This revision was landed with ongoing or failed builds.
This revision was automatically updated to reflect the committed changes.
Closed by commit rGd77c62053c94: [clang][AMDGPU]: Dont use byval for
struct arguments in function ABI (authored by cfang).
Herald added a project: clang.
Herald added a subscriber: cfe-commits.
Changed prior to commit:
https://reviews.llvm.org/D155986?vs=549545=549546#toc
Repository:
rG LLVM Github Monorepo
CHANGES SINCE LAST ACTION
https://reviews.llvm.org/D155986/new/
https://reviews.llvm.org/D155986
Files:
clang/docs/ReleaseNotes.rst
clang/lib/CodeGen/CGCall.cpp
clang/lib/CodeGen/Targets/AMDGPU.cpp
clang/test/CodeGenCUDA/kernel-args.cu
clang/test/CodeGenCXX/amdgcn-func-arg.cpp
clang/test/CodeGenOpenCL/addr-space-struct-arg.cl
clang/test/CodeGenOpenCL/amdgpu-abi-struct-arg-byref.cl
clang/test/CodeGenOpenCL/amdgpu-abi-struct-coerce.cl
clang/test/CodeGenOpenCL/byval.cl
llvm/docs/AMDGPUUsage.rst
Index: llvm/docs/AMDGPUUsage.rst
===
--- llvm/docs/AMDGPUUsage.rst
+++ llvm/docs/AMDGPUUsage.rst
@@ -13812,6 +13812,10 @@
9. All other registers are unspecified.
10. Any necessary ``s_waitcnt`` has been performed to ensure memory is available
to the function.
+11: Use pass-by-reference (byref) in stead of pass-by-value (byval) for struct
+arguments in C ABI. Callee is responsible for allocating stack memory and
+copying the value of the struct if modified. Note that the backend still
+supports byval for struct arguments.
On exit from a function:
Index: clang/test/CodeGenOpenCL/byval.cl
===
--- clang/test/CodeGenOpenCL/byval.cl
+++ clang/test/CodeGenOpenCL/byval.cl
@@ -1,5 +1,5 @@
-// RUN: %clang_cc1 -emit-llvm -o - -triple amdgcn %s | FileCheck %s
-
+// RUN: %clang_cc1 -emit-llvm -o - -triple i686-pc-darwin %s | FileCheck -check-prefix=X86 %s
+// RUN: %clang_cc1 -emit-llvm -o - -triple amdgcn %s | FileCheck -check-prefix=AMDGCN %s
struct A {
int x[100];
};
@@ -8,8 +8,10 @@
int g() {
struct A a;
- // CHECK: call i32 @f(ptr addrspace(5) noundef byval{{.*}}%a)
+ // X86:call i32 @f(ptr noundef nonnull byval(%struct.A) align 4 %a)
+ // AMDGCN: call i32 @f(ptr addrspace(5) noundef byref{{.*}}%a)
return f(a);
}
-// CHECK: declare i32 @f(ptr addrspace(5) noundef byval{{.*}})
+// X86: declare i32 @f(ptr noundef byval(%struct.A) align 4)
+// AMDGCN: declare i32 @f(ptr addrspace(5) noundef byref{{.*}})
Index: clang/test/CodeGenOpenCL/amdgpu-abi-struct-coerce.cl
===
--- clang/test/CodeGenOpenCL/amdgpu-abi-struct-coerce.cl
+++ clang/test/CodeGenOpenCL/amdgpu-abi-struct-coerce.cl
@@ -448,11 +448,11 @@
// CHECK: define{{.*}} void @func_reg_state_lo(<4 x i32> noundef %arg0, <4 x i32> noundef %arg1, <4 x i32> noundef %arg2, i32 noundef %arg3, i32 %s.coerce0, float %s.coerce1, i32 %s.coerce2)
void func_reg_state_lo(int4 arg0, int4 arg1, int4 arg2, int arg3, struct_arg_t s) { }
-// CHECK: define{{.*}} void @func_reg_state_hi(<4 x i32> noundef %arg0, <4 x i32> noundef %arg1, <4 x i32> noundef %arg2, i32 noundef %arg3, i32 noundef %arg4, ptr addrspace(5) nocapture noundef readnone byval(%struct.struct_arg) align 4 %s)
+// CHECK: define{{.*}} void @func_reg_state_hi(<4 x i32> noundef %arg0, <4 x i32> noundef %arg1, <4 x i32> noundef %arg2, i32 noundef %arg3, i32 noundef %arg4, ptr addrspace(5) nocapture noundef readnone byref(%struct.struct_arg) align 4 %{{.*}})
void func_reg_state_hi(int4 arg0, int4 arg1, int4 arg2, int arg3, int arg4, struct_arg_t s) { }
// XXX - Why don't the inner structs flatten?
-// CHECK: define{{.*}} void @func_reg_state_num_regs_nested_struct(<4 x i32> noundef %arg0, i32 noundef %arg1, i32 %arg2.coerce0, %struct.nested %arg2.coerce1, i32 %arg3.coerce0, %struct.nested %arg3.coerce1, ptr addrspace(5) nocapture noundef readnone byval(%struct.num_regs_nested_struct) align 8 %arg4)
+// CHECK: define{{.*}} void @func_reg_state_num_regs_nested_struct(<4 x i32> noundef %arg0, i32 noundef %arg1, i32 %arg2.coerce0, %struct.nested %arg2.coerce1, i32 %arg3.coerce0, %struct.nested %arg3.coerce1, ptr addrspace(5) nocapture noundef readnone byref(%struct.num_regs_nested_struct) align 8 %{{.*}})
void func_reg_state_num_regs_nested_struct(int4 arg0, int arg1, num_regs_nested_struct arg2, num_regs_nested_struct arg3, num_regs_nested_struct arg4) { }
// CHECK: define{{.*}} void @func_double_nested_struct_arg(<4 x i32> noundef %arg0, i32 noundef %arg1, i32 %arg2.coerce0, %struct.double_nested %arg2.coerce1, i16 %arg2.coerce2)
@@ -467,7 +467,7 @@
// CHECK: define{{.*}} void @func_large_struct_padding_arg_direct(i8 %arg.coerce0, i32 %arg.coerce1, i8 %arg.coerce2, i32 %arg.coerce3, i8 %arg.coerce4, i8 %arg.coerce5, i16 %arg.coerce6, i16 %arg.coerce7, [3 x i8] %arg.coerce8, i64 %arg.coerce9, i32 %arg.coerce10, i8
