[RS4GC] Fix rematerialization of bitcast of bitcast.

[mjacob]

Summary

Previously, only the outer (last) bitcast was rematerialized, resulting in a
use of the unrelocated inner (first) bitcast after the statepoint. See the
test case for an example.

[reames]

I think you need to leave in:

if (!CI->isNoopCast(CI->getModule()->getDataLayout()))

• return false;

This is needed to catch things like addrspacecast.

Other than that, LGTM.

[igor-laevsky]

Looks good for me too. I agree with Philip's comments - better leave isNoopCast check.

[mjacob]

Only rematerialize noop casts, add test for this.

[reames]

LGTM.

lib/Transforms/Scalar/RewriteStatepointsForGC.cpp

static bool findRematerializableChainToBasePointer(
   if (GetElementPtrInst *GEP = dyn_cast<GetElementPtrInst>(CurrentValue)) {
     ChainToBase.push_back(GEP);
     return findRematerializableChainToBasePointer(ChainToBase,
                                                   GEP->getPointerOperand(),
                                                   BaseValue);
   }
 
   if (CastInst *CI = dyn_cast<CastInst>(CurrentValue)) {
-    Value *Def = CI->stripPointerCasts();
-
-    // This two checks are basically similar. First one is here for the
-    // consistency with findBasePointers logic.
-    assert(!isa<CastInst>(Def) && "not a pointer cast found");
     if (!CI->isNoopCast(CI->getModule()->getDataLayout()))
       return false;
 
     ChainToBase.push_back(CI);
-    return findRematerializableChainToBasePointer(ChainToBase, Def, BaseValue);
+    return findRematerializableChainToBasePointer(ChainToBase,
+                                                  CI->getOperand(0), BaseValue);
   }
 
   // Not supported instruction in the chain
   return false;
 }
 
 // Helper function for the "rematerializeLiveValues". Compute cost of the use
 // chain we are going to rematerialize.

test/Transforms/RewriteStatepointsForGC/rematerialize-derived-pointers.ll

entry:
   ; CHECK: %base.relocated = call coldcc i8 addrspace(1)* @llvm.experimental.gc.relocate.p1i8(token %sp, i32 7, i32 7)
   ; CHECK: %base.relocated.casted = bitcast i8 addrspace(1)* %base.relocated to i32 addrspace(1)*
   ; CHECK: bitcast i32 addrspace(1)* %base.relocated.casted to i64 addrspace(1)*
   call void @use_obj32(i32 addrspace(1)* %base)
   call void @use_obj64(i64 addrspace(1)* %ptr)
   ret void
 }
 
+define void @"test_bitcast_bitcast"(i32 addrspace(1)* %base) gc "statepoint-example" {
+; CHECK-LABEL: test_bitcast_bitcast
+entry:
+  %ptr1 = bitcast i32 addrspace(1)* %base to i64 addrspace(1)*
+  %ptr2 = bitcast i64 addrspace(1)* %ptr1 to i16 addrspace(1)*
+  ; CHECK: bitcast i32 addrspace(1)* %base to i64 addrspace(1)*
+  ; CHECK: bitcast i64 addrspace(1)* %ptr1 to i16 addrspace(1)*
+  %sp = call token (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)
+  ; CHECK: %base.relocated = call coldcc i8 addrspace(1)* @llvm.experimental.gc.relocate.p1i8(token %sp, i32 7, i32 7)
+  ; CHECK: %base.relocated.casted = bitcast i8 addrspace(1)* %base.relocated to i32 addrspace(1)*
+  ; CHECK: bitcast i32 addrspace(1)* %base.relocated.casted to i64 addrspace(1)*
+  ; CHECK: bitcast i64 addrspace(1)* %ptr1.remat to i16 addrspace(1)*
+  call void @use_obj32(i32 addrspace(1)* %base)
+  call void @use_obj16(i16 addrspace(1)* %ptr2)
+  ret void
+}
+
+define void @"test_addrspacecast_addrspacecast"(i32 addrspace(1)* %base) gc "statepoint-example" {
+; CHECK-LABEL: test_addrspacecast_addrspacecast
+entry:
+  %ptr1 = addrspacecast i32 addrspace(1)* %base to i32*
+  %ptr2 = addrspacecast i32* %ptr1 to i32 addrspace(1)*
+  ; CHECK: addrspacecast i32 addrspace(1)* %base to i32*
+  ; CHECK: addrspacecast i32* %ptr1 to i32 addrspace(1)*
+  %sp = call token (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)
+  ; CHECK: %base.relocated = call coldcc i8 addrspace(1)* @llvm.experimental.gc.relocate.p1i8(token %sp, i32 7, i32 7)
+  ; CHECK: %base.relocated.casted = bitcast i8 addrspace(1)* %base.relocated to i32 addrspace(1)*
+  ; CHECK: %ptr2.relocated = call coldcc i8 addrspace(1)* @llvm.experimental.gc.relocate.p1i8(token %sp, i32 7, i32 8)
+  ; CHECK: %ptr2.relocated.casted = bitcast i8 addrspace(1)* %ptr2.relocated to i32 addrspace(1)*
+  call void @use_obj32(i32 addrspace(1)* %base)
+  call void @use_obj32(i32 addrspace(1)* %ptr2)
+  ret void
+}
+
 define void @"test_bitcast_gep"(i32 addrspace(1)* %base) gc "statepoint-example" {
 ; CHECK-LABEL: test_bitcast_gep
 entry:
   %ptr.gep = getelementptr i32, i32 addrspace(1)* %base, i32 15
   ; CHECK: getelementptr
   %ptr.cast = bitcast i32 addrspace(1)* %ptr.gep to i64 addrspace(1)*
   ; CHECK: bitcast
   %sp = call token (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)