forked from OSchip/llvm-project
[WebAssembly] WebAssemblyFastISel getelementptr variable index support
Summary: Previously -fast-isel getelementptr would constant-fold non-constant i8 load/stores. Reviewers: sunfish Subscribers: jfb, dschuff, sbc100, llvm-commits Differential Revision: https://reviews.llvm.org/D34044 llvm-svn: 306060
This commit is contained in:
parent
9b7c1d2dcf
commit
a31ec61c46
|
@ -63,12 +63,16 @@ class WebAssemblyFastISel final : public FastISel {
|
|||
public:
|
||||
// Innocuous defaults for our address.
|
||||
Address() : Kind(RegBase), Offset(0), GV(0) { Base.Reg = 0; }
|
||||
void setKind(BaseKind K) { Kind = K; }
|
||||
void setKind(BaseKind K) {
|
||||
assert(!isSet() && "Can't change kind with non-zero base");
|
||||
Kind = K;
|
||||
}
|
||||
BaseKind getKind() const { return Kind; }
|
||||
bool isRegBase() const { return Kind == RegBase; }
|
||||
bool isFIBase() const { return Kind == FrameIndexBase; }
|
||||
void setReg(unsigned Reg) {
|
||||
assert(isRegBase() && "Invalid base register access!");
|
||||
assert(Base.Reg == 0 && "Overwriting non-zero register");
|
||||
Base.Reg = Reg;
|
||||
}
|
||||
unsigned getReg() const {
|
||||
|
@ -77,6 +81,7 @@ class WebAssemblyFastISel final : public FastISel {
|
|||
}
|
||||
void setFI(unsigned FI) {
|
||||
assert(isFIBase() && "Invalid base frame index access!");
|
||||
assert(Base.FI == 0 && "Overwriting non-zero frame index");
|
||||
Base.FI = FI;
|
||||
}
|
||||
unsigned getFI() const {
|
||||
|
@ -91,6 +96,13 @@ class WebAssemblyFastISel final : public FastISel {
|
|||
int64_t getOffset() const { return Offset; }
|
||||
void setGlobalValue(const GlobalValue *G) { GV = G; }
|
||||
const GlobalValue *getGlobalValue() const { return GV; }
|
||||
bool isSet() const {
|
||||
if (isRegBase()) {
|
||||
return Base.Reg != 0;
|
||||
} else {
|
||||
return Base.FI != 0;
|
||||
}
|
||||
}
|
||||
};
|
||||
|
||||
/// Keep a pointer to the WebAssemblySubtarget around so that we can make the
|
||||
|
@ -297,6 +309,9 @@ bool WebAssemblyFastISel::computeAddress(const Value *Obj, Address &Addr) {
|
|||
DenseMap<const AllocaInst *, int>::iterator SI =
|
||||
FuncInfo.StaticAllocaMap.find(AI);
|
||||
if (SI != FuncInfo.StaticAllocaMap.end()) {
|
||||
if (Addr.isSet()) {
|
||||
return false;
|
||||
}
|
||||
Addr.setKind(Address::FrameIndexBase);
|
||||
Addr.setFI(SI->second);
|
||||
return true;
|
||||
|
@ -341,6 +356,9 @@ bool WebAssemblyFastISel::computeAddress(const Value *Obj, Address &Addr) {
|
|||
break;
|
||||
}
|
||||
}
|
||||
if (Addr.isSet()) {
|
||||
return false;
|
||||
}
|
||||
Addr.setReg(getRegForValue(Obj));
|
||||
return Addr.getReg() != 0;
|
||||
}
|
||||
|
|
|
@ -0,0 +1,100 @@
|
|||
; RUN: llc < %s -asm-verbose=false -disable-wasm-explicit-locals -fast-isel -fast-isel-abort=1 | FileCheck %s
|
||||
|
||||
; TODO: Merge this with offset.ll when fast-isel matches better.
