Index: lib/Analysis/ScalarEvolution.cpp =================================================================== --- lib/Analysis/ScalarEvolution.cpp +++ lib/Analysis/ScalarEvolution.cpp @@ -5315,28 +5315,61 @@ break; case Instruction::AShr: - // For a two-shift sext-inreg, use sext(trunc(x)) as the SCEV expression. - if (ConstantInt *CI = dyn_cast(BO->RHS)) - if (Operator *L = dyn_cast(BO->LHS)) - if (L->getOpcode() == Instruction::Shl && - L->getOperand(1) == BO->RHS) { - uint64_t BitWidth = getTypeSizeInBits(BO->LHS->getType()); - - // If the shift count is not less than the bitwidth, the result of - // the shift is undefined. Don't try to analyze it, because the - // resolution chosen here may differ from the resolution chosen in - // other parts of the compiler. - if (CI->getValue().uge(BitWidth)) - break; + // AShr X, C, where C is a constant. + ConstantInt *CI = dyn_cast(BO->RHS); + if (!CI) + break; - uint64_t Amt = BitWidth - CI->getZExtValue(); - if (Amt == BitWidth) - return getSCEV(L->getOperand(0)); // shift by zero --> noop + Type *SExtTy = BO->LHS->getType(); + uint64_t BitWidth = getTypeSizeInBits(SExtTy); + // If the shift count is not less than the bitwidth, the result of + // the shift is undefined. Don't try to analyze it, because the + // resolution chosen here may differ from the resolution chosen in + // other parts of the compiler. + if (CI->getValue().uge(BitWidth)) + break; + + if (CI->isNullValue()) + return getSCEV(BO->LHS); // shift by zero --> noop + + uint64_t AShrAmt = CI->getZExtValue(); + uint64_t TruncToWidth = BitWidth - AShrAmt; + Type *TruncTy = IntegerType::get(getContext(), TruncToWidth); + + Operator *L = dyn_cast(BO->LHS); + if (L && L->getOpcode() == Instruction::Shl) { + // X = Shl A, C0 + // Y = AShr X, C1 + + const SCEV *ShlOp0SCEV = getSCEV(L->getOperand(0)); + if (L->getOperand(1) == BO->RHS) + // For a two-shift sext-inreg, i.e. n = m, + // use sext(trunc(x)) as the SCEV expression. + return getSignExtendExpr( + getTruncateExpr(ShlOp0SCEV, TruncTy), SExtTy); + + ConstantInt *ShlAmtCI = dyn_cast(L->getOperand(1)); + if (ShlAmtCI && ShlAmtCI->getValue().ult(BitWidth)) { + uint64_t ShlAmt = ShlAmtCI->getZExtValue(); + if (ShlAmt > AShrAmt) { + // When n > m, use sext(mul(trunc(x), 2^(n-m)))) as the SCEV + // expression. We already checked that ShlAmt < BitWidth, so + // the multiplier, 1 << (LhlAmt - AShrAmt), fits into TruncTy as + // LhlAmt - AShrAmt < Amt. + APInt Mul = APInt::getOneBitSet(TruncToWidth, ShlAmt - AShrAmt); return getSignExtendExpr( - getTruncateExpr(getSCEV(L->getOperand(0)), - IntegerType::get(getContext(), Amt)), - BO->LHS->getType()); + getMulExpr(getTruncateExpr(ShlOp0SCEV, TruncTy), + getConstant(Mul)), SExtTy); } + } + } + if (Value *LV = dyn_cast(BO->LHS)) { + // Transform AShr i32 %x, C to sext(trunc(udiv(x, (1 << C)))). + APInt Div = APInt::getOneBitSet(BitWidth, CI->getZExtValue()); + return getSignExtendExpr( + getTruncateExpr(getUDivExpr(getSCEV(LV), getConstant(Div)), + TruncTy), SExtTy); + } break; } } Index: test/Analysis/ScalarEvolution/flags-from-poison.ll =================================================================== --- test/Analysis/ScalarEvolution/flags-from-poison.ll +++ test/Analysis/ScalarEvolution/flags-from-poison.ll @@ -582,7 +582,7 @@ %i = phi i32 [ %nexti, %loop ], [ %start, %entry ] ; CHECK: %index32 = -; CHECK: --> {((-1 * %halfsub) + %start),+,1} +; CHECK: --> {((-1 * (sext i31 (trunc i32 (%sub /u 2) to i31) to i32)) + %start),+,1} %index32 = sub nsw i32 %i, %halfsub %index64 = sext i32 %index32 to i64 Index: test/Analysis/ScalarEvolution/scev-expander-reuse-unroll.ll =================================================================== --- test/Analysis/ScalarEvolution/scev-expander-reuse-unroll.ll +++ test/Analysis/ScalarEvolution/scev-expander-reuse-unroll.ll @@ -3,6 +3,7 @@ ; Check SCEV expansion uses existing value when unrolling an inner loop with runtime trip count in a loop nest. ; CHECK-LABEL: @foo( ; CHECK: select +; CHECK: select {{.*}} i32 %shr ; CHECK-NOT: select ; CHECK: ret Index: test/Analysis/ScalarEvolution/sext-div.ll =================================================================== --- /dev/null +++ test/Analysis/ScalarEvolution/sext-div.ll @@ -0,0 +1,34 @@ +; RUN: opt < %s -analyze -scalar-evolution | FileCheck %s + + +; CHECK: %tmp10 = ashr exact i64 %tmp8, 13 +; CHECK-NEXT: --> ({0,+,1}<%bb7> /u 8192) {{.*}} Exits: ((-1 + (zext i32 %arg2 to i64)) /u 8192) +; CHECK: %tmp11 = getelementptr inbounds i32, i32* %arg, i64 %tmp10 +; CHECK-NEXT: --> ((4 * ({0,+,1}<%bb7> /u 8192)) + %arg) {{.*}} Exits: ((4 * ((-1 + (zext i32 %arg2 to i64)) /u 8192)) + %arg) + +define void @foo(i32* nocapture %arg, i32 %arg1, i32 %arg2) { +bb: + %tmp = icmp sgt i32 %arg2, 0 + br i1 %tmp, label %bb3, label %bb6 + +bb3: ; preds = %bb + %tmp4 = zext i32 %arg2 to i64 + br label %bb7 + +bb5: ; preds = %bb7 + br label %bb6 + +bb6: ; preds = %bb5, %bb + ret void + +bb7: ; preds = %bb7, %bb3 + %tmp8 = phi i64 [ %tmp18, %bb7 ], [ 0, %bb3 ] + %tmp10 = ashr exact i64 %tmp8, 13 + %tmp11 = getelementptr inbounds i32, i32* %arg, i64 %tmp10 + %tmp12 = load i32, i32* %tmp11, align 4 + %tmp13 = sub nsw i32 %tmp12, %arg1 + store i32 %tmp13, i32* %tmp11, align 4 + %tmp18 = add nuw nsw i64 %tmp8, 1 + %tmp19 = icmp eq i64 %tmp18, %tmp4 + br i1 %tmp19, label %bb5, label %bb7 +} Index: test/Analysis/ScalarEvolution/sext-mul.ll =================================================================== --- /dev/null +++ test/Analysis/ScalarEvolution/sext-mul.ll @@ -0,0 +1,89 @@ +; RUN: opt < %s -analyze -scalar-evolution | FileCheck %s + +; CHECK: %tmp9 = shl i64 %tmp8, 33 +; CHECK-NEXT: --> {{.