[AArch64] Enable libm vectorized functions via SLEEF

[danielkiss]

Summary

It enables trigonometry functions vectorization via SLEEF: http://sleef.org/.

• A new vectorization library enum is added to TargetLibraryInfo.h: SLEEF.
• A new option is added to TargetLibraryInfoImpl - ClVectorLibrary: SLEEF.
• A comprehensive test case is included in this changeset.
• A new vectorization library argument is added to -fveclib: -fveclib=SLEEF.

Trigonometry functions that are vectorized by sleef:
acos
asin
atan
atanh
cos
cosh
exp
exp2
exp10
lgamma
log10
log2
log
sin
sinh
sqrt
tan
tanh
tgamma

Co-authored-by: Stefan Teleman

[danielkiss]

supersedes: D53927 and D53928.

[danielkiss]

ping

[paulwalker-arm]

clang/lib/CodeGen/BackendUtil.cpp

299

What does GNUABI signify? My understanding is the SLEEF functions use the Vector ABI (which is somewhat target neutral?) to construct their name.

Just a thought but to be a bit more target neutral what about splitting TargetLibraryInfoImpl::SLEEF based on vector length. So here we'll have

TLII->addVectorizableFunctionsFromVecLib(TargetLibraryInfoImpl::SLEEF_VF2_...)
TLII->addVectorizableFunctionsFromVecLib(TargetLibraryInfoImpl::SLEEF_VF4_...)

This way there will be one version of TargetLibraryInfo for SLEEF and different targets can pick and choose based on vectorisation factors.

clang/lib/Driver/ToolChains/Clang.cpp

5134–5154

Do tests exist for these diagnostics? If not can you add them.

[danielkiss]

address review comments, added more tests. rebased.

[danielkiss]

clang/lib/CodeGen/BackendUtil.cpp

299

What does GNUABI signify? My understanding is the SLEEF functions use the Vector ABI (which is somewhat target neutral?) to construct their name.

GNUABI comes from the libsleefgnuabi.so. it is compatible with libmvec but has more functions. Normal sleef ABI is different.

I added triplet to addVectorizableFunctionsFromVecLib so vectorisation factors per target then can be handled there without bloating the enum.

[danielkiss]

ping

[duplexsystem]

Is there any chance of enabling this on platforms other than AArch64? Sleef has x86, AArch32, PowerPC64, System/390, CUDA, and WebAssembly support (although I am mostly interested in x86), in addition to AArch64. This makes sleef a very useful for platforms without libmvec (due either to a lack of architecture support or lack of glibc). I understand this MR is likely motivated by a lack of libmvec on anything but x86, but there are use cases on x86 particularly systems using musl libc.

[danielkiss]

In D134719#4048366, @duplexsystem wrote:

Is there any chance of enabling this on platforms other than AArch64? Sleef has x86, AArch32, PowerPC64, System/390, CUDA, and WebAssembly support (although I am mostly interested in x86), in addition to AArch64.

I'll look into adding x86, x86_64, probably in new patch top of this. I would add targets where we have demand.

This makes sleef a very useful for platforms without libmvec (due either to a lack of architecture support or lack of glibc).

Correct, this is the main motivation.

I understand this MR is likely motivated by a lack of libmvec on anything but x86, but there are use cases on x86 particularly systems using musl libc.

Thanks for the use case.

[paulwalker-arm]

clang/lib/CodeGen/BackendUtil.cpp

290–294

NOTE: A following comment might make this one redundant.

Given you emit a diagnostic for -fveclib for currently unsupported targets and addVectorizableFunctionsFromVecLib takes a target triple so that it'll be a NOP for unsupported targets, can this restriction be removed? It just seems like redundant duplication.

299

The target triple doesn't convey things like SVE being available does it? The same goes for other targets I guess in that for x86 does the triple specify the target's vector length?

There's also the question of how the SLEEF library has been built. Can we guarantee the SLEEF library will always match the target the user has chosen. (i.e. just because the user specifies +sve doesn't mean the SLEEF library has functions for the scalable vector types).

Perhaps this is really a toolchain packaging problem but either way it feels like something that must be solved within clang via either a tighter TLI interface and/or a more specific set of -fveclib options?

That's really the crux of the problem. The other -fveclib options has a very specific set of functions they provide whereas SLEEF does not. So perhaps the options should be SLEEF_NEON or SLEEF64, SLEEF128 (not sure if there's a generic way to describe scalable vectors so perhaps we cannot escape SLEEF_SVE?), which might also suggests the parsing for -fveclib requires expanding if for example we want to allow -fveclib= SLEEF64,SLEEF128. NOTE: I can see for MVEC LIBMVEC_X86 exists.

For what it's worth this is why there's the idea to add pragmas to decorate the math function declarations so vector function mappings can be added automatically based on whatever math.h header is included.

[duplexsystem]

In D134719#4056381, @danielkiss wrote:

In D134719#4048366, @duplexsystem wrote:

Is there any chance of enabling this on platforms other than AArch64? Sleef has x86, AArch32, PowerPC64, System/390, CUDA, and WebAssembly support (although I am mostly interested in x86), in addition to AArch64.

I'll look into adding x86, x86_64, probably in new patch top of this. I would add targets where we have demand.

This makes sleef a very useful for platforms without libmvec (due either to a lack of architecture support or lack of glibc).

Correct, this is the main motivation.

I understand this MR is likely motivated by a lack of libmvec on anything but x86, but there are use cases on x86 particularly systems using musl libc.

Thanks for the use case.

Thanks for the willingness to look into x86 support! If you need anything from me (elaborate on use case, testing, etc) let me know.

[danielkiss]

clang/lib/CodeGen/BackendUtil.cpp

290–294

ack

299

Perhaps this is really a toolchain packaging problem but either way it feels like something that must be solved within clang via either a tighter TLI interface and/or a more specific set of -fveclib options?

That's really the crux of the problem. The other -fveclib options has a very specific set of functions they provide whereas SLEEF does not. So perhaps the options should be SLEEF_NEON or SLEEF64, SLEEF128 (not sure if there's a generic way to describe scalable vectors so perhaps we cannot escape SLEEF_SVE?), which might also suggests the parsing for -fveclib requires expanding if for example we want to allow -fveclib= SLEEF64,SLEEF128. NOTE: I can see for MVEC LIBMVEC_X86 exists.

IIRC there is no other platform right now for libmvec beside x86 so LIBMVEC_X86 is what it is, once others are added I'd rename it too just LIBMVEC.

Once SVE is enabled for in Sleef the SVE version of functions are additions to the current set.
Depends on how the sleef library is packed into the toolchain\platform one could add conditional logic for certain platform, version etc based on the triplet. Right now it will be useful to add x86 base versions.
-mveclib_options=<arch_specifics> or similar option could be there to override, drive such a decision.

[paulwalker-arm]

Thanks @danielkiss this all sounds reasonable to me. So other than my comment relating to redundant code in createTLII this patch looks good to me. One extra datapoint is that I'm pretty sure Sleef has supported SVE for a few years now and there are patches in flight to improve LoopVectorize to be able to emit function calls that take a predicate so we're not too far away from having complete support in this regard.

[danielkiss]

clean up createTLII since now fronted checks for the target support.

In D134719#4061906, @paulwalker-arm wrote:

Thanks @danielkiss this all sounds reasonable to me. So other than my comment relating to redundant code in createTLII this patch looks good to me. One extra datapoint is that I'm pretty sure Sleef has supported SVE for a few years now and there are patches in flight to improve LoopVectorize to be able to emit function calls that take a predicate so we're not too far away from having complete support in this regard.

