Revert "[flang] Integrate the option -flang-experimental-integer-overflow into -fno-wrapv" #113901
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
…flow int…" This reverts commit 96bb375.
|
@llvm/pr-subscribers-flang-openmp @llvm/pr-subscribers-flang-driver Author: Yusuke MINATO (yus3710-fj) ChangesReverts llvm/llvm-project#110063 due to the performance regression on 503.bwaves_r in SPEC2017. Patch is 101.96 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/113901.diff 40 Files Affected:
diff --git a/clang/include/clang/Driver/Options.td b/clang/include/clang/Driver/Options.td
index 5df6ddd5e6a0c5..75b4607b1b2391 100644
--- a/clang/include/clang/Driver/Options.td
+++ b/clang/include/clang/Driver/Options.td
@@ -6787,6 +6787,10 @@ def flang_deprecated_no_hlfir : Flag<["-"], "flang-deprecated-no-hlfir">,
Flags<[HelpHidden]>, Visibility<[FlangOption, FC1Option]>,
HelpText<"Do not use HLFIR lowering (deprecated)">;
+def flang_experimental_integer_overflow : Flag<["-"], "flang-experimental-integer-overflow">,
+ Flags<[HelpHidden]>, Visibility<[FlangOption, FC1Option]>,
+ HelpText<"Add nsw flag to internal operations such as do-variable increment (experimental)">;
+
//===----------------------------------------------------------------------===//
// FLangOption + CoreOption + NoXarchOption
//===----------------------------------------------------------------------===//
diff --git a/clang/lib/Driver/ToolChains/Flang.cpp b/clang/lib/Driver/ToolChains/Flang.cpp
index 366cadc2e54775..a9d2b7a4dc48f9 100644
--- a/clang/lib/Driver/ToolChains/Flang.cpp
+++ b/clang/lib/Driver/ToolChains/Flang.cpp
@@ -148,6 +148,7 @@ void Flang::addCodegenOptions(const ArgList &Args,
Args.addAllArgs(CmdArgs, {options::OPT_flang_experimental_hlfir,
options::OPT_flang_deprecated_no_hlfir,
+ options::OPT_flang_experimental_integer_overflow,
options::OPT_fno_ppc_native_vec_elem_order,
options::OPT_fppc_native_vec_elem_order});
}
diff --git a/flang/include/flang/Lower/LoweringOptions.def b/flang/include/flang/Lower/LoweringOptions.def
index 0b22e54b648e94..231de533fbd30a 100644
--- a/flang/include/flang/Lower/LoweringOptions.def
+++ b/flang/include/flang/Lower/LoweringOptions.def
@@ -38,5 +38,10 @@ ENUM_LOWERINGOPT(Underscoring, unsigned, 1, 1)
/// (i.e. wraps around as two's complement). Off by default.
ENUM_LOWERINGOPT(IntegerWrapAround, unsigned, 1, 0)
+/// If true, add nsw flags to loop variable increments.
+/// Off by default.
