[clang] [llvm] [LoongArch] Support LA V1.1 feature that div.w[u] and mod.w[u] instructions with inputs not signed-extended. (PR #116764)
via cfe-commits
cfe-commits at lists.llvm.org
Tue Nov 19 22:39:08 PST 2024
https://github.com/tangaac updated https://github.com/llvm/llvm-project/pull/116764
>From 78e214321a273636f7cf4838f0b1ce04ba21d445 Mon Sep 17 00:00:00 2001
From: tangaac <tangyan01 at loongson.cn>
Date: Tue, 19 Nov 2024 15:04:29 +0800
Subject: [PATCH 1/2] [LoongArch] Support LA V1.1 feature that div.w[u] and
mod.w[u] instructions with inputs not signed-extended.
---
clang/include/clang/Driver/Options.td | 4 +++
clang/lib/Basic/Targets/LoongArch.cpp | 7 ++++-
clang/lib/Basic/Targets/LoongArch.h | 2 ++
.../lib/Driver/ToolChains/Arch/LoongArch.cpp | 9 ++++++
clang/test/Driver/loongarch-march.c | 8 ++---
clang/test/Driver/loongarch-mdiv32.c | 30 +++++++++++++++++++
clang/test/Preprocessor/init-loongarch.c | 25 +++++++++++-----
.../TargetParser/LoongArchTargetParser.def | 3 +-
.../llvm/TargetParser/LoongArchTargetParser.h | 3 ++
llvm/lib/Target/LoongArch/LoongArch.td | 9 +++++-
.../LoongArch/LoongArchISelLowering.cpp | 16 ++++++++--
.../Target/LoongArch/LoongArchISelLowering.h | 2 ++
.../Target/LoongArch/LoongArchInstrInfo.td | 4 +++
.../TargetParser/LoongArchTargetParser.cpp | 1 +
.../ir-instruction/sdiv-udiv-srem-urem.ll | 24 +++++++--------
15 files changed, 118 insertions(+), 29 deletions(-)
create mode 100644 clang/test/Driver/loongarch-mdiv32.c
diff --git a/clang/include/clang/Driver/Options.td b/clang/include/clang/Driver/Options.td
index d7230dd7272fd6..e3358216b3db7e 100644
--- a/clang/include/clang/Driver/Options.td
+++ b/clang/include/clang/Driver/Options.td
@@ -5416,6 +5416,10 @@ def mlam_bh : Flag<["-"], "mlam-bh">, Group<m_loongarch_Features_Group>,
HelpText<"Enable amswap[_db].{b/h} and amadd[_db].{b/h}">;
def mno_lam_bh : Flag<["-"], "mno-lam-bh">, Group<m_loongarch_Features_Group>,
HelpText<"Disable amswap[_db].{b/h} and amadd[_db].{b/h}">;
+def mdiv32 : Flag<["-"], "mdiv32">, Group<m_loongarch_Features_Group>,
+ HelpText<"Use div.w[u] and mod.w[u] instructions with input not sign-extended.">;
+def mno_div32 : Flag<["-"], "mno-div32">, Group<m_loongarch_Features_Group>,
+ HelpText<"Do not use div.w[u] and mod.w[u] instructions with input not sign-extended.">;
def mannotate_tablejump : Flag<["-"], "mannotate-tablejump">, Group<m_loongarch_Features_Group>,
HelpText<"Enable annotate table jump instruction to correlate it with the jump table.">;
def mno_annotate_tablejump : Flag<["-"], "mno-annotate-tablejump">, Group<m_loongarch_Features_Group>,
diff --git a/clang/lib/Basic/Targets/LoongArch.cpp b/clang/lib/Basic/Targets/LoongArch.cpp
index 07b22b35f603ce..2124d8e32ff607 100644
--- a/clang/lib/Basic/Targets/LoongArch.cpp
+++ b/clang/lib/Basic/Targets/LoongArch.cpp
@@ -205,7 +205,7 @@ void LoongArchTargetInfo::getTargetDefines(const LangOptions &Opts,
// TODO: As more features of the V1.1 ISA are supported, a unified "v1.1"
// arch feature set will be used to include all sub-features belonging to
// the V1.1 ISA version.
- if (HasFeatureFrecipe && HasFeatureLAM_BH)
+ if (HasFeatureFrecipe && HasFeatureLAM_BH && HasFeatureDiv32)
Builder.defineMacro("__loongarch_arch",
Twine('"') + "la64v1.1" + Twine('"'));
else
@@ -239,6 +239,9 @@ void LoongArchTargetInfo::getTargetDefines(const LangOptions &Opts,
if (HasFeatureLAM_BH)
Builder.defineMacro("__loongarch_lam_bh", Twine(1));
+ if (HasFeatureDiv32)
+ Builder.defineMacro("__loongarch_div32", Twine(1));
+
StringRef ABI = getABI();
if (ABI == "lp64d" || ABI == "lp64f" || ABI == "lp64s")
Builder.defineMacro("__loongarch_lp64");
@@ -317,6 +320,8 @@ bool LoongArchTargetInfo::handleTargetFeatures(
HasFeatureFrecipe = true;
else if (Feature == "+lam-bh")
HasFeatureLAM_BH = true;
+ else if (Feature == "+div32")
+ HasFeatureDiv32 = true;
}
return true;
}
diff --git a/clang/lib/Basic/Targets/LoongArch.h b/clang/lib/Basic/Targets/LoongArch.h
index 3585e9f7968b4b..16ffb0eddf50da 100644
--- a/clang/lib/Basic/Targets/LoongArch.h
+++ b/clang/lib/Basic/Targets/LoongArch.h
@@ -31,6 +31,7 @@ class LLVM_LIBRARY_VISIBILITY LoongArchTargetInfo : public TargetInfo {
bool HasFeatureLASX;
bool HasFeatureFrecipe;
bool HasFeatureLAM_BH;
+ bool HasFeatureDiv32;
public:
LoongArchTargetInfo(const llvm::Triple &Triple, const TargetOptions &)
@@ -41,6 +42,7 @@ class LLVM_LIBRARY_VISIBILITY LoongArchTargetInfo : public TargetInfo {
HasFeatureLASX = false;
HasFeatureFrecipe = false;
HasFeatureLAM_BH = false;
+ HasFeatureDiv32 = false;
LongDoubleWidth = 128;
LongDoubleAlign = 128;
LongDoubleFormat = &llvm::APFloat::IEEEquad();
diff --git a/clang/lib/Driver/ToolChains/Arch/LoongArch.cpp b/clang/lib/Driver/ToolChains/Arch/LoongArch.cpp
index 987db4638fca88..3e85d4ad076ea5 100644
--- a/clang/lib/Driver/ToolChains/Arch/LoongArch.cpp
+++ b/clang/lib/Driver/ToolChains/Arch/LoongArch.cpp
@@ -274,6 +274,15 @@ void loongarch::getLoongArchTargetFeatures(const Driver &D,
else
Features.push_back("-lam-bh");
}
+
+ // Select div32 feature determined by -m[no-]div32.
