[OpenMP][NFC] Precommit test that exposes a bug in our optnone handling

diff --git a/llvm/test/Transforms/OpenMP/get_hardware_num_threads_in_block_fold_optnone.ll b/llvm/test/Transforms/OpenMP/get_hardware_num_threads_in_block_fold_optnone.ll
new file mode 100644 (file)
index 0000000..a6cbd20
--- /dev/null
+++ b/llvm/test/Transforms/OpenMP/get_hardware_num_threads_in_block_fold_optnone.ll
@@ -0,0 +1,136 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --function-signature --check-globals
+; RUN: opt -S -passes=openmp-opt < %s | FileCheck %s
+target triple = "nvptx64"
+
+%struct.ident_t = type { i32, i32, i32, i32, i8* }
+
+@kernel0_exec_mode = weak constant i8 1
+
+@G = external global i32
+;.
+; CHECK: @[[KERNEL0_EXEC_MODE:[a-zA-Z0-9_$"\\.-]+]] = weak constant i8 1
+; CHECK: @[[G:[a-zA-Z0-9_$"\\.-]+]] = external global i32
+; CHECK: @[[KERNEL1_EXEC_MODE:[a-zA-Z0-9_$"\\.-]+]] = weak constant i8 1
+; CHECK: @[[KERNEL2_EXEC_MODE:[a-zA-Z0-9_$"\\.-]+]] = weak constant i8 1
+;.
+define weak void @kernel0() #0 {
+; CHECK-LABEL: define {{[^@]+}}@kernel0
+; CHECK-SAME: () #[[ATTR0:[0-9]+]] {
+; CHECK-NEXT:    [[I:%.*]] = call i32 @__kmpc_target_init(%struct.ident_t* null, i1 true, i1 false, i1 false)
+; CHECK-NEXT:    call void @helper0()
+; CHECK-NEXT:    call void @helper1()
+; CHECK-NEXT:    call void @helper2()
+; CHECK-NEXT:    call void @__kmpc_target_deinit(%struct.ident_t* null, i1 true, i1 false)
+; CHECK-NEXT:    ret void
+;
+  %i = call i32 @__kmpc_target_init(%struct.ident_t* null, i1 true, i1 false, i1 false)
+  call void @helper0()
+  call void @helper1()
+  call void @helper2()
+  call void @__kmpc_target_deinit(%struct.ident_t* null, i1 true, i1 false)
+  ret void
+}
+
+@kernel1_exec_mode = weak constant i8 1
+
+define weak void @kernel1() #0 {
+; CHECK-LABEL: define {{[^@]+}}@kernel1
+; CHECK-SAME: () #[[ATTR0]] {
+; CHECK-NEXT:    [[I:%.*]] = call i32 @__kmpc_target_init(%struct.ident_t* null, i1 true, i1 false, i1 false)
+; CHECK-NEXT:    call void @helper1()
+; CHECK-NEXT:    call void @__kmpc_target_deinit(%struct.ident_t* null, i1 false, i1 false)
+; CHECK-NEXT:    ret void
+;
+  %i = call i32 @__kmpc_target_init(%struct.ident_t* null, i1 true, i1 false, i1 false)
+  call void @helper1()
+  call void @__kmpc_target_deinit(%struct.ident_t* null, i1 false, i1 false)
+  ret void
+}
+
+@kernel2_exec_mode = weak constant i8 1
+
+define weak void @kernel2() #0 {
+; CHECK-LABEL: define {{[^@]+}}@kernel2
+; CHECK-SAME: () #[[ATTR0]] {
+; CHECK-NEXT:    [[I:%.*]] = call i32 @__kmpc_target_init(%struct.ident_t* null, i1 false, i1 false, i1 false)
+; CHECK-NEXT:    call void @helper0()
+; CHECK-NEXT:    call void @helper1()
+; CHECK-NEXT:    call void @helper2()
+; CHECK-NEXT:    call void @__kmpc_target_deinit(%struct.ident_t* null, i1 false, i1 false)
