maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

Revert "[DAGCombiner] Allow zextended load combines." 

Breaks some bots.
This commit is contained in:
Clement Courbet 2019-11-22 09:00:16 +01:00
parent 95fe54931f
commit 88e205525c
6 changed files with 97 additions and 98 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

73
llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
View File

@ -6750,6 +6750,12 @@ SDValue DAGCombiner::MatchLoadCombine(SDNode *N) {
return SDValue();
unsigned ByteWidth = VT.getSizeInBits() / 8;
// Before legalize we can introduce too wide illegal loads which will be later
// split into legal sized loads. This enables us to combine i64 load by i8
// patterns to a couple of i32 loads on 32 bit targets.
if (LegalOperations && !TLI.isOperationLegal(ISD::LOAD, VT))
return SDValue();
bool IsBigEndianTarget = DAG.getDataLayout().isBigEndian();
auto MemoryByteOffset = [&] (ByteProvider P) {
assert(P.isMemory() && "Must be a memory byte provider");
@ -6772,21 +6778,11 @@ SDValue DAGCombiner::MatchLoadCombine(SDNode *N) {
// Check if all the bytes of the OR we are looking at are loaded from the same
// base address. Collect bytes offsets from Base address in ByteOffsets.
SmallVector<int64_t, 8> ByteOffsets(ByteWidth);
unsigned ZeroExtendedBytes = 0;
for (int i = ByteWidth - 1; i >= 0; --i) {
for (unsigned i = 0; i < ByteWidth; i++) {
auto P = calculateByteProvider(SDValue(N, 0), i, 0, /*Root=*/true);
if (!P)
if (!P || !P->isMemory()) // All the bytes must be loaded from memory
return SDValue();
if (P->isConstantZero()) {
// It's OK for the N most significant bytes to be 0, we can just
// zero-extend the load.
if (++ZeroExtendedBytes != (ByteWidth - static_cast<unsigned>(i)))
return SDValue();
continue;
}
assert(P->isMemory() && "provenance should either be memory or zero");
LoadSDNode *L = P->Load;
assert(L->hasNUsesOfValue(1, 0) && L->isSimple() &&
!L->isIndexed() &&
@ -6825,23 +6821,9 @@ SDValue DAGCombiner::MatchLoadCombine(SDNode *N) {
assert(Base && "Base address of the accessed memory location must be set");
assert(FirstOffset != INT64_MAX && "First byte offset must be set");
bool NeedsZext = ZeroExtendedBytes > 0;
EVT MemVT =
EVT::getIntegerVT(*DAG.getContext(), (ByteWidth - ZeroExtendedBytes) * 8);
// Before legalize we can introduce too wide illegal loads which will be later
// split into legal sized loads. This enables us to combine i64 load by i8
// patterns to a couple of i32 loads on 32 bit targets.
if (LegalOperations &&
!TLI.isOperationLegal(NeedsZext ? ISD::ZEXTLOAD : ISD::NON_EXTLOAD,
MemVT))
return SDValue();
// Check if the bytes of the OR we are looking at match with either big or
// little endian value load
Optional<bool> IsBigEndian = isBigEndian(
makeArrayRef(ByteOffsets).drop_back(ZeroExtendedBytes), FirstOffset);
Optional<bool> IsBigEndian = isBigEndian(ByteOffsets, FirstOffset);
if (!IsBigEndian.hasValue())
return SDValue();
@ -6854,8 +6836,7 @@ SDValue DAGCombiner::MatchLoadCombine(SDNode *N) {
LoadSDNode *FirstLoad = FirstByteProvider->Load;
// The node we are looking at matches with the pattern, check if we can
// replace it with a single (possibly zero-extended) load and bswap + shift if
// needed.
// replace it with a single load and bswap if needed.
// If the load needs byte swap check if the target supports it
bool NeedsBswap = IsBigEndianTarget != *IsBigEndian;
@ -6863,45 +6844,25 @@ SDValue DAGCombiner::MatchLoadCombine(SDNode *N) {
// Before legalize we can introduce illegal bswaps which will be later
// converted to an explicit bswap sequence. This way we end up with a single
// load and byte shuffling instead of several loads and byte shuffling.
// We do not introduce illegal bswaps when zero-extending as this tends to
// introduce too many arithmetic instructions.
if (NeedsBswap && (LegalOperations || NeedsZext) &&
!TLI.isOperationLegal(ISD::BSWAP, VT))
return SDValue();
// If we need to bswap and zero extend, we have to insert a shift. Check that
// it is legal.
if (NeedsBswap && NeedsZext && LegalOperations &&
!TLI.isOperationLegal(ISD::SHL, VT))
if (NeedsBswap && LegalOperations && !TLI.isOperationLegal(ISD::BSWAP, VT))
return SDValue();
// Check that a load of the wide type is both allowed and fast on the target
bool Fast = false;
bool Allowed =
TLI.allowsMemoryAccess(*DAG.getContext(), DAG.getDataLayout(), MemVT,
*FirstLoad->getMemOperand(), &Fast);
bool Allowed = TLI.allowsMemoryAccess(*DAG.getContext(), DAG.getDataLayout(),
VT, *FirstLoad->getMemOperand(), &Fast);
if (!Allowed || !Fast)
return SDValue();
SDValue NewLoad = DAG.getExtLoad(NeedsZext ? ISD::ZEXTLOAD : ISD::NON_EXTLOAD,
SDLoc(N), VT, Chain, FirstLoad->getBasePtr(),
FirstLoad->getPointerInfo(), MemVT,
FirstLoad->getAlignment());
SDValue NewLoad =
DAG.getLoad(VT, SDLoc(N), Chain, FirstLoad->getBasePtr(),
FirstLoad->getPointerInfo(), FirstLoad->getAlignment());
// Transfer chain users from old loads to the new load.
for (LoadSDNode *L : Loads)
DAG.ReplaceAllUsesOfValueWith(SDValue(L, 1), SDValue(NewLoad.getNode(), 1));
if (!NeedsBswap)
return NewLoad;
SDValue ShiftedLoad =
NeedsZext
? DAG.getNode(ISD::SHL, SDLoc(N), VT, NewLoad,
DAG.getShiftAmountConstant(ZeroExtendedBytes * 8, VT,
SDLoc(N), LegalOperations))
: NewLoad;
return DAG.getNode(ISD::BSWAP, SDLoc(N), VT, ShiftedLoad);
return NeedsBswap ? DAG.getNode(ISD::BSWAP, SDLoc(N), VT, NewLoad) : NewLoad;
}
// If the target has andn, bsl, or a similar bit-select instruction,

