[DAG] Do MergeConsecutiveStores again before Instruction Selection

Summary:

Now that store-merge is only generates type-safe stores, do a second
pass just before instruction selection to allow lowered intrinsics to
be merged as well.

Reviewers: jyknight, hfinkel, RKSimon, efriedma, rnk, jmolloy

Subscribers: javed.absar, llvm-commits

Differential Revision: https://reviews.llvm.org/D33675

llvm-svn: 319036

diff --git a/llvm/include/llvm/CodeGen/TargetLowering.h b/llvm/include/llvm/CodeGen/TargetLowering.h
index 78080ab..4210f58 100644 (file)
--- a/llvm/include/llvm/CodeGen/TargetLowering.h
+++ b/llvm/include/llvm/CodeGen/TargetLowering.h
@@ -413,7 +413,7 @@ public:
   /// Allow store merging after legalization in addition to before legalization.
   /// This may catch stores that do not exist earlier (eg, stores created from
   /// intrinsics).
-  virtual bool mergeStoresAfterLegalization() const { return false; }
+  virtual bool mergeStoresAfterLegalization() const { return true; }
 
   /// Returns if it's reasonable to merge stores to MemVT size.
   virtual bool canMergeStoresTo(unsigned AS, EVT MemVT,

diff --git a/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp b/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
index 4481e07..589abaa 100644 (file)
--- a/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
+++ b/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
@@ -9562,8 +9562,6 @@ static SDValue replaceSplatVectorStore(SelectionDAG &DAG, StoreSDNode &St) {
 static SDValue splitStores(SDNode *N, TargetLowering::DAGCombinerInfo &DCI,
                            SelectionDAG &DAG,
                            const AArch64Subtarget *Subtarget) {
-  if (!DCI.isBeforeLegalize())
-    return SDValue();
 
   StoreSDNode *S = cast<StoreSDNode>(N);
   if (S->isVolatile() || S->isIndexed())

diff --git a/llvm/test/CodeGen/AArch64/arm64-complex-ret.ll b/llvm/test/CodeGen/AArch64/arm64-complex-ret.ll
index 250edac..b4a3854 100644 (file)
--- a/llvm/test/CodeGen/AArch64/arm64-complex-ret.ll
+++ b/llvm/test/CodeGen/AArch64/arm64-complex-ret.ll
@@ -2,6 +2,7 @@
 
 define { i192, i192, i21, i192 } @foo(i192) {
 ; CHECK-LABEL: foo:
-; CHECK: stp xzr, xzr, [x8]
+; CHECK-DAG: str xzr, [x8, #16]
+; CHECK-DAG: str q0, [x8]
   ret { i192, i192, i21, i192 } {i192 0, i192 1, i21 2, i192 3}
 }

diff --git a/llvm/test/CodeGen/AArch64/arm64-narrow-st-merge.ll b/llvm/test/CodeGen/AArch64/arm64-narrow-st-merge.ll
index ec7c227..b48f3b4 100644 (file)
--- a/llvm/test/CodeGen/AArch64/arm64-narrow-st-merge.ll
+++ b/llvm/test/CodeGen/AArch64/arm64-narrow-st-merge.ll
@@ -19,7 +19,7 @@ entry:
 }
 
 ; CHECK-LABEL: Strh_zero_4
-; CHECK: stp wzr, wzr
+; CHECK: str xzr
 ; CHECK-STRICT-LABEL: Strh_zero_4
 ; CHECK-STRICT: strh wzr
 ; CHECK-STRICT: strh wzr
@@ -137,7 +137,7 @@ entry:
 }
 
 ; CHECK-LABEL: Sturh_zero_4
-; CHECK: stp wzr, wzr
+; CHECK: stur xzr
 ; CHECK-STRICT-LABEL: Sturh_zero_4
 ; CHECK-STRICT: sturh wzr
 ; CHECK-STRICT: sturh wzr

diff --git a/llvm/test/CodeGen/AArch64/arm64-variadic-aapcs.ll b/llvm/test/CodeGen/AArch64/arm64-variadic-aapcs.ll
index 375877c..a09853a 100644 (file)
--- a/llvm/test/CodeGen/AArch64/arm64-variadic-aapcs.ll
+++ b/llvm/test/CodeGen/AArch64/arm64-variadic-aapcs.ll
@@ -32,11 +32,9 @@ define void @test_simple(i32 %n, ...) {
 ; CHECK: add [[VR_TOP:x[0-9]+]], [[VR_TOPTMP]], #128
 ; CHECK: str [[VR_TOP]], [x[[VA_LIST]], #16]
 