+ if (const Arg *A =
+ Args.getLastArg(options::OPT_mdiv32, options::OPT_mno_div32)) {
+ if (A->getOption().matches(options::OPT_mdiv32))
+ Features.push_back("+div32");
+ else
+ Features.push_back("-div32");
+ }
}
std::string loongarch::postProcessTargetCPUString(const std::string &CPU,
diff --git a/clang/test/Driver/loongarch-march.c b/clang/test/Driver/loongarch-march.c
index d4cd5b07ae905f..c2b82bb71bec74 100644
--- a/clang/test/Driver/loongarch-march.c
+++ b/clang/test/Driver/loongarch-march.c
@@ -39,21 +39,21 @@
// CC1-LA64V1P1: "-target-cpu" "loongarch64"
// CC1-LA64V1P1-NOT: "-target-feature"
-// CC1-LA64V1P1: "-target-feature" "+64bit" "-target-feature" "+d" "-target-feature" "+lsx" "-target-feature" "+ual" "-target-feature" "+frecipe" "-target-feature" "+lam-bh"
+// CC1-LA64V1P1: "-target-feature" "+64bit" "-target-feature" "+d" "-target-feature" "+lsx" "-target-feature" "+ual" "-target-feature" "+frecipe" "-target-feature" "+lam-bh" "-target-feature" "+div32"
// CC1-LA64V1P1-NOT: "-target-feature"
// CC1-LA64V1P1: "-target-abi" "lp64d"
// CC1-LA664: "-target-cpu" "la664"
// CC1-LA664-NOT: "-target-feature"
-// CC1-LA664: "-target-feature" "+64bit" "-target-feature" "+f" "-target-feature" "+d" "-target-feature" "+lsx" "-target-feature" "+lasx" "-target-feature" "+ual" "-target-feature" "+frecipe" "-target-feature" "+lam-bh"
+// CC1-LA664: "-target-feature" "+64bit" "-target-feature" "+f" "-target-feature" "+d" "-target-feature" "+lsx" "-target-feature" "+lasx" "-target-feature" "+ual" "-target-feature" "+frecipe" "-target-feature" "+lam-bh" "-target-feature" "+div32"
// CC1-LA664-NOT: "-target-feature"
// CC1-LA664: "-target-abi" "lp64d"
// IR-LOONGARCH64: attributes #[[#]] ={{.*}}"target-cpu"="loongarch64" {{.*}}"target-features"="+64bit,+d,+f,+ual"
// IR-LA464: attributes #[[#]] ={{.*}}"target-cpu"="la464" {{.*}}"target-features"="+64bit,+d,+f,+lasx,+lsx,+ual"
// IR-LA64V1P0: attributes #[[#]] ={{.*}}"target-cpu"="loongarch64" {{.*}}"target-features"="+64bit,+d,+lsx,+ual"
-// IR-LA64V1P1: attributes #[[#]] ={{.*}}"target-cpu"="loongarch64" {{.*}}"target-features"="+64bit,+d,+frecipe,+lam-bh,+lsx,+ual"
-// IR-LA664: attributes #[[#]] ={{.*}}"target-cpu"="la664" {{.*}}"target-features"="+64bit,+d,+f,+frecipe,+lam-bh,+lasx,+lsx,+ual"
+// IR-LA64V1P1: attributes #[[#]] ={{.*}}"target-cpu"="loongarch64" {{.*}}"target-features"="+64bit,+d,+div32,+frecipe,+lam-bh,+lsx,+ual"
+// IR-LA664: attributes #[[#]] ={{.*}}"target-cpu"="la664" {{.*}}"target-features"="+64bit,+d,+div32,+f,+frecipe,+lam-bh,+lasx,+lsx,+ual"
int foo(void) {
return 3;
diff --git a/clang/test/Driver/loongarch-mdiv32.c b/clang/test/Driver/loongarch-mdiv32.c
new file mode 100644
index 00000000000000..cf774b3818c55d
--- /dev/null
+++ b/clang/test/Driver/loongarch-mdiv32.c
@@ -0,0 +1,30 @@
+/// Test -m[no]div32 options.