12
llvm/test/CodeGen/AArch64/load-combine-big-endian.ll
View File

@ -445,9 +445,10 @@ define i32 @load_i32_by_i8_base_offset_index_2(i8* %arg, i32 %i) {
define i32 @zext_load_i32_by_i8(i32* %arg) {
; CHECK-LABEL: zext_load_i32_by_i8:
; CHECK: // %bb.0:
; CHECK-NEXT: ldrh w8, [x0]
; CHECK-NEXT: lsl w8, w8, #16
; CHECK-NEXT: rev w0, w8
; CHECK-NEXT: ldrb w8, [x0]
; CHECK-NEXT: ldrb w9, [x0, #1]
; CHECK-NEXT: bfi w8, w9, #8, #8
; CHECK-NEXT: mov w0, w8
; CHECK-NEXT: ret
%tmp = bitcast i32* %arg to i8*
@ -514,7 +515,10 @@ define i32 @zext_load_i32_by_i8_shl_16(i32* %arg) {
define i32 @zext_load_i32_by_i8_bswap(i32* %arg) {
; CHECK-LABEL: zext_load_i32_by_i8_bswap:
; CHECK: // %bb.0:
; CHECK-NEXT: ldrh w0, [x0]
; CHECK-NEXT: ldrb w8, [x0, #1]
; CHECK-NEXT: ldrb w9, [x0]
; CHECK-NEXT: bfi w8, w9, #8, #8
; CHECK-NEXT: mov w0, w8
; CHECK-NEXT: ret
%tmp = bitcast i32* %arg to i8*