Thanks, Sound good, looking forward to support that too :)

clang/include/clang/Basic/CodeGenOptions.h

public:
   };
 
   enum VectorLibrary {
     NoLibrary,         // Don't use any vector library.
     Accelerate,        // Use the Accelerate framework.
     LIBMVEC,           // GLIBC vector math library.
     MASSV,             // IBM MASS vector library.
     SVML,              // Intel short vector math library.
+    SLEEF,             // SLEEF SIMD Library for Evaluating Elementary Functions.
     Darwin_libsystem_m // Use Darwin's libsytem_m vector functions.
   };
 
   enum ObjCDispatchMethodKind {
     Legacy = 0,
     NonLegacy = 1,
     Mixed = 2
   };

clang/include/clang/Driver/Options.td

 def fno_inline_functions : Flag<["-"], "fno-inline-functions">, Group<f_clang_Group>, Flags<[CC1Option]>;
 def fno_inline : Flag<["-"], "fno-inline">, Group<f_clang_Group>, Flags<[CC1Option]>;
 def fno_global_isel : Flag<["-"], "fno-global-isel">, Group<f_clang_Group>,
   HelpText<"Disables the global instruction selector">;
 def fno_experimental_isel : Flag<["-"], "fno-experimental-isel">, Group<f_clang_Group>,
   Alias<fno_global_isel>;
 def fveclib : Joined<["-"], "fveclib=">, Group<f_Group>, Flags<[CC1Option]>,
     HelpText<"Use the given vector functions library">,
-    Values<"Accelerate,libmvec,MASSV,SVML,Darwin_libsystem_m,none">,
+    Values<"Accelerate,libmvec,MASSV,SVML,SLEEF,Darwin_libsystem_m,none">,
     NormalizedValuesScope<"CodeGenOptions">,
-    NormalizedValues<["Accelerate", "LIBMVEC", "MASSV", "SVML",
+    NormalizedValues<["Accelerate", "LIBMVEC", "MASSV", "SVML", "SLEEF",
                       "Darwin_libsystem_m", "NoLibrary"]>,
     MarshallingInfoEnum<CodeGenOpts<"VecLib">, "NoLibrary">;
 def fno_lax_vector_conversions : Flag<["-"], "fno-lax-vector-conversions">, Group<f_Group>,
   Alias<flax_vector_conversions_EQ>, AliasArgs<["none"]>;
 def fno_implicit_module_maps : Flag <["-"], "fno-implicit-module-maps">, Group<f_Group>,
   Flags<[NoXarchOption]>;
 def fno_module_maps : Flag <["-"], "fno-module-maps">, Alias<fno_implicit_module_maps>;
 def fno_modules_strict_decluse : Flag <["-"], "fno-strict-modules-decluse">, Group<f_Group>,

clang/lib/CodeGen/BackendUtil.cpp

 }
 
 static TargetLibraryInfoImpl *createTLII(llvm::Triple &TargetTriple,
                                          const CodeGenOptions &CodeGenOpts) {
   TargetLibraryInfoImpl *TLII = new TargetLibraryInfoImpl(TargetTriple);
 
   switch (CodeGenOpts.getVecLib()) {
   case CodeGenOptions::Accelerate:
-    TLII->addVectorizableFunctionsFromVecLib(TargetLibraryInfoImpl::Accelerate);
+    TLII->addVectorizableFunctionsFromVecLib(TargetLibraryInfoImpl::Accelerate,
+                                             TargetTriple);
     break;
   case CodeGenOptions::LIBMVEC:
-    switch(TargetTriple.getArch()) {
-      default:
-        break;
-      case llvm::Triple::x86_64:
-        TLII->addVectorizableFunctionsFromVecLib
-                (TargetLibraryInfoImpl::LIBMVEC_X86);
-        break;
-    }
+    TLII->addVectorizableFunctionsFromVecLib(TargetLibraryInfoImpl::LIBMVEC_X86,
+                                             TargetTriple);
     break;
   case CodeGenOptions::MASSV:
-    TLII->addVectorizableFunctionsFromVecLib(TargetLibraryInfoImpl::MASSV);
+    TLII->addVectorizableFunctionsFromVecLib(TargetLibraryInfoImpl::MASSV,
+                                             TargetTriple);
     break;
   case CodeGenOptions::SVML:
-    TLII->addVectorizableFunctionsFromVecLib(TargetLibraryInfoImpl::SVML);
+    TLII->addVectorizableFunctionsFromVecLib(TargetLibraryInfoImpl::SVML,
+                                             TargetTriple);
+    break;
+  case CodeGenOptions::SLEEF:
+    TLII->addVectorizableFunctionsFromVecLib(TargetLibraryInfoImpl::SLEEFGNUABI,
+                                             TargetTriple);
     break;
   case CodeGenOptions::Darwin_libsystem_m:
     TLII->addVectorizableFunctionsFromVecLib(
-        TargetLibraryInfoImpl::DarwinLibSystemM);
+        TargetLibraryInfoImpl::DarwinLibSystemM, TargetTriple);
     break;
   default:
     break;
   }
   return TLII;
 }
 
 static CodeGenOpt::Level getCGOptLevel(const CodeGenOptions &CodeGenOpts) {
   switch (CodeGenOpts.OptimizationLevel) {
   default:
     llvm_unreachable("Invalid optimization level!");
   case 0:

clang/lib/Driver/ToolChains/Clang.cpp

if (Triple.isOSBinFormatELF()) {
     } else
       Model = TC.getThreadModel();
     if (Model != "posix") {
       CmdArgs.push_back("-mthread-model");
       CmdArgs.push_back(Args.MakeArgString(Model));
     }
   }
 
-  Args.AddLastArg(CmdArgs, options::OPT_fveclib);
+  if (Arg *A = Args.getLastArg(options::OPT_fveclib)) {
+    StringRef Name = A->getValue();
+    if (Name == "SVML") {
+      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-X86") {
+      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 == "SLEEF") {
+      if (Triple.getArch() != llvm::Triple::aarch64 &&
+          Triple.getArch() != llvm::Triple::aarch64_be)
+        D.Diag(diag::err_drv_unsupported_opt_for_target)
+            << Name << Triple.getArchName();
+    }
+    A->render(Args, CmdArgs);
+  }
 
   if (Args.hasFlag(options::OPT_fmerge_all_constants,
                    options::OPT_fno_merge_all_constants, false))
     CmdArgs.push_back("-fmerge-all-constants");
 
   Args.addOptOutFlag(CmdArgs, options::OPT_fdelete_null_pointer_checks,
                      options::OPT_fno_delete_null_pointer_checks);
 
   // LLVM Code Generator Options.

clang/test/Driver/autocomplete.c

 // FLTOALL: full
 // FLTOALL-NEXT: thin
 // RUN: %clang --autocomplete=-fveclib= | FileCheck %s -check-prefix=FVECLIBALL
 // FVECLIBALL: Accelerate
 // FVECLIBALL-NEXT: Darwin_libsystem_m
 // FVECLIBALL-NEXT: libmvec
 // FVECLIBALL-NEXT: MASSV
 // FVECLIBALL-NEXT: none
+// FVECLIBALL-NEXT: SLEEF
 // FVECLIBALL-NEXT: SVML
 // RUN: %clang --autocomplete=-fshow-overloads= | FileCheck %s -check-prefix=FSOVERALL
 // FSOVERALL: all
 // FSOVERALL-NEXT: best
 // RUN: %clang --autocomplete=-fvisibility= | FileCheck %s -check-prefix=FVISIBILITYALL
 // FVISIBILITYALL: default
 // FVISIBILITYALL-NEXT: hidden
 // RUN: %clang --autocomplete=-mfloat-abi= | FileCheck %s -check-prefix=MFLOATABIALL

clang/test/Driver/fveclib.c

 // RUN: %clang -### -c -fveclib=none %s 2>&1 | FileCheck -check-prefix CHECK-NOLIB %s
 // RUN: %clang -### -c -fveclib=Accelerate %s 2>&1 | FileCheck -check-prefix CHECK-ACCELERATE %s
 // RUN: %clang -### -c -fveclib=libmvec %s 2>&1 | FileCheck -check-prefix CHECK-libmvec %s
 // RUN: %clang -### -c -fveclib=MASSV %s 2>&1 | FileCheck -check-prefix CHECK-MASSV %s
 // RUN: %clang -### -c -fveclib=Darwin_libsystem_m %s 2>&1 | FileCheck -check-prefix CHECK-DARWIN_LIBSYSTEM_M %s
+// RUN: %clang -### -c --target=aarch64-none-none -fveclib=SLEEF %s 2>&1 | FileCheck -check-prefix CHECK-SLEEF %s
 // RUN: not %clang -c -fveclib=something %s 2>&1 | FileCheck -check-prefix CHECK-INVALID %s
 
