Re-land MachineInstr: Reason locally about some memory objects before going to AA.

[bmakam]

Summary

Reverts r311008 to reinstate r310825 with a fix.

Refine alias checking for pseudo vs value to be conservative.
This fixes the original failure in builtbot unittest SingleSource/UnitTests/2003-07-09-SignedArgs.

[bmakam]

Trim the patch and avoid handling stack references for non-value MMOs to prevent LNT test failures.

[bmakam]

rebase and fix x86 lit test.

[bjope]

lib/CodeGen/MachineInstr.cpp

1702

These asserts are related to the interface to AA, right? (I think it says so in the comments above)

Are they also important for the new new checks you have added, or could/should the asserts perhaps be moved closer to the AA->alias call?
Now it kind of looks like the asserts are guarding your new checks, but the comments are referring to assumptions made by the API to AA.

(Some more background to why I'm asking:)
Our out-of-tree target is actually creating StackPointer relative MachingMemOperands with negative offsets. In the past we never hit those asserts since the ealier (!MMOa->getValue() || !MMOb->getValue()) check would make us return before checking for negative operands.
I do not think that we need those negative offsets, so I'll probably try to get rid of them regardless of this patch. But as long as you put the asserts before the "if (!ValA || !ValB)", then we must stop using negative offsets in PseudoSourceValue kind of MachingMemOperands or we will hit the assert.

[bmakam]

Move assert closer to AA->alias call.

[efriedma]

Makes sense.

lib/CodeGen/MachineInstr.cpp

1712

Indentation?

[bmakam]

Thanks for the review.

lib/CodeGen/MachineInstr.cpp

bool MachineInstr::mayAlias(AliasAnalysis *AA, MachineInstr &Other,
   // meaningful way, even if they read from the same address.
   if (!mayStore() && !Other.mayStore())
     return false;
 
   // Let the target decide if memory accesses cannot possibly overlap.
   if (TII->areMemAccessesTriviallyDisjoint(*this, Other, AA))
     return false;
 
-  if (!AA)
-    return true;
-
   // FIXME: Need to handle multiple memory operands to support all targets.
   if (!hasOneMemOperand() || !Other.hasOneMemOperand())
     return true;
 
   MachineMemOperand *MMOa = *memoperands_begin();
   MachineMemOperand *MMOb = *Other.memoperands_begin();
 
-  if (!MMOa->getValue() || !MMOb->getValue())
-    return true;
-
   // The following interface to AA is fashioned after DAGCombiner::isAlias
   // and operates with MachineMemOperand offset with some important
   // assumptions:
   //   - LLVM fundamentally assumes flat address spaces.
   //   - MachineOperand offset can *only* result from legalization and
   //     cannot affect queries other than the trivial case of overlap
   //     checking.
   //   - These offsets never wrap and never step outside
   //     of allocated objects.
   //   - There should never be any negative offsets here.
   //
   // FIXME: Modify API to hide this math from "user"
-  // FIXME: Even before we go to AA we can reason locally about some
+  // Even before we go to AA we can reason locally about some
   // memory objects. It can save compile time, and possibly catch some
   // corner cases not currently covered.
 
-  assert((MMOa->getOffset() >= 0) && "Negative MachineMemOperand offset");
-  assert((MMOb->getOffset() >= 0) && "Negative MachineMemOperand offset");
+  int64_t OffsetA = MMOa->getOffset();
+  int64_t OffsetB = MMOb->getOffset();
+
+  assert((OffsetA >= 0) && "Negative MachineMemOperand offset");
+  assert((OffsetB >= 0) && "Negative MachineMemOperand offset");
+
+  int64_t MinOffset = std::min(OffsetA, OffsetB);
+  int64_t WidthA = MMOa->getSize();
+  int64_t WidthB = MMOb->getSize();
+  const Value *ValA = MMOa->getValue();
+  const Value *ValB = MMOb->getValue();
+  bool SameVal = (ValA && ValB && (ValA == ValB));
+  if (!SameVal) {
+    const PseudoSourceValue *PSVa = MMOa->getPseudoValue();
+    const PseudoSourceValue *PSVb = MMOb->getPseudoValue();
+    if (PSVa && ValB &&
+        (PSVa->isGOT() || PSVa->isConstantPool() || PSVa->isJumpTable()))
+        return false;
+    if (PSVb && ValA &&
+        (PSVb->isGOT() || PSVb->isConstantPool() || PSVb->isJumpTable()))
+      return false;
+    if (PSVa && PSVb && (PSVa == PSVb))
+      SameVal = true;
+  }
+
+  if (SameVal) {
+    int64_t MaxOffset = std::max(OffsetA, OffsetB);
+    int64_t LowWidth = (MinOffset == OffsetA) ? WidthA : WidthB;
+    return (MinOffset + LowWidth > MaxOffset);
+  }
+
+  if (!AA)
+    return true;
+
+  if (!ValA || !ValB)
+    return true;
+
+  int64_t Overlapa = WidthA + OffsetA - MinOffset;
+  int64_t Overlapb = WidthB + OffsetB - MinOffset;
 