+; CHECK-NEXT:    ret void
+;
+  %i = call i32 @__kmpc_target_init(%struct.ident_t* null, i1 false, i1 false, i1 false)
+  call void @helper0()
+  call void @helper1()
+  call void @helper2()
+  call void @__kmpc_target_deinit(%struct.ident_t* null, i1 false, i1 false)
+  ret void
+}
+
+define internal void @helper0() {
+; CHECK-LABEL: define {{[^@]+}}@helper0() {
+; CHECK-NEXT:    [[THREADLIMIT:%.*]] = call i32 @__kmpc_get_hardware_num_threads_in_block() #[[ATTR1:[0-9]+]]
+; CHECK-NEXT:    store i32 undef, i32* @G, align 4
+; CHECK-NEXT:    ret void
+;
+  %threadLimit = call i32 @__kmpc_get_hardware_num_threads_in_block()
+  store i32 %threadLimit, i32* @G
+  ret void
+}
+
+define internal void @helper1() {
+; CHECK-LABEL: define {{[^@]+}}@helper1() {
+; CHECK-NEXT:    [[THREADLIMIT:%.*]] = call i32 @__kmpc_get_hardware_num_threads_in_block() #[[ATTR1]]
+; CHECK-NEXT:    unreachable
+; CHECK:       t:
+; CHECK-NEXT:    unreachable
+; CHECK:       f:
+; CHECK-NEXT:    unreachable
+;
+  %threadLimit = call i32 @__kmpc_get_hardware_num_threads_in_block()
+  %c = icmp eq i32 %threadLimit, 666
+  br i1 %c, label %f, label %t
+t:
+  call void @helper0()
+  ret void
+f:
+  ret void
+}
+
+define internal void @helper2() {
+; CHECK-LABEL: define {{[^@]+}}@helper2() {
+; CHECK-NEXT:    [[THREADLIMIT:%.*]] = call i32 @__kmpc_get_hardware_num_threads_in_block() #[[ATTR1]]
+; CHECK-NEXT:    store i32 undef, i32* @G, align 4
+; CHECK-NEXT:    ret void
+;
+  %threadLimit = call i32 @__kmpc_get_hardware_num_threads_in_block()
+  store i32 %threadLimit, i32* @G
+  ret void
+}
+
+declare i32 @__kmpc_get_hardware_num_threads_in_block()
+declare i32 @__kmpc_target_init(%struct.ident_t*, i1 zeroext, i1 zeroext, i1 zeroext) #1
+declare void @__kmpc_target_deinit(%struct.ident_t* nocapture readnone, i1 zeroext, i1 zeroext) #1
+
+
+!llvm.module.flags = !{!0, !1}
+!nvvm.annotations = !{!2, !3, !4}
+
+attributes #0 = { optnone noinline "omp_target_thread_limit"="666" "omp_target_num_teams"="777"}
+
+!0 = !{i32 7, !"openmp", i32 50}
+!1 = !{i32 7, !"openmp-device", i32 50}
+!2 = !{void ()* @kernel0, !"kernel", i32 1}
+!3 = !{void ()* @kernel1, !"kernel", i32 1}
+!4 = !{void ()* @kernel2, !"kernel", i32 1}
+;
+;.
+; CHECK: attributes #[[ATTR0]] = { noinline optnone "omp_target_num_teams"="777" "omp_target_thread_limit"="666" }
+; CHECK: attributes #[[ATTR1]] = { nounwind }
+;.
+; CHECK: [[META0:![0-9]+]] = !{i32 7, !"openmp", i32 50}
+; CHECK: [[META1:![0-9]+]] = !{i32 7, !"openmp-device", i32 50}
+; CHECK: [[META2:![0-9]+]] = !{void ()* @kernel0, !"kernel", i32 1}
+; CHECK: [[META3:![0-9]+]] = !{void ()* @kernel1, !"kernel", i32 1}
+; CHECK: [[META4:![0-9]+]] = !{void ()* @kernel2, !"kernel", i32 1}
+;.