 // CHECK-NOLIB: "-fveclib=none"
 // CHECK-ACCELERATE: "-fveclib=Accelerate"
 // CHECK-libmvec: "-fveclib=libmvec"
 // CHECK-MASSV: "-fveclib=MASSV"
 // CHECK-DARWIN_LIBSYSTEM_M: "-fveclib=Darwin_libsystem_m"
+// CHECK-SLEEF: "-fveclib=SLEEF"
 
 // CHECK-INVALID: error: invalid value 'something' in '-fveclib=something'
 
+// RUN: not %clang --target=x86-none-none -c -fveclib=SLEEF %s 2>&1 | FileCheck -check-prefix CHECK-ERROR %s
+// RUN: not %clang --target=aarch64-none-none -c -fveclib=LIBMVEC-X86 %s 2>&1 | FileCheck -check-prefix CHECK-ERROR %s
+// RUN: not %clang --target=aarch64-none-none -c -fveclib=SVML %s 2>&1 | FileCheck -check-prefix CHECK-ERROR %s
+// CHECK-ERROR: unsupported option {{.*}} for target
+
 // RUN: %clang -fveclib=Accelerate %s -target arm64-apple-ios8.0.0 -### 2>&1 | FileCheck --check-prefix=CHECK-LINK %s
 // CHECK-LINK: "-framework" "Accelerate"
 
 // RUN: %clang -fveclib=Accelerate %s -nostdlib -target arm64-apple-ios8.0.0 -### 2>&1 | FileCheck --check-prefix=CHECK-LINK-NOSTDLIB %s
 // CHECK-LINK-NOSTDLIB-NOT: "-framework" "Accelerate"
 
 // RUN: %clang -fveclib=Accelerate %s -nodefaultlibs -target arm64-apple-ios8.0.0 -### 2>&1 | FileCheck --check-prefix=CHECK-LINK-NODEFAULTLIBS %s
 // CHECK-LINK-NODEFAULTLIBS-NOT: "-framework" "Accelerate"

llvm/include/llvm/Analysis/TargetLibraryInfo.h

public:
   /// addVectorizableFunctionsFromVecLib for filling up the tables of
   /// vectorizable functions.
   enum VectorLibrary {
     NoLibrary,        // Don't use any vector library.
     Accelerate,       // Use Accelerate framework.
     DarwinLibSystemM, // Use Darwin's libsystem_m.
     LIBMVEC_X86,      // GLIBC Vector Math library.
     MASSV,            // IBM MASS vector library.
-    SVML              // Intel short vector math library.
+    SVML,             // Intel short vector math library.
+    SLEEFGNUABI       // SLEEF - SIMD Library for Evaluating Elementary Functions.
   };
 
   TargetLibraryInfoImpl();
   explicit TargetLibraryInfoImpl(const Triple &T);
 
   // Provide value semantics.
   TargetLibraryInfoImpl(const TargetLibraryInfoImpl &TLI);
   TargetLibraryInfoImpl(TargetLibraryInfoImpl &&TLI);
public:
   void disableAllFunctions();
 
   /// Add a set of scalar -> vector mappings, queryable via
   /// getVectorizedFunction and getScalarizedFunction.
   void addVectorizableFunctions(ArrayRef<VecDesc> Fns);
 
   /// Calls addVectorizableFunctions with a known preset of functions for the
   /// given vector library.
-  void addVectorizableFunctionsFromVecLib(enum VectorLibrary VecLib);
+  void addVectorizableFunctionsFromVecLib(enum VectorLibrary VecLib,
+                                          const llvm::Triple &TargetTriple);
 
   /// Return true if the function F has a vector equivalent with vectorization
   /// factor VF.
   bool isFunctionVectorizable(StringRef F, const ElementCount &VF) const {
     return !getVectorizedFunction(F, VF).empty();
   }
 
   /// Return true if the function F has a vector equivalent with any

llvm/include/llvm/Analysis/VecFuncs.def

 TLI_DEFINE_VECFUNC("__exp2_finite", "__svml_exp22", FIXED(2))
 TLI_DEFINE_VECFUNC("__exp2_finite", "__svml_exp24", FIXED(4))
 TLI_DEFINE_VECFUNC("__exp2_finite", "__svml_exp28", FIXED(8))
 
 TLI_DEFINE_VECFUNC("__exp2f_finite", "__svml_exp2f4", FIXED(4))
 TLI_DEFINE_VECFUNC("__exp2f_finite", "__svml_exp2f8", FIXED(8))
 TLI_DEFINE_VECFUNC("__exp2f_finite", "__svml_exp2f16", FIXED(16))
 
