[Flang][AArch64][VecLib] Add libmvec support for Flang/AArch64 (#146453)

`-fveclib=libmvec` for AArch64 (NEON and SVE) in Clang was supported by
#143696. This patch does the same for Flang.

Vector functions defined in `libmvec` are used for the following Fortran
operator and functions currently.

- Power operator (`**`)
- Fortran intrinsic functions listed below for `real(kind=4)` and
`real(kind=8)` (including their coresponding specific intrinsic
functions)
- Fortran intrinsic functions which are expanded using functions listed
below (for example, `sin` for `complex(kind=8)`)

```
sin
tan
cos
asin
acos
atan (both atan(x) and atan(y, x))
atan2
cosh
tanh
asinh
acosh
atanh
erf
erfc
exp
log
log10
```

As with Clang/AArch64, glibc 2.40 or higher is required to use all these
functions.

Author: kawashima-fj

clang/include/clang/Driver/Options.td

@@ -3489,7 +3489,8 @@ def fno_experimental_isel : Flag<["-"], "fno-experimental-isel">, Group<f_clang_
   Alias<fno_global_isel>;
 def fveclib : Joined<["-"], "fveclib=">, Group<f_Group>,
   Visibility<[ClangOption, CC1Option, FlangOption, FC1Option]>,
-    HelpText<"Use the given vector functions library">,
+    HelpText<"Use the given vector functions library.\n"
+             "  Note: -fveclib=libmvec on AArch64 requires GLIBC 2.40 or newer.">,
     HelpTextForVariants<[ClangOption, CC1Option],
       "Use the given vector functions library.\n"
       "  Note: -fveclib={ArmPL,SLEEF,libmvec} implies -fno-math-errno.\n"

clang/lib/Driver/ToolChains/Flang.cpp

@@ -484,11 +484,18 @@ void Flang::addTargetOptions(const ArgList &Args,
           Triple.getArch() != llvm::Triple::x86_64)
         D.Diag(diag::err_drv_unsupported_opt_for_target)
             << Name << Triple.getArchName();
-    } else if (Name == "libmvec" || Name == "AMDLIBM") {
+    } else if (Name == "AMDLIBM") {
       if (Triple.getArch() != llvm::Triple::x86 &&
           Triple.getArch() != llvm::Triple::x86_64)
         D.Diag(diag::err_drv_unsupported_opt_for_target)
             << Name << Triple.getArchName();
+    } else if (Name == "libmvec") {
+      if (Triple.getArch() != llvm::Triple::x86 &&
+          Triple.getArch() != llvm::Triple::x86_64 &&
+          Triple.getArch() != llvm::Triple::aarch64 &&
+          Triple.getArch() != llvm::Triple::aarch64_be)
+        D.Diag(diag::err_drv_unsupported_opt_for_target)
+            << Name << Triple.getArchName();
     } else if (Name == "SLEEF" || Name == "ArmPL") {
       if (Triple.getArch() != llvm::Triple::aarch64 &&
           Triple.getArch() != llvm::Triple::aarch64_be)

flang/docs/ReleaseNotes.md

@@ -34,6 +34,8 @@ page](https://llvm.org/releases/).
 
 * -floop-interchange is now recognized by flang.
 * -floop-interchange is enabled by default at -O2 and above.
+* -fveclib=libmvec is supported for AArch64 (same as Flang/x86 and
+  Clang/AArch64) (requires GLIBC 2.40 or newer)
 