-  int64_t MinOffset = std::min(MMOa->getOffset(), MMOb->getOffset());
-  int64_t Overlapa = MMOa->getSize() + MMOa->getOffset() - MinOffset;
-  int64_t Overlapb = MMOb->getSize() + MMOb->getOffset() - MinOffset;
-
-  AliasResult AAResult =
-      AA->alias(MemoryLocation(MMOa->getValue(), Overlapa,
-                               UseTBAA ? MMOa->getAAInfo() : AAMDNodes()),
-                MemoryLocation(MMOb->getValue(), Overlapb,
-                               UseTBAA ? MMOb->getAAInfo() : AAMDNodes()));
+  AliasResult AAResult = AA->alias(
+      MemoryLocation(ValA, Overlapa, UseTBAA ? MMOa->getAAInfo() : AAMDNodes()),
+      MemoryLocation(ValB, Overlapb,
 
   return (AAResult != NoAlias);
 }
 
 /// hasOrderedMemoryRef - Return true if this instruction may have an ordered
 /// or volatile memory reference, or if the information describing the memory
 /// reference is not available. Return false if it is known to have no ordered
 /// memory references.

test/CodeGen/AArch64/ldst-opt.ll

entry:
   ret void
 }
 
 ; Similar to merge_zr32, but for 64-bit values and with unaligned stores.
 define void @merge_zr64_unalign(<2 x i64>* %p) {
 ; CHECK-LABEL: merge_zr64_unalign:
 ; CHECK: // %entry
 ; NOSTRICTALIGN-NEXT: stp xzr, xzr, [x{{[0-9]+}}]
-; STRICTALIGN: strb wzr,
+; STRICTALIGN: strb
 ; STRICTALIGN: strb
 ; STRICTALIGN: strb
 ; STRICTALIGN: strb
 ; STRICTALIGN: strb
 ; STRICTALIGN: strb
 ; STRICTALIGN: strb
 ; STRICTALIGN: strb
 ; STRICTALIGN: strb

test/CodeGen/AMDGPU/call-argument-types.ll

 ; HSA-DAG: buffer_store_byte [[VAL0]], off, s[0:3], s33 offset:8
 ; HSA-DAG: buffer_store_dword [[VAL1]], off, s[0:3], s33 offset:12
 
 ; GCN: s_add_u32 [[SP]], [[SP]], 0x200
 
 ; HSA: buffer_load_dword [[RELOAD_VAL0:v[0-9]+]], off, s[0:3], s33 offset:8
 ; HSA: buffer_load_dword [[RELOAD_VAL1:v[0-9]+]], off, s[0:3], s33 offset:12
 
-; HSA: buffer_store_dword [[RELOAD_VAL1]], off, s[0:3], [[SP]] offset:8
 ; HSA: buffer_store_dword [[RELOAD_VAL0]], off, s[0:3], [[SP]] offset:4
+; HSA: buffer_store_dword [[RELOAD_VAL1]], off, s[0:3], [[SP]] offset:8
 
 
 ; MESA: buffer_load_dword [[RELOAD_VAL0:v[0-9]+]], off, s[36:39], s33 offset:8
 ; MESA: buffer_load_dword [[RELOAD_VAL1:v[0-9]+]], off, s[36:39], s33 offset:12
 
-; MESA: buffer_store_dword [[RELOAD_VAL1]], off, s[36:39], [[SP]] offset:8
 ; MESA: buffer_store_dword [[RELOAD_VAL0]], off, s[36:39], [[SP]] offset:4
+; MESA: buffer_store_dword [[RELOAD_VAL1]], off, s[36:39], [[SP]] offset:8
 