-; CHECK: mov [[GR_OFFS:w[0-9]+]], #-56
-; CHECK: str [[GR_OFFS]], [x[[VA_LIST]], #24]
-
-; CHECK: orr [[VR_OFFS:w[0-9]+]], wzr, #0xffffff80
-; CHECK: str [[VR_OFFS]], [x[[VA_LIST]], #28]
+; CHECK: mov     [[GRVR:x[0-9]+]], #-545460846720
+; CHECK: movk    [[GRVR]], #65480
+; CHECK: str     [[GRVR]], [x[[VA_LIST]], #24]
 
   %addr = bitcast %va_list* @var to i8*
   call void @llvm.va_start(i8* %addr)
@@ -70,11 +68,9 @@ define void @test_fewargs(i32 %n, i32 %n1, i32 %n2, float %m, ...) {
 ; CHECK: add [[VR_TOP:x[0-9]+]], [[VR_TOPTMP]], #112
 ; CHECK: str [[VR_TOP]], [x[[VA_LIST]], #16]
 
-; CHECK: mov [[GR_OFFS:w[0-9]+]], #-40
-; CHECK: str [[GR_OFFS]], [x[[VA_LIST]], #24]
-
-; CHECK: mov [[VR_OFFS:w[0-9]+]], #-11
-; CHECK: str [[VR_OFFS]], [x[[VA_LIST]], #28]
+; CHECK: mov  [[GRVR_OFFS:x[0-9]+]], #-40
+; CHECK: movk [[GRVR_OFFS]], #65424, lsl #32
+; CHECK: str  [[GRVR_OFFS]], [x[[VA_LIST]], #24]
 
   %addr = bitcast %va_list* @var to i8*
   call void @llvm.va_start(i8* %addr)

diff --git a/llvm/test/CodeGen/AArch64/tailcall-explicit-sret.ll b/llvm/test/CodeGen/AArch64/tailcall-explicit-sret.ll
index c157933..b60958b 100644 (file)
--- a/llvm/test/CodeGen/AArch64/tailcall-explicit-sret.ll
+++ b/llvm/test/CodeGen/AArch64/tailcall-explicit-sret.ll
@@ -35,7 +35,7 @@ define void @test_tailcall_explicit_sret_alloca_unused() #0 {
 }
 