+/// TODO: integrate this option with the above
+ENUM_LOWERINGOPT(NSWOnLoopVarInc, unsigned, 1, 0)
+
#undef LOWERINGOPT
#undef ENUM_LOWERINGOPT
diff --git a/flang/include/flang/Optimizer/Transforms/Passes.h b/flang/include/flang/Optimizer/Transforms/Passes.h
index e1453cfa374bfc..e8f0a8444a31a1 100644
--- a/flang/include/flang/Optimizer/Transforms/Passes.h
+++ b/flang/include/flang/Optimizer/Transforms/Passes.h
@@ -66,7 +66,7 @@ namespace fir {
std::unique_ptr<mlir::Pass> createAffineDemotionPass();
std::unique_ptr<mlir::Pass>
createArrayValueCopyPass(fir::ArrayValueCopyOptions options = {});
-std::unique_ptr<mlir::Pass> createCFGConversionPassWithoutNSW();
+std::unique_ptr<mlir::Pass> createCFGConversionPassWithNSW();
std::unique_ptr<mlir::Pass> createMemDataFlowOptPass();
std::unique_ptr<mlir::Pass> createPromoteToAffinePass();
std::unique_ptr<mlir::Pass>
@@ -83,7 +83,7 @@ createVScaleAttrPass(std::pair<unsigned, unsigned> vscaleAttr);
void populateCfgConversionRewrites(mlir::RewritePatternSet &patterns,
bool forceLoopToExecuteOnce = false,
- bool setNSW = true);
+ bool setNSW = false);
// declarative passes
#define GEN_PASS_REGISTRATION
diff --git a/flang/include/flang/Optimizer/Transforms/Passes.td b/flang/include/flang/Optimizer/Transforms/Passes.td
index 54b43adbfc6bbf..a41f0f348f27a6 100644
--- a/flang/include/flang/Optimizer/Transforms/Passes.td
+++ b/flang/include/flang/Optimizer/Transforms/Passes.td
@@ -153,7 +153,7 @@ def CFGConversion : Pass<"cfg-conversion"> {
/*default=*/"false",
"force the body of a loop to execute at least once">,
Option<"setNSW", "set-nsw", "bool",
- /*default=*/"true",
+ /*default=*/"false",
"set nsw on loop variable increment">
];
}
diff --git a/flang/include/flang/Tools/CrossToolHelpers.h b/flang/include/flang/Tools/CrossToolHelpers.h
index 1626970600eff2..df4b21ada058fe 100644
--- a/flang/include/flang/Tools/CrossToolHelpers.h
+++ b/flang/include/flang/Tools/CrossToolHelpers.h
@@ -122,7 +122,7 @@ struct MLIRToLLVMPassPipelineConfig : public FlangEPCallBacks {
bool NoSignedZerosFPMath =
false; ///< Set no-signed-zeros-fp-math attribute for functions.
bool UnsafeFPMath = false; ///< Set unsafe-fp-math attribute for functions.
- bool NSWOnLoopVarInc = true; ///< Add nsw flag to loop variable increments.
+ bool NSWOnLoopVarInc = false; ///< Add nsw flag to loop variable increments.
};
struct OffloadModuleOpts {
diff --git a/flang/lib/Frontend/CompilerInvocation.cpp b/flang/lib/Frontend/CompilerInvocation.cpp
index 5da5236af2b0e1..94d3d115417877 100644
--- a/flang/lib/Frontend/CompilerInvocation.cpp
+++ b/flang/lib/Frontend/CompilerInvocation.cpp
@@ -1350,6 +1350,12 @@ bool CompilerInvocation::createFromArgs(
invoc.loweringOpts.setNoPPCNativeVecElemOrder(true);
}
+ // -flang-experimental-integer-overflow
+ if (args.hasArg(
+ clang::driver::options::OPT_flang_experimental_integer_overflow)) {
+ invoc.loweringOpts.setNSWOnLoopVarInc(true);
+ }
+
// Preserve all the remark options requested, i.e. -Rpass, -Rpass-missed or
// -Rpass-analysis. This will be used later when processing and outputting the
// remarks generated by LLVM in ExecuteCompilerInvocation.cpp.