|
||||
|
||||
target datalayout = "e-m:e-p:32:32-i64:64-n32:64-S128"
|
||||
target triple = "wasm32-unknown-unknown-elf"
|
||||
|
||||
; CHECK-LABEL: store_i8_with_variable_gep_offset:
|
||||
; CHECK: i32.add $push[[L0:[0-9]+]]=, $0, $1{{$}}
|
||||
; CHECK: i32.const $push[[L1:[0-9]+]]=, 0{{$}}
|
||||
; CHECK: i32.store8 0($pop[[L0]]), $pop[[L1]]{{$}}
|
||||
define void @store_i8_with_variable_gep_offset(i8* %p, i32 %idx) {
|
||||
%s = getelementptr inbounds i8, i8* %p, i32 %idx
|
||||
store i8 0, i8* %s
|
||||
ret void
|
||||
}
|
||||
|
||||
; CHECK-LABEL: store_i8_with_array_alloca_gep:
|
||||
; CHECK: i32.const $push[[L0:[0-9]+]]=, 0{{$}}
|
||||
; CHECK: i32.load $push[[L1:[0-9]+]]=, __stack_pointer($pop[[L0]]){{$}}
|
||||
; CHECK: i32.const $push[[L2:[0-9]+]]=, 32{{$}}
|
||||
; CHECK: i32.sub $push{{[0-9]+}}=, $pop[[L1]], $pop[[L2]]{{$}}
|
||||
; CHECK: i32.add $push[[L4:[0-9]+]]=, $pop{{[0-9]+}}, $0{{$}}
|
||||
; CHECK: i32.const $push[[L5:[0-9]+]]=, 0{{$}}
|
||||
; CHECK: i32.store8 0($pop[[L4]]), $pop[[L5]]{{$}}
|
||||
define hidden void @store_i8_with_array_alloca_gep(i32 %idx) {
|
||||
%A = alloca [30 x i8], align 16
|
||||
%s = getelementptr inbounds [30 x i8], [30 x i8]* %A, i32 0, i32 %idx
|
||||
store i8 0, i8* %s, align 1
|
||||
ret void
|
||||
}
|
||||
|
||||
; CHECK-LABEL: store_i32_with_unfolded_gep_offset:
|
||||
; CHECK: i32.const $push[[L0:[0-9]+]]=, 24{{$}}
|
||||
; CHECK: i32.add $push[[L1:[0-9]+]]=, $0, $pop[[L0]]{{$}}
|
||||
; CHECK: i32.const $push[[L2:[0-9]+]]=, 0{{$}}
|
||||
; CHECK: i32.store 0($pop[[L1]]), $pop[[L2]]{{$}}
|
||||
define void @store_i32_with_unfolded_gep_offset(i32* %p) {
|
||||
%s = getelementptr i32, i32* %p, i32 6
|
||||
store i32 0, i32* %s
|
||||
ret void
|
||||
}
|
||||
|
||||
; CHECK-LABEL: store_i32_with_folded_gep_offset:
|
||||
; CHECK: i32.store 24($0), $pop{{[0-9]+$}}
|
||||
define void @store_i32_with_folded_gep_offset(i32* %p) {
|
||||
%s = getelementptr inbounds i32, i32* %p, i32 6
|
||||
store i32 0, i32* %s
|
||||
ret void
|
||||
}
|
||||
|
||||
; CHECK-LABEL: load_i32_with_folded_gep_offset:
|
||||
; CHECK: i32.load $push{{[0-9]+}}=, 24($0){{$}}
|
||||
define i32 @load_i32_with_folded_gep_offset(i32* %p) {
|
||||
%s = getelementptr inbounds i32, i32* %p, i32 6
|
||||
%t = load i32, i32* %s
|
||||
ret i32 %t
|
||||
}
|
||||
|
||||
; CHECK-LABEL: store_i64_with_unfolded_gep_offset:
|
||||
; CHECK: i32.const $push[[L0:[0-9]+]]=, 24{{$}}
|
||||
; CHECK: i32.add $push[[L1:[0-9]+]]=, $0, $pop[[L0]]{{$}}
|
||||
; CHECK: i64.const $push[[L2:[0-9]+]]=, 0{{$}}
|
||||
; CHECK: i64.store 0($pop[[L1]]), $pop[[L2]]{{$}}
|
||||
define void @store_i64_with_unfolded_gep_offset(i64* %p) {
|
||||
%s = getelementptr i64, i64* %p, i32 3
|
||||
store i64 0, i64* %s
|
||||
ret void
|
||||
}
|
||||
|
||||
; CHECK-LABEL: store_i8_with_folded_gep_offset:
|
||||
; CHECK: i32.store8 24($0), $pop{{[0-9]+$}}
|
||||
define void @store_i8_with_folded_gep_offset(i8* %p) {
|
||||
%s = getelementptr inbounds i8, i8* %p, i32 24
|
||||
store i8 0, i8* %s
|
||||
ret void
|
||||
}
|
||||
|
||||
; CHECK-LABEL: load_i8_u_with_folded_offset:
|
||||
; CHECK: i32.load8_u $push{{[0-9]+}}=, 24($0){{$}}
|
||||
define i32 @load_i8_u_with_folded_offset(i8* %p) {
|
||||
%q = ptrtoint i8* %p to i32
|
||||
%r = add nuw i32 %q, 24
|
||||
%s = inttoptr i32 %r to i8*
|
||||
%t = load i8, i8* %s
|
||||
%u = zext i8 %t to i32
|
||||
ret i32 %u
|
||||
}
|
||||
|
||||
; TODO: this should be load8_s, need to fold sign-/zero-extend in fast-isel
|
||||
; CHECK-LABEL: load_i8_s_with_folded_offset:
|
||||
; CHECK: i32.load8_u $push{{[0-9]+}}=, 24($0){{$}}
|
||||
define i32 @load_i8_s_with_folded_offset(i8* %p) {
|
||||
%q = ptrtoint i8* %p to i32
|
||||
%r = add nuw i32 %q, 24
|
||||
%s = inttoptr i32 %r to i8*
|
||||
%t = load i8, i8* %s
|
||||
%u = sext i8 %t to i32
|
||||
ret i32 %u
|
||||
}
|
Loading…
Reference in New Issue