 ; CHECK-LABEL: _test_tailcall_explicit_sret_alloca_dummyusers:
-; CHECK: ldr [[PTRLOAD1:x[0-9]+]], [x0]
+; CHECK: ldr [[PTRLOAD1:q[0-9]+]], [x0]
 ; CHECK: str [[PTRLOAD1]], [sp]
 ; CHECK: mov  x8, sp
 ; CHECK-NEXT: bl _test_explicit_sret
@@ -64,8 +64,8 @@ define void @test_tailcall_explicit_sret_gep(i1024* %ptr) #0 {
 ; CHECK: mov  x[[CALLERX8NUM:[0-9]+]], x8
 ; CHECK: mov  x8, sp
 ; CHECK-NEXT: bl _test_explicit_sret
-; CHECK-NEXT: ldr [[CALLERSRET1:x[0-9]+]], [sp]
-; CHECK: str [[CALLERSRET1:x[0-9]+]], [x[[CALLERX8NUM]]]
+; CHECK-NEXT: ldr [[CALLERSRET1:q[0-9]+]], [sp]
+; CHECK: str [[CALLERSRET1:q[0-9]+]], [x[[CALLERX8NUM]]]
 ; CHECK: ret
 define i1024 @test_tailcall_explicit_sret_alloca_returned() #0 {
   %l = alloca i1024, align 8
@@ -79,8 +79,8 @@ define i1024 @test_tailcall_explicit_sret_alloca_returned() #0 {
 ; CHECK-DAG: mov  [[FPTR:x[0-9]+]], x0
 ; CHECK: mov  x0, sp
 ; CHECK-NEXT: blr [[FPTR]]
-; CHECK-NEXT: ldr [[CALLERSRET1:x[0-9]+]], [sp]
-; CHECK: str [[CALLERSRET1:x[0-9]+]], [x[[CALLERX8NUM]]]
+; CHECK: ldr [[CALLERSRET1:q[0-9]+]], [sp]
+; CHECK: str [[CALLERSRET1:q[0-9]+]], [x[[CALLERX8NUM]]]
 ; CHECK: ret
 define void @test_indirect_tailcall_explicit_sret_nosret_arg(i1024* sret %arg, void (i1024*)* %f) #0 {
   %l = alloca i1024, align 8
@@ -94,8 +94,8 @@ define void @test_indirect_tailcall_explicit_sret_nosret_arg(i1024* sret %arg, v
 ; CHECK: mov  x[[CALLERX8NUM:[0-9]+]], x8
 ; CHECK: mov  x8, sp
 ; CHECK-NEXT: blr x0
-; CHECK-NEXT: ldr [[CALLERSRET1:x[0-9]+]], [sp]
-; CHECK: str [[CALLERSRET1:x[0-9]+]], [x[[CALLERX8NUM]]]
+; CHECK: ldr [[CALLERSRET1:q[0-9]+]], [sp]
+; CHECK: str [[CALLERSRET1:q[0-9]+]], [x[[CALLERX8NUM]]]
 ; CHECK: ret
 define void @test_indirect_tailcall_explicit_sret_(i1024* sret %arg, i1024 ()* %f) #0 {
   %ret = tail call i1024 %f()

diff --git a/llvm/test/CodeGen/AArch64/tailcall-implicit-sret.ll b/llvm/test/CodeGen/AArch64/tailcall-implicit-sret.ll
index 10c4ba4..f449a7e 100644 (file)
--- a/llvm/test/CodeGen/AArch64/tailcall-implicit-sret.ll
+++ b/llvm/test/CodeGen/AArch64/tailcall-implicit-sret.ll
@@ -11,8 +11,8 @@ declare i1024 @test_sret() #0
 ; CHECK: mov  x[[CALLERX8NUM:[0-9]+]], x8
 ; CHECK: mov  x8, sp
 ; CHECK-NEXT: bl _test_sret
-; CHECK-NEXT: ldr [[CALLERSRET1:x[0-9]+]], [sp]
-; CHECK: str [[CALLERSRET1:x[0-9]+]], [x[[CALLERX8NUM]]]
+; CHECK: ldr [[CALLERSRET1:q[0-9]+]], [sp]
+; CHECK: str [[CALLERSRET1:q[0-9]+]], [x[[CALLERX8NUM]]]
 ; CHECK: ret
 define i1024 @test_call_sret() #0 {
   %a = call i1024 @test_sret()
@@ -23,8 +23,8 @@ define i1024 @test_call_sret() #0 {
 ; CHECK: mov  x[[CALLERX8NUM:[0-9]+]], x8
 ; CHECK: mov  x8, sp
 ; CHECK-NEXT: bl _test_sret
-; CHECK-NEXT: ldr [[CALLERSRET1:x[0-9]+]], [sp]
-; CHECK: str [[CALLERSRET1:x[0-9]+]], [x[[CALLERX8NUM]]]
+; CHECK: ldr [[CALLERSRET1:q[0-9]+]], [sp]
+; CHECK: str [[CALLERSRET1:q[0-9]+]], [x[[CALLERX8NUM]]]
 ; CHECK: ret
 define i1024 @test_tailcall_sret() #0 {
   %a = tail call i1024 @test_sret()
@@ -35,8 +35,8 @@ define i1024 @test_tailcall_sret() #0 {
 ; CHECK: mov  x[[CALLERX8NUM:[0-9]+]], x8
 ; CHECK: mov  x8, sp
 ; CHECK-NEXT: blr x0
-; CHECK-NEXT: ldr [[CALLERSRET1:x[0-9]+]], [sp]
-; CHECK: str [[CALLERSRET1:x[0-9]+]], [x[[CALLERX8NUM]]]
+; CHECK: ldr [[CALLERSRET1:q[0-9]+]], [sp]
+; CHECK: str [[CALLERSRET1:q[0-9]+]], [x[[CALLERX8NUM]]]
 ; CHECK: ret
 define i1024 @test_indirect_tailcall_sret(i1024 ()* %f) #0 {
   %a = tail call i1024 %f()