 ; GCN-NEXT: s_swappc_b64
 ; GCN-NEXT: s_sub_u32 [[SP]], [[SP]], 0x200
 define amdgpu_kernel void @test_call_external_void_func_byval_struct_i8_i32() #0 {
   %val = alloca { i8, i32 }, align 4
   %gep0 = getelementptr inbounds { i8, i32 }, { i8, i32 }* %val, i32 0, i32 0
   %gep1 = getelementptr inbounds { i8, i32 }, { i8, i32 }* %val, i32 0, i32 1
   store i8 3, i8* %gep0

 ; GCN-DAG: v_mov_b32_e32 [[VAL1:v[0-9]+]], 8
 ; GCN-DAG: buffer_store_byte [[VAL0]], off, s{{\[[0-9]+:[0-9]+\]}}, [[FP_REG]] offset:8
 ; GCN-DAG: buffer_store_dword [[VAL1]], off, s{{\[[0-9]+:[0-9]+\]}}, [[FP_REG]] offset:12
 
 ; GCN-DAG: buffer_load_dword [[RELOAD_VAL0:v[0-9]+]], off, s{{\[[0-9]+:[0-9]+\]}}, [[FP_REG]] offset:8
 ; GCN-DAG: buffer_load_dword [[RELOAD_VAL1:v[0-9]+]], off, s{{\[[0-9]+:[0-9]+\]}}, [[FP_REG]] offset:12
 
 ; GCN-DAG: s_add_u32 [[SP]], [[SP]], 0x200
-; GCN: buffer_store_dword [[RELOAD_VAL1]], off, s{{\[[0-9]+:[0-9]+\]}}, [[SP]] offset:8
 ; GCN: buffer_store_dword [[RELOAD_VAL0]], off, s{{\[[0-9]+:[0-9]+\]}}, [[SP]] offset:4
+; GCN: buffer_store_dword [[RELOAD_VAL1]], off, s{{\[[0-9]+:[0-9]+\]}}, [[SP]] offset:8
 ; GCN-NEXT: s_swappc_b64
 ; GCN-DAG: buffer_load_ubyte [[LOAD_OUT_VAL0:v[0-9]+]], off, s{{\[[0-9]+:[0-9]+\]}}, [[FP_REG]] offset:16
 ; GCN-DAG: buffer_load_dword [[LOAD_OUT_VAL1:v[0-9]+]], off, s{{\[[0-9]+:[0-9]+\]}}, [[FP_REG]] offset:20
 ; GCN: s_sub_u32 [[SP]], [[SP]], 0x200
 
 ; GCN: buffer_store_byte [[LOAD_OUT_VAL0]], off
 ; GCN: buffer_store_dword [[LOAD_OUT_VAL1]], off
 define amdgpu_kernel void @test_call_external_void_func_sret_struct_i8_i32_byval_struct_i8_i32(i32) #0 {

test/CodeGen/AMDGPU/load-global-i16.ll

define amdgpu_kernel void @global_sextload_v2i16_to_v2i32(<2 x i32> addrspace(1)* %out, <2 x i16> addrspace(1)* %in) #0 {
   store <2 x i32> %ext, <2 x i32> addrspace(1)* %out
   ret void
 }
 
 ; FUNC-LABEL: {{^}}global_zextload_v3i16_to_v3i32:
 ; GCN-NOHSA: buffer_load_dwordx2
 ; GCN-HSA: flat_load_dwordx2
 
-; CM: MEM_RAT_CACHELESS STORE_DWORD [[ST_HI:T[0-9]]].X, {{T[0-9]\.[XYZW]}}
 ; CM: MEM_RAT_CACHELESS STORE_DWORD [[ST_LO:T[0-9]]], {{T[0-9]\.[XYZW]}}
+; CM: MEM_RAT_CACHELESS STORE_DWORD [[ST_HI:T[0-9]]].X, {{T[0-9]\.[XYZW]}}
 ; EG: MEM_RAT_CACHELESS STORE_RAW [[ST_HI:T[0-9]]].X, {{T[0-9]\.[XYZW]}},
 ; EG: MEM_RAT_CACHELESS STORE_RAW [[ST_LO:T[0-9]]].XY, {{T[0-9]\.[XYZW]}},
 ; EGCM-DAG: VTX_READ_32 [[DST_LO:T[0-9]\.[XYZW]]], {{T[0-9]\.[XYZW]}}, 0, #1
 ; EGCM-DAG: VTX_READ_16 [[DST_HI:T[0-9]\.[XYZW]]], {{T[0-9]\.[XYZW]}}, 4, #1
 ; TODO: This should use DST, but for some there are redundant MOVs
 ; EGCM: LSHR {{[* ]*}}[[ST_LO]].Y, {{T[0-9]\.[XYZW]}}, literal
 ; EGCM: 16
-; EGCM: AND_INT {{[* ]*}}[[ST_LO]].X, {{T[0-9]\.[XYZW]}}, literal
-; EGCM: AND_INT {{[* ]*}}[[ST_HI]].X, [[DST_HI]], literal
 define amdgpu_kernel void @global_zextload_v3i16_to_v3i32(<3 x i32> addrspace(1)* %out, <3 x i16> addrspace(1)* %in) {
 entry:
   %ld = load <3 x i16>, <3 x i16> addrspace(1)* %in
   %ext = zext <3 x i16> %ld to <3 x i32>
   store <3 x i32> %ext, <3 x i32> addrspace(1)* %out
   ret void
 }
 
