[attrs] Handle convergent CallSites.

Summary:
Previously we had a notion of convergent functions but not of convergent
calls.  This is insufficient to correctly analyze calls where the target
is unknown, e.g. indirect calls.

Now a call is convergent if it targets a known-convergent function, or
if it's explicitly marked as convergent.  As usual, we can remove
convergent where we can prove that no convergent operations are
performed in the call.

Reviewers: chandlerc, jingyue

Subscribers: hfinkel, jhen, tra, llvm-commits

Differential Revision: http://reviews.llvm.org/D17317

llvm-svn: 261544

1 files changed, 30 insertions, 18 deletions

diff --git a/llvm/test/Transforms/FunctionAttrs/convergent.ll b/llvm/test/Transforms/FunctionAttrs/convergent.ll
index 46370d7bf30..bc21d85ec22 100644
--- a/llvm/test/Transforms/FunctionAttrs/convergent.ll
+++ b/llvm/test/Transforms/FunctionAttrs/convergent.ll
@@ -1,4 +1,4 @@
-; RUN: opt < %s -basicaa -functionattrs -rpo-functionattrs -S | FileCheck %s
+; RUN: opt -functionattrs -S < %s | FileCheck %s
 
 ; CHECK: Function Attrs
 ; CHECK-NOT: convergent
@@ -24,20 +24,41 @@ declare i32 @k() convergent
 ; CHECK-SAME: convergent
 ; CHECK-NEXT: define i32 @extern()
 define i32 @extern() convergent {
-  %a = call i32 @k()
+  %a = call i32 @k() convergent
   ret i32 %a
 }
 
+; Convergent should not be removed on the function here.  Although the call is
+; not explicitly convergent, it picks up the convergent attr from the callee.
+;
 ; CHECK: Function Attrs
 ; CHECK-SAME: convergent
-; CHECK-NEXT: define i32 @call_extern()
-define i32 @call_extern() convergent {
-  %a = call i32 @extern()
+; CHECK-NEXT: define i32 @extern_non_convergent_call()
+define i32 @extern_non_convergent_call() convergent {
+  %a = call i32 @k()
   ret i32 %a
 }
 
 ; CHECK: Function Attrs
 ; CHECK-SAME: convergent
+; CHECK-NEXT: define i32 @indirect_convergent_call(
+define i32 @indirect_convergent_call(i32 ()* %f) convergent {
+   %a = call i32 %f() convergent
+   ret i32 %a
+}
+; Give indirect_non_convergent_call the norecurse attribute so we get a
+; "Function Attrs" comment in the output.
+;
+; CHECK: Function Attrs
+; CHECK-NOT: convergent
+; CHECK-NEXT: define i32 @indirect_non_convergent_call(
+define i32 @indirect_non_convergent_call(i32 ()* %f) convergent norecurse {
+   %a = call i32 %f()
+   ret i32 %a
+}
+
+; CHECK: Function Attrs
+; CHECK-SAME: convergent
 ; CHECK-NEXT: declare void @llvm.cuda.syncthreads()
 declare void @llvm.cuda.syncthreads() convergent
 
@@ -45,25 +66,16 @@ declare void @llvm.cuda.syncthreads() convergent
 ; CHECK-SAME: convergent
 ; CHECK-NEXT: define i32 @intrinsic()
 define i32 @intrinsic() convergent {
+  ; Implicitly convergent, because the intrinsic is convergent.
   call void @llvm.cuda.syncthreads()
   ret i32 0
 }
 
-@xyz = global i32 ()* null
-; CHECK: Function Attrs
-; CHECK-SAME: convergent
-; CHECK-NEXT: define i32 @functionptr()
-define i32 @functionptr() convergent {
-  %1 = load i32 ()*, i32 ()** @xyz
-  %2 = call i32 %1()
-  ret i32 %2
-}
-
 ; CHECK: Function Attrs
 ; CHECK-NOT: convergent
 ; CHECK-NEXT: define i32 @recursive1()
 define i32 @recursive1() convergent {
-  %a = call i32 @recursive2()
+  %a = call i32 @recursive2() convergent
   ret i32 %a
 }
 
@@ -71,7 +83,7 @@ define i32 @recursive1() convergent {
 ; CHECK-NOT: convergent
 ; CHECK-NEXT: define i32 @recursive2()
 define i32 @recursive2() convergent {
-  %a = call i32 @recursive1()
+  %a = call i32 @recursive1() convergent
   ret i32 %a
 }
 
@@ -79,7 +91,7 @@ define i32 @recursive2() convergent {
 ; CHECK-SAME: convergent
 ; CHECK-NEXT: define i32 @noopt()
 define i32 @noopt() convergent optnone noinline {
-  %a = call i32 @noopt_friend()
+  %a = call i32 @noopt_friend() convergent
   ret i32 0
 }