diff --git a/llvm/test/CodeGen/AMDGPU/amdgpu.private-memory.ll b/llvm/test/CodeGen/AMDGPU/amdgpu.private-memory.ll
index 71c4c83..228d3c7 100644 (file)
--- a/llvm/test/CodeGen/AMDGPU/amdgpu.private-memory.ll
+++ b/llvm/test/CodeGen/AMDGPU/amdgpu.private-memory.ll
@@ -251,8 +251,7 @@ entry:
 
 ; R600: MOVA_INT
 
-; SI-PROMOTE-DAG: buffer_store_byte v{{[0-9]+}}, off, s[{{[0-9]+:[0-9]+}}], s{{[0-9]+}} offset:4 ; encoding:
-; SI-PROMOTE-DAG: buffer_store_byte v{{[0-9]+}}, off, s[{{[0-9]+:[0-9]+}}], s{{[0-9]+}} offset:5 ; encoding:
+; SI-PROMOTE-DAG: buffer_store_short v{{[0-9]+}}, off, s[{{[0-9]+:[0-9]+}}], s{{[0-9]+}} offset:4 ; encoding:
 
 ; SI-ALLOCA-DAG: buffer_store_byte v{{[0-9]+}}, off, s[{{[0-9]+:[0-9]+}}], s{{[0-9]+}} offset:4 ; encoding: [0x04,0x00,0x60,0xe0
 ; SI-ALLOCA-DAG: buffer_store_byte v{{[0-9]+}}, off, s[{{[0-9]+:[0-9]+}}], s{{[0-9]+}} offset:5 ; encoding: [0x05,0x00,0x60,0xe0

diff --git a/llvm/test/CodeGen/ARM/fp16-promote.ll b/llvm/test/CodeGen/ARM/fp16-promote.ll
index 257d99d..da2a1df 100644 (file)
--- a/llvm/test/CodeGen/ARM/fp16-promote.ll
+++ b/llvm/test/CodeGen/ARM/fp16-promote.ll
@@ -817,25 +817,37 @@ define void @test_fmuladd(half* %p, half* %q, half* %r) #0 {
 
 ; CHECK-ALL-LABEL: test_insertelement:
 ; CHECK-ALL: sub sp, sp, #8
-; CHECK-ALL: ldrh
-; CHECK-ALL: ldrh
-; CHECK-ALL: ldrh
-; CHECK-ALL: ldrh
-; CHECK-ALL-DAG: strh
-; CHECK-ALL-DAG: strh
-; CHECK-ALL-DAG: mov
-; CHECK-ALL-DAG: ldrh
-; CHECK-ALL-DAG: orr
-; CHECK-ALL-DAG: strh
-; CHECK-ALL-DAG: strh
-; CHECK-ALL-DAG: strh
-; CHECK-ALL-DAG: ldrh
-; CHECK-ALL-DAG: ldrh
-; CHECK-ALL-DAG: ldrh
-; CHECK-ALL-DAG: strh
-; CHECK-ALL-DAG: strh
-; CHECK-ALL-DAG: strh
-; CHECK-ALL-DAG: strh
+
+; CHECK-VFP:   and     
+; CHECK-VFP:   mov     
+; CHECK-VFP:   ldrd    
+; CHECK-VFP:   orr     
+; CHECK-VFP:   ldrh    
+; CHECK-VFP:   stm     
+; CHECK-VFP:   strh    
+; CHECK-VFP:   ldm     
+; CHECK-VFP:   stm     
+
+; CHECK-NOVFP: ldrh
+; CHECK-NOVFP: ldrh
+; CHECK-NOVFP: ldrh
+; CHECK-NOVFP: ldrh
+; CHECK-NOVFP-DAG: strh
+; CHECK-NOVFP-DAG: strh
+; CHECK-NOVFP-DAG: mov
+; CHECK-NOVFP-DAG: ldrh
+; CHECK-NOVFP-DAG: orr
+; CHECK-NOVFP-DAG: strh
+; CHECK-NOVFP-DAG: strh
+; CHECK-NOVFP-DAG: strh
+; CHECK-NOVFP-DAG: ldrh
+; CHECK-NOVFP-DAG: ldrh
+; CHECK-NOVFP-DAG: ldrh
+; CHECK-NOVFP-DAG: strh
+; CHECK-NOVFP-DAG: strh
+; CHECK-NOVFP-DAG: strh
+; CHECK-NOVFP-DAG: strh
+
 ; CHECK-ALL: add sp, sp, #8
 define void @test_insertelement(half* %p, <4 x half>* %q, i32 %i) #0 {
   %a = load half, half* %p, align 2

