https://github.com/DavidTruby updated
https://github.com/llvm/llvm-project/pull/119718
>From af135a1a4156be9076931ceeb92f75171a0cb7ad Mon Sep 17 00:00:00 2001
From: David Truby <david.tr...@arm.com>
Date: Thu, 12 Dec 2024 14:50:19 +0000
Subject: [PATCH] [flang] Add -f[no-]vectorize flags
---
clang/include/clang/Driver/Options.td | 11 +++++--
clang/lib/Driver/ToolChains/Clang.cpp | 33 -------------------
clang/lib/Driver/ToolChains/CommonArgs.cpp | 33 +++++++++++++++++++
clang/lib/Driver/ToolChains/CommonArgs.h | 2 ++
clang/lib/Driver/ToolChains/Flang.cpp | 10 ++++++
.../include/flang/Frontend/CodeGenOptions.def | 1 +
flang/lib/Frontend/CompilerInvocation.cpp | 4 +++
flang/lib/Frontend/FrontendActions.cpp | 2 ++
flang/test/Driver/optimization-remark.f90 | 22 ++++++-------
flang/test/Integration/unroll-loops.f90 | 4 +--
flang/test/Lower/HLFIR/unroll-loops.fir | 4 +--
11 files changed, 75 insertions(+), 51 deletions(-)
diff --git a/clang/include/clang/Driver/Options.td
b/clang/include/clang/Driver/Options.td
index 5ad187926e710..6824ffb8828d4 100644
--- a/clang/include/clang/Driver/Options.td
+++ b/clang/include/clang/Driver/Options.td
@@ -3986,11 +3986,15 @@ defm assumptions : BoolFOption<"assumptions",
"Disable codegen and compile-time checks for C++23's [[assume]]
attribute">,
PosFlag<SetTrue>>;
+
+let Visibility = [ClangOption, FlangOption] in {
def fvectorize : Flag<["-"], "fvectorize">, Group<f_Group>,
HelpText<"Enable the loop vectorization passes">;
def fno_vectorize : Flag<["-"], "fno-vectorize">, Group<f_Group>;
def : Flag<["-"], "ftree-vectorize">, Alias<fvectorize>;
def : Flag<["-"], "fno-tree-vectorize">, Alias<fno_vectorize>;
+}
+
def fslp_vectorize : Flag<["-"], "fslp-vectorize">, Group<f_Group>,
HelpText<"Enable the superword-level parallelism vectorization passes">;
def fno_slp_vectorize : Flag<["-"], "fno-slp-vectorize">, Group<f_Group>;
@@ -7332,6 +7336,10 @@ def mlink_builtin_bitcode : Separate<["-"],
"mlink-builtin-bitcode">,
def mlink_bitcode_file
: Separate<["-"], "mlink-bitcode-file">,
HelpText<"Link the given bitcode file before performing optimizations.">;
+
+def vectorize_loops : Flag<["-"], "vectorize-loops">,
+ HelpText<"Run the Loop vectorization passes">,
+ MarshallingInfoFlag<CodeGenOpts<"VectorizeLoop">>;
} // let Visibility = [CC1Option, FC1Option]
let Visibility = [CC1Option] in {
@@ -7447,9 +7455,6 @@ defm link_builtin_bitcode_postopt:
BoolMOption<"link-builtin-bitcode-postopt",
PosFlag<SetTrue, [], [ClangOption], "Link builtin bitcodes after the "
"optimization pipeline">,
NegFlag<SetFalse, [], [ClangOption]>>;
-def vectorize_loops : Flag<["-"], "vectorize-loops">,
- HelpText<"Run the Loop vectorization passes">,
- MarshallingInfoFlag<CodeGenOpts<"VectorizeLoop">>;
def vectorize_slp : Flag<["-"], "vectorize-slp">,
HelpText<"Run the SLP vectorization passes">,
MarshallingInfoFlag<CodeGenOpts<"VectorizeSLP">>;
diff --git a/clang/lib/Driver/ToolChains/Clang.cpp
b/clang/lib/Driver/ToolChains/Clang.cpp
index 96af466e067a8..7c50970068fa9 100644
--- a/clang/lib/Driver/ToolChains/Clang.cpp
+++ b/clang/lib/Driver/ToolChains/Clang.cpp
@@ -511,39 +511,6 @@ static void addCoveragePrefixMapArg(const Driver &D, const
ArgList &Args,
}
}
-/// Vectorize at all optimization levels greater than 1 except for -Oz.