diff --git a/flang/lib/Frontend/FrontendActions.cpp b/flang/lib/Frontend/FrontendActions.cpp
index 3ea242315484fd..f2e460fc53a67f 100644
--- a/flang/lib/Frontend/FrontendActions.cpp
+++ b/flang/lib/Frontend/FrontendActions.cpp
@@ -828,8 +828,8 @@ void CodeGenAction::generateLLVMIR() {
config.VScaleMax = vsr->second;
}
- if (ci.getInvocation().getLoweringOpts().getIntegerWrapAround())
- config.NSWOnLoopVarInc = false;
+ if (ci.getInvocation().getLoweringOpts().getNSWOnLoopVarInc())
+ config.NSWOnLoopVarInc = true;
// Create the pass pipeline
fir::createMLIRToLLVMPassPipeline(pm, config, getCurrentFile());
diff --git a/flang/lib/Lower/Bridge.cpp b/flang/lib/Lower/Bridge.cpp
index a3bd1ace11da21..877fe122265dd0 100644
--- a/flang/lib/Lower/Bridge.cpp
+++ b/flang/lib/Lower/Bridge.cpp
@@ -2271,7 +2271,7 @@ class FirConverter : public Fortran::lower::AbstractConverter {
assert(!incrementLoopNestInfo.empty() && "empty loop nest");
mlir::Location loc = toLocation();
mlir::arith::IntegerOverflowFlags flags{};
- if (!getLoweringOptions().getIntegerWrapAround())
+ if (getLoweringOptions().getNSWOnLoopVarInc())
flags = bitEnumSet(flags, mlir::arith::IntegerOverflowFlags::nsw);
auto iofAttr = mlir::arith::IntegerOverflowFlagsAttr::get(
builder->getContext(), flags);
diff --git a/flang/lib/Lower/IO.cpp b/flang/lib/Lower/IO.cpp
index b534c81a605a90..1894b0cfd1bec2 100644
--- a/flang/lib/Lower/IO.cpp
+++ b/flang/lib/Lower/IO.cpp
@@ -929,7 +929,7 @@ static void genIoLoop(Fortran::lower::AbstractConverter &converter,
fir::FirOpBuilder &builder = converter.getFirOpBuilder();
mlir::Location loc = converter.getCurrentLocation();
mlir::arith::IntegerOverflowFlags flags{};
- if (!converter.getLoweringOptions().getIntegerWrapAround())
+ if (converter.getLoweringOptions().getNSWOnLoopVarInc())
flags = bitEnumSet(flags, mlir::arith::IntegerOverflowFlags::nsw);
auto iofAttr =
mlir::arith::IntegerOverflowFlagsAttr::get(builder.getContext(), flags);
diff --git a/flang/lib/Optimizer/Passes/Pipelines.cpp b/flang/lib/Optimizer/Passes/Pipelines.cpp
index 091b7c4c164e40..3c139f7e93405c 100644
--- a/flang/lib/Optimizer/Passes/Pipelines.cpp
+++ b/flang/lib/Optimizer/Passes/Pipelines.cpp
@@ -35,11 +35,11 @@ void addCanonicalizerPassWithoutRegionSimplification(mlir::OpPassManager &pm) {
void addCfgConversionPass(mlir::PassManager &pm,
const MLIRToLLVMPassPipelineConfig &config) {
if (config.NSWOnLoopVarInc)
+ addNestedPassToAllTopLevelOperationsConditionally(
+ pm, disableCfgConversion, fir::createCFGConversionPassWithNSW);
+ else
addNestedPassToAllTopLevelOperationsConditionally(pm, disableCfgConversion,
fir::createCFGConversion);
- else
- addNestedPassToAllTopLevelOperationsConditionally(
- pm, disableCfgConversion, fir::createCFGConversionPassWithoutNSW);
}