+
+// RUN: %clang --target=loongarch64 -mdiv32 -fsyntax-only %s -### 2>&1 | \
+// RUN: FileCheck %s --check-prefix=CC1-DIV32
+// RUN: %clang --target=loongarch64 -mno-div32 -fsyntax-only %s -### 2>&1 | \
+// RUN: FileCheck %s --check-prefix=CC1-NO-DIV32
+// RUN: %clang --target=loongarch64 -mno-div32 -mdiv32 -fsyntax-only %s -### 2>&1 | \
+// RUN: FileCheck %s --check-prefix=CC1-DIV32
+// RUN: %clang --target=loongarch64 -mdiv32 -mno-div32 -fsyntax-only %s -### 2>&1 | \
+// RUN: FileCheck %s --check-prefix=CC1-NO-DIV32
+
+// RUN: %clang --target=loongarch64 -mdiv32 -S -emit-llvm %s -o - | \
+// RUN: FileCheck %s --check-prefix=IR-DIV32
+// RUN: %clang --target=loongarch64 -mno-div32 -S -emit-llvm %s -o - | \
+// RUN: FileCheck %s --check-prefix=IR-NO-DIV32
+// RUN: %clang --target=loongarch64 -mno-div32 -mdiv32 -S -emit-llvm %s -o - | \
+// RUN: FileCheck %s --check-prefix=IR-DIV32
+// RUN: %clang --target=loongarch64 -mdiv32 -mno-div32 -S -emit-llvm %s -o - | \
+// RUN: FileCheck %s --check-prefix=IR-NO-DIV32
+
+
+// CC1-DIV32: "-target-feature" "+div32"
+// CC1-NO-DIV32: "-target-feature" "-div32"
+
+// IR-DIV32: attributes #[[#]] ={{.*}}"target-features"="{{(.*,)?}}+div32{{(,.*)?}}"
+// IR-NO-DIV32: attributes #[[#]] ={{.*}}"target-features"="{{(.*,)?}}-div32{{(,.*)?}}"
+
+int foo(void) {
+ return 42;
+}
diff --git a/clang/test/Preprocessor/init-loongarch.c b/clang/test/Preprocessor/init-loongarch.c
index 8019292e0f10e0..8a3d3d5b023de7 100644
--- a/clang/test/Preprocessor/init-loongarch.c
+++ b/clang/test/Preprocessor/init-loongarch.c
@@ -798,7 +798,7 @@
// LA64-FPU0-LP64S-NOT: #define __loongarch_single_float
// LA64-FPU0-LP64S: #define __loongarch_soft_float 1
-/// Check __loongarch_arch{_tune/_frecipe/_lam_bh}.
+/// Check __loongarch_arch{_tune/_frecipe/_lam_bh/_div32}.
// RUN: %clang --target=loongarch64 -x c -E -dM %s -o - | \
// RUN: FileCheck --match-full-lines --check-prefix=ARCH-TUNE -DARCH=la64v1.0 -DTUNE=loongarch64 %s
@@ -823,11 +823,11 @@
// RUN: %clang --target=loongarch64 -x c -E -dM %s -o - -march=loongarch64 -Xclang -target-feature -Xclang +lsx | \
// RUN: FileCheck --match-full-lines --check-prefix=ARCH-TUNE -DARCH=la64v1.0 -DTUNE=loongarch64 %s
// RUN: %clang --target=loongarch64 -x c -E -dM %s -o - -march=la64v1.1 | \
-// RUN: FileCheck --match-full-lines --check-prefixes=ARCH-TUNE,FRECIPE,LAM-BH -DARCH=la64v1.1 -DTUNE=loongarch64 %s
+// RUN: FileCheck --match-full-lines --check-prefixes=ARCH-TUNE,FRECIPE,LAM-BH,DIV32 -DARCH=la64v1.1 -DTUNE=loongarch64 %s
// RUN: %clang --target=loongarch64 -x c -E -dM %s -o - -march=la64v1.1 -Xclang -target-feature -Xclang -frecipe | \
-// RUN: FileCheck --match-full-lines --check-prefixes=ARCH-TUNE,LAM-BH -DARCH=la64v1.0 -DTUNE=loongarch64 %s
+// RUN: FileCheck --match-full-lines --check-prefixes=ARCH-TUNE,LAM-BH,DIV32 -DARCH=la64v1.0 -DTUNE=loongarch64 %s
// RUN: %clang --target=loongarch64 -x c -E -dM %s -o - -march=la64v1.1 -Xclang -target-feature -Xclang -lsx | \
-// RUN: FileCheck --match-full-lines --check-prefixes=ARCH-TUNE,FRECIPE,LAM-BH -DARCH=loongarch64 -DTUNE=loongarch64 %s
+// RUN: FileCheck --match-full-lines --check-prefixes=ARCH-TUNE,FRECIPE,LAM-BH,DIV32 -DARCH=loongarch64 -DTUNE=loongarch64 %s
// RUN: %clang --target=loongarch64 -x c -E -dM %s -o - -march=loongarch64 -Xclang -target-feature -Xclang +frecipe | \
// RUN: FileCheck --match-full-lines --check-prefixes=ARCH-TUNE,FRECIPE -DARCH=loongarch64 -DTUNE=loongarch64 %s
// RUN: %clang --target=loongarch64 -x c -E -dM %s -o - -march=loongarch64 -Xclang -target-feature -Xclang +lsx -Xclang -target-feature -Xclang +frecipe | \