-/// For -Oz the loop vectorizer is disabled, while the slp vectorizer is
-/// enabled.
-static bool shouldEnableVectorizerAtOLevel(const ArgList &Args, bool isSlpVec)
{
- if (Arg *A = Args.getLastArg(options::OPT_O_Group)) {
- if (A->getOption().matches(options::OPT_O4) ||
- A->getOption().matches(options::OPT_Ofast))
- return true;
-
- if (A->getOption().matches(options::OPT_O0))
- return false;
-
- assert(A->getOption().matches(options::OPT_O) && "Must have a -O flag");
-
- // Vectorize -Os.
- StringRef S(A->getValue());
- if (S == "s")
- return true;
-
- // Don't vectorize -Oz, unless it's the slp vectorizer.
- if (S == "z")
- return isSlpVec;
-
- unsigned OptLevel = 0;
- if (S.getAsInteger(10, OptLevel))
- return false;
-
- return OptLevel > 1;
- }
-
- return false;
-}
-
/// Add -x lang to \p CmdArgs for \p Input.
static void addDashXForInput(const ArgList &Args, const InputInfo &Input,
ArgStringList &CmdArgs) {
diff --git a/clang/lib/Driver/ToolChains/CommonArgs.cpp
b/clang/lib/Driver/ToolChains/CommonArgs.cpp
index 2d01943ca1ac4..1a2299a92c54e 100644
--- a/clang/lib/Driver/ToolChains/CommonArgs.cpp
+++ b/clang/lib/Driver/ToolChains/CommonArgs.cpp
@@ -3133,3 +3133,36 @@ void tools::renderCommonIntegerOverflowOptions(const
ArgList &Args,
if (use_fwrapv_pointer)
CmdArgs.push_back("-fwrapv-pointer");
}
+
+/// Vectorize at all optimization levels greater than 1 except for -Oz.
+/// For -Oz the loop vectorizer is disabled, while the slp vectorizer is
+/// enabled.
+bool tools::shouldEnableVectorizerAtOLevel(const ArgList &Args, bool isSlpVec)
{
+ if (Arg *A = Args.getLastArg(options::OPT_O_Group)) {
+ if (A->getOption().matches(options::OPT_O4) ||
+ A->getOption().matches(options::OPT_Ofast))
+ return true;
+
+ if (A->getOption().matches(options::OPT_O0))
+ return false;
+
+ assert(A->getOption().matches(options::OPT_O) && "Must have a -O flag");
+
+ // Vectorize -Os.
+ StringRef S(A->getValue());
+ if (S == "s")
+ return true;
+
+ // Don't vectorize -Oz, unless it's the slp vectorizer.
+ if (S == "z")
+ return isSlpVec;
+
+ unsigned OptLevel = 0;
+ if (S.getAsInteger(10, OptLevel))
+ return false;
+
+ return OptLevel > 1;
+ }
+
+ return false;
+}
diff --git a/clang/lib/Driver/ToolChains/CommonArgs.h
b/clang/lib/Driver/ToolChains/CommonArgs.h
index b6ddd99b87279..783a1f834b33d 100644
--- a/clang/lib/Driver/ToolChains/CommonArgs.h
+++ b/clang/lib/Driver/ToolChains/CommonArgs.h
@@ -265,6 +265,8 @@ bool shouldRecordCommandLine(const ToolChain &TC,
void renderCommonIntegerOverflowOptions(const llvm::opt::ArgList &Args,
llvm::opt::ArgStringList &CmdArgs);
+bool shouldEnableVectorizerAtOLevel(const llvm::opt::ArgList &Args,
+ bool isSlpVec);
} // end namespace tools
} // end namespace driver
} // end namespace clang
diff --git a/clang/lib/Driver/ToolChains/Flang.cpp
b/clang/lib/Driver/ToolChains/Flang.cpp
index 9ad795edd724d..45c26cf8c3159 100644
--- a/clang/lib/Driver/ToolChains/Flang.cpp
+++ b/clang/lib/Driver/ToolChains/Flang.cpp
@@ -149,6 +149,16 @@ void Flang::addCodegenOptions(const ArgList &Args,
!stackArrays->getOption().matches(options::OPT_fno_stack_arrays))
CmdArgs.push_back("-fstack-arrays");
+ // Enable vectorization per default according to the optimization level
+ // selected. For optimization levels that want vectorization we use the alias
+ // option to simplify the hasFlag logic.