 ; FUNC-LABEL: {{^}}global_sextload_v3i16_to_v3i32:
 ; GCN-NOHSA: buffer_load_dwordx2
 ; GCN-HSA: flat_load_dwordx2
 
-; CM: MEM_RAT_CACHELESS STORE_DWORD [[ST_HI:T[0-9]]].X, {{T[0-9]\.[XYZW]}}
 ; CM: MEM_RAT_CACHELESS STORE_DWORD [[ST_LO:T[0-9]]], {{T[0-9]\.[XYZW]}}
+; CM: MEM_RAT_CACHELESS STORE_DWORD [[ST_HI:T[0-9]]].X, {{T[0-9]\.[XYZW]}}
 ; EG: MEM_RAT_CACHELESS STORE_RAW [[ST_HI:T[0-9]]].X, {{T[0-9]\.[XYZW]}},
 ; EG: MEM_RAT_CACHELESS STORE_RAW [[ST_LO:T[0-9]]].XY, {{T[0-9]\.[XYZW]}},
 ; EGCM-DAG: VTX_READ_32 [[DST_LO:T[0-9]\.[XYZW]]], {{T[0-9].[XYZW]}}, 0, #1
 ; EGCM-DAG: VTX_READ_16 [[DST_HI:T[0-9]\.[XYZW]]], {{T[0-9].[XYZW]}}, 4, #1
 ; TODO: This should use DST, but for some there are redundant MOVs
 ; EGCM-DAG: ASHR {{[* ]*}}[[ST_LO]].Y, {{T[0-9]\.[XYZW]}}, literal
 ; EGCM-DAG: BFE_INT {{[* ]*}}[[ST_LO]].X, {{T[0-9]\.[XYZW]}}, 0.0, literal
 ; EGCM-DAG: BFE_INT {{[* ]*}}[[ST_HI]].X, [[DST_HI]], 0.0, literal

test/CodeGen/AMDGPU/load-global-i8.ll

define amdgpu_kernel void @global_zextload_v16i8_to_v16i32(<16 x i32> addrspace(1)* %out, <16 x i8> addrspace(1)* %in) #0 {
   store <16 x i32> %ext, <16 x i32> addrspace(1)* %out
   ret void
 }
 
 ; FUNC-LABEL: {{^}}global_sextload_v16i8_to_v16i32:
 
 ; EG: VTX_READ_128 [[DST:T[0-9]+\.XYZW]], T{{[0-9]+}}.X, 0, #1
 ; TODO: These should use DST, but for some there are redundant MOVs
-; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
-; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
-; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
-; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
-; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
-; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
-; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
-; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
-; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
-; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
-; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
-; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
-; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
-; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
-; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
-; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9].[XYZW]}}, {{.*}}, 0.0, literal
+; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9]*.[XYZW]}}, {{.*}}, 0.0, literal
+; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9]*.[XYZW]}}, {{.*}}, 0.0, literal
+; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9]*.[XYZW]}}, {{.*}}, 0.0, literal
+; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9]*.[XYZW]}}, {{.*}}, 0.0, literal
+; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9]*.[XYZW]}}, {{.*}}, 0.0, literal
+; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9]*.[XYZW]}}, {{.*}}, 0.0, literal
+; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9]*.[XYZW]}}, {{.*}}, 0.0, literal
+; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9]*.[XYZW]}}, {{.*}}, 0.0, literal
+; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9]*.[XYZW]}}, {{.*}}, 0.0, literal
+; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9]*.[XYZW]}}, {{.*}}, 0.0, literal
+; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9]*.[XYZW]}}, {{.*}}, 0.0, literal
+; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9]*.[XYZW]}}, {{.*}}, 0.0, literal
+; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9]*.[XYZW]}}, {{.*}}, 0.0, literal
+; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9]*.[XYZW]}}, {{.*}}, 0.0, literal
+; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9]*.[XYZW]}}, {{.*}}, 0.0, literal
+; EG-DAG: BFE_INT {{[* ]*}}T{{[0-9]*.[XYZW]}}, {{.*}}, 0.0, literal
 ; EG-DAG: 8
 ; EG-DAG: 8
 ; EG-DAG: 8
 ; EG-DAG: 8
 ; EG-DAG: 8
 ; EG-DAG: 8
 ; EG-DAG: 8
 ; EG-DAG: 8