@@ -835,23 +835,32 @@
// RUN: %clang --target=loongarch64 -x c -E -dM %s -o - -march=la64v1.0 -Xclang -target-feature -Xclang +lam-bh | \
// RUN: FileCheck --match-full-lines --check-prefixes=ARCH-TUNE,LAM-BH -DARCH=la64v1.0 -DTUNE=loongarch64 %s
// RUN: %clang --target=loongarch64 -x c -E -dM %s -o - -march=la64v1.1 -Xclang -target-feature -Xclang -lam-bh | \
-// RUN: FileCheck --match-full-lines --check-prefixes=ARCH-TUNE,FRECIPE -DARCH=la64v1.0 -DTUNE=loongarch64 %s
+// RUN: FileCheck --match-full-lines --check-prefixes=ARCH-TUNE,FRECIPE,DIV32 -DARCH=la64v1.0 -DTUNE=loongarch64 %s
// RUN: %clang --target=loongarch64 -x c -E -dM %s -o - -march=loongarch64 -Xclang -target-feature -Xclang +lam-bh | \
// RUN: FileCheck --match-full-lines --check-prefixes=ARCH-TUNE,LAM-BH -DARCH=loongarch64 -DTUNE=loongarch64 %s
// RUN: %clang --target=loongarch64 -x c -E -dM %s -o - -march=loongarch64 -Xclang -target-feature -Xclang +lsx -Xclang -target-feature -Xclang +lam-bh | \
// RUN: FileCheck --match-full-lines --check-prefixes=ARCH-TUNE,LAM-BH -DARCH=la64v1.0 -DTUNE=loongarch64 %s
-// RUN: %clang --target=loongarch64 -x c -E -dM %s -o - -march=la64v1.0 -Xclang -target-feature -Xclang +frecipe -Xclang -target-feature -Xclang +lam-bh | \
+// RUN: %clang --target=loongarch64 -x c -E -dM %s -o - -march=la64v1.0 -Xclang -target-feature -Xclang +div32 | \
+// RUN: FileCheck --match-full-lines --check-prefixes=ARCH-TUNE,DIV32 -DARCH=la64v1.0 -DTUNE=loongarch64 %s
+// RUN: %clang --target=loongarch64 -x c -E -dM %s -o - -march=la64v1.1 -Xclang -target-feature -Xclang -div32| \
+// RUN: FileCheck --match-full-lines --check-prefixes=ARCH-TUNE,FRECIPE,LAM-BH -DARCH=la64v1.0 -DTUNE=loongarch64 %s
+// RUN: %clang --target=loongarch64 -x c -E -dM %s -o - -march=loongarch64 -Xclang -target-feature -Xclang +div32 | \
+// RUN: FileCheck --match-full-lines --check-prefixes=ARCH-TUNE,DIV32 -DARCH=loongarch64 -DTUNE=loongarch64 %s
+// RUN: %clang --target=loongarch64 -x c -E -dM %s -o - -march=loongarch64 -Xclang -target-feature -Xclang +lsx -Xclang -target-feature -Xclang +div32 | \
+// RUN: FileCheck --match-full-lines --check-prefixes=ARCH-TUNE,DIV32 -DARCH=la64v1.0 -DTUNE=loongarch64 %s
+// RUN: %clang --target=loongarch64 -x c -E -dM %s -o - -march=la64v1.0 -Xclang -target-feature -Xclang +frecipe -Xclang -target-feature -Xclang +lam-bh -Xclang -target-feature -Xclang +div32 | \
// RUN: FileCheck --match-full-lines --check-prefixes=ARCH-TUNE -DARCH=la64v1.1 -DTUNE=loongarch64 %s
// RUN: %clang --target=loongarch64 -x c -E -dM %s -o - -march=la664 | \
-// RUN: FileCheck --match-full-lines --check-prefixes=ARCH-TUNE,FRECIPE,LAM-BH -DARCH=la664 -DTUNE=la664 %s
+// RUN: FileCheck --match-full-lines --check-prefixes=ARCH-TUNE,FRECIPE,LAM-BH,DIV32 -DARCH=la664 -DTUNE=la664 %s
// RUN: %clang --target=loongarch64 -x c -E -dM %s -o - -mtune=la664 | \
// RUN: FileCheck --match-full-lines --check-prefix=ARCH-TUNE -DARCH=la64v1.0 -DTUNE=la664 %s
// RUN: %clang --target=loongarch64 -x c -E -dM %s -o - -march=loongarch64 -mtune=la664 | \
// RUN: FileCheck --match-full-lines --check-prefix=ARCH-TUNE -DARCH=loongarch64 -DTUNE=la664 %s
// RUN: %clang --target=loongarch64 -x c -E -dM %s -o - -march=la664 -mtune=loongarch64 | \
-// RUN: FileCheck --match-full-lines --check-prefixes=ARCH-TUNE,FRECIPE,LAM-BH -DARCH=la664 -DTUNE=loongarch64 %s
+// RUN: FileCheck --match-full-lines --check-prefixes=ARCH-TUNE,FRECIPE,LAM-BH,DIV32 -DARCH=la664 -DTUNE=loongarch64 %s
