[flang] Add -f[no-]unroll-loops flag (#122906)

This commit is contained in:
David Truby
2025-01-16 06:43:32 +00:00
committed by GitHub
parent 1797fb6b23
commit 0195ec452e
8 changed files with 89 additions and 3 deletions

View File

@@ -4157,9 +4157,9 @@ def ftrap_function_EQ : Joined<["-"], "ftrap-function=">, Group<f_Group>,
HelpText<"Issue call to specified function rather than a trap instruction">,
MarshallingInfoString<CodeGenOpts<"TrapFuncName">>;
def funroll_loops : Flag<["-"], "funroll-loops">, Group<f_Group>,
HelpText<"Turn on loop unroller">, Visibility<[ClangOption, CC1Option]>;
HelpText<"Turn on loop unroller">, Visibility<[ClangOption, CC1Option, FlangOption, FC1Option]>;
def fno_unroll_loops : Flag<["-"], "fno-unroll-loops">, Group<f_Group>,
HelpText<"Turn off loop unroller">, Visibility<[ClangOption, CC1Option]>;
HelpText<"Turn off loop unroller">, Visibility<[ClangOption, CC1Option, FlangOption, FC1Option]>;
def ffinite_loops: Flag<["-"], "ffinite-loops">, Group<f_Group>,
HelpText<"Assume all non-trivial loops are finite.">, Visibility<[ClangOption, CC1Option]>;
def fno_finite_loops: Flag<["-"], "fno-finite-loops">, Group<f_Group>,

View File

@@ -155,7 +155,8 @@ void Flang::addCodegenOptions(const ArgList &Args,
options::OPT_flang_deprecated_no_hlfir,
options::OPT_fno_ppc_native_vec_elem_order,
options::OPT_fppc_native_vec_elem_order,
options::OPT_ftime_report, options::OPT_ftime_report_EQ});
options::OPT_ftime_report, options::OPT_ftime_report_EQ,
options::OPT_funroll_loops, options::OPT_fno_unroll_loops});
}
void Flang::addPicOptions(const ArgList &Args, ArgStringList &CmdArgs) const {

View File

@@ -32,6 +32,7 @@ CODEGENOPT(PrepareForThinLTO , 1, 0) ///< Set when -flto=thin is enabled on the
///< compile step.
CODEGENOPT(StackArrays, 1, 0) ///< -fstack-arrays (enable the stack-arrays pass)
CODEGENOPT(LoopVersioning, 1, 0) ///< Enable loop versioning.
CODEGENOPT(UnrollLoops, 1, 0) ///< Enable loop unrolling
CODEGENOPT(AliasAnalysis, 1, 0) ///< Enable alias analysis pass
CODEGENOPT(Underscoring, 1, 1)

View File

@@ -246,6 +246,10 @@ static void parseCodeGenArgs(Fortran::frontend::CodeGenOptions &opts,
clang::driver::options::OPT_fno_loop_versioning, false))
opts.LoopVersioning = 1;
opts.UnrollLoops = args.hasFlag(clang::driver::options::OPT_funroll_loops,
clang::driver::options::OPT_fno_unroll_loops,
(opts.OptimizationLevel > 1));
opts.AliasAnalysis = opts.OptimizationLevel > 0;
// -mframe-pointer=none/non-leaf/all option.

View File

@@ -1028,6 +1028,8 @@ void CodeGenAction::runOptimizationPipeline(llvm::raw_pwrite_stream &os) {
si.registerCallbacks(pic, &mam);
if (ci.isTimingEnabled())
si.getTimePasses().setOutStream(ci.getTimingStreamLLVM());
pto.LoopUnrolling = opts.UnrollLoops;
pto.LoopInterleaving = opts.UnrollLoops;
llvm::PassBuilder pb(targetMachine, pto, pgoOpt, &pic);
// Attempt to load pass plugins and register their callbacks with PB.

View File

@@ -0,0 +1,5 @@
! RUN: %flang -### -funroll-loops %s 2>&1 | FileCheck %s -check-prefix UNROLL
! RUN: %flang -### -fno-unroll-loops %s 2>&1 | FileCheck %s -check-prefix NO-UNROLL
! UNROLL: "-funroll-loops"
! NO-UNROLL: "-fno-unroll-loops"