12
llvm/test/CodeGen/AArch64/load-combine.ll
View File

@ -431,7 +431,10 @@ define i32 @load_i32_by_i8_base_offset_index_2(i8* %arg, i32 %i) {
define i32 @zext_load_i32_by_i8(i32* %arg) {
; CHECK-LABEL: zext_load_i32_by_i8:
; CHECK: // %bb.0:
; CHECK-NEXT: ldrh w0, [x0]
; CHECK-NEXT: ldrb w8, [x0]
; CHECK-NEXT: ldrb w9, [x0, #1]
; CHECK-NEXT: bfi w8, w9, #8, #8
; CHECK-NEXT: mov w0, w8
; CHECK-NEXT: ret
%tmp = bitcast i32* %arg to i8*
@ -498,9 +501,10 @@ define i32 @zext_load_i32_by_i8_shl_16(i32* %arg) {
define i32 @zext_load_i32_by_i8_bswap(i32* %arg) {
; CHECK-LABEL: zext_load_i32_by_i8_bswap:
; CHECK: // %bb.0:
; CHECK-NEXT: ldrh w8, [x0]
; CHECK-NEXT: lsl w8, w8, #16
; CHECK-NEXT: rev w0, w8
; CHECK-NEXT: ldrb w8, [x0, #1]
; CHECK-NEXT: ldrb w9, [x0]
; CHECK-NEXT: bfi w8, w9, #8, #8
; CHECK-NEXT: mov w0, w8
; CHECK-NEXT: ret
%tmp = bitcast i32* %arg to i8*

38
llvm/test/CodeGen/ARM/load-combine-big-endian.ll
View File

@ -824,23 +824,25 @@ define i32 @zext_load_i32_by_i8(i32* %arg) {
;
; CHECK-ARMv6-LABEL: zext_load_i32_by_i8:
; CHECK-ARMv6: @ %bb.0:
; CHECK-ARMv6-NEXT: ldrh r0, [r0]
; CHECK-ARMv6-NEXT: lsl r0, r0, #16
; CHECK-ARMv6-NEXT: rev r0, r0
; CHECK-ARMv6-NEXT: ldrb r1, [r0]
; CHECK-ARMv6-NEXT: ldrb r0, [r0, #1]
; CHECK-ARMv6-NEXT: orr r0, r1, r0, lsl #8
; CHECK-ARMv6-NEXT: bx lr
;
; CHECK-THUMBv6-LABEL: zext_load_i32_by_i8:
; CHECK-THUMBv6: @ %bb.0:
; CHECK-THUMBv6-NEXT: ldrh r0, [r0]
; CHECK-THUMBv6-NEXT: lsls r0, r0, #16
; CHECK-THUMBv6-NEXT: rev r0, r0
; CHECK-THUMBv6-NEXT: ldrb r1, [r0]
; CHECK-THUMBv6-NEXT: ldrb r0, [r0, #1]
; CHECK-THUMBv6-NEXT: lsls r0, r0, #8
; CHECK-THUMBv6-NEXT: adds r0, r0, r1
; CHECK-THUMBv6-NEXT: bx lr
;
; CHECK-THUMBv7-LABEL: zext_load_i32_by_i8:
; CHECK-THUMBv7: @ %bb.0:
; CHECK-THUMBv7-NEXT: ldrh r0, [r0]
; CHECK-THUMBv7-NEXT: lsls r0, r0, #16
; CHECK-THUMBv7-NEXT: rev r0, r0
; CHECK-THUMBv7-NEXT: ldrb r1, [r0]
; CHECK-THUMBv7-NEXT: ldrb r0, [r0, #1]
; CHECK-THUMBv7-NEXT: lsls r0, r0, #8
; CHECK-THUMBv7-NEXT: adds r0, r0, r1
; CHECK-THUMBv7-NEXT: bx lr
%tmp = bitcast i32* %arg to i8*
@ -960,22 +962,32 @@ define i32 @zext_load_i32_by_i8_shl_16(i32* %arg) {
define i32 @zext_load_i32_by_i8_bswap(i32* %arg) {
; CHECK-LABEL: zext_load_i32_by_i8_bswap:
; CHECK: @ %bb.0:
; CHECK-NEXT: ldrh r0, [r0]
; CHECK-NEXT: ldrb r1, [r0]
; CHECK-NEXT: ldrb r0, [r0, #1]
; CHECK-NEXT: orr r0, r0, r1, lsl #8
; CHECK-NEXT: mov pc, lr
;
; CHECK-ARMv6-LABEL: zext_load_i32_by_i8_bswap:
; CHECK-ARMv6: @ %bb.0:
; CHECK-ARMv6-NEXT: ldrh r0, [r0]
; CHECK-ARMv6-NEXT: ldrb r1, [r0]
; CHECK-ARMv6-NEXT: ldrb r0, [r0, #1]
; CHECK-ARMv6-NEXT: orr r0, r0, r1, lsl #8
; CHECK-ARMv6-NEXT: bx lr
;
; CHECK-THUMBv6-LABEL: zext_load_i32_by_i8_bswap:
; CHECK-THUMBv6: @ %bb.0:
; CHECK-THUMBv6-NEXT: ldrh r0, [r0]
; CHECK-THUMBv6-NEXT: ldrb r1, [r0, #1]
; CHECK-THUMBv6-NEXT: ldrb r0, [r0]
; CHECK-THUMBv6-NEXT: lsls r0, r0, #8
; CHECK-THUMBv6-NEXT: adds r0, r0, r1
; CHECK-THUMBv6-NEXT: bx lr
;
; CHECK-THUMBv7-LABEL: zext_load_i32_by_i8_bswap:
; CHECK-THUMBv7: @ %bb.0:
; CHECK-THUMBv7-NEXT: ldrh r0, [r0]
; CHECK-THUMBv7-NEXT: ldrb r1, [r0, #1]
; CHECK-THUMBv7-NEXT: ldrb r0, [r0]
; CHECK-THUMBv7-NEXT: lsls r0, r0, #8
; CHECK-THUMBv7-NEXT: adds r0, r0, r1
; CHECK-THUMBv7-NEXT: bx lr
%tmp = bitcast i32* %arg to i8*

