fd739804e0
For a default visibility external linkage definition, dso_local is set for ELF
-fno-pic/-fpie and COFF and Mach-O. Since default clang -cc1 for ELF is similar
to -fpic ("PIC Level" is not set), this nuance causes unneeded binary format differences.
To make emitted IR similar, ELF -cc1 -fpic will default to -fno-semantic-interposition,
which sets dso_local for default visibility external linkage definitions.
To make this flip smooth and enable future (dso_local as definition default),
this patch replaces (function) `define ` with `define{{.*}} `,
(variable/constant/alias) `= ` with `={{.*}} `, or inserts appropriate `{{.*}} `.
51 lines
2.0 KiB
Plaintext
51 lines
2.0 KiB
Plaintext
// RUN: echo "GPU binary would be here" > %t
|
|
|
|
// RUN: %clang_cc1 -triple x86_64-linux-gnu -emit-llvm %s -O0 \
|
|
// RUN: -fcuda-include-gpubinary %t -debug-info-kind=limited \
|
|
// RUN: -o - -x hip | FileCheck -check-prefixes=CHECK,O0 %s
|
|
// RUN: %clang_cc1 -triple amdgcn-amd-amdhsa -emit-llvm %s -O0 \
|
|
// RUN: -fcuda-include-gpubinary %t -debug-info-kind=limited \
|
|
// RUN: -o - -x hip -fcuda-is-device | FileCheck -check-prefix=DEV %s
|
|
|
|
// RUN: %clang_cc1 -triple x86_64-linux-gnu -emit-llvm %s -O0 \
|
|
// RUN: -fcuda-include-gpubinary %t -debug-info-kind=limited \
|
|
// RUN: -o - -x hip -debugger-tuning=gdb -dwarf-version=4 \
|
|
// RUN: | FileCheck -check-prefixes=CHECK,O0 %s
|
|
// RUN: %clang_cc1 -triple amdgcn-amd-amdhsa -emit-llvm %s -O0 \
|
|
// RUN: -fcuda-include-gpubinary %t -debug-info-kind=limited \
|
|
// RUN: -o - -x hip -debugger-tuning=gdb -dwarf-version=4 \
|
|
// RUN: -fcuda-is-device | FileCheck -check-prefix=DEV %s
|
|
|
|
// RUN: %clang_cc1 -triple x86_64-linux-gnu -emit-llvm %s -O3 \
|
|
// RUN: -fcuda-include-gpubinary %t -debug-info-kind=limited \
|
|
// RUN: -o - -x hip -debugger-tuning=gdb -dwarf-version=4 | FileCheck %s
|
|
// RUN: %clang_cc1 -triple amdgcn-amd-amdhsa -emit-llvm %s -O3 \
|
|
// RUN: -fcuda-include-gpubinary %t -debug-info-kind=limited \
|
|
// RUN: -o - -x hip -debugger-tuning=gdb -dwarf-version=4 \
|
|
// RUN: -fcuda-is-device | FileCheck -check-prefix=DEV %s
|
|
|
|
#include "Inputs/cuda.h"
|
|
|
|
extern "C" __global__ void ckernel(int *a) {
|
|
*a = 1;
|
|
}
|
|
|
|
// Device side kernel names
|
|
// CHECK: @[[CKERN:[0-9]*]] = {{.*}} c"ckernel\00"
|
|
|
|
// DEV: define {{.*}}@ckernel{{.*}}!dbg
|
|
// DEV: store {{.*}}!dbg
|
|
// DEV: ret {{.*}}!dbg
|
|
|
|
// Make sure there is no !dbg between function attributes and '{'
|
|
// CHECK: define{{.*}} void @[[CSTUB:__device_stub__ckernel]]{{.*}} #{{[0-9]+}} {
|
|
// CHECK-NOT: call {{.*}}@hipLaunchByPtr{{.*}}!dbg
|
|
// CHECK: call {{.*}}@hipLaunchByPtr{{.*}}@[[CSTUB]]
|
|
// CHECK-NOT: ret {{.*}}!dbg
|
|
|
|
// CHECK-LABEL: define {{.*}}@_Z8hostfuncPi{{.*}}!dbg
|
|
// O0: call void @[[CSTUB]]{{.*}}!dbg
|
|
void hostfunc(int *a) {
|
|
ckernel<<<1, 1>>>(a);
|
|
}
|