[RewriteStatepointsForGC] Reduce the number of new instructions for base pointers

When computing base pointers, we introduce new instructions to propagate the base of existing instructions which might not be bases. However, the algorithm doesn't make any effort to recognize when the new instruction to be inserted is the same as an existing one already in the IR. Since this is happening immediately before rewriting, we don't really have a chance to fix it after the pass runs without teaching loop passes about statepoints.

I'm really not thrilled with this patch. I've rewritten it 4 different ways now, but this is the best I've come up with. The case where the new instruction is just the original base defining value could be merged into the existing algorithm with some complexity. The problem is that we might have something like an extractelement from a phi of two vectors. It may be trivially obvious that the base of the 0th element is an existing instruction, but I can't see how to make the algorithm itself figure that out. Thus, I resort to the call to SimplifyInstruction instead.

Note that we can only adjust the instructions we've inserted ourselves. The live sets are still being tracked in side structures at this point in the code. We can't easily muck with instructions which might be in them. Long term, I'm really thinking we need to materialize the live pointer sets explicitly in the IR somehow rather than using side structures to track them.

Differential Revision: http://reviews.llvm.org/D12004

llvm-svn: 246133

4 files changed, 22 insertions, 18 deletions

diff --git a/llvm/test/Transforms/RewriteStatepointsForGC/base-pointers-4.ll b/llvm/test/Transforms/RewriteStatepointsForGC/base-pointers-4.ll
index 9ffe08628ef..9faaefba5cc 100644
--- a/llvm/test/Transforms/RewriteStatepointsForGC/base-pointers-4.ll
+++ b/llvm/test/Transforms/RewriteStatepointsForGC/base-pointers-4.ll
@@ -1,7 +1,7 @@
 ; RUN: opt %s -rewrite-statepoints-for-gc -spp-print-base-pointers -S 2>&1 | FileCheck %s
 
 
-; CHECK: derived %obj_to_consume base %obj_to_consume.base
+; CHECK: derived %obj_to_consume base %obj_to_consume
 
 declare void @foo()
 declare i64 addrspace(1)* @generate_obj()
@@ -33,7 +33,6 @@ dest_c:
 
 merge:
 ; CHECK: merge:
-; CHECK:  %obj_to_consume.base = phi i64 addrspace(1)* [ %obj2, %dest_a ], [ null, %dest_b ], [ null, %dest_c ]
 ; CHECK:  %obj_to_consume = phi i64 addrspace(1)* [ %obj2, %dest_a ], [ null, %dest_b ], [ null, %dest_c ]
 
   %obj_to_consume = phi i64 addrspace(1)* [ %obj2, %dest_a ], [ null, %dest_b ], [ null, %dest_c ]
diff --git a/llvm/test/Transforms/RewriteStatepointsForGC/base-pointers.ll b/llvm/test/Transforms/RewriteStatepointsForGC/base-pointers.ll
index 2b5b44aa695..a5081315d7e 100644
--- a/llvm/test/Transforms/RewriteStatepointsForGC/base-pointers.ll
+++ b/llvm/test/Transforms/RewriteStatepointsForGC/base-pointers.ll
@@ -80,7 +80,6 @@ loop:                                             ; preds = %loop, %entry
 ; we'd have commoned these, but that's a missed optimization, not correctness.
 ; CHECK-DAG: [ [[DISCARD:%.*.base.relocated.casted]], %loop ]
 ; CHECK-NOT: extra.base
-; CHECK: next.base = select
 ; CHECK: next = select
 ; CHECK: extra2.base = select
 ; CHECK: extra2 = select
@@ -95,6 +94,24 @@ loop:                                             ; preds = %loop, %entry
   br label %loop
 }
 