36
llvm/test/CodeGen/ARM/load-combine.ll
View File

@ -734,22 +734,31 @@ define i32 @load_i32_by_i8_base_offset_index_2(i8* %arg, i32 %i) {
define i32 @zext_load_i32_by_i8(i32* %arg) {
; CHECK-LABEL: zext_load_i32_by_i8:
; CHECK: @ %bb.0:
; CHECK-NEXT: ldrh r0, [r0]
; CHECK-NEXT: ldrb r1, [r0]
; CHECK-NEXT: ldrb r0, [r0, #1]
; CHECK-NEXT: orr r0, r1, r0, lsl #8
; CHECK-NEXT: mov pc, lr
;
; CHECK-ARMv6-LABEL: zext_load_i32_by_i8:
; CHECK-ARMv6: @ %bb.0:
; CHECK-ARMv6-NEXT: ldrh r0, [r0]
; CHECK-ARMv6-NEXT: ldrb r1, [r0]
; CHECK-ARMv6-NEXT: ldrb r0, [r0, #1]
; CHECK-ARMv6-NEXT: orr r0, r1, r0, lsl #8
; CHECK-ARMv6-NEXT: bx lr
;
; CHECK-THUMBv6-LABEL: zext_load_i32_by_i8:
; CHECK-THUMBv6: @ %bb.0:
; CHECK-THUMBv6-NEXT: ldrh r0, [r0]
; CHECK-THUMBv6-NEXT: ldrb r1, [r0]
; CHECK-THUMBv6-NEXT: ldrb r0, [r0, #1]
; CHECK-THUMBv6-NEXT: lsls r0, r0, #8
; CHECK-THUMBv6-NEXT: adds r0, r0, r1
; CHECK-THUMBv6-NEXT: bx lr
;
; CHECK-THUMBv7-LABEL: zext_load_i32_by_i8:
; CHECK-THUMBv7: @ %bb.0:
; CHECK-THUMBv7-NEXT: ldrh r0, [r0]
; CHECK-THUMBv7-NEXT: ldrb r1, [r0]
; CHECK-THUMBv7-NEXT: ldrb r0, [r0, #1]
; CHECK-THUMBv7-NEXT: orr.w r0, r1, r0, lsl #8
; CHECK-THUMBv7-NEXT: bx lr
%tmp = bitcast i32* %arg to i8*
@ -874,23 +883,24 @@ define i32 @zext_load_i32_by_i8_bswap(i32* %arg) {
;
; CHECK-ARMv6-LABEL: zext_load_i32_by_i8_bswap:
; CHECK-ARMv6: @ %bb.0:
; CHECK-ARMv6-NEXT: ldrh r0, [r0]
; CHECK-ARMv6-NEXT: lsl r0, r0, #16
; CHECK-ARMv6-NEXT: rev r0, r0
; CHECK-ARMv6-NEXT: ldrb r1, [r0]
; CHECK-ARMv6-NEXT: ldrb r0, [r0, #1]
; CHECK-ARMv6-NEXT: orr r0, r0, r1, lsl #8
; CHECK-ARMv6-NEXT: bx lr
;
; CHECK-THUMBv6-LABEL: zext_load_i32_by_i8_bswap:
; CHECK-THUMBv6: @ %bb.0:
; CHECK-THUMBv6-NEXT: ldrh r0, [r0]
; CHECK-THUMBv6-NEXT: lsls r0, r0, #16
; CHECK-THUMBv6-NEXT: rev r0, r0
; CHECK-THUMBv6-NEXT: ldrb r1, [r0, #1]
; CHECK-THUMBv6-NEXT: ldrb r0, [r0]
; CHECK-THUMBv6-NEXT: lsls r0, r0, #8
; CHECK-THUMBv6-NEXT: adds r0, r0, r1
; CHECK-THUMBv6-NEXT: bx lr
;
; CHECK-THUMBv7-LABEL: zext_load_i32_by_i8_bswap:
; CHECK-THUMBv7: @ %bb.0:
; CHECK-THUMBv7-NEXT: ldrh r0, [r0]
; CHECK-THUMBv7-NEXT: lsls r0, r0, #16
; CHECK-THUMBv7-NEXT: rev r0, r0
; CHECK-THUMBv7-NEXT: ldrb r1, [r0]
; CHECK-THUMBv7-NEXT: ldrb r0, [r0, #1]
; CHECK-THUMBv7-NEXT: orr.w r0, r0, r1, lsl #8
; CHECK-THUMBv7-NEXT: bx lr
%tmp = bitcast i32* %arg to i8*

