d8f22514eb
Summary: This patch causes us to respect the `-fconvergent-functions` and `-fno-convergent-functions` options correctly. GPU targets should have this set all the time, but we now offer `-fno-convergent-functions` to opt-out if you want to test broken behavior. This munged about with a lot of the old weird logic, but I don't think it makes any real changes.
18 lines
808 B
C
18 lines
808 B
C
// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py UTC_ARGS: --function-signature --check-attributes --check-globals
|
|
// RUN: %clang_cc1 -triple nvptx64-nvidia-cuda -target-cpu sm_61 -emit-llvm %s -o - | FileCheck %s
|
|
|
|
// CHECK: Function Attrs: convergent noinline nounwind optnone
|
|
// CHECK-LABEL: define {{[^@]+}}@foo
|
|
// CHECK-SAME: (ptr noundef [[RET:%.*]]) #[[ATTR0:[0-9]+]] {
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[RET_ADDR:%.*]] = alloca ptr, align 8
|
|
// CHECK-NEXT: store ptr [[RET]], ptr [[RET_ADDR]], align 8
|
|
// CHECK-NEXT: [[TMP0:%.*]] = load ptr, ptr [[RET_ADDR]], align 8
|
|
// CHECK-NEXT: store i32 1, ptr [[TMP0]], align 4
|
|
// CHECK-NEXT: ret void
|
|
__attribute__((nvptx_kernel)) void foo(int *ret) {
|
|
*ret = 1;
|
|
}
|
|
|
|
// CHECK: !0 = !{ptr @foo, !"kernel", i32 1}
|