+ bool enableVec = shouldEnableVectorizerAtOLevel(Args, false);
+ OptSpecifier vectorizeAliasOption =
+ enableVec ? options::OPT_O_Group : options::OPT_fvectorize;
+ if (Args.hasFlag(options::OPT_fvectorize, vectorizeAliasOption,
+ options::OPT_fno_vectorize, enableVec))
+ CmdArgs.push_back("-vectorize-loops");
+
if (shouldLoopVersion(Args))
CmdArgs.push_back("-fversion-loops-for-stride");
diff --git a/flang/include/flang/Frontend/CodeGenOptions.def
b/flang/include/flang/Frontend/CodeGenOptions.def
index deb8d1aede518..44cb5a2cdd497 100644
--- a/flang/include/flang/Frontend/CodeGenOptions.def
+++ b/flang/include/flang/Frontend/CodeGenOptions.def
@@ -31,6 +31,7 @@ CODEGENOPT(PrepareForFullLTO , 1, 0) ///< Set when -flto is
enabled on the
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(VectorizeLoop, 1, 0) ///< Enable loop vectorization.
CODEGENOPT(LoopVersioning, 1, 0) ///< Enable loop versioning.
CODEGENOPT(UnrollLoops, 1, 0) ///< Enable loop unrolling
CODEGENOPT(AliasAnalysis, 1, 0) ///< Enable alias analysis pass
diff --git a/flang/lib/Frontend/CompilerInvocation.cpp
b/flang/lib/Frontend/CompilerInvocation.cpp
index f3d9432c62d3b..724316f1b30c7 100644
--- a/flang/lib/Frontend/CompilerInvocation.cpp
+++ b/flang/lib/Frontend/CompilerInvocation.cpp
@@ -23,6 +23,7 @@
#include "clang/Basic/AllDiagnostics.h"
#include "clang/Basic/DiagnosticDriver.h"
#include "clang/Basic/DiagnosticOptions.h"
+#include "clang/Driver/Driver.h"
#include "clang/Driver/DriverDiagnostic.h"
#include "clang/Driver/OptionUtils.h"
#include "clang/Driver/Options.h"
@@ -242,6 +243,9 @@ static void
parseCodeGenArgs(Fortran::frontend::CodeGenOptions &opts,
clang::driver::options::OPT_fno_stack_arrays, false))
opts.StackArrays = 1;
+ if (args.getLastArg(clang::driver::options::OPT_vectorize_loops))
+ opts.VectorizeLoop = 1;
+
if (args.hasFlag(clang::driver::options::OPT_floop_versioning,
clang::driver::options::OPT_fno_loop_versioning, false))
opts.LoopVersioning = 1;
diff --git a/flang/lib/Frontend/FrontendActions.cpp
b/flang/lib/Frontend/FrontendActions.cpp
index 763c810ace0eb..76d329d043731 100644
--- a/flang/lib/Frontend/FrontendActions.cpp
+++ b/flang/lib/Frontend/FrontendActions.cpp
@@ -1037,6 +1037,8 @@ void
CodeGenAction::runOptimizationPipeline(llvm::raw_pwrite_stream &os) {
si.getTimePasses().setOutStream(ci.getTimingStreamLLVM());
pto.LoopUnrolling = opts.UnrollLoops;
pto.LoopInterleaving = opts.UnrollLoops;
+ pto.LoopVectorization = opts.VectorizeLoop;
+
llvm::PassBuilder pb(targetMachine, pto, pgoOpt, &pic);
// Attempt to load pass plugins and register their callbacks with PB.