diff --git a/llvm/test/CodeGen/BPF/undef.ll b/llvm/test/CodeGen/BPF/undef.ll
index 11bc9eb..586a24d 100644 (file)
--- a/llvm/test/CodeGen/BPF/undef.ll
+++ b/llvm/test/CodeGen/BPF/undef.ll
@@ -14,12 +14,10 @@
 
 ; Function Attrs: nounwind uwtable
 define i32 @ebpf_filter(%struct.__sk_buff* nocapture readnone %ebpf_packet) #0 section "socket1" {
-; EL: r1 = 134678021
-; EB: r1 = 84281096
-; CHECK: *(u32 *)(r10 - 8) = r1
-; EL: r1 = 2569
-; EB: r1 = 2314
-; CHECK: *(u16 *)(r10 - 4) = r1
+
+; EL: r1 = 11033905661445 ll
+; EB: r1 = 361984551142686720 ll
+; CHECK: *(u64 *)(r10 - 8) = r1
 
 ; CHECK: r1 = 0
 ; CHECK: *(u16 *)(r10 + 24) = r1
@@ -35,7 +33,6 @@ define i32 @ebpf_filter(%struct.__sk_buff* nocapture readnone %ebpf_packet) #0 s
 ; CHECK: *(u16 *)(r10 + 4) = r1
 ; CHECK: *(u16 *)(r10 + 2) = r1
 ; CHECK: *(u16 *)(r10 + 0) = r1
-; CHECK: *(u16 *)(r10 - 2) = r1
 ; CHECK: *(u16 *)(r10 + 26) = r1
 
 ; CHECK: r2 = r10

diff --git a/llvm/test/CodeGen/Mips/cconv/vector.ll b/llvm/test/CodeGen/Mips/cconv/vector.ll
index 5a88d06..02d6272 100644 (file)
--- a/llvm/test/CodeGen/Mips/cconv/vector.ll
+++ b/llvm/test/CodeGen/Mips/cconv/vector.ll
@@ -821,8 +821,10 @@ entry:
 ; MIPS32R5: jal
 ; MIPS32R5: sw $2, {{[0-9]+}}($sp)
 
-; MIPS32R5-DAG: sb ${{[0-9]+}}, 1(${{[0-9]+}})
-; MIPS32R5-DAG; sb ${{[0-9]+}}, %lo(gv2i8)(${{[0-9]+}})
+; MIPS32R5-DAG; sh ${{[0-9]+}}, %lo(gv2i8)(${{[0-9]+}})
+
+; MIPS32R5-NOT: sb ${{[0-9]+}}, 1(${{[0-9]+}})
+; MIPS32R5-NOT; sb ${{[0-9]+}}, %lo(gv2i8)(${{[0-9]+}})
 
 ; MIPS64EB: daddiu $4, $zero, 1543
 ; MIPS64EB: daddiu $5, $zero, 3080
@@ -870,14 +872,14 @@ entry:
 ; MIPS32-NOT: ori $6
 ; MIPS32-NOT: ori $7
 