*}} Exits: (-8589934592 + (8589934592 * (zext i32 %arg2 to i64))) LoopDispositions: { %bb7: Computable } +; CHECK: %tmp10 = ashr exact i64 %tmp9, 32 +; CHECK-NEXT: --> {{.*}} Exits: (sext i32 (-2 + (2 * %arg2)) to i64) LoopDispositions: { %bb7: Computable } +; CHECK: %tmp11 = getelementptr inbounds i32, i32* %arg, i64 %tmp10 +; CHECK: --> {{.*}} Exits: ((4 * (sext i32 (-2 + (2 * %arg2)) to i64)) + %arg) LoopDispositions: { %bb7: Computable } +; CHECK: %tmp14 = or i64 %tmp10, 1 +; CHECK: --> {{.*}} Exits: (1 + (sext i32 (-2 + (2 * %arg2)) to i64)) LoopDispositions: { %bb7: Computable } +; CHECK: %tmp15 = getelementptr inbounds i32, i32* %arg, i64 %tmp14 +; CHECK: --> {{.*}} Exits: (4 + (4 * (sext i32 (-2 + (2 * %arg2)) to i64)) + %arg) LoopDispositions: { %bb7: Computable } +; CHECK:Loop %bb7: backedge-taken count is (-1 + (zext i32 %arg2 to i64)) +; CHECK:Loop %bb7: max backedge-taken count is -1 +; CHECK:Loop %bb7: Predicated backedge-taken count is (-1 + (zext i32 %arg2 to i64)) + +define void @foo(i32* nocapture %arg, i32 %arg1, i32 %arg2) { +bb: + %tmp = icmp sgt i32 %arg2, 0 + br i1 %tmp, label %bb3, label %bb6 + +bb3: ; preds = %bb + %tmp4 = zext i32 %arg2 to i64 + br label %bb7 + +bb5: ; preds = %bb7 + br label %bb6 + +bb6: ; preds = %bb5, %bb + ret void + +bb7: ; preds = %bb7, %bb3 + %tmp8 = phi i64 [ %tmp18, %bb7 ], [ 0, %bb3 ] + %tmp9 = shl i64 %tmp8, 33 + %tmp10 = ashr exact i64 %tmp9, 32 + %tmp11 = getelementptr inbounds i32, i32* %arg, i64 %tmp10 + %tmp12 = load i32, i32* %tmp11, align 4 + %tmp13 = sub nsw i32 %tmp12, %arg1 + store i32 %tmp13, i32* %tmp11, align 4 + %tmp14 = or i64 %tmp10, 1 + %tmp15 = getelementptr inbounds i32, i32* %arg, i64 %tmp14 + %tmp16 = load i32, i32* %tmp15, align 4 + %tmp17 = mul nsw i32 %tmp16, %arg1 + store i32 %tmp17, i32* %tmp15, align 4 + %tmp18 = add nuw nsw i64 %tmp8, 1 + %tmp19 = icmp eq i64 %tmp18, %tmp4 + br i1 %tmp19, label %bb5, label %bb7 +} + +; CHECK: %t10 = ashr exact i128 %t9, 1 +; CHECK-NEXT: --> {{.*}} Exits: (sext i127 (-633825300114114700748351602688 + (633825300114114700748351602688 * (zext i32 %arg5 to i127))) to i128) LoopDispositions: { %bb7: Computable } +; CHECK: %t14 = or i128 %t10, 1 +; CHECK-NEXT: --> {{.