24
llvm/test/CodeGen/X86/load-combine.ll
View File

@ -1119,12 +1119,18 @@ define i32 @zext_load_i32_by_i8(i32* %arg) {
; CHECK-LABEL: zext_load_i32_by_i8:
; CHECK: # %bb.0:
; CHECK-NEXT: movl {{[0-9]+}}(%esp), %eax
; CHECK-NEXT: movzwl (%eax), %eax
; CHECK-NEXT: movzbl (%eax), %ecx
; CHECK-NEXT: movzbl 1(%eax), %eax
; CHECK-NEXT: shll $8, %eax
; CHECK-NEXT: orl %ecx, %eax
; CHECK-NEXT: retl
;
; CHECK64-LABEL: zext_load_i32_by_i8:
; CHECK64: # %bb.0:
; CHECK64-NEXT: movzwl (%rdi), %eax
; CHECK64-NEXT: movzbl (%rdi), %ecx
; CHECK64-NEXT: movzbl 1(%rdi), %eax
; CHECK64-NEXT: shll $8, %eax
; CHECK64-NEXT: orl %ecx, %eax
; CHECK64-NEXT: retq
%tmp = bitcast i32* %arg to i8*
%tmp1 = getelementptr inbounds i8, i8* %tmp, i32 0
@ -1212,16 +1218,18 @@ define i32 @zext_load_i32_by_i8_bswap(i32* %arg) {
; CHECK-LABEL: zext_load_i32_by_i8_bswap:
; CHECK: # %bb.0:
; CHECK-NEXT: movl {{[0-9]+}}(%esp), %eax
; CHECK-NEXT: movzwl (%eax), %eax
; CHECK-NEXT: shll $16, %eax
; CHECK-NEXT: bswapl %eax
; CHECK-NEXT: movzbl 1(%eax), %ecx
; CHECK-NEXT: movzbl (%eax), %eax
; CHECK-NEXT: shll $8, %eax
; CHECK-NEXT: orl %ecx, %eax
; CHECK-NEXT: retl
;
; CHECK64-LABEL: zext_load_i32_by_i8_bswap:
; CHECK64: # %bb.0:
; CHECK64-NEXT: movzwl (%rdi), %eax
; CHECK64-NEXT: shll $16, %eax
; CHECK64-NEXT: bswapl %eax
; CHECK64-NEXT: movzbl 1(%rdi), %ecx
; CHECK64-NEXT: movzbl (%rdi), %eax
; CHECK64-NEXT: shll $8, %eax
; CHECK64-NEXT: orl %ecx, %eax
; CHECK64-NEXT: retq
%tmp = bitcast i32* %arg to i8*
%tmp1 = getelementptr inbounds i8, i8* %tmp, i32 1