View File

@@ -0,0 +1,39 @@
// RUN: %flang_fc1 -emit-llvm -O1 -funroll-loops -mllvm -force-vector-width=2 -o- %s | FileCheck %s --check-prefixes=CHECK,UNROLL
// RUN: %flang_fc1 -emit-llvm -O2 -mllvm -force-vector-width=2 -o- %s | FileCheck %s --check-prefixes=CHECK,UNROLL
// RUN: %flang_fc1 -emit-llvm -O1 -fno-unroll-loops -mllvm -force-vector-width=2 -o- %s | FileCheck %s --check-prefixes=CHECK,NO-UNROLL
// RUN: %flang_fc1 -emit-llvm -O1 -mllvm -force-vector-width=2 -o- %s | FileCheck %s --check-prefixes=CHECK,NO-UNROLL
// CHECK-LABEL: @unroll
// CHECK-SAME: (ptr nocapture writeonly %[[ARG0:.*]])
func.func @unroll(%arg0: !fir.ref<!fir.array<1000 x index>> {fir.bindc_name = "a"}) {
%scope = fir.dummy_scope : !fir.dscope
%c1000 = arith.constant 1000 : index
%shape = fir.shape %c1000 : (index) -> !fir.shape<1>
%a:2 = hlfir.declare %arg0(%shape) dummy_scope %scope {uniq_name = "unrollEa"} : (!fir.ref<!fir.array<1000xindex>>, !fir.shape<1>, !fir.dscope) -> (!fir.ref<!fir.array<1000 x index>>, !fir.ref<!fir.array<1000 x index>>)
%c1 = arith.constant 1 : index
fir.do_loop %arg1 = %c1 to %c1000 step %c1 {
// CHECK: br label %[[BLK:.*]]
// CHECK: [[BLK]]:
// CHECK-NEXT: %[[IND:.*]] = phi i64 [ 0, %{{.*}} ], [ %[[NIV:.*]], %[[BLK]] ]
// CHECK-NEXT: %[[VIND:.*]] = phi <2 x i64> [ <i64 1, i64 2>, %{{.*}} ], [ %[[NVIND:.*]], %[[BLK]] ]
// NO-UNROLL-NEXT: %[[GEP:.*]] = getelementptr i64, ptr %[[ARG0]], i64 %[[IND]]
// NO-UNROLL-NEXT: store <2 x i64> %[[VIND]], ptr %[[GEP]]
// NO-UNROLL-NEXT: %[[NIV:.*]] = add nuw i64 %{{.*}}, 2
// NO-UNROLL-NEXT: %[[NVIND]] = add <2 x i64> %[[VIND]], splat (i64 2)
// UNROLL-NEXT: %[[VIND1:.*]] = add <2 x i64> %[[VIND]], splat (i64 2)
// UNROLL-NEXT: %[[GEP0:.*]] = getelementptr i64, ptr %[[ARG0]], i64 %[[IND]]
// UNROLL-NEXT: %[[GEP1:.*]] = getelementptr i8, ptr %[[GEP0]], i64 16
// UNROLL-NEXT: store <2 x i64> %[[VIND]], ptr %[[GEP0]]
// UNROLL-NEXT: store <2 x i64> %[[VIND1]], ptr %[[GEP1]]
// UNROLL-NEXT: %[[NIV:.*]] = add nuw i64 %[[IND]], 4
// UNROLL-NEXT: %[[NVIND:.*]] = add <2 x i64> %[[VIND]], splat (i64 4)
// CHECK-NEXT: %[[EXIT:.*]] = icmp eq i64 %[[NIV]], 1000
// CHECK-NEXT: br i1 %[[EXIT]], label %{{.*}}, label %[[BLK]]
%ai = hlfir.designate %a#0 (%arg1) : (!fir.ref<!fir.array<1000 x index>>, index) -> !fir.ref<index>
hlfir.assign %arg1 to %ai : index, !fir.ref<index>
}
return
}

View File

@@ -0,0 +1,34 @@
! RUN: %flang_fc1 -emit-llvm -O1 -funroll-loops -mllvm -force-vector-width=2 -o- %s | FileCheck %s --check-prefixes=CHECK,UNROLL
! RUN: %flang_fc1 -emit-llvm -O2 -mllvm -force-vector-width=2 -o- %s | FileCheck %s --check-prefixes=CHECK,UNROLL
! RUN: %flang_fc1 -emit-llvm -O1 -fno-unroll-loops -mllvm -force-vector-width=2 -o- %s | FileCheck %s --check-prefixes=CHECK,NO-UNROLL
! RUN: %flang_fc1 -emit-llvm -O1 -mllvm -force-vector-width=2 -o- %s | FileCheck %s --check-prefixes=CHECK,NO-UNROLL
! CHECK-LABEL: @unroll
! CHECK-SAME: (ptr nocapture writeonly %[[ARG0:.*]])
subroutine unroll(a)
integer(kind=8), intent(out) :: a(1000)
integer(kind=8) :: i
! CHECK: br label %[[BLK:.*]]
! CHECK: [[BLK]]:
! CHECK-NEXT: %[[IND:.*]] = phi i64 [ 0, %{{.*}} ], [ %[[NIV:.*]], %[[BLK]] ]
! CHECK-NEXT: %[[VIND:.*]] = phi <2 x i64> [ <i64 1, i64 2>, %{{.*}} ], [ %[[NVIND:.*]], %[[BLK]] ]
!
! NO-UNROLL-NEXT: %[[GEP:.*]] = getelementptr i64, ptr %[[ARG0]], i64 %[[IND]]
! NO-UNROLL-NEXT: store <2 x i64> %[[VIND]], ptr %[[GEP]]
! NO-UNROLL-NEXT: %[[NIV:.*]] = add nuw i64 %{{.*}}, 2
! NO-UNROLL-NEXT: %[[NVIND]] = add <2 x i64> %[[VIND]], splat (i64 2)
!
! UNROLL-NEXT: %[[VIND1:.*]] = add <2 x i64> %[[VIND]], splat (i64 2)
! UNROLL-NEXT: %[[GEP0:.*]] = getelementptr i64, ptr %[[ARG0]], i64 %[[IND]]
! UNROLL-NEXT: %[[GEP1:.*]] = getelementptr i8, ptr %[[GEP0]], i64 16
! UNROLL-NEXT: store <2 x i64> %[[VIND]], ptr %[[GEP0]]
! UNROLL-NEXT: store <2 x i64> %[[VIND1]], ptr %[[GEP1]]
! UNROLL-NEXT: %[[NIV:.*]] = add nuw i64 %[[IND]], 4
! UNROLL-NEXT: %[[NVIND:.*]] = add <2 x i64> %[[VIND]], splat (i64 4)
!
! CHECK-NEXT: %[[EXIT:.*]] = icmp eq i64 %[[NIV]], 1000
! CHECK-NEXT: br i1 %[[EXIT]], label %{{.*}}, label %[[BLK]]
do i=1,1000
a(i) = i
end do
end subroutine