void addAVC(mlir::PassManager &pm, const llvm::OptimizationLevel &optLevel) {
diff --git a/flang/lib/Optimizer/Transforms/ControlFlowConverter.cpp b/flang/lib/Optimizer/Transforms/ControlFlowConverter.cpp
index 411bf7f364a602..3b79d6d311b71c 100644
--- a/flang/lib/Optimizer/Transforms/ControlFlowConverter.cpp
+++ b/flang/lib/Optimizer/Transforms/ControlFlowConverter.cpp
@@ -332,6 +332,8 @@ class CfgConversion : public fir::impl::CFGConversionBase<CfgConversion> {
public:
using CFGConversionBase<CfgConversion>::CFGConversionBase;
+ CfgConversion(bool setNSW) { this->setNSW = setNSW; }
+
void runOnOperation() override {
auto *context = &this->getContext();
mlir::RewritePatternSet patterns(context);
@@ -364,8 +366,6 @@ void fir::populateCfgConversionRewrites(mlir::RewritePatternSet &patterns,
patterns.getContext(), forceLoopToExecuteOnce, setNSW);
}
-std::unique_ptr<mlir::Pass> fir::createCFGConversionPassWithoutNSW() {
- fir::CFGConversionOptions options;
- options.setNSW = false;
- return fir::createCFGConversion(options);
+std::unique_ptr<mlir::Pass> fir::createCFGConversionPassWithNSW() {
+ return std::make_unique<CfgConversion>(true);
}
diff --git a/flang/test/Driver/frontend-forwarding.f90 b/flang/test/Driver/frontend-forwarding.f90
index 55a74ccf40467b..ff2d6609521464 100644
--- a/flang/test/Driver/frontend-forwarding.f90
+++ b/flang/test/Driver/frontend-forwarding.f90
@@ -20,6 +20,7 @@
! RUN: -fversion-loops-for-stride \
! RUN: -flang-experimental-hlfir \
! RUN: -flang-deprecated-no-hlfir \
+! RUN: -flang-experimental-integer-overflow \
! RUN: -fno-ppc-native-vector-element-order \
! RUN: -fppc-native-vector-element-order \
! RUN: -mllvm -print-before-all \
@@ -51,6 +52,7 @@
! CHECK: "-fversion-loops-for-stride"
! CHECK: "-flang-experimental-hlfir"
! CHECK: "-flang-deprecated-no-hlfir"
+! CHECK: "-flang-experimental-integer-overflow"
! CHECK: "-fno-ppc-native-vector-element-order"
! CHECK: "-fppc-native-vector-element-order"
! CHECK: "-Rpass"
diff --git a/flang/test/Fir/convert-to-llvm-openmp-and-fir.fir b/flang/test/Fir/convert-to-llvm-openmp-and-fir.fir
index 00f8e6e6cc9a6b..335877e7c9a872 100644
--- a/flang/test/Fir/convert-to-llvm-openmp-and-fir.fir
+++ b/flang/test/Fir/convert-to-llvm-openmp-and-fir.fir
@@ -358,10 +358,10 @@ func.func @_QPopenmp_target_data_region() {
%9 = arith.subi %8, %c1_i64 : i64
%10 = fir.coordinate_of %0, %9 : (!fir.ref<!fir.array<1024xi32>>, i64) -> !fir.ref<i32>
fir.store %6 to %10 : !fir.ref<i32>
- %11 = arith.addi %arg0, %c1 overflow<nsw> : index
+ %11 = arith.addi %arg0, %c1 : index
%12 = fir.convert %c1 : (index) -> i32
%13 = fir.load %1 : !fir.ref<i32>
- %14 = arith.addi %13, %12 overflow<nsw> : i32
+ %14 = arith.addi %13, %12 : i32
fir.result %11, %14 : index, i32
}
fir.store %5#1 to %1 : !fir.ref<i32>
@@ -404,11 +404,11 @@ func.func @_QPopenmp_target_data_region() {