test/CodeGen/AMDGPU/load-local-i16.ll

 
 ; GCN: ds_write_b64 v{{[0-9]+}}, v{{\[}}[[LO]]:[[HI]]]
 
 ; EG: MOV {{[* ]*}}[[FROM:T[0-9]+\.[XYZW]]], KC0[2].Z
 ; EG: LDS_USHORT_READ_RET {{.*}} [[FROM]]
 ; EG-DAG: MOV {{[* ]*}}[[DATA:T[0-9]+\.[XYZW]]], OQAP
 ; EG-DAG: MOV {{[* ]*}}[[TO:T[0-9]+\.[XYZW]]], KC0[2].Y
 ; EG-DAG: LDS_WRITE
-; EG: LDS_WRITE {{\*?}} [[TO]], [[DATA]]
 define amdgpu_kernel void @local_zextload_i16_to_i64(i64 addrspace(3)* %out, i16 addrspace(3)* %in) #0 {
   %a = load i16, i16 addrspace(3)* %in
   %ext = zext i16 %a to i64
   store i64 %ext, i64 addrspace(3)* %out
   ret void
 }
 
 ; FUNC-LABEL: {{^}}local_sextload_i16_to_i64:

 
 ; FUNC-LABEL: {{^}}local_zextload_v1i16_to_v1i64:
 
 ; EG: MOV {{[* ]*}}[[FROM:T[0-9]+\.[XYZW]]], KC0[2].Z
 ; EG: LDS_USHORT_READ_RET {{.*}} [[FROM]]
 ; EG-DAG: MOV {{[* ]*}}[[DATA:T[0-9]+\.[XYZW]]], OQAP
 ; EG-DAG: MOV {{[* ]*}}[[TO:T[0-9]+\.[XYZW]]], KC0[2].Y
 ; EG-DAG: LDS_WRITE
-; EG: LDS_WRITE {{\*?}} [[TO]], [[DATA]]
 define amdgpu_kernel void @local_zextload_v1i16_to_v1i64(<1 x i64> addrspace(3)* %out, <1 x i16> addrspace(3)* %in) #0 {
   %load = load <1 x i16>, <1 x i16> addrspace(3)* %in
   %ext = zext <1 x i16> %load to <1 x i64>
   store <1 x i64> %ext, <1 x i64> addrspace(3)* %out
   ret void
 }
 
 ; FUNC-LABEL: {{^}}local_sextload_v1i16_to_v1i64:

test/CodeGen/ARM/2009-10-27-double-align.ll

-; RUN: llc < %s  -mtriple=arm-linux-gnueabi | FileCheck %s
-; RUN: llc < %s  -mtriple=arm-linux-gnueabi -regalloc=basic | FileCheck %s
+; RUN: llc < %s  -mtriple=arm-linux-gnueabi | FileCheck %s --check-prefix=NOREGALLOC
+; RUN: llc < %s  -mtriple=arm-linux-gnueabi -regalloc=basic | FileCheck %s --check-prefix=REGALLOC
 
 @.str = private constant [1 x i8] zeroinitializer, align 1
 
 define void @g() {
 entry:
 ;CHECK: [sp, #8]
-;CHECK: [sp, #12]
-;CHECK: [sp]
+;NOREGALLOC: [sp, #12]
+;NOREGALLOC: [sp]
+;REGALLOC: [sp]
+;REGALLOC: [sp, #12]
         tail call  void (i8*, ...) @f(i8* getelementptr ([1 x i8], [1 x i8]* @.str, i32 0, i32 0), i32 1, double 2.000000e+00, i32 3, double 4.000000e+00)
         ret void
 }
 
 declare void @f(i8*, ...)