diff --git a/flang/test/Driver/optimization-remark.f90
b/flang/test/Driver/optimization-remark.f90
index e90baa892f46a..90e310d36c807 100644
--- a/flang/test/Driver/optimization-remark.f90
+++ b/flang/test/Driver/optimization-remark.f90
@@ -5,33 +5,33 @@
! DEFINE: %{output} = -emit-llvm -flang-deprecated-no-hlfir -o /dev/null 2>&1
! Check fc1 can handle -Rpass
-! RUN: %flang_fc1 %s -O1 -Rpass %{output} 2>&1 | FileCheck %s
--check-prefix=REMARKS
+! RUN: %flang_fc1 %s -O1 -vectorize-loops -Rpass %{output} 2>&1 | FileCheck %s
--check-prefix=REMARKS
! Check that we can override -Rpass= with -Rno-pass.
-! RUN: %flang_fc1 %s -O1 -Rpass -Rno-pass %{output} 2>&1 | FileCheck %s
--allow-empty --check-prefix=NO-REMARKS
+! RUN: %flang_fc1 %s -O1 -vectorize-loops -Rpass -Rno-pass %{output} 2>&1 |
FileCheck %s --allow-empty --check-prefix=NO-REMARKS
! Check -Rno-pass, -Rno-pass-analysis, -Rno-pass-missed nothing emitted
-! RUN: %flang %s -O1 -Rno-pass -S %{output} 2>&1 | FileCheck %s --allow-empty
--check-prefix=NO-REMARKS
-! RUN: %flang %s -O1 -Rno-pass-missed -S %{output} 2>&1 | FileCheck %s
--allow-empty --check-prefix=NO-REMARKS
-! RUN: %flang %s -O1 -Rno-pass-analysis -S %{output} 2>&1 | FileCheck %s
--allow-empty --check-prefix=NO-REMARKS
+! RUN: %flang %s -O2 -Rno-pass -S %{output} 2>&1 | FileCheck %s --allow-empty
--check-prefix=NO-REMARKS
+! RUN: %flang %s -O2 -Rno-pass-missed -S %{output} 2>&1 | FileCheck %s
--allow-empty --check-prefix=NO-REMARKS
+! RUN: %flang %s -O2 -Rno-pass-analysis -S %{output} 2>&1 | FileCheck %s
--allow-empty --check-prefix=NO-REMARKS
! Check valid -Rpass regex
-! RUN: %flang %s -O1 -Rpass=loop -S %{output} 2>&1 | FileCheck %s
--check-prefix=PASS-REGEX-LOOP-ONLY
+! RUN: %flang %s -O2 -Rpass=loop -S %{output} 2>&1 | FileCheck %s
--check-prefix=PASS-REGEX-LOOP-ONLY
! Check valid -Rpass-missed regex
-! RUN: %flang %s -O1 -Rpass-missed=loop -S %{output} 2>&1 | FileCheck %s
--check-prefix=MISSED-REGEX-LOOP-ONLY
+! RUN: %flang %s -O2 -Rpass-missed=loop -S %{output} 2>&1 | FileCheck %s
--check-prefix=MISSED-REGEX-LOOP-ONLY
! Check valid -Rpass-analysis regex
-! RUN: %flang %s -O1 -Rpass-analysis=loop -S %{output} 2>&1 | FileCheck %s
--check-prefix=ANALYSIS-REGEX-LOOP-ONLY
+! RUN: %flang %s -O2 -Rpass-analysis=loop -S %{output} 2>&1 | FileCheck %s
--check-prefix=ANALYSIS-REGEX-LOOP-ONLY
! Check full -Rpass message is emitted
-! RUN: %flang %s -O1 -Rpass -S %{output} 2>&1 | FileCheck %s
--check-prefix=PASS
+! RUN: %flang %s -O2 -Rpass -S %{output} 2>&1 | FileCheck %s
--check-prefix=PASS
! Check full -Rpass-missed message is emitted
-! RUN: %flang %s -O1 -Rpass-missed -S %{output} 2>&1 | FileCheck %s