// CHECK: %[[VAL_21:.*]] = llvm.sub %[[VAL_19]], %[[VAL_20]] : i64
// CHECK: %[[VAL_22:.*]] = llvm.getelementptr %[[VAL_1]][0, %[[VAL_21]]] : (!llvm.ptr, i64) -> !llvm.ptr
// CHECK: llvm.store %[[VAL_17]], %[[VAL_22]] : i32, !llvm.ptr
-// CHECK: %[[VAL_23:.*]] = llvm.add %[[VAL_12]], %[[VAL_8]] overflow<nsw> : i64
+// CHECK: %[[VAL_23:.*]] = llvm.add %[[VAL_12]], %[[VAL_8]] : i64
// CHECK: %[[VAL_24:.*]] = llvm.trunc %[[VAL_8]] : i64 to i32
// CHECK: %[[VAL_25:.*]] = llvm.load %[[VAL_3]] : !llvm.ptr -> i32
-// CHECK: %[[VAL_26:.*]] = llvm.add %[[VAL_25]], %[[VAL_24]] overflow<nsw> : i32
-// CHECK: %[[VAL_27:.*]] = llvm.add %[[VAL_12]], %[[VAL_8]] overflow<nsw> : i64
+// CHECK: %[[VAL_26:.*]] = llvm.add %[[VAL_25]], %[[VAL_24]] : i32
+// CHECK: %[[VAL_27:.*]] = llvm.add %[[VAL_12]], %[[VAL_8]] : i64
// CHECK: %[[VAL_28:.*]] = llvm.mlir.constant(1 : index) : i64
// CHECK: %[[VAL_29:.*]] = llvm.sub %[[VAL_14]], %[[VAL_28]] : i64
// CHECK: llvm.br ^bb1(%[[VAL_27]], %[[VAL_26]], %[[VAL_29]] : i64, i32, i64)
diff --git a/flang/test/Fir/loop01.fir b/flang/test/Fir/loop01.fir
index 30d10b9bbdb979..c1cbb522c378c0 100644
--- a/flang/test/Fir/loop01.fir
+++ b/flang/test/Fir/loop01.fir
@@ -1,7 +1,5 @@
// RUN: fir-opt --split-input-file --cfg-conversion %s | FileCheck %s
-// RUN: fir-opt --split-input-file --cfg-conversion="set-nsw=false" %s | FileCheck %s --check-prefix=NO-NSW
-
-// NO-NSW-NOT: overflow<nsw>
+// RUN: fir-opt --split-input-file --cfg-conversion="set-nsw=true" %s | FileCheck %s --check-prefix=NSW
func.func @x(%lb : index, %ub : index, %step : index, %b : i1, %addr : !fir.ref<index>) {
fir.do_loop %iv = %lb to %ub step %step unordered {
@@ -37,7 +35,7 @@ func.func private @f2() -> i1
// CHECK: fir.store %[[VAL_12]] to %[[VAL_4]] : !fir.ref<index>
// CHECK: br ^bb5
// CHECK: ^bb5:
-// CHECK: %[[VAL_13:.*]] = arith.addi %[[VAL_8]], %[[VAL_2]] overflow<nsw> : index
+// CHECK: %[[VAL_13:.*]] = arith.addi %[[VAL_8]], %[[VAL_2]] : index
// CHECK: %[[VAL_14:.*]] = arith.constant 1 : index
// CHECK: %[[VAL_15:.*]] = arith.subi %[[VAL_9]], %[[VAL_14]] : index
// CHECK: br ^bb1(%[[VAL_13]], %[[VAL_15]] : index, index)
@@ -46,6 +44,34 @@ func.func private @f2() -> i1
// CHECK: }
// CHECK: func private @f2() -> i1
+// NSW: func @x(%[[VAL_0:.*]]: index, %[[VAL_1:.*]]: index, %[[VAL_2:.*]]: index, %[[VAL_3:.*]]: i1, %[[VAL_4:.*]]: !fir.ref<index>) {
+// NSW: %[[VAL_5:.*]] = arith.subi %[[VAL_1]], %[[VAL_0]] : index
+// NSW: %[[VAL_6:.*]] = arith.addi %[[VAL_5]], %[[VAL_2]] : index
+// NSW: %[[VAL_7:.*]] = arith.divsi %[[VAL_6]], %[[VAL_2]] : index
+// NSW: br ^bb1(%[[VAL_0]], %[[VAL_7]] : index, index)
+// NSW: ^bb1(%[[VAL_8:.*]]: index, %[[VAL_9:.*]]: index):
+// NSW: %[[VAL_10:.*]] = arith.constant 0 : index