+#elif defined(TLI_DEFINE_SLEEFGNUABI_VF2_VECFUNCS)
+
+TLI_DEFINE_VECFUNC( "acos", "_ZGVnN2v_acos", FIXED(2))
+TLI_DEFINE_VECFUNC( "llvm.acos.f64", "_ZGVnN2v_acos", FIXED(2))
+
+TLI_DEFINE_VECFUNC( "asin", "_ZGVnN2v_asin", FIXED(2))
+TLI_DEFINE_VECFUNC( "llvm.asin.f64", "_ZGVnN2v_asin", FIXED(2))
+
+TLI_DEFINE_VECFUNC( "atan", "_ZGVnN2v_atan", FIXED(2))
+TLI_DEFINE_VECFUNC( "llvm.atan.f64", "_ZGVnN2v_atan", FIXED(2))
+
+TLI_DEFINE_VECFUNC( "atan2", "_ZGVnN2vv_atan2", FIXED(2))
+TLI_DEFINE_VECFUNC( "llvm.atan2.f64", "_ZGVnN2vv_atan2", FIXED(2))
+TLI_DEFINE_VECFUNC( "llvm.atan2.v2f64", "_ZGVnN2vv_atan2", FIXED(2))
+
+TLI_DEFINE_VECFUNC( "atanh", "_ZGVnN2v_atanh", FIXED(2))
+TLI_DEFINE_VECFUNC( "llvm.atanh.f64", "_ZGVnN2v_atanh", FIXED(2))
+
+TLI_DEFINE_VECFUNC( "cos", "_ZGVnN2v_cos", FIXED(2))
+TLI_DEFINE_VECFUNC( "llvm.cos.f64", "_ZGVnN2v_cos", FIXED(2))
+
+TLI_DEFINE_VECFUNC( "cosh", "_ZGVnN2v_cosh", FIXED(2))
+TLI_DEFINE_VECFUNC( "llvm.cosh.f64", "_ZGVnN2v_cosh", FIXED(2))
+
+TLI_DEFINE_VECFUNC( "exp", "_ZGVnN2v_exp", FIXED(2))
+TLI_DEFINE_VECFUNC( "llvm.exp.f64", "_ZGVnN2v_exp", FIXED(2))
+TLI_DEFINE_VECFUNC( "llvm.exp.v2f64", "_ZGVnN2v_exp", FIXED(2))
+
+TLI_DEFINE_VECFUNC( "exp2", "_ZGVnN2v_exp2", FIXED(2))
+TLI_DEFINE_VECFUNC( "llvm.exp2.f64", "_ZGVnN2v_exp2", FIXED(2))
+TLI_DEFINE_VECFUNC( "llvm.exp2.v2f64", "_ZGVnN2v_exp2", FIXED(2))
+
+TLI_DEFINE_VECFUNC( "exp10", "_ZGVnN2v_exp10", FIXED(2))
+TLI_DEFINE_VECFUNC( "llvm.exp10.f64", "_ZGVnN2v_exp10", FIXED(2))
+TLI_DEFINE_VECFUNC( "llvm.exp10.v2f64", "_ZGVnN2v_exp10", FIXED(2))
+
+TLI_DEFINE_VECFUNC( "lgamma", "_ZGVnN2v_lgamma", FIXED(2))
+TLI_DEFINE_VECFUNC( "llvm.lgamma.f64", "_ZGVnN2v_lgamma", FIXED(2))
+
+TLI_DEFINE_VECFUNC( "log", "_ZGVnN2v_log", FIXED(2))
+TLI_DEFINE_VECFUNC( "llvm.log.f64", "_ZGVnN2v_log", FIXED(2))
+
+TLI_DEFINE_VECFUNC( "log2", "_ZGVnN2v_log2", FIXED(2))
+TLI_DEFINE_VECFUNC( "llvm.log2.f64", "_ZGVnN2v_log2", FIXED(2))
+
+TLI_DEFINE_VECFUNC( "log10", "_ZGVnN2v_log10", FIXED(2))
+TLI_DEFINE_VECFUNC( "llvm.log10.f64", "_ZGVnN2v_log10", FIXED(2))
+
+TLI_DEFINE_VECFUNC( "pow", "_ZGVnN2vv_pow", FIXED(2))
+TLI_DEFINE_VECFUNC( "llvm.pow.f64", "_ZGVnN2vv_pow", FIXED(2))
+TLI_DEFINE_VECFUNC( "llvm.pow.v2f64", "_ZGVnN2vv_pow", FIXED(2))
+
+TLI_DEFINE_VECFUNC( "sin", "_ZGVnN2v_sin", FIXED(2))
+TLI_DEFINE_VECFUNC( "llvm.sin.f64", "_ZGVnN2v_sin", FIXED(2))
+
+TLI_DEFINE_VECFUNC( "sinh", "_ZGVnN2v_sinh", FIXED(2))
+TLI_DEFINE_VECFUNC( "llvm.sinh.f64", "_ZGVnN2v_sinh", FIXED(2))
+
+TLI_DEFINE_VECFUNC( "sqrt", "_ZGVnN2v_sqrt", FIXED(2))
+TLI_DEFINE_VECFUNC( "llvm.sqrt.f64", "_ZGVnN2v_sqrt", FIXED(2))
+
+TLI_DEFINE_VECFUNC( "tan", "_ZGVnN2v_tan", FIXED(2))
+TLI_DEFINE_VECFUNC( "llvm.tan.f64", "_ZGVnN2v_tan", FIXED(2))
+
+TLI_DEFINE_VECFUNC( "tanh", "_ZGVnN2v_tanh", FIXED(2))
+TLI_DEFINE_VECFUNC( "llvm.tanh.f64", "_ZGVnN2v_tanh", FIXED(2))
+
+TLI_DEFINE_VECFUNC( "tgamma", "_ZGVnN2v_tgamma", FIXED(2))
+TLI_DEFINE_VECFUNC( "llvm.tgamma.f64", "_ZGVnN2v_tgamma", FIXED(2))
+
+#elif defined(TLI_DEFINE_SLEEFGNUABI_VF4_VECFUNCS)
+
+TLI_DEFINE_VECFUNC( "acosf", "_ZGVnN4v_acosf", FIXED(4))
+TLI_DEFINE_VECFUNC( "llvm.acos.f32", "_ZGVnN4v_acosf", FIXED(4))
+
+TLI_DEFINE_VECFUNC( "asinf", "_ZGVnN4v_asinf", FIXED(4))
+TLI_DEFINE_VECFUNC( "llvm.asin.f32", "_ZGVnN4v_asinf", FIXED(4))
+
+TLI_DEFINE_VECFUNC( "atanf", "_ZGVnN4v_atanf", FIXED(4))
+TLI_DEFINE_VECFUNC( "llvm.atan.f32", "_ZGVnN4v_atanf", FIXED(4))
+
+TLI_DEFINE_VECFUNC( "atan2f", "_ZGVnN4vv_atan2f", FIXED(4))
+TLI_DEFINE_VECFUNC( "llvm.atan2.f32", "_ZGVnN4vv_atan2f", FIXED(4))
+TLI_DEFINE_VECFUNC( "llvm.atan2.v4f32", "_ZGVnN4vv_atan2f", FIXED(4))
+
+TLI_DEFINE_VECFUNC( "atanhf", "_ZGVnN4v_atanhf", FIXED(4))
+TLI_DEFINE_VECFUNC( "llvm.atanh.f32", "_ZGVnN4v_atanhf", FIXED(4))
+
+TLI_DEFINE_VECFUNC( "cosf", "_ZGVnN4v_cosf", FIXED(4))
+TLI_DEFINE_VECFUNC( "llvm.cos.f32", "_ZGVnN4v_cosf", FIXED(4))
+
+TLI_DEFINE_VECFUNC( "coshf", "_ZGVnN4v_coshf", FIXED(4))
+TLI_DEFINE_VECFUNC( "llvm.cosh.f32", "_ZGVnN4v_coshf", FIXED(4))
+
+TLI_DEFINE_VECFUNC( "expf", "_ZGVnN4v_expf", FIXED(4))
+TLI_DEFINE_VECFUNC( "llvm.exp.f32", "_ZGVnN4v_expf", FIXED(4))
+TLI_DEFINE_VECFUNC( "llvm.exp.v4f32", "_ZGVnN4v_expf", FIXED(4))
+
+TLI_DEFINE_VECFUNC( "exp2f", "_ZGVnN4v_exp2f", FIXED(4))
+TLI_DEFINE_VECFUNC( "llvm.exp2.f32", "_ZGVnN4v_exp2f", FIXED(4))
+TLI_DEFINE_VECFUNC( "llvm.exp2.v4f32", "_ZGVnN4v_exp2f", FIXED(4))
+
+TLI_DEFINE_VECFUNC( "exp10f", "_ZGVnN4v_exp10f", FIXED(4))
+TLI_DEFINE_VECFUNC( "llvm.exp10.f32", "_ZGVnN4v_exp10f", FIXED(4))
+TLI_DEFINE_VECFUNC( "llvm.exp10.v4f32", "_ZGVnN4v_exp10f", FIXED(4))
+
+TLI_DEFINE_VECFUNC( "lgammaf", "_ZGVnN4v_lgammaf", FIXED(4))
+TLI_DEFINE_VECFUNC( "llvm.lgamma.f32", "_ZGVnN4v_lgammaf", FIXED(4))
+
+TLI_DEFINE_VECFUNC( "logf", "_ZGVnN4v_logf", FIXED(4))
+TLI_DEFINE_VECFUNC( "llvm.log.f32", "_ZGVnN4v_logf", FIXED(4))
+
+TLI_DEFINE_VECFUNC( "log2f", "_ZGVnN4v_log2f", FIXED(4))
+TLI_DEFINE_VECFUNC( "llvm.log2.f32", "_ZGVnN4v_log2f", FIXED(4))
+
+TLI_DEFINE_VECFUNC( "log10f", "_ZGVnN4v_log10f", FIXED(4))
+TLI_DEFINE_VECFUNC( "llvm.log10.f32", "_ZGVnN4v_log10f", FIXED(4))
+
+TLI_DEFINE_VECFUNC( "powf", "_ZGVnN4vv_powf", FIXED(4))
+TLI_DEFINE_VECFUNC( "llvm.pow.f32", "_ZGVnN4vv_powf", FIXED(4))
+TLI_DEFINE_VECFUNC( "llvm.pow.v4f32", "_ZGVnN4vv_powf", FIXED(4))
+
+TLI_DEFINE_VECFUNC( "sinf", "_ZGVnN4v_sinf", FIXED(4))
+TLI_DEFINE_VECFUNC( "llvm.sin.f32", "_ZGVnN4v_sinf", FIXED(4))
+
+TLI_DEFINE_VECFUNC( "sinhf", "_ZGVnN4v_sinhf", FIXED(4))
+TLI_DEFINE_VECFUNC( "llvm.sinh.f32", "_ZGVnN4v_sinhf", FIXED(4))
+
+TLI_DEFINE_VECFUNC( "sqrtf", "_ZGVnN4v_sqrtf", FIXED(4))
+TLI_DEFINE_VECFUNC( "llvm.sqrt.f32", "_ZGVnN4v_sqrtf", FIXED(4))
+
+TLI_DEFINE_VECFUNC( "tanf", "_ZGVnN4v_tanf", FIXED(4))
+TLI_DEFINE_VECFUNC( "llvm.tan.f32", "_ZGVnN4v_tanf", FIXED(4))
+
+TLI_DEFINE_VECFUNC( "tanhf", "_ZGVnN4v_tanhf", FIXED(4))
+TLI_DEFINE_VECFUNC( "llvm.tanh.f32", "_ZGVnN4v_tanhf", FIXED(4))
+
+TLI_DEFINE_VECFUNC( "tgammaf", "_ZGVnN4v_tgammaf", FIXED(4))
+TLI_DEFINE_VECFUNC( "llvm.tgamma.f32", "_ZGVnN4v_tgammaf", FIXED(4))
+
 #else
 #error "Must choose which vector library functions are to be defined."
 #endif
 