test/CodeGen/ARM/illegal-bitfield-loadstore.ll

 ; LE-NEXT:    orr r1, r1, #384
 ; LE-NEXT:    bic r1, r1, #127
 ; LE-NEXT:    str r1, [r0]
 ; LE-NEXT:    mov pc, lr
 ;
 ; BE-LABEL: i56_and_or:
 ; BE:       @ BB#0:
 ; BE-NEXT:    mov r1, r0
-; BE-NEXT:    mov r3, #128
+; BE-NEXT:    ldr r12, [r0]
 ; BE-NEXT:    ldrh r2, [r1, #4]!
+; BE-NEXT:    mov r3, #128
 ; BE-NEXT:    strb r3, [r1, #2]
-; BE-NEXT:    ldr r12, [r0]
 ; BE-NEXT:    lsl r2, r2, #8
 ; BE-NEXT:    orr r2, r2, r12, lsl #24
 ; BE-NEXT:    orr r2, r2, #384
 ; BE-NEXT:    lsr r3, r2, #8
 ; BE-NEXT:    strh r3, [r1]
 ; BE-NEXT:    bic r1, r12, #255
 ; BE-NEXT:    orr r1, r1, r2, lsr #24
 ; BE-NEXT:    str r1, [r0]

test/CodeGen/X86/illegal-bitfield-loadstore.ll

 ; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
 ; X86-NEXT:    orl $384, (%eax) # imm = 0x180
 ; X86-NEXT:    retl
 ;
 ; X64-LABEL: i56_or:
 ; X64:       # BB#0:
 ; X64-NEXT:    movzwl 4(%rdi), %eax
 ; X64-NEXT:    movzbl 6(%rdi), %ecx
-; X64-NEXT:    movl (%rdi), %edx
 ; X64-NEXT:    movb %cl, 6(%rdi)
 ; X64-NEXT:    # kill: %ECX<def> %ECX<kill> %RCX<kill> %RCX<def>
 ; X64-NEXT:    shll $16, %ecx
 ; X64-NEXT:    orl %eax, %ecx
 ; X64-NEXT:    shlq $32, %rcx
-; X64-NEXT:    orq %rcx, %rdx
-; X64-NEXT:    orq $384, %rdx # imm = 0x180
-; X64-NEXT:    movl %edx, (%rdi)
-; X64-NEXT:    shrq $32, %rdx
-; X64-NEXT:    movw %dx, 4(%rdi)
+; X64-NEXT:    movl (%rdi), %eax
+; X64-NEXT:    orq %rcx, %rax
+; X64-NEXT:    orq $384, %rax # imm = 0x180
+; X64-NEXT:    movl %eax, (%rdi)
+; X64-NEXT:    shrq $32, %rax
+; X64-NEXT:    movw %ax, 4(%rdi)
 ; X64-NEXT:    retq
   %aa = load i56, i56* %a, align 1
   %b = or i56 %aa, 384
   store i56 %b, i56* %a, align 1
   ret void
 }
 
 define void @i56_and_or(i56* %a) {
 ; X86-LABEL: i56_and_or:
 ; X86:       # BB#0:
 ; X86-NEXT:    movl {{[0-9]+}}(%esp), %eax
 ; X86-NEXT:    movl $384, %ecx # imm = 0x180
 ; X86-NEXT:    orl (%eax), %ecx
 ; X86-NEXT:    andl $-128, %ecx
 ; X86-NEXT:    movl %ecx, (%eax)
 ; X86-NEXT:    retl
 ;
 ; X64-LABEL: i56_and_or:
 ; X64:       # BB#0:
 ; X64-NEXT:    movzwl 4(%rdi), %eax
 ; X64-NEXT:    movzbl 6(%rdi), %ecx
-; X64-NEXT:    movl (%rdi), %edx
 ; X64-NEXT:    movb %cl, 6(%rdi)
 ; X64-NEXT:    # kill: %ECX<def> %ECX<kill> %RCX<kill> %RCX<def>
 ; X64-NEXT:    shll $16, %ecx
 ; X64-NEXT:    orl %eax, %ecx
 ; X64-NEXT:    shlq $32, %rcx
-; X64-NEXT:    orq %rcx, %rdx
-; X64-NEXT:    orq $384, %rdx # imm = 0x180
-; X64-NEXT:    movabsq $72057594037927808, %rax # imm = 0xFFFFFFFFFFFF80
-; X64-NEXT:    andq %rdx, %rax
-; X64-NEXT:    movl %eax, (%rdi)
-; X64-NEXT:    shrq $32, %rax
-; X64-NEXT:    movw %ax, 4(%rdi)
+; X64-NEXT:    movl (%rdi), %eax
+; X64-NEXT:    orq %rcx, %rax
+; X64-NEXT:    orq $384, %rax # imm = 0x180
+; X64-NEXT:    movabsq $72057594037927808, %rcx # imm = 0xFFFFFFFFFFFF80
+; X64-NEXT:    andq %rax, %rcx
+; X64-NEXT:    movl %ecx, (%rdi)
+; X64-NEXT:    shrq $32, %rcx
+; X64-NEXT:    movw %cx, 4(%rdi)
 ; X64-NEXT:    retq
   %b = load i56, i56* %a, align 1
   %c = and i56 %b, -128
   %d = or i56 %c, 384
   store i56 %d, i56* %a, align 1
   ret void
 }
 