+// NSW: %[[VAL_11:.*]] = arith.cmpi sgt, %[[VAL_9]], %[[VAL_10]] : index
+// NSW: cond_br %[[VAL_11]], ^bb2, ^bb6
+// NSW: ^bb2:
+// NSW: cond_br %[[VAL_3]], ^bb3, ^bb4
+// NSW: ^bb3:
+// NSW: fir.store %[[VAL_8]] to %[[VAL_4]] : !fir.ref<index>
+// NSW: br ^bb5
+// NSW: ^bb4:
+// NSW: %[[VAL_12:.*]] = arith.constant 0 : index
+// NSW: fir.store %[[VAL_12]] to %[[VAL_4]] : !fir.ref<index>
+// NSW: br ^bb5
+// NSW: ^bb5:
+// NSW: %[[VAL_13:.*]] = arith.addi %[[VAL_8]], %[[VAL_2]] overflow<nsw> : index
+// NSW: %[[VAL_14:.*]] = arith.constant 1 : index
+// NSW: %[[VAL_15:.*]] = arith.subi %[[VAL_9]], %[[VAL_14]] : index
+// NSW: br ^bb1(%[[VAL_13]], %[[VAL_15]] : index, index)
+// NSW: ^bb6:
+// NSW: return
+// NSW: }
+// NSW: func private @f2() -> i1
+
// -----
func.func @x2(%lo : index, %up : index, %ok : i1) {
@@ -75,13 +101,36 @@ func.func private @f3(i16)
// CHECK: cond_br %[[VAL_14]], ^bb2, ^bb3
// CHECK: ^bb2:
// CHECK: %[[VAL_15:.*]] = fir.call @f2() : () -> i1
-// CHECK: %[[VAL_16:.*]] = arith.addi %[[VAL_4]], %[[VAL_3]] overflow<nsw> : index
+// CHECK: %[[VAL_16:.*]] = arith.addi %[[VAL_4]], %[[VAL_3]] : index
// CHECK: br ^bb1(%[[VAL_16]], %[[VAL_15]] : index, i1)
// CHECK: ^bb3:
// CHECK: return
// CHECK: }
// CHECK: func private @f3(i16)
+// NSW: func @x2(%[[VAL_0:.*]]: index, %[[VAL_1:.*]]: index, %[[VAL_2:.*]]: i1) {
+// NSW: %[[VAL_3:.*]] = arith.constant 1 : index
+// NSW: br ^bb1(%[[VAL_0]], %[[VAL_2]] : index, i1)
+// NSW: ^bb1(%[[VAL_4:.*]]: index, %[[VAL_5:.*]]: i1):
+// NSW: %[[VAL_6:.*]] = arith.constant 0 : index
+// NSW: %[[VAL_7:.*]] = arith.cmpi slt, %[[VAL_6]], %[[VAL_3]] : index
+// NSW: %[[VAL_8:.*]] = arith.cmpi sle, %[[VAL_4]], %[[VAL_1]] : index
+// NSW: %[[VAL_9:.*]] = arith.cmpi slt, %[[VAL_3]], %[[VAL_6]] : index
+// NSW: %[[VAL_10:.*]] = arith.cmpi sle, %[[VAL_1]], %[[VAL_4]] : index
+// NSW: %[[VAL_11:.*]] = arith.andi %[[VAL_7]], %[[VAL_8]] : i1
+// NSW: %[[VAL_12:.*]] = arith.andi %[[VAL_9]], %[[VAL_10]] : i1
+// NSW: %[[VAL_13:.*]] = arith.ori %[[VAL_11]], %[[VAL_12]] : i1
+// NSW: %[[VAL_14:.*]] = arith.andi %[[VAL_5]], %[[VAL_13]] : i1
+// NSW: cond_br %[[VAL_14]], ^bb2, ^bb3
+// NSW: ^bb2:
+// NSW: %[[VAL_15:.*]] = fir.call @f2() : () -> i1
+// NSW: %[[VAL_16:.*]] = arith.addi %[[VAL_4]], %[[VAL_3]] overflow<nsw> : index
+// NSW: br ^bb1(%[[VAL_16]], %[[VAL_15]] : index, i1)
+// NSW: ^bb3:
+// NSW: return
+// NSW: }
+// NSW: func private @f3(i16)
+
// -----
// do_loop with an extra loop-carried value
@@ -110,7 +159,7 @@ func.func @x3(%lo : index, %up : index) -> i1 {
// CHECK: cond_br %[[VAL_11]], ^bb2, ^bb3
// CHECK: ^bb2:
// CHECK: %[[VAL_12:.*]] = fir.call @f2() : () -> i1
-// CHECK: %[[VAL_13:.*]] = arith.addi %[[VAL_7]], %[[VAL_2]] overflow<nsw> : index
+// CHECK: %[[VAL_13:.*]] = arith.addi %[[VAL_7]], %[[VAL_2]] : index