 #undef TLI_DEFINE_VECFUNC
 #undef TLI_DEFINE_ACCELERATE_VECFUNCS
 #undef TLI_DEFINE_DARWIN_LIBSYSTEM_M_VECFUNCS
 #undef TLI_DEFINE_LIBMVEC_X86_VECFUNCS
 #undef TLI_DEFINE_MASSV_VECFUNCS
 #undef TLI_DEFINE_SVML_VECFUNCS
+#undef TLI_DEFINE_SLEEFGNUABI_VF2_VECFUNCS
+#undef TLI_DEFINE_SLEEFGNUABI_VF4_VECFUNCS
 #undef TLI_DEFINE_MASSV_VECFUNCS_NAMES

llvm/lib/Analysis/TargetLibraryInfo.cpp

cl::values(clEnumValN(TargetLibraryInfoImpl::NoLibrary, "none",
                           "Accelerate framework"),
                clEnumValN(TargetLibraryInfoImpl::DarwinLibSystemM,
                           "Darwin_libsystem_m", "Darwin libsystem_m"),
                clEnumValN(TargetLibraryInfoImpl::LIBMVEC_X86, "LIBMVEC-X86",
                           "GLIBC Vector Math library"),
                clEnumValN(TargetLibraryInfoImpl::MASSV, "MASSV",
                           "IBM MASS vector library"),
                clEnumValN(TargetLibraryInfoImpl::SVML, "SVML",
-                          "Intel SVML library")));
+                          "Intel SVML library"),
+               clEnumValN(TargetLibraryInfoImpl::SLEEFGNUABI, "sleefgnuabi",
+                          "SIMD Library for Evaluating Elementary Functions")));
 
 StringLiteral const TargetLibraryInfoImpl::StandardNames[LibFunc::NumLibFuncs] =
     {
 #define TLI_DEFINE_STRING
 #include "llvm/Analysis/TargetLibraryInfo.def"
 };
 
 // Recognized types of library function arguments and return types.
static void initialize(TargetLibraryInfoImpl &TLI, const Triple &T,
   // These vec_malloc/free routines are only available on AIX.
   if (!T.isOSAIX()) {
     TLI.setUnavailable(LibFunc_vec_calloc);
     TLI.setUnavailable(LibFunc_vec_malloc);
     TLI.setUnavailable(LibFunc_vec_realloc);
     TLI.setUnavailable(LibFunc_vec_free);
   }
 
-  TLI.addVectorizableFunctionsFromVecLib(ClVectorLibrary);
+  TLI.addVectorizableFunctionsFromVecLib(ClVectorLibrary, T);
 }
 
 TargetLibraryInfoImpl::TargetLibraryInfoImpl() {
   // Default to everything being available.
   memset(AvailableArray, -1, sizeof(AvailableArray));
 
   initialize(*this, Triple(), StandardNames);
 }
void TargetLibraryInfoImpl::addVectorizableFunctions(ArrayRef<VecDesc> Fns) {
   llvm::append_range(VectorDescs, Fns);
   llvm::sort(VectorDescs, compareByScalarFnName);
 
   llvm::append_range(ScalarDescs, Fns);
   llvm::sort(ScalarDescs, compareByVectorFnName);
 }
 
 void TargetLibraryInfoImpl::addVectorizableFunctionsFromVecLib(
-    enum VectorLibrary VecLib) {
+    enum VectorLibrary VecLib, const llvm::Triple &TargetTriple) {
   switch (VecLib) {
   case Accelerate: {
     const VecDesc VecFuncs[] = {
     #define TLI_DEFINE_ACCELERATE_VECFUNCS
     #include "llvm/Analysis/VecFuncs.def"
     };
     addVectorizableFunctions(VecFuncs);
     break;
void TargetLibraryInfoImpl::addVectorizableFunctionsFromVecLib(
   case SVML: {
     const VecDesc VecFuncs[] = {
     #define TLI_DEFINE_SVML_VECFUNCS
     #include "llvm/Analysis/VecFuncs.def"
     };
     addVectorizableFunctions(VecFuncs);
     break;
   }
+  case SLEEFGNUABI: {
+    const VecDesc VecFuncs_VF2[] = {
+#define TLI_DEFINE_SLEEFGNUABI_VF2_VECFUNCS
+#include "llvm/Analysis/VecFuncs.def"
+    };
+    const VecDesc VecFuncs_VF4[] = {
+#define TLI_DEFINE_SLEEFGNUABI_VF4_VECFUNCS
+#include "llvm/Analysis/VecFuncs.def"
+    };
+
+    switch (TargetTriple.getArch()) {
+    default:
+      break;
+    case llvm::Triple::aarch64:
+    case llvm::Triple::aarch64_be:
+      addVectorizableFunctions(VecFuncs_VF2);
+      addVectorizableFunctions(VecFuncs_VF4);
+      break;
+    }
+    break;
+  }
   case NoLibrary:
     break;
   }
 }
 
 bool TargetLibraryInfoImpl::isFunctionVectorizable(StringRef funcName) const {
   funcName = sanitizeFunctionName(funcName);
   if (funcName.empty())