// ARCH-TUNE: #define __loongarch_arch "[[ARCH]]"
+// DIV32: #define __loongarch_div32 1
// FRECIPE: #define __loongarch_frecipe 1
// LAM-BH: #define __loongarch_lam_bh 1
// ARCH-TUNE: #define __loongarch_tune "[[TUNE]]"
diff --git a/llvm/include/llvm/TargetParser/LoongArchTargetParser.def b/llvm/include/llvm/TargetParser/LoongArchTargetParser.def
index 6cd2018b7b59cb..aecab7263c6cbf 100644
--- a/llvm/include/llvm/TargetParser/LoongArchTargetParser.def
+++ b/llvm/include/llvm/TargetParser/LoongArchTargetParser.def
@@ -12,6 +12,7 @@ LOONGARCH_FEATURE("+lvz", FK_LVZ)
LOONGARCH_FEATURE("+ual", FK_UAL)
LOONGARCH_FEATURE("+frecipe", FK_FRECIPE)
LOONGARCH_FEATURE("+lam-bh", FK_LAM_BH)
+LOONGARCH_FEATURE("+div32", FK_DIV32)
#undef LOONGARCH_FEATURE
@@ -21,6 +22,6 @@ LOONGARCH_FEATURE("+lam-bh", FK_LAM_BH)
LOONGARCH_ARCH("loongarch64", AK_LOONGARCH64, FK_64BIT | FK_FP32 | FK_FP64 | FK_UAL)
LOONGARCH_ARCH("la464", AK_LA464, FK_64BIT | FK_FP32 | FK_FP64 | FK_LSX | FK_LASX | FK_UAL)
-LOONGARCH_ARCH("la664", AK_LA664, FK_64BIT | FK_FP32 | FK_FP64 | FK_LSX | FK_LASX | FK_UAL | FK_FRECIPE | FK_LAM_BH)
+LOONGARCH_ARCH("la664", AK_LA664, FK_64BIT | FK_FP32 | FK_FP64 | FK_LSX | FK_LASX | FK_UAL | FK_FRECIPE | FK_LAM_BH | FK_DIV32)
#undef LOONGARCH_ARCH
diff --git a/llvm/include/llvm/TargetParser/LoongArchTargetParser.h b/llvm/include/llvm/TargetParser/LoongArchTargetParser.h
index b5be03b1b67fbb..a0e21e4484ce39 100644
--- a/llvm/include/llvm/TargetParser/LoongArchTargetParser.h
+++ b/llvm/include/llvm/TargetParser/LoongArchTargetParser.h
@@ -53,6 +53,9 @@ enum FeatureKind : uint32_t {
// Atomic memory swap and add instructions for byte and half word are
// available.
FK_LAM_BH = 1 << 10,
+
+ // Assume div.w[u] and mod.w[u] can handle inputs that are not sign-extended.
+ FK_DIV32 = 1 << 13,
};
struct FeatureInfo {
diff --git a/llvm/lib/Target/LoongArch/LoongArch.td b/llvm/lib/Target/LoongArch/LoongArch.td
index ecd00cd6d5d619..cdab5a736bd693 100644
--- a/llvm/lib/Target/LoongArch/LoongArch.td
+++ b/llvm/lib/Target/LoongArch/LoongArch.td
@@ -118,6 +118,12 @@ def FeatureLAM_BH
"Support amswap[_db].{b/h} and amadd[_db].{b/h} instructions.">;
def HasLAM_BH : Predicate<"Subtarget->hasLAM_BH()">;
+// Assume div.w[u] and mod.w[u] can handle inputs that are not sign-extended.
+def FeatureDiv32
+ : SubtargetFeature<"div32", "HasDiv32", "true",
+ "Support div.w[u] and mod.w[u] can handle inputs that are not sign-extended">;
+def HasDiv32 : Predicate<"Subtarget->hasDiv32()">;
+
def TunePreferWInst
: SubtargetFeature<"prefer-w-inst", "PreferWInst", "true",
"Prefer instructions with W suffix">;
@@ -160,7 +166,8 @@ def : ProcessorModel<"la664", NoSchedModel, [Feature64Bit,
FeatureExtLVZ,
FeatureExtLBT,
FeatureFrecipe,
- FeatureLAM_BH]>;
+ FeatureLAM_BH,
+ FeatureDiv32]>;
//===----------------------------------------------------------------------===//
// Define the LoongArch target.
diff --git a/llvm/lib/Target/LoongArch/LoongArchISelLowering.cpp b/llvm/lib/Target/LoongArch/LoongArchISelLowering.cpp
index 5c567ed4a6f724..9fb59a11bb9caf 100644
--- a/llvm/lib/Target/LoongArch/LoongArchISelLowering.cpp
+++ b/llvm/lib/Target/LoongArch/LoongArchISelLowering.cpp
@@ -141,7 +141,8 @@ LoongArchTargetLowering::LoongArchTargetLowering(const TargetMachine &TM,
setOperationAction(ISD::BITREVERSE, MVT::i32, Custom);
setOperationAction(ISD::BSWAP, MVT::i32, Custom);
- setOperationAction({ISD::UDIV, ISD::UREM}, MVT::i32, Custom);
+ setOperationAction({ISD::SDIV, ISD::UDIV, ISD::SREM, ISD::UREM}, MVT::i32,