// CHECK: %[[VAL_14:.*]] = arith.constant 1 : index
// CHECK: %[[VAL_15:.*]] = arith.subi %[[VAL_9]], %[[VAL_14]] : index
// CHECK: br ^bb1(%[[VAL_13]], %[[VAL_12]], %[[VAL_15]] : index, i1, index)
@@ -118,6 +167,29 @@ func.func @x3(%lo : index, %up : index) -> i1 {
// CHECK: return %[[VAL_8]] : i1
// CHECK: }
+// NSW-LABEL: func @x3(
+// NSW-SAME: %[[VAL_0:.*]]: index,
+// NSW-SAME: %[[VAL_1:.*]]: index) -> i1 {
+// NSW: %[[VAL_2:.*]] = arith.constant 1 : index
+// NSW: %[[VAL_3:.*]] = arith.constant true
+// NSW: %[[VAL_4:.*]] = arith.subi %[[VAL_1]], %[[VAL_0]] : index
+// NSW: %[[VAL_5:.*]] = arith.addi %[[VAL_4]], %[[VAL_2]] : index
+// NSW: %[[VAL_6:.*]] = arith.divsi %[[VAL_5]], %[[VAL_2]] : index
+// NSW: br ^bb1(%[[VAL_0]], %[[VAL_3]], %[[VAL_6]] : index, i1, index)
+// NSW: ^bb1(%[[VAL_7:.*]]: index, %[[VAL_8:.*]]: i1, %[[VAL_9:.*]]: index):
+// NSW: %[[VAL_10:.*]] = arith.constant 0 : index
+// NSW: %[[VAL_11:.*]] = arith.cmpi sgt, %[[VAL_9]], %[[VAL_10]] : index
+// NSW: cond_br %[[VAL_11]], ^bb2, ^bb3
+// NSW: ^bb2:
+// NSW: %[[VAL_12:.*]] = fir.call @f2() : () -> i1
+// NSW: %[[VAL_13:.*]] = arith.addi %[[VAL_7]], %[[VAL_2]] overflow<nsw> : index
+// NSW: %[[VAL_14:.*]] = arith.constant 1 : index
+// NSW: %[[VAL_15:.*]] = arith.subi %[[VAL_9]], %[[VAL_14]] : index
+// NSW: br ^bb1(%[[VAL_13]], %[[VAL_12]], %[[VAL_15]] : index, i1, index)
+// NSW: ^bb3:
+// NSW: return %[[VAL_8]] : i1
+// NSW: }
+
// -----
// iterate_while with an extra loop-carried value
@@ -155,7 +227,7 @@ func.func private @f4(i32) -> i1
// CHECK: cond_br %[[VAL_16]], ^bb2, ^bb3
// CHECK: ^bb2:
// CHECK: %[[VAL_17:.*]] = fir.call @f2() : () -> i1
-// CHECK: %[[VAL_18:.*]] = arith.addi %[[VAL_5]], %[[VAL_2]] overflow<nsw> : index
+// CHECK: %[[VAL_18:.*]] = arith.addi %[[VAL_5]], %[[VAL_2]] : index
// CHECK: br ^bb1(%[[VAL_18]], %[[VAL_6]], %[[VAL_17]] : index, i1, i1)
// CHECK: ^bb3:
// CHECK: %[[VAL_19:.*]] = arith.andi %[[VAL_6]], %[[VAL_7]] : i1
@@ -163,6 +235,34 @@ func.func private @f4(i32) -> i1
// CHECK: }
// CHECK: func private @f4(i32) -> i1
+// NSW-LABEL: func @y3(
+// NSW-SAME: %[[VAL_0:.*]]: index,
+// NSW-SAME: %[[VAL_1:.*]]: index) -> i1 {
+// NSW: %[[VAL_2:.*]] = arith.constant 1 : index
+// NSW: %[[VAL_3:.*]] = arith.constant true
+// NSW: %[[VAL_4:.*]] = fir.call @f2() : () -> i1
+// NSW: br ^bb1(%[[VAL_0]], %[[VAL_3]], %[[VAL_4]] : index, i1, i1)
+// NSW: ^bb1(%[[VAL_5:.*]]: index, %[[VAL_6:.*]]: i...
[truncated]
|
NoumanAmir657
pushed a commit
to NoumanAmir657/llvm-project
that referenced
this pull request
Nov 4, 2024
…flow into -fno-wrapv" (llvm#113901) Reverts llvm#110063 due to the performance regression on 503.bwaves_r in SPEC2017.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Reverts #110063 due to the performance regression on 503.bwaves_r in SPEC2017.