llvm/test/Transforms/LoopVectorize/AArch64/sleef-calls-aarch64.ll

+; Do NOT use -O3. It will lower exp2 to ldexp, and the test will fail.
+; RUN: opt -vector-library=sleefgnuabi -replace-with-veclib -loop-unroll -loop-vectorize -S < %s | FileCheck %s
+
+target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128"
+target triple = "aarch64-unknown-linux-gnu"
+
+declare double @acos(double) #0
+declare float @acosf(float) #0
+declare double @llvm.acos.f64(double) #0
+declare float @llvm.acos.f32(float) #0
+
+define void @acos_f64(double* nocapture %varray) {
+  ; CHECK-LABEL: @acos_f64(
+  ; CHECK:    [[TMP5:%.*]] = call <2 x double> @_ZGVnN2v_acos(<2 x double> [[TMP4:%.*]])
+  ; CHECK:    ret void
+  ;
+  entry:
+  br label %for.body
+
+  for.body:
+  %iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
+  %tmp = trunc i64 %iv to i32
+  %conv = sitofp i32 %tmp to double
+  %call = tail call double @acos(double %conv)
+  %arrayidx = getelementptr inbounds double, double* %varray, i64 %iv
+  store double %call, double* %arrayidx, align 8
+  %iv.next = add nuw nsw i64 %iv, 1
+  %exitcond = icmp eq i64 %iv.next, 1000
+  br i1 %exitcond, label %for.end, label %for.body
+
+  for.end:
+  ret void
+}
+
+define void @acos_f32(float* nocapture %varray) {
+  ; CHECK-LABEL: @acos_f32(
+  ; CHECK:    [[TMP5:%.*]] = call <4 x float> @_ZGVnN4v_acosf(<4 x float> [[TMP4:%.*]])
+  ; CHECK:    ret void
+  ;
+  entry:
+  br label %for.body
+
+  for.body:
+  %iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
+  %tmp = trunc i64 %iv to i32
+  %conv = sitofp i32 %tmp to float
+  %call = tail call float @acosf(float %conv)
+  %arrayidx = getelementptr inbounds float, float* %varray, i64 %iv
+  store float %call, float* %arrayidx, align 4
+  %iv.next = add nuw nsw i64 %iv, 1
+  %exitcond = icmp eq i64 %iv.next, 1000
+  br i1 %exitcond, label %for.end, label %for.body
+
+  for.end:
+  ret void
+}
+
+declare double @asin(double) #0
+declare float @asinf(float) #0
+declare double @llvm.asin.f64(double) #0
+declare float @llvm.asin.f32(float) #0
+
+define void @asin_f64(double* nocapture %varray) {
+  ; CHECK-LABEL: @asin_f64(
+  ; CHECK:    [[TMP5:%.*]] = call <2 x double> @_ZGVnN2v_asin(<2 x double> [[TMP4:%.*]])
+  ; CHECK:    ret void
+  ;
+  entry:
+  br label %for.body
+
+  for.body:
+  %iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
+  %tmp = trunc i64 %iv to i32
+  %conv = sitofp i32 %tmp to double
+  %call = tail call double @asin(double %conv)
+  %arrayidx = getelementptr inbounds double, double* %varray, i64 %iv
+  store double %call, double* %arrayidx, align 8
+  %iv.next = add nuw nsw i64 %iv, 1
+  %exitcond = icmp eq i64 %iv.next, 1000
+  br i1 %exitcond, label %for.end, label %for.body
+
+  for.end:
+  ret void
+}
+
+define void @asin_f32(float* nocapture %varray) {
+  ; CHECK-LABEL: @asin_f32(
+  ; CHECK:    [[TMP5:%.*]] = call <4 x float> @_ZGVnN4v_asinf(<4 x float> [[TMP4:%.*]])
+  ; CHECK:    ret void
+  ;
+  entry:
+  br label %for.body
+
+  for.body:
+  %iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
+  %tmp = trunc i64 %iv to i32
+  %conv = sitofp i32 %tmp to float
+  %call = tail call float @asinf(float %conv)
+  %arrayidx = getelementptr inbounds float, float* %varray, i64 %iv
+  store float %call, float* %arrayidx, align 4
+  %iv.next = add nuw nsw i64 %iv, 1
+  %exitcond = icmp eq i64 %iv.next, 1000
+  br i1 %exitcond, label %for.end, label %for.body
+
+  for.end:
+  ret void
+}
+
+declare double @atan(double) #0
+declare float @atanf(float) #0
+declare double @llvm.atan.f64(double) #0
+declare float @llvm.atan.f32(float) #0
+
+define void @atan_f64(double* nocapture %varray) {
+  ; CHECK-LABEL: @atan_f64(
+  ; CHECK:    [[TMP5:%.*]] = call <2 x double> @_ZGVnN2v_atan(<2 x double> [[TMP4:%.*]])
+  ; CHECK:    ret void
+  ;
+  entry:
+  br label %for.body
+
+  for.body:
+  %iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
+  %tmp = trunc i64 %iv to i32
+  %conv = sitofp i32 %tmp to double
+  %call = tail call double @atan(double %conv)
+  %arrayidx = getelementptr inbounds double, double* %varray, i64 %iv
+  store double %call, double* %arrayidx, align 8
+  %iv.next = add nuw nsw i64 %iv, 1
+  %exitcond = icmp eq i64 %iv.next, 1000
+  br i1 %exitcond, label %for.end, label %for.body
+
+  for.end:
+  ret void
+}
+
+define void @atan_f32(float* nocapture %varray) {
+  ; CHECK-LABEL: @atan_f32(
+  ; CHECK:    [[TMP5:%.*]] = call <4 x float> @_ZGVnN4v_atanf(<4 x float> [[TMP4:%.*]])
+  ; CHECK:    ret void
+  ;
+  entry:
+  br label %for.body
+
+  for.body:
+  %iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
+  %tmp = trunc i64 %iv to i32
+  %conv = sitofp i32 %tmp to float
+  %call = tail call float @atanf(float %conv)
+  %arrayidx = getelementptr inbounds float, float* %varray, i64 %iv
+  store float %call, float* %arrayidx, align 4
+  %iv.next = add nuw nsw i64 %iv, 1
+  %exitcond = icmp eq i64 %iv.next, 1000
+  br i1 %exitcond, label %for.end, label %for.body
+
+  for.end:
+  ret void
+}
+
+declare double @atan2(double, double) #0
+declare float @atan2f(float, float) #0
+declare double @llvm.atan2.f64(double, double) #0
+declare float @llvm.atan2.f32(float, float) #0
+
+define void @atan2_f64(double* nocapture %varray) {
+  ; CHECK-LABEL: @atan2_f64(
+  ; CHECK:    [[TMP5:%.*]] = call <2 x double> @_ZGVnN2vv_atan2(<2 x double> [[TMP4:%.*]], <2 x double> [[TMP4:%.*]])
+  ; CHECK:    ret void
+  ;
+  entry:
+  br label %for.body
+
+  for.body:
+  %iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
+  %tmp = trunc i64 %iv to i32
+  %conv = sitofp i32 %tmp to double
+  %call = tail call double @atan2(double %conv, double %conv)
+  %arrayidx = getelementptr inbounds double, double* %varray, i64 %iv
+  store double %call, double* %arrayidx, align 8
+  %iv.next = add nuw nsw i64 %iv, 1
+  %exitcond = icmp eq i64 %iv.next, 1000
+  br i1 %exitcond, label %for.end, label %for.body
+
+  for.end:
+  ret void
+}
+
+define void @atan2_f32(float* nocapture %varray) {
+  ; CHECK-LABEL: @atan2_f32(
+  ; CHECK:    [[TMP5:%.*]] = call <4 x float> @_ZGVnN4vv_atan2f(<4 x float> [[TMP4:%.*]], <4 x float> [[TMP4:%.*]])
+  ; CHECK:    ret void
+  ;
+  entry:
+  br label %for.body
+
+  for.body:
+  %iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
+  %tmp = trunc i64 %iv to i32
+  %conv = sitofp i32 %tmp to float
+  %call = tail call float @atan2f(float %conv, float %conv)