-; MIPS32R5-DAG: lw $4, {{[0-9]+}}($sp)
-; MIPS32R5-DAG: lw $5, {{[0-9]+}}($sp)
+; MIPS32R5-NOT: lw $4, {{[0-9]+}}($sp)
+; MIPS32R5-NOT: lw $5, {{[0-9]+}}($sp)
 
 ; MIPS64: ori $4
 ; MIPS64: ori $5
 
-; MIPS64R5: lw $4
-; MIPS64R5: lw $5
+; MIPS64R5-NOT: lw $4
+; MIPS64R5-NOT: lw $5
 
 ; MIPS32: jal i8_4
 ; MIPS64: jalr $25
@@ -996,14 +998,14 @@ entry:
 ; MIPS32-DAG: ori $4
 ; MIPS32-DAG: ori $5
 
-; MIPS32R5-DAG: lw $4
-; MIPS32R5-DAG: lw $5
+; MIPS32R5-NOT: lw $4
+; MIPS32R5-NOT: lw $5
 
 ; MIPS64: ori $4
 ; MIPS64: ori $5
 
-; MIPS64R5-DAG: lw $4
-; MIPS64R5-DAG: lw $5
+; MIPS64R5-NOT: lw $4
+; MIPS64R5-NOT: lw $5
 
 ; MIPS32: jal i16_2
 ; MIPS64: jalr $25
@@ -1037,8 +1039,8 @@ entry:
 ; MIPS64-DAG: daddiu $4
 ; MIPS64-DAG: daddiu $5
 
-; MIPS64R5-DAG: ld $4
-; MIPS64R5-DAG: ld $5
+; MIPS64R5-NOT: ld $4
+; MIPS64R5-NOT: ld $5
 
 ; MIPS32: jal i16_4
 ; MIPS64: jalr $25
@@ -1133,8 +1135,8 @@ entry:
 ; MIPS64: daddiu $4
 ; MIPS64: daddiu $5
 
-; MIPS64R5-DAG: ld $4
-; MIPS64R5-DAG: ld $5
+; MIPS64R5-NOT ld $4
+; MIPS64R5-NOT: ld $5
 
 ; MIPS32: jal i32_2
 ; MIPS64: jalr $25

diff --git a/llvm/test/CodeGen/Mips/llvm-ir/extractelement.ll b/llvm/test/CodeGen/Mips/llvm-ir/extractelement.ll
index 3c7df4a..f7b8ea5 100644 (file)
--- a/llvm/test/CodeGen/Mips/llvm-ir/extractelement.ll
+++ b/llvm/test/CodeGen/Mips/llvm-ir/extractelement.ll
@@ -12,8 +12,7 @@ define i1 @via_stack_bug(i8 signext %idx) {
 
 ; ALL-LABEL: via_stack_bug:
 ; ALL-DAG:       addiu  [[ONE:\$[0-9]+]], $zero, 1
-; ALL-DAG:       sb     [[ONE]], 7($sp)
-; ALL-DAG:       sb     $zero, 6($sp)
+; ALL-DAG:       sh     [[ONE]], 6($sp)
 ; ALL-DAG:       andi   [[MASKED_IDX:\$[0-9]+]], $4, 1
 ; ALL-DAG:       addiu  [[VPTR:\$[0-9]+]], $sp, 6
 ; ALL-DAG:       or   [[EPTR:\$[0-9]+]], [[MASKED_IDX]], [[VPTR]]

diff --git a/llvm/test/CodeGen/SystemZ/fp-move-13.ll b/llvm/test/CodeGen/SystemZ/fp-move-13.ll
index d6c53ea..4ef9d11 100644 (file)
--- a/llvm/test/CodeGen/SystemZ/fp-move-13.ll
+++ b/llvm/test/CodeGen/SystemZ/fp-move-13.ll
@@ -22,10 +22,8 @@ define void @f1(fp128 *%x) {
 ; so this goes through memory.
 define void @f2(fp128 *%a, i128 *%b) {
 ; CHECK-LABEL: f2:
-; CHECK: lg
-; CHECK: lg
-; CHECK: stg
-; CHECK: stg
+; CHECK: vl
+; CHECK: vst
 ; CHECK: br %r14
   %val = load i128 , i128 *%b
   %res = bitcast i128 %val to fp128