 ; X86-NEXT:    movl %edx, (%eax)
 ; X86-NEXT:    retl
 ;
 ; X64-LABEL: i56_insert_bit:
 ; X64:       # BB#0:
 ; X64-NEXT:    movzbl %sil, %eax
 ; X64-NEXT:    movzwl 4(%rdi), %ecx
 ; X64-NEXT:    movzbl 6(%rdi), %edx
-; X64-NEXT:    movl (%rdi), %esi
 ; X64-NEXT:    movb %dl, 6(%rdi)
 ; X64-NEXT:    # kill: %EDX<def> %EDX<kill> %RDX<kill> %RDX<def>
 ; X64-NEXT:    shll $16, %edx
 ; X64-NEXT:    orl %ecx, %edx
 ; X64-NEXT:    shlq $32, %rdx
-; X64-NEXT:    orq %rdx, %rsi
+; X64-NEXT:    movl (%rdi), %ecx
+; X64-NEXT:    orq %rdx, %rcx
 ; X64-NEXT:    shlq $13, %rax
-; X64-NEXT:    movabsq $72057594037919743, %rcx # imm = 0xFFFFFFFFFFDFFF
-; X64-NEXT:    andq %rsi, %rcx
-; X64-NEXT:    orq %rax, %rcx
-; X64-NEXT:    movl %ecx, (%rdi)
-; X64-NEXT:    shrq $32, %rcx
-; X64-NEXT:    movw %cx, 4(%rdi)
+; X64-NEXT:    movabsq $72057594037919743, %rdx # imm = 0xFFFFFFFFFFDFFF
+; X64-NEXT:    andq %rcx, %rdx
+; X64-NEXT:    orq %rax, %rdx
+; X64-NEXT:    movl %edx, (%rdi)
+; X64-NEXT:    shrq $32, %rdx
+; X64-NEXT:    movw %dx, 4(%rdi)
 ; X64-NEXT:    retq
   %extbit = zext i1 %bit to i56
   %b = load i56, i56* %a, align 1
   %extbit.shl = shl nuw nsw i56 %extbit, 13
   %c = and i56 %b, -8193
   %d = or i56 %c, %extbit.shl
   store i56 %d, i56* %a, align 1
   ret void
 }
 

test/CodeGen/X86/memcpy-2.ll

 ; RUN: llc < %s -mattr=+sse2      -mtriple=i686-apple-darwin -mcpu=core2 | FileCheck %s -check-prefix=SSE2-Darwin
 ; RUN: llc < %s -mattr=+sse2      -mtriple=i686-pc-mingw32 -mcpu=core2 | FileCheck %s -check-prefix=SSE2-Mingw32
 ; RUN: llc < %s -mattr=+sse,-sse2 -mtriple=i686-apple-darwin -mcpu=core2 | FileCheck %s -check-prefix=SSE1
 ; RUN: llc < %s -mattr=-sse       -mtriple=i686-apple-darwin -mcpu=core2 | FileCheck %s -check-prefix=NOSSE
 ; RUN: llc < %s                 -mtriple=x86_64-apple-darwin -mcpu=core2 | FileCheck %s -check-prefix=X86-64
 ; RUN: llc < %s                 -mtriple=x86_64-apple-darwin -mcpu=nehalem | FileCheck %s -check-prefix=NHM_64
 
 
 @.str = internal constant [25 x i8] c"image\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00"
 @.str2 = internal constant [30 x i8] c"xxxxxxxxxxxxxxxxxxxxxxxxxxxxx\00", align 4
 
 define void @t1(i32 %argc, i8** %argv) nounwind  {
 entry:
 ; SSE2-Darwin-LABEL: t1:
-; SSE2-Darwin: movsd _.str+16, %xmm0
-; SSE2-Darwin: movsd %xmm0, 16(%esp)
 ; SSE2-Darwin: movaps _.str, %xmm0
 ; SSE2-Darwin: movaps %xmm0
+; SSE2-Darwin: movsd _.str+16, %xmm0
+; SSE2-Darwin: movsd %xmm0, 16(%esp)
 ; SSE2-Darwin: movb $0, 24(%esp)
 