 ## Windows Support
 

flang/test/Driver/fveclib-codegen.f90

@@ -1,6 +1,8 @@
 ! test that -fveclib= is passed to the backend
 ! RUN: %if aarch64-registered-target %{ %flang -S -Ofast -target aarch64-unknown-linux-gnu -fveclib=SLEEF -o - %s | FileCheck %s --check-prefix=SLEEF %}
 ! RUN: %if x86-registered-target %{ %flang -S -Ofast -target x86_64-unknown-linux-gnu -fveclib=libmvec -o - %s | FileCheck %s %}
+! RUN: %if aarch64-registered-target %{ %flang -S -Ofast -target aarch64-unknown-linux-gnu -fveclib=libmvec -march=armv8.2-a+nosve -o - %s | FileCheck %s --check-prefix=LIBMVEC-AARCH64-NEON %}
+! RUN: %if aarch64-registered-target %{ %flang -S -Ofast -target aarch64-unknown-linux-gnu -fveclib=libmvec -march=armv8.2-a+sve -o - %s | FileCheck %s --check-prefix=LIBMVEC-AARCH64-SVE %}
 ! RUN: %if x86-registered-target %{ %flang -S -O3 -ffast-math -target x86_64-unknown-linux-gnu -fveclib=AMDLIBM -o - %s | FileCheck %s --check-prefix=AMDLIBM %}
 ! RUN: %flang -S -Ofast -fveclib=NoLibrary -o - %s | FileCheck %s --check-prefix=NOLIB
 
@@ -11,6 +13,8 @@ subroutine sb(a, b)
 ! check that we used a vectorized call to powf()
 ! CHECK: _ZGVbN4vv_powf
 ! SLEEF: _ZGVnN4vv_powf
+! LIBMVEC-AARCH64-NEON: _ZGVnN4vv_powf
+! LIBMVEC-AARCH64-SVE: _ZGVsMxvv_powf
 ! AMDLIBM: amd_vrs4_powf
 ! NOLIB: powf
     a(i) = a(i) ** b(i)

flang/test/Driver/fveclib.f90

@@ -1,6 +1,7 @@
 ! RUN: %flang -### -c -fveclib=none %s 2>&1 | FileCheck -check-prefix CHECK-NOLIB %s
 ! RUN: %flang -### -c -fveclib=Accelerate %s 2>&1 | FileCheck -check-prefix CHECK-ACCELERATE %s
 ! RUN: %flang -### -c --target=x86_64-unknown-linux-gnu -fveclib=libmvec %s 2>&1 | FileCheck -check-prefix CHECK-libmvec %s
+! RUN: %flang -### -c --target=aarch64-unknown-linux-gnu -fveclib=libmvec %s 2>&1 | FileCheck -check-prefix CHECK-libmvec %s
 ! RUN: %flang -### -c -fveclib=MASSV %s 2>&1 | FileCheck -check-prefix CHECK-MASSV %s
 ! RUN: %flang -### -c -fveclib=Darwin_libsystem_m %s 2>&1 | FileCheck -check-prefix CHECK-DARWIN_LIBSYSTEM_M %s
 ! RUN: %flang -### -c --target=aarch64-none-none -fveclib=SLEEF %s 2>&1 | FileCheck -check-prefix CHECK-SLEEF %s
@@ -23,7 +24,7 @@
 
 ! RUN: not %flang --target=x86-none-none -c -fveclib=SLEEF %s 2>&1 | FileCheck -check-prefix CHECK-ERROR %s
 ! RUN: not %flang --target=x86-none-none -c -fveclib=ArmPL %s 2>&1 | FileCheck -check-prefix CHECK-ERROR %s
-! RUN: not %flang --target=aarch64-none-none -c -fveclib=libmvec %s 2>&1 | FileCheck -check-prefix CHECK-ERROR %s
+! RUN: not %flang --target=riscv64-none-none -c -fveclib=libmvec %s 2>&1 | FileCheck -check-prefix CHECK-ERROR %s
 ! RUN: not %flang --target=aarch64-none-none -c -fveclib=SVML %s 2>&1 | FileCheck -check-prefix CHECK-ERROR %s
 ! RUN: not %flang --target=aarch64-none-none -c -fveclib=AMDLIBM %s 2>&1 | FileCheck -check-prefix CHECK-ERROR %s
 ! CHECK-ERROR: unsupported option {{.*}} for target