+ Custom);
setOperationAction(ISD::LROUND, MVT::i32, Custom);
}
@@ -2629,8 +2630,12 @@ static LoongArchISD::NodeType getLoongArchWOpcode(unsigned Opcode) {
switch (Opcode) {
default:
llvm_unreachable("Unexpected opcode");
+ case ISD::SDIV:
+ return LoongArchISD::DIV_W;
case ISD::UDIV:
return LoongArchISD::DIV_WU;
+ case ISD::SREM:
+ return LoongArchISD::MOD_W;
case ISD::UREM:
return LoongArchISD::MOD_WU;
case ISD::SHL:
@@ -2827,11 +2832,16 @@ void LoongArchTargetLowering::ReplaceNodeResults(
"Unexpected custom legalisation");
Results.push_back(customLegalizeToWOpWithSExt(N, DAG));
break;
+ case ISD::SDIV:
case ISD::UDIV:
+ case ISD::SREM:
case ISD::UREM:
assert(VT == MVT::i32 && Subtarget.is64Bit() &&
"Unexpected custom legalisation");
- Results.push_back(customLegalizeToWOp(N, DAG, 2, ISD::SIGN_EXTEND));
+ Results.push_back(customLegalizeToWOp(N, DAG, 2,
+ Subtarget.hasDiv32() && VT == MVT::i32
+ ? ISD::ANY_EXTEND
+ : ISD::SIGN_EXTEND));
break;
case ISD::SHL:
case ISD::SRA:
@@ -4667,7 +4677,9 @@ const char *LoongArchTargetLowering::getTargetNodeName(unsigned Opcode) const {
NODE_NAME_CASE(BITREV_W)
NODE_NAME_CASE(ROTR_W)
NODE_NAME_CASE(ROTL_W)
+ NODE_NAME_CASE(DIV_W)
NODE_NAME_CASE(DIV_WU)
+ NODE_NAME_CASE(MOD_W)
NODE_NAME_CASE(MOD_WU)
NODE_NAME_CASE(CLZ_W)
NODE_NAME_CASE(CTZ_W)
diff --git a/llvm/lib/Target/LoongArch/LoongArchISelLowering.h b/llvm/lib/Target/LoongArch/LoongArchISelLowering.h
index 1aa686695b49b8..5a47dfb257175f 100644
--- a/llvm/lib/Target/LoongArch/LoongArchISelLowering.h
+++ b/llvm/lib/Target/LoongArch/LoongArchISelLowering.h
@@ -44,6 +44,8 @@ enum NodeType : unsigned {
ROTR_W,
// unsigned 32-bit integer division
+ DIV_W,
+ MOD_W,
DIV_WU,
MOD_WU,
diff --git a/llvm/lib/Target/LoongArch/LoongArchInstrInfo.td b/llvm/lib/Target/LoongArch/LoongArchInstrInfo.td
index 3de20d6e599dbf..1a7165015a86d9 100644
--- a/llvm/lib/Target/LoongArch/LoongArchInstrInfo.td
+++ b/llvm/lib/Target/LoongArch/LoongArchInstrInfo.td
@@ -85,7 +85,9 @@ def loongarch_sll_w : SDNode<"LoongArchISD::SLL_W", SDT_LoongArchIntBinOpW>;
def loongarch_sra_w : SDNode<"LoongArchISD::SRA_W", SDT_LoongArchIntBinOpW>;
def loongarch_srl_w : SDNode<"LoongArchISD::SRL_W", SDT_LoongArchIntBinOpW>;
def loongarch_rotr_w : SDNode<"LoongArchISD::ROTR_W", SDT_LoongArchIntBinOpW>;
+def loongarch_div_w : SDNode<"LoongArchISD::DIV_W", SDT_LoongArchIntBinOpW>;
def loongarch_div_wu : SDNode<"LoongArchISD::DIV_WU", SDT_LoongArchIntBinOpW>;
+def loongarch_mod_w : SDNode<"LoongArchISD::MOD_W", SDT_LoongArchIntBinOpW>;
def loongarch_mod_wu : SDNode<"LoongArchISD::MOD_WU", SDT_LoongArchIntBinOpW>;
def loongarch_crc_w_b_w
: SDNode<"LoongArchISD::CRC_W_B_W", SDT_LoongArchIntBinOpW, [SDNPHasChain]>;
@@ -1144,10 +1146,12 @@ def : PatGprGpr<sub, SUB_D>;
def : PatGprGpr<sdiv, DIV_D>;
def : PatGprGpr_32<sdiv, DIV_W>;
def : PatGprGpr<udiv, DIV_DU>;
+def : PatGprGpr<loongarch_div_w, DIV_W>;
def : PatGprGpr<loongarch_div_wu, DIV_WU>;
def : PatGprGpr<srem, MOD_D>;
def : PatGprGpr_32<srem, MOD_W>;
def : PatGprGpr<urem, MOD_DU>;
+def : PatGprGpr<loongarch_mod_w, MOD_W>;
def : PatGprGpr<loongarch_mod_wu, MOD_WU>;
def : PatGprGpr<shiftop<rotr>, ROTR_D>;
def : PatGprGpr<shiftopw<loongarch_rotr_w>, ROTR_W>;
diff --git a/llvm/lib/TargetParser/LoongArchTargetParser.cpp b/llvm/lib/TargetParser/LoongArchTargetParser.cpp
index 27e3b5683c5a6e..930a6d1c35ddd2 100644
--- a/llvm/lib/TargetParser/LoongArchTargetParser.cpp
+++ b/llvm/lib/TargetParser/LoongArchTargetParser.cpp
@@ -53,6 +53,7 @@ bool LoongArch::getArchFeatures(StringRef Arch,