*}} Exits: (1 + (sext i127 (-633825300114114700748351602688 + (633825300114114700748351602688 * (zext i32 %arg5 to i127))) to i128)) LoopDispositions: { %bb7: Computable } +; CHECK: Loop %bb7: backedge-taken count is (-1 + (zext i32 %arg5 to i128)) +; CHECK-NEXT: Loop %bb7: max backedge-taken count is -1 +; CHECK-NEXT: Loop %bb7: Predicated backedge-taken count is (-1 + (zext i32 %arg5 to i128)) + +define void @goo(i32* nocapture %arg3, i32 %arg4, i32 %arg5) { +bb: + %t = icmp sgt i32 %arg5, 0 + br i1 %t, label %bb3, label %bb6 + +bb3: ; preds = %bb + %t4 = zext i32 %arg5 to i128 + br label %bb7 + +bb5: ; preds = %bb7 + br label %bb6 + +bb6: ; preds = %bb5, %bb + ret void + +bb7: ; preds = %bb7, %bb3 + %t8 = phi i128 [ %t18, %bb7 ], [ 0, %bb3 ] + %t9 = shl i128 %t8, 100 + %t10 = ashr exact i128 %t9, 1 + %t11 = getelementptr inbounds i32, i32* %arg3, i128 %t10 + %t12 = load i32, i32* %t11, align 4 + %t13 = sub nsw i32 %t12, %arg4 + store i32 %t13, i32* %t11, align 4 + %t14 = or i128 %t10, 1 + %t15 = getelementptr inbounds i32, i32* %arg3, i128 %t14 + %t16 = load i32, i32* %t15, align 4 + %t17 = mul nsw i32 %t16, %arg4 + store i32 %t17, i32* %t15, align 4 + %t18 = add nuw nsw i128 %t8, 1 + %t19 = icmp eq i128 %t18, %t4 + br i1 %t19, label %bb5, label %bb7 +} Index: test/Analysis/ScalarEvolution/sext-zero.ll =================================================================== --- /dev/null +++ test/Analysis/ScalarEvolution/sext-zero.ll @@ -0,0 +1,39 @@ +; RUN: opt < %s -analyze -scalar-evolution | FileCheck %s + +; CHECK: %tmp9 = shl i64 %tmp8, 33 +; CHECK-NEXT: --> {0,+,8589934592}<%bb7> U: [0,-8589934591) S: [-9223372036854775808,9223372028264841217) Exits: (-8589934592 + (8589934592 * (zext i32 %arg2 to i64))) LoopDispositions: { %bb7: Computable } +; CHECK-NEXT: %tmp10 = ashr exact i64 %tmp9, 0 +; CHECK-NEXT: --> {0,+,8589934592}<%bb7> U: [0,-8589934591) S: [-9223372036854775808,9223372028264841217) Exits: (-8589934592 + (8589934592 * (zext i32 %arg2 to i64))) LoopDispositions: { %bb7: Computable } + +define void @foo(i32* nocapture %arg, i32 %arg1, i32 %arg2) { +bb: + %tmp = icmp sgt i32 %arg2, 0 + br i1 %tmp, label %bb3, label %bb6 + +bb3: ; preds = %bb + %tmp4 = zext i32 %arg2 to i64 + br label %bb7 + +bb5: ; preds = %bb7 + br label %bb6 + +bb6: ; preds = %bb5, %bb + ret void + +bb7: ; preds = %bb7, %bb3 + %tmp8 = phi i64 [ %tmp18, %bb7 ], [ 0, %bb3 ] + %tmp9 = shl i64 %tmp8, 33 + %tmp10 = ashr exact i64 %tmp9, 0 + %tmp11 = getelementptr inbounds i32, i32* %arg, i64 %tmp10 + %tmp12 = load i32, i32* %tmp11, align 4 + %tmp13 = sub nsw i32 %tmp12, %arg1 + store i32 %tmp13, i32* %tmp11, align 4 + %tmp14 = or i64 %tmp10, 1 + %tmp15 = getelementptr inbounds i32, i32* %arg, i64 %tmp14 + %tmp16 = load i32, i32* %tmp15, align 4 + %tmp17 = mul nsw i32 %tmp16, %arg1 + store i32 %tmp17, i32* %tmp15, align 4 + %tmp18 = add nuw nsw i64 %tmp8, 1 + %tmp19 = icmp eq i64 %tmp18, %tmp4 + br i1 %tmp19, label %bb5, label %bb7 +}