+  %arrayidx = getelementptr inbounds float, float* %varray, i64 %iv
+  store float %call, float* %arrayidx, align 4
+  %iv.next = add nuw nsw i64 %iv, 1
+  %exitcond = icmp eq i64 %iv.next, 1000
+  br i1 %exitcond, label %for.end, label %for.body
+
+  for.end:
+  ret void
+}
+
+declare double @atanh(double) #0
+declare float @atanhf(float) #0
+declare double @llvm.atanh.f64(double) #0
+declare float @llvm.atanh.f32(float) #0
+
+define void @atanh_f64(double* nocapture %varray) {
+  ; CHECK-LABEL: @atanh_f64(
+  ; CHECK:    [[TMP5:%.*]] = call <2 x double> @_ZGVnN2v_atanh(<2 x double> [[TMP4:%.*]])
+  ; CHECK:    ret void
+  ;
+  entry:
+  br label %for.body
+
+  for.body:
+  %iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
+  %tmp = trunc i64 %iv to i32
+  %conv = sitofp i32 %tmp to double
+  %call = tail call double @atanh(double %conv)
+  %arrayidx = getelementptr inbounds double, double* %varray, i64 %iv
+  store double %call, double* %arrayidx, align 8
+  %iv.next = add nuw nsw i64 %iv, 1
+  %exitcond = icmp eq i64 %iv.next, 1000
+  br i1 %exitcond, label %for.end, label %for.body
+
+  for.end:
+  ret void
+}
+
+define void @atanh_f32(float* nocapture %varray) {
+  ; CHECK-LABEL: @atanh_f32(
+  ; CHECK:    [[TMP5:%.*]] = call <4 x float> @_ZGVnN4v_atanhf(<4 x float> [[TMP4:%.*]])
+  ; CHECK:    ret void
+  ;
+  entry:
+  br label %for.body
+
+  for.body:
+  %iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
+  %tmp = trunc i64 %iv to i32
+  %conv = sitofp i32 %tmp to float
+  %call = tail call float @atanhf(float %conv)
+  %arrayidx = getelementptr inbounds float, float* %varray, i64 %iv
+  store float %call, float* %arrayidx, align 4
+  %iv.next = add nuw nsw i64 %iv, 1
+  %exitcond = icmp eq i64 %iv.next, 1000
+  br i1 %exitcond, label %for.end, label %for.body
+
+  for.end:
+  ret void
+}
+
+declare double @cos(double) #0
+declare float @cosf(float) #0
+declare double @llvm.cos.f64(double) #0
+declare float @llvm.cos.f32(float) #0
+
+define void @cos_f64(double* nocapture %varray) {
+  ; CHECK-LABEL: @cos_f64(
+  ; CHECK:    [[TMP5:%.*]] = call <2 x double> @_ZGVnN2v_cos(<2 x double> [[TMP4:%.*]])
+  ; CHECK:    ret void
+  ;
+  entry:
+  br label %for.body
+
+  for.body:
+  %iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
+  %tmp = trunc i64 %iv to i32
+  %conv = sitofp i32 %tmp to double
+  %call = tail call double @cos(double %conv)
+  %arrayidx = getelementptr inbounds double, double* %varray, i64 %iv
+  store double %call, double* %arrayidx, align 8
+  %iv.next = add nuw nsw i64 %iv, 1
+  %exitcond = icmp eq i64 %iv.next, 1000
+  br i1 %exitcond, label %for.end, label %for.body
+
+  for.end:
+  ret void
+}
+
+define void @cos_f32(float* nocapture %varray) {
+  ; CHECK-LABEL: @cos_f32(
+  ; CHECK:    [[TMP5:%.*]] = call <4 x float> @_ZGVnN4v_cosf(<4 x float> [[TMP4:%.*]])
+  ; CHECK:    ret void
+  ;
+  entry:
+  br label %for.body
+
+  for.body:
+  %iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
+  %tmp = trunc i64 %iv to i32
+  %conv = sitofp i32 %tmp to float
+  %call = tail call float @cosf(float %conv)
+  %arrayidx = getelementptr inbounds float, float* %varray, i64 %iv
+  store float %call, float* %arrayidx, align 4
+  %iv.next = add nuw nsw i64 %iv, 1
+  %exitcond = icmp eq i64 %iv.next, 1000
+  br i1 %exitcond, label %for.end, label %for.body
+
+  for.end:
+  ret void
+}
+
+declare double @cosh(double) #0
+declare float @coshf(float) #0
+declare double @llvm.cosh.f64(double) #0
+declare float @llvm.cosh.f32(float) #0
+
+define void @cosh_f64(double* nocapture %varray) {
+  ; CHECK-LABEL: @cosh_f64(
+  ; CHECK:    [[TMP5:%.*]] = call <2 x double> @_ZGVnN2v_cosh(<2 x double> [[TMP4:%.*]])
+  ; CHECK:    ret void
+  ;
+  entry:
+  br label %for.body
+
+  for.body:
+  %iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
+  %tmp = trunc i64 %iv to i32
+  %conv = sitofp i32 %tmp to double
+  %call = tail call double @cosh(double %conv)
+  %arrayidx = getelementptr inbounds double, double* %varray, i64 %iv
+  store double %call, double* %arrayidx, align 8
+  %iv.next = add nuw nsw i64 %iv, 1
+  %exitcond = icmp eq i64 %iv.next, 1000
+  br i1 %exitcond, label %for.end, label %for.body
+
+  for.end:
+  ret void
+}
+
+define void @cosh_f32(float* nocapture %varray) {
+  ; CHECK-LABEL: @cosh_f32(
+  ; CHECK:    [[TMP5:%.*]] = call <4 x float> @_ZGVnN4v_coshf(<4 x float> [[TMP4:%.*]])
+  ; CHECK:    ret void
+  ;
+  entry:
+  br label %for.body
+
+  for.body:
+  %iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
+  %tmp = trunc i64 %iv to i32
+  %conv = sitofp i32 %tmp to float
+  %call = tail call float @coshf(float %conv)
+  %arrayidx = getelementptr inbounds float, float* %varray, i64 %iv
+  store float %call, float* %arrayidx, align 4
+  %iv.next = add nuw nsw i64 %iv, 1
+  %exitcond = icmp eq i64 %iv.next, 1000
+  br i1 %exitcond, label %for.end, label %for.body
+
+  for.end:
+  ret void
+}
+
+declare double @exp(double) #0
+declare float @expf(float) #0
+declare double @llvm.exp.f64(double) #0
+declare float @llvm.exp.f32(float) #0
+
+define void @exp_f64(double* nocapture %varray) {
+  ; CHECK-LABEL: @exp_f64(
+  ; CHECK:    [[TMP5:%.*]] = call <2 x double> @_ZGVnN2v_exp(<2 x double> [[TMP4:%.*]])
+  ; CHECK:    ret void
+  ;
+  entry:
+  br label %for.body
+
+  for.body:
+  %iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
+  %tmp = trunc i64 %iv to i32
+  %conv = sitofp i32 %tmp to double
+  %call = tail call double @exp(double %conv)
+  %arrayidx = getelementptr inbounds double, double* %varray, i64 %iv
+  store double %call, double* %arrayidx, align 8
+  %iv.next = add nuw nsw i64 %iv, 1
+  %exitcond = icmp eq i64 %iv.next, 1000
+  br i1 %exitcond, label %for.end, label %for.body
+
+  for.end:
+  ret void
+}
+
+define void @exp_f32(float* nocapture %varray) {
+  ; CHECK-LABEL: @exp_f32(
+  ; CHECK:    [[TMP5:%.*]] = call <4 x float> @_ZGVnN4v_expf(<4 x float> [[TMP4:%.*]])
+  ; CHECK:    ret void
+  ;
+  entry:
+  br label %for.body
+
+  for.body:
+  %iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
+  %tmp = trunc i64 %iv to i32
+  %conv = sitofp i32 %tmp to float
+  %call = tail call float @expf(float %conv)
+  %arrayidx = getelementptr inbounds float, float* %varray, i64 %iv
+  store float %call, float* %arrayidx, align 4
+  %iv.next = add nuw nsw i64 %iv, 1
+  %exitcond = icmp eq i64 %iv.next, 1000
+  br i1 %exitcond, label %for.end, label %for.body
+
+  for.end:
+  ret void