 ; SSE2-Mingw32-LABEL: t1:
-; SSE2-Mingw32: movsd _.str+16, %xmm0
-; SSE2-Mingw32: movsd %xmm0, 16(%esp)
 ; SSE2-Mingw32: movaps _.str, %xmm0
 ; SSE2-Mingw32: movups %xmm0
+; SSE2-Mingw32: movsd _.str+16, %xmm0
+; SSE2-Mingw32: movsd %xmm0, 16(%esp)
 ; SSE2-Mingw32: movb $0, 24(%esp)
 
 ; SSE1-LABEL: t1:
 ; SSE1: movaps _.str, %xmm0
-; SSE1: movaps %xmm0
 ; SSE1: movb $0, 24(%esp)
+; SSE1: movaps %xmm0
 ; SSE1: movl $0, 20(%esp)
 ; SSE1: movl $0, 16(%esp)
 
 ; NOSSE-LABEL: t1:
 ; NOSSE: movb $0
 ; NOSSE: movl $0
 ; NOSSE: movl $0
 ; NOSSE: movl $0

test/CodeGen/X86/pr34088.ll

 ; CHECK-NEXT:    .cfi_def_cfa_register %ebp
 ; CHECK-NEXT:    andl $-16, %esp
 ; CHECK-NEXT:    subl $32, %esp
 ; CHECK-NEXT:    xorps %xmm0, %xmm0
 ; CHECK-NEXT:    movaps {{.*#+}} xmm1 = [205,205,205,205,205,205,205,205,205,205,205,205,205,205,205,205]
 ; CHECK-NEXT:    xorl %eax, %eax
 ; CHECK-NEXT:    movaps %xmm0, (%esp)
 ; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
-; CHECK-NEXT:    movaps %xmm1, (%esp)
 ; CHECK-NEXT:    movl $-842150451, {{[0-9]+}}(%esp) # imm = 0xCDCDCDCD
+; CHECK-NEXT:    movaps %xmm1, (%esp)
 ; CHECK-NEXT:    movsd %xmm0, {{[0-9]+}}(%esp)
 ; CHECK-NEXT:    movl %ebp, %esp
 ; CHECK-NEXT:    popl %ebp
 ; CHECK-NEXT:    retl
 entry:
   %foo = alloca %struct.Foo, align 4
   %0 = bitcast %struct.Foo* %foo to i8*
   call void @llvm.memset.p0i8.i32(i8* nonnull %0, i8 0, i32 20, i32 4, i1 false)

test/CodeGen/X86/widen_arith-3.ll

 ; CHECK:       # BB#0: # %entry
 ; CHECK-NEXT:    pushl %ebp
 ; CHECK-NEXT:    movl %esp, %ebp
 ; CHECK-NEXT:    andl $-8, %esp
 ; CHECK-NEXT:    subl $40, %esp
 ; CHECK-NEXT:    movl {{\.LCPI.*}}, %eax
 ; CHECK-NEXT:    movdqa {{.*#+}} xmm1 = [0,1,4,5,8,9,12,13,8,9,12,13,12,13,14,15]
 ; CHECK-NEXT:    pcmpeqd %xmm0, %xmm0
+; CHECK-NEXT:    movw $1, {{[0-9]+}}(%esp)
 ; CHECK-NEXT:    movl $0, {{[0-9]+}}(%esp)
 ; CHECK-NEXT:    movl %eax, {{[0-9]+}}(%esp)
-; CHECK-NEXT:    movw $1, {{[0-9]+}}(%esp)
 ; CHECK-NEXT:    jmp .LBB0_1
 ; CHECK-NEXT:    .p2align 4, 0x90
 ; CHECK-NEXT:  .LBB0_2: # %forbody
 ; CHECK-NEXT:    # in Loop: Header=BB0_1 Depth=1
 ; CHECK-NEXT:    movl {{[0-9]+}}(%esp), %eax
 ; CHECK-NEXT:    movl 12(%ebp), %edx
 ; CHECK-NEXT:    movl 8(%ebp), %ecx
 ; CHECK-NEXT:    movd {{.*#+}} xmm2 = mem[0],zero,zero,zero