if (Arch == "la64v1.1") {
Features.push_back("+frecipe");
Features.push_back("+lam-bh");
+ Features.push_back("+div32");
}
return true;
}
diff --git a/llvm/test/CodeGen/LoongArch/ir-instruction/sdiv-udiv-srem-urem.ll b/llvm/test/CodeGen/LoongArch/ir-instruction/sdiv-udiv-srem-urem.ll
index c5af79157eaadc..99824f6d7718e7 100644
--- a/llvm/test/CodeGen/LoongArch/ir-instruction/sdiv-udiv-srem-urem.ll
+++ b/llvm/test/CodeGen/LoongArch/ir-instruction/sdiv-udiv-srem-urem.ll
@@ -121,7 +121,7 @@ define i32 @sdiv_i32(i32 %a, i32 %b) {
; LA64: # %bb.0: # %entry
; LA64-NEXT: addi.w $a1, $a1, 0
; LA64-NEXT: addi.w $a0, $a0, 0
-; LA64-NEXT: div.d $a0, $a0, $a1
+; LA64-NEXT: div.w $a0, $a0, $a1
; LA64-NEXT: ret
;
; LA32-TRAP-LABEL: sdiv_i32:
@@ -137,7 +137,7 @@ define i32 @sdiv_i32(i32 %a, i32 %b) {
; LA64-TRAP: # %bb.0: # %entry
; LA64-TRAP-NEXT: addi.w $a1, $a1, 0
; LA64-TRAP-NEXT: addi.w $a0, $a0, 0
-; LA64-TRAP-NEXT: div.d $a0, $a0, $a1
+; LA64-TRAP-NEXT: div.w $a0, $a0, $a1
; LA64-TRAP-NEXT: bnez $a1, .LBB3_2
; LA64-TRAP-NEXT: # %bb.1: # %entry
; LA64-TRAP-NEXT: break 7
@@ -156,7 +156,7 @@ define i32 @sdiv_ui32_si32_si32(i32 signext %a, i32 signext %b) {
;
; LA64-LABEL: sdiv_ui32_si32_si32:
; LA64: # %bb.0: # %entry
-; LA64-NEXT: div.d $a0, $a0, $a1
+; LA64-NEXT: div.w $a0, $a0, $a1
; LA64-NEXT: ret
;
; LA32-TRAP-LABEL: sdiv_ui32_si32_si32:
@@ -170,7 +170,7 @@ define i32 @sdiv_ui32_si32_si32(i32 signext %a, i32 signext %b) {
;
; LA64-TRAP-LABEL: sdiv_ui32_si32_si32:
; LA64-TRAP: # %bb.0: # %entry
-; LA64-TRAP-NEXT: div.d $a0, $a0, $a1
+; LA64-TRAP-NEXT: div.w $a0, $a0, $a1
; LA64-TRAP-NEXT: bnez $a1, .LBB4_2
; LA64-TRAP-NEXT: # %bb.1: # %entry
; LA64-TRAP-NEXT: break 7
@@ -693,7 +693,7 @@ define i32 @srem_i32(i32 %a, i32 %b) {
; LA64: # %bb.0: # %entry
; LA64-NEXT: addi.w $a1, $a1, 0
; LA64-NEXT: addi.w $a0, $a0, 0
-; LA64-NEXT: mod.d $a0, $a0, $a1
+; LA64-NEXT: mod.w $a0, $a0, $a1
; LA64-NEXT: ret
;
; LA32-TRAP-LABEL: srem_i32:
@@ -709,7 +709,7 @@ define i32 @srem_i32(i32 %a, i32 %b) {
; LA64-TRAP: # %bb.0: # %entry
; LA64-TRAP-NEXT: addi.w $a1, $a1, 0
; LA64-TRAP-NEXT: addi.w $a0, $a0, 0
-; LA64-TRAP-NEXT: mod.d $a0, $a0, $a1
+; LA64-TRAP-NEXT: mod.w $a0, $a0, $a1
; LA64-TRAP-NEXT: bnez $a1, .LBB19_2
; LA64-TRAP-NEXT: # %bb.1: # %entry
; LA64-TRAP-NEXT: break 7
@@ -728,7 +728,7 @@ define i32 @srem_ui32_si32_si32(i32 signext %a, i32 signext %b) {
;
; LA64-LABEL: srem_ui32_si32_si32:
; LA64: # %bb.0: # %entry
-; LA64-NEXT: mod.d $a0, $a0, $a1
+; LA64-NEXT: mod.w $a0, $a0, $a1
; LA64-NEXT: ret
;
; LA32-TRAP-LABEL: srem_ui32_si32_si32:
@@ -742,7 +742,7 @@ define i32 @srem_ui32_si32_si32(i32 signext %a, i32 signext %b) {
;
; LA64-TRAP-LABEL: srem_ui32_si32_si32:
; LA64-TRAP: # %bb.0: # %entry
-; LA64-TRAP-NEXT: mod.d $a0, $a0, $a1
+; LA64-TRAP-NEXT: mod.w $a0, $a0, $a1
; LA64-TRAP-NEXT: bnez $a1, .LBB20_2
; LA64-TRAP-NEXT: # %bb.1: # %entry
; LA64-TRAP-NEXT: break 7
@@ -763,7 +763,7 @@ define signext i32 @srem_si32_ui32_ui32(i32 %a, i32 %b) {
; LA64: # %bb.0: # %entry
; LA64-NEXT: addi.w $a1, $a1, 0
; LA64-NEXT: addi.w $a0, $a0, 0
-; LA64-NEXT: mod.d $a0, $a0, $a1
+; LA64-NEXT: mod.w $a0, $a0, $a1
; LA64-NEXT: ret
;
; LA32-TRAP-LABEL: srem_si32_ui32_ui32:
@@ -779,7 +779,7 @@ define signext i32 @srem_si32_ui32_ui32(i32 %a, i32 %b) {
; LA64-TRAP: # %bb.0: # %entry
; LA64-TRAP-NEXT: addi.w $a1, $a1, 0
; LA64-TRAP-NEXT: addi.w $a0, $a0, 0
-; LA64-TRAP-NEXT: mod.d $a0, $a0, $a1
+; LA64-TRAP-NEXT: mod.w $a0, $a0, $a1
; LA64-TRAP-NEXT: bnez $a1, .LBB21_2
; LA64-TRAP-NEXT: # %bb.1: # %entry
; LA64-TRAP-NEXT: break 7