+define i64 addrspace(1)* @test3(i1 %cnd, i64 addrspace(1)* %obj, 
+                                i64 addrspace(1)* %obj2)
+    gc "statepoint-example" {
+; CHECK-LABEL: @test3
+entry:
+  br i1 %cnd, label %merge, label %taken
+taken:
+  br label %merge
+merge:
+; CHECK-LABEL: merge:
+; CHECK-NEXT: %bdv = phi
+; CHECK-NEXT: gc.statepoint
+  %bdv = phi i64 addrspace(1)* [ %obj, %entry ], [ %obj2, %taken ]
+  %safepoint_token = call i32 (i64, i32, void ()*, i32, i32, ...) @llvm.experimental.gc.statepoint.p0f_isVoidf(i64 0, i32 0, void ()* @foo, i32 0, i32 0, i32 0, i32 5, i32 0, i32 -1, i32 0, i32 0, i32 0)
+  ret i64 addrspace(1)* %bdv
+}
+
+
 declare void @foo()
 declare i32 @llvm.experimental.gc.statepoint.p0f_isVoidf(i64, i32, void ()*, i32, i32, ...)
 declare i32 @llvm.experimental.gc.statepoint.p0f_isVoidp1i64f(i64, i32, void (i64 addrspace(1)*)*, i32, i32, ...)
diff --git a/llvm/test/Transforms/RewriteStatepointsForGC/base-vector.ll b/llvm/test/Transforms/RewriteStatepointsForGC/base-vector.ll
index 2cba038a770..95011e86413 100644
--- a/llvm/test/Transforms/RewriteStatepointsForGC/base-vector.ll
+++ b/llvm/test/Transforms/RewriteStatepointsForGC/base-vector.ll
@@ -40,13 +40,10 @@ untaken2:
   br label %merge2
 merge2:
 ; CHECK-LABEL: merge2:
-; CHECK: %obj.base = phi i64 addrspace(1)*
-; CHECK: %obj = phi i64 addrspace(1)*
-; CHECK: statepoint
-; CHECK: gc.relocate
-; CHECK-DAG: ; (%obj.base, %obj)
+; CHECK-NEXT: %obj = phi i64 addrspace(1)*
+; CHECK-NEXT: statepoint
 ; CHECK: gc.relocate
-; CHECK-DAG: ; (%obj.base, %obj.base)
+; CHECK-DAG: ; (%obj, %obj)
   %obj = phi i64 addrspace(1)* [%obj0, %taken2], [%obj1, %untaken2]
   %safepoint_token = call i32 (i64, i32, void ()*, i32, i32, ...) @llvm.experimental.gc.statepoint.p0f_isVoidf(i64 0, i32 0, void ()* @do_safepoint, i32 0, i32 0, i32 0, i32 0)
   ret i64 addrspace(1)* %obj
diff --git a/llvm/test/Transforms/RewriteStatepointsForGC/live-vector.ll b/llvm/test/Transforms/RewriteStatepointsForGC/live-vector.ll
index 26ad73737ad..20640b58a31 100644
--- a/llvm/test/Transforms/RewriteStatepointsForGC/live-vector.ll
+++ b/llvm/test/Transforms/RewriteStatepointsForGC/live-vector.ll
@@ -121,9 +121,6 @@ define <2 x i64 addrspace(1)*> @test6(i1 %cnd, <2 x i64 addrspace(1)*>* %ptr)
 ; CHECK-LABEL: test6
 ; CHECK-LABEL: merge:
 ; CHECK-NEXT: = phi
-; CHECK-NEXT: = phi
-; CHECK-NEXT: extractelement
-; CHECK-NEXT: extractelement
 ; CHECK-NEXT: extractelement
 ; CHECK-NEXT: extractelement
 ; CHECK-NEXT: gc.statepoint
@@ -131,12 +128,6 @@ define <2 x i64 addrspace(1)*> @test6(i1 %cnd, <2 x i64 addrspace(1)*>* %ptr)
 ; CHECK-NEXT: bitcast
 ; CHECK-NEXT: gc.relocate
 ; CHECK-NEXT: bitcast
-; CHECK-NEXT: gc.relocate
-; CHECK-NEXT: bitcast
-; CHECK-NEXT: gc.relocate
-; CHECK-NEXT: bitcast
-; CHECK-NEXT: insertelement
-; CHECK-NEXT: insertelement
 ; CHECK-NEXT: insertelement
 ; CHECK-NEXT: insertelement
 ; CHECK-NEXT: ret <2 x i64 addrspace(1)*>