--check-prefix=MISSED
+! RUN: %flang %s -O2 -Rpass-missed -S %{output} 2>&1 | FileCheck %s
--check-prefix=MISSED
! Check full -Rpass-analysis message is emitted
-! RUN: %flang %s -O1 -Rpass-analysis -S -o /dev/null 2>&1 | FileCheck %s
--check-prefix=ANALYSIS
+! RUN: %flang %s -O2 -Rpass-analysis -S -o /dev/null 2>&1 | FileCheck %s
--check-prefix=ANALYSIS
! REMARKS: remark:
! NO-REMARKS-NOT: remark:
diff --git a/flang/test/Integration/unroll-loops.f90
b/flang/test/Integration/unroll-loops.f90
index c3fcf1c3a7cf3..debe45e0ec359 100644
--- a/flang/test/Integration/unroll-loops.f90
+++ b/flang/test/Integration/unroll-loops.f90
@@ -1,8 +1,8 @@
! FIXME: https://github.com/llvm/llvm-project/issues/123668
!
! DEFINE: %{triple} =
-! DEFINE: %{check-unroll} = %flang_fc1 -emit-llvm -O1 -funroll-loops -mllvm
-force-vector-width=2 -triple %{triple} -o- %s | FileCheck %s
--check-prefixes=CHECK,UNROLL
-! DEFINE: %{check-nounroll} = %flang_fc1 -emit-llvm -O1 -mllvm
-force-vector-width=2 -triple %{triple} -o- %s | FileCheck %s
--check-prefixes=CHECK,NO-UNROLL
+! DEFINE: %{check-unroll} = %flang_fc1 -emit-llvm -O1 -vectorize-loops
-funroll-loops -mllvm -force-vector-width=2 -triple %{triple} -o- %s |
FileCheck %s --check-prefixes=CHECK,UNROLL
+! DEFINE: %{check-nounroll} = %flang_fc1 -emit-llvm -O1 -vectorize-loops
-mllvm -force-vector-width=2 -triple %{triple} -o- %s | FileCheck %s
--check-prefixes=CHECK,NO-UNROLL
!
! REDEFINE: %{triple} = aarch64-unknown-linux-gnu
! RUN: %if aarch64-registered-target %{ %{check-unroll} %}
diff --git a/flang/test/Lower/HLFIR/unroll-loops.fir
b/flang/test/Lower/HLFIR/unroll-loops.fir
index 6a9dd28a37b6d..1321f39677405 100644
--- a/flang/test/Lower/HLFIR/unroll-loops.fir
+++ b/flang/test/Lower/HLFIR/unroll-loops.fir
@@ -1,6 +1,6 @@
// DEFINE: %{triple} =
-// DEFINE: %{check-unroll} = %flang_fc1 -emit-llvm -O1 -funroll-loops -mllvm
-force-vector-width=2 -triple %{triple} -o- %s | FileCheck %s
--check-prefixes=CHECK,UNROLL
-// DEFINE: %{check-nounroll} = %flang_fc1 -emit-llvm -O1 -mllvm
-force-vector-width=2 -triple %{triple} -o- %s | FileCheck %s
--check-prefixes=CHECK,NO-UNROLL
+// DEFINE: %{check-unroll} = %flang_fc1 -emit-llvm -O1 -vectorize-loops
-funroll-loops -mllvm -force-vector-width=2 -triple %{triple} -o- %s |
FileCheck %s --check-prefixes=CHECK,UNROLL
+// DEFINE: %{check-nounroll} = %flang_fc1 -emit-llvm -O1 -vectorize-loops
-mllvm -force-vector-width=2 -triple %{triple} -o- %s | FileCheck %s
--check-prefixes=CHECK,NO-UNROLL
// REDEFINE: %{triple} = aarch64-unknown-linux-gnu
// RUN: %if aarch64-registered-target %{ %{check-unroll} %}
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