@@ -798,7 +798,7 @@ define signext i32 @srem_si32_si32_si32(i32 signext %a, i32 signext %b) {
;
; LA64-LABEL: srem_si32_si32_si32:
; LA64: # %bb.0: # %entry
-; LA64-NEXT: mod.d $a0, $a0, $a1
+; LA64-NEXT: mod.w $a0, $a0, $a1
; LA64-NEXT: ret
;
; LA32-TRAP-LABEL: srem_si32_si32_si32:
@@ -812,7 +812,7 @@ define signext i32 @srem_si32_si32_si32(i32 signext %a, i32 signext %b) {
;
; LA64-TRAP-LABEL: srem_si32_si32_si32:
; LA64-TRAP: # %bb.0: # %entry
-; LA64-TRAP-NEXT: mod.d $a0, $a0, $a1
+; LA64-TRAP-NEXT: mod.w $a0, $a0, $a1
; LA64-TRAP-NEXT: bnez $a1, .LBB22_2
; LA64-TRAP-NEXT: # %bb.1: # %entry
; LA64-TRAP-NEXT: break 7
>From cffa8d88a6d36e1aedcb1f60622b7c2d5681b303 Mon Sep 17 00:00:00 2001
From: tangaac <tangyan01 at loongson.cn>
Date: Wed, 20 Nov 2024 14:36:37 +0800
Subject: [PATCH 2/2] add a test
---
.../sdiv-udiv-srem-urem-div32.ll | 75 +++++++++++++++++++
1 file changed, 75 insertions(+)
create mode 100644 llvm/test/CodeGen/LoongArch/ir-instruction/sdiv-udiv-srem-urem-div32.ll
diff --git a/llvm/test/CodeGen/LoongArch/ir-instruction/sdiv-udiv-srem-urem-div32.ll b/llvm/test/CodeGen/LoongArch/ir-instruction/sdiv-udiv-srem-urem-div32.ll
new file mode 100644
index 00000000000000..d22b4e9c30fd61
--- /dev/null
+++ b/llvm/test/CodeGen/LoongArch/ir-instruction/sdiv-udiv-srem-urem-div32.ll
@@ -0,0 +1,75 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc --mtriple=loongarch64 -mattr=+d,-div32 < %s | FileCheck %s --check-prefix=LA64
+; RUN: llc --mtriple=loongarch64 -mattr=+d,+div32 < %s | FileCheck %s --check-prefix=LA64-DIV32
+
+define dso_local noundef signext i32 @divw(i64 noundef %0, i64 noundef %1) local_unnamed_addr #0 {
+; LA64-LABEL: divw:
+; LA64: # %bb.0:
+; LA64-NEXT: addi.w $a1, $a1, 0
+; LA64-NEXT: addi.w $a0, $a0, 0
+; LA64-NEXT: div.w $a0, $a0, $a1
+; LA64-NEXT: ret
+;
+; LA64-DIV32-LABEL: divw:
+; LA64-DIV32: # %bb.0:
+; LA64-DIV32-NEXT: div.w $a0, $a0, $a1
+; LA64-DIV32-NEXT: ret
+ %3 = trunc i64 %0 to i32
+ %4 = trunc i64 %1 to i32
+ %5 = sdiv i32 %3, %4
+ ret i32 %5
+}
+
+define dso_local noundef signext i32 @divwu(i64 noundef %0, i64 noundef %1) local_unnamed_addr #0 {
+; LA64-LABEL: divwu:
+; LA64: # %bb.0:
+; LA64-NEXT: addi.w $a1, $a1, 0
+; LA64-NEXT: addi.w $a0, $a0, 0
+; LA64-NEXT: div.wu $a0, $a0, $a1
+; LA64-NEXT: ret
+;
+; LA64-DIV32-LABEL: divwu:
+; LA64-DIV32: # %bb.0:
+; LA64-DIV32-NEXT: div.wu $a0, $a0, $a1
+; LA64-DIV32-NEXT: ret
+ %3 = trunc i64 %0 to i32
+ %4 = trunc i64 %1 to i32
+ %5 = udiv i32 %3, %4
+ ret i32 %5
+}
+
+define dso_local signext range(i32 -2147483647, -2147483648) i32 @modw(i64 noundef %0, i64 noundef %1) local_unnamed_addr #0 {
+; LA64-LABEL: modw:
+; LA64: # %bb.0:
+; LA64-NEXT: addi.w $a1, $a1, 0
+; LA64-NEXT: addi.w $a0, $a0, 0
+; LA64-NEXT: mod.w $a0, $a0, $a1
+; LA64-NEXT: ret
+;
+; LA64-DIV32-LABEL: modw:
+; LA64-DIV32: # %bb.0:
+; LA64-DIV32-NEXT: mod.w $a0, $a0, $a1
+; LA64-DIV32-NEXT: ret
+ %3 = trunc i64 %0 to i32
+ %4 = trunc i64 %1 to i32
+ %5 = srem i32 %3, %4
+ ret i32 %5
+}
+
+define dso_local signext range(i32 0, -1) i32 @modwu(i64 noundef %0, i64 noundef %1) local_unnamed_addr #0 {
+; LA64-LABEL: modwu:
+; LA64: # %bb.0:
+; LA64-NEXT: addi.w $a1, $a1, 0
+; LA64-NEXT: addi.w $a0, $a0, 0
+; LA64-NEXT: mod.wu $a0, $a0, $a1
+; LA64-NEXT: ret
+;
+; LA64-DIV32-LABEL: modwu:
+; LA64-DIV32: # %bb.0:
+; LA64-DIV32-NEXT: mod.wu $a0, $a0, $a1
+; LA64-DIV32-NEXT: ret
+ %3 = trunc i64 %0 to i32
+ %4 = trunc i64 %1 to i32
+ %5 = urem i32 %3, %4
+ ret i32 %5
+}
More information about the cfe-commits
mailing list