From e1819eb4e384bbd65a7ec3320142f7c885ba175d Mon Sep 17 00:00:00 2001
From: Matt Arsenault <Matthew.Arsenault@amd.com>
Date: Fri, 10 Jul 2015 22:17:40 +0000
Subject: [PATCH] DAGCombiner: Assume invariant load cannot alias a store

The motivation is to allow GatherAllAliases / FindBetterChain
to not give up on dependent loads of a pointer from constant memory.

This is important for AMDGPU, because most loads are pointers
derived from a load of a kernel argument from constant memory.

llvm-svn: 241948
---
 lib/CodeGen/SelectionDAG/DAGCombiner.cpp      |  9 +++++
 .../AMDGPU/invariant-load-no-alias-store.ll   | 35 +++++++++++++++++++
 2 files changed, 44 insertions(+)
 create mode 100644 test/CodeGen/AMDGPU/invariant-load-no-alias-store.ll

diff --git a/lib/CodeGen/SelectionDAG/DAGCombiner.cpp b/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
index e05714342d2..52d620b1d54 100644
--- a/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
+++ b/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
@@ -13844,6 +13844,15 @@ bool DAGCombiner::isAlias(LSBaseSDNode *Op0, LSBaseSDNode *Op1) const {
   // If they are both volatile then they cannot be reordered.
   if (Op0->isVolatile() && Op1->isVolatile()) return true;
 
+  // If one operation reads from invariant memory, and the other may store, they
+  // cannot alias. These should really be checking the equivalent of mayWrite,
+  // but it only matters for memory nodes other than load /store.
+  if (Op0->isInvariant() && Op1->writeMem())
+    return false;
+
+  if (Op1->isInvariant() && Op0->writeMem())
+    return false;
+
   // Gather base node and offset information.
   SDValue Base1, Base2;
   int64_t Offset1, Offset2;
diff --git a/test/CodeGen/AMDGPU/invariant-load-no-alias-store.ll b/test/CodeGen/AMDGPU/invariant-load-no-alias-store.ll
new file mode 100644
index 00000000000..2a01a621fc4
--- /dev/null
+++ b/test/CodeGen/AMDGPU/invariant-load-no-alias-store.ll
@@ -0,0 +1,35 @@
+; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
+
+; GatherAllAliases gives up on trying to analyze cases where the
+; pointer may have been loaded from an aliased store, so make sure
+; that this works and allows moving the stores to a better chain to
+; allow them to be merged merged when it's clear the pointer is loaded
+; from constant/invariant memory.
+
+; GCN-LABEL: {{^}}test_merge_store_constant_i16_invariant_global_pointer_load:
+; GCN: buffer_load_dwordx2 [[PTR:v\[[0-9]+:[0-9]+\]]],
+; GCN: v_mov_b32_e32 [[K:v[0-9]+]], 0x1c8007b
+; GCN: buffer_store_dword [[K]], [[PTR]]
+define void @test_merge_store_constant_i16_invariant_global_pointer_load(i16 addrspace(1)* addrspace(1)* dereferenceable(4096) nonnull %in) #0 {
+  %ptr = load i16 addrspace(1)*, i16 addrspace(1)* addrspace(1)* %in, !invariant.load !0
+  %ptr.1 = getelementptr i16, i16 addrspace(1)* %ptr, i64 1
+  store i16 123, i16 addrspace(1)* %ptr, align 4
+  store i16 456, i16 addrspace(1)* %ptr.1
+  ret void
+}
+
+; GCN-LABEL: {{^}}test_merge_store_constant_i16_invariant_constant_pointer_load:
+; GCN: s_load_dwordx2 s{{\[}}[[SPTR_LO:[0-9]+]]:[[SPTR_HI:[0-9]+]]{{\]}}
+; GCN: v_mov_b32_e32 [[K:v[0-9]+]], 0x1c8007b
+; GCN: buffer_store_dword [[K]], s{{\[}}[[SPTR_LO]]:
+define void @test_merge_store_constant_i16_invariant_constant_pointer_load(i16 addrspace(1)* addrspace(2)* dereferenceable(4096) nonnull %in) #0 {
+  %ptr = load i16 addrspace(1)*, i16 addrspace(1)* addrspace(2)* %in, !invariant.load !0
+  %ptr.1 = getelementptr i16, i16 addrspace(1)* %ptr, i64 1
+  store i16 123, i16 addrspace(1)* %ptr, align 4
+  store i16 456, i16 addrspace(1)* %ptr.1
+  ret void
+}
+
+!0 = !{}
+
+attributes #0 = { nounwind }
\ No newline at end of file