-LABEL: define internal void @__cuda_register_globals
----------------
RiverDave wrote:
given LLVM-HOST and OGCG-HOST checks are identical, you can merge those under
LLVM-HOST and dropping the OGCG blocks.
https://github.com/llvm/llvm-project/pull/236849
_______________________________________________
cfe-commits mailing list
[email protected]
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