+}
+
+declare double @exp2(double) #0
+declare float @exp2f(float) #0
+declare double @llvm.exp2.f64(double) #0
+declare float @llvm.exp2.f32(float) #0
+
+define void @exp2_f64(double* nocapture %varray) {
+  ; CHECK-LABEL: @exp2_f64(
+  ; CHECK:    [[TMP5:%.*]] = call <2 x double> @_ZGVnN2v_exp2(<2 x double> [[TMP4:%.*]])
+  ; CHECK:    ret void
+  ;
+  entry:
+  br label %for.body
+
+  for.body:
+  %iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
+  %tmp = trunc i64 %iv to i32
+  %conv = sitofp i32 %tmp to double
+  %call = tail call double @exp2(double %conv)
+  %arrayidx = getelementptr inbounds double, double* %varray, i64 %iv
+  store double %call, double* %arrayidx, align 8
+  %iv.next = add nuw nsw i64 %iv, 1
+  %exitcond = icmp eq i64 %iv.next, 1000
+  br i1 %exitcond, label %for.end, label %for.body
+
+  for.end:
+  ret void
+}
+
+define void @exp2_f32(float* nocapture %varray) {
+  ; CHECK-LABEL: @exp2_f32(
+  ; CHECK:    [[TMP5:%.*]] = call <4 x float> @_ZGVnN4v_exp2f(<4 x float> [[TMP4:%.*]])
+  ; CHECK:    ret void
+  ;
+  entry:
+  br label %for.body
+
+  for.body:
+  %iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
+  %tmp = trunc i64 %iv to i32
+  %conv = sitofp i32 %tmp to float
+  %call = tail call float @exp2f(float %conv)
+  %arrayidx = getelementptr inbounds float, float* %varray, i64 %iv
+  store float %call, float* %arrayidx, align 4
+  %iv.next = add nuw nsw i64 %iv, 1
+  %exitcond = icmp eq i64 %iv.next, 1000
+  br i1 %exitcond, label %for.end, label %for.body
+
+  for.end:
+  ret void
+}
+
+declare double @exp10(double) #0
+declare float @exp10f(float) #0
+declare double @llvm.exp10.f64(double) #0
+declare float @llvm.exp10.f32(float) #0
+
+define void @exp10_f64(double* nocapture %varray) {
+  ; CHECK-LABEL: @exp10_f64(
+  ; CHECK:    [[TMP5:%.*]] = call <2 x double> @_ZGVnN2v_exp10(<2 x double> [[TMP4:%.*]])
+  ; CHECK:    ret void
+  ;
+  entry:
+  br label %for.body
+
+  for.body:
+  %iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
+  %tmp = trunc i64 %iv to i32
+  %conv = sitofp i32 %tmp to double
+  %call = tail call double @exp10(double %conv)
+  %arrayidx = getelementptr inbounds double, double* %varray, i64 %iv
+  store double %call, double* %arrayidx, align 8
+  %iv.next = add nuw nsw i64 %iv, 1
+  %exitcond = icmp eq i64 %iv.next, 1000
+  br i1 %exitcond, label %for.end, label %for.body
+
+  for.end:
+  ret void
+}
+
+define void @exp10_f32(float* nocapture %varray) {
+  ; CHECK-LABEL: @exp10_f32(
+  ; CHECK:    [[TMP5:%.*]] = call <4 x float> @_ZGVnN4v_exp10f(<4 x float> [[TMP4:%.*]])
+  ; CHECK:    ret void
+  ;
+  entry:
+  br label %for.body
+
+  for.body:
+  %iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
+  %tmp = trunc i64 %iv to i32
+  %conv = sitofp i32 %tmp to float
+  %call = tail call float @exp10f(float %conv)
+  %arrayidx = getelementptr inbounds float, float* %varray, i64 %iv
+  store float %call, float* %arrayidx, align 4
+  %iv.next = add nuw nsw i64 %iv, 1
+  %exitcond = icmp eq i64 %iv.next, 1000
+  br i1 %exitcond, label %for.end, label %for.body
+
+  for.end:
+  ret void
+}
+
+declare double @lgamma(double) #0
+declare float @lgammaf(float) #0
+declare double @llvm.lgamma.f64(double) #0
+declare float @llvm.lgamma.f32(float) #0
+
+define void @lgamma_f64(double* nocapture %varray) {
+  ; CHECK-LABEL: @lgamma_f64(
+  ; CHECK:    [[TMP5:%.*]] = call <2 x double> @_ZGVnN2v_lgamma(<2 x double> [[TMP4:%.*]])
+  ; CHECK:    ret void
+  ;
+  entry:
+  br label %for.body
+
+  for.body:
+  %iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
+  %tmp = trunc i64 %iv to i32
+  %conv = sitofp i32 %tmp to double
+  %call = tail call double @lgamma(double %conv)
+  %arrayidx = getelementptr inbounds double, double* %varray, i64 %iv
+  store double %call, double* %arrayidx, align 8
+  %iv.next = add nuw nsw i64 %iv, 1
+  %exitcond = icmp eq i64 %iv.next, 1000
+  br i1 %exitcond, label %for.end, label %for.body
+
+  for.end:
+  ret void
+}
+
+define void @lgamma_f32(float* nocapture %varray) {
+  ; CHECK-LABEL: @lgamma_f32(
+  ; CHECK:    [[TMP5:%.*]] = call <4 x float> @_ZGVnN4v_lgammaf(<4 x float> [[TMP4:%.*]])
+  ; CHECK:    ret void
+  ;
+  entry:
+  br label %for.body
+
+  for.body:
+  %iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
+  %tmp = trunc i64 %iv to i32
+  %conv = sitofp i32 %tmp to float
+  %call = tail call float @lgammaf(float %conv)
+  %arrayidx = getelementptr inbounds float, float* %varray, i64 %iv
+  store float %call, float* %arrayidx, align 4
+  %iv.next = add nuw nsw i64 %iv, 1
+  %exitcond = icmp eq i64 %iv.next, 1000
+  br i1 %exitcond, label %for.end, label %for.body
+
+  for.end:
+  ret void
+}
+
+declare double @log10(double) #0
+declare float @log10f(float) #0
+declare double @llvm.log10.f64(double) #0
+declare float @llvm.log10.f32(float) #0
+
+define void @log10_f64(double* nocapture %varray) {
+  ; CHECK-LABEL: @log10_f64(
+  ; CHECK:    [[TMP5:%.*]] = call <2 x double> @_ZGVnN2v_log10(<2 x double> [[TMP4:%.*]])
+  ; CHECK:    ret void
+  ;
+  entry:
+  br label %for.body
+
+  for.body:
+  %iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
+  %tmp = trunc i64 %iv to i32
+  %conv = sitofp i32 %tmp to double
+  %call = tail call double @log10(double %conv)
+  %arrayidx = getelementptr inbounds double, double* %varray, i64 %iv
+  store double %call, double* %arrayidx, align 8
+  %iv.next = add nuw nsw i64 %iv, 1
+  %exitcond = icmp eq i64 %iv.next, 1000
+  br i1 %exitcond, label %for.end, label %for.body
+
+  for.end:
+  ret void
+}
+
+define void @log10_f32(float* nocapture %varray) {
+  ; CHECK-LABEL: @log10_f32(
+  ; CHECK:    [[TMP5:%.*]] = call <4 x float> @_ZGVnN4v_log10f(<4 x float> [[TMP4:%.*]])
+  ; CHECK:    ret void
+  ;
+  entry:
+  br label %for.body
+
+  for.body:
+  %iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
+  %tmp = trunc i64 %iv to i32
+  %conv = sitofp i32 %tmp to float
+  %call = tail call float @log10f(float %conv)
+  %arrayidx = getelementptr inbounds float, float* %varray, i64 %iv
+  store float %call, float* %arrayidx, align 4
+  %iv.next = add nuw nsw i64 %iv, 1
+  %exitcond = icmp eq i64 %iv.next, 1000
+  br i1 %exitcond, label %for.end, label %for.body
+
+  for.end:
+  ret void
+}
+
+declare double @log2(double) #0
+declare float @log2f(float) #0
+declare double @llvm.log2.f64(double) #0
+declare float @llvm.log2.f32(float) #0
+
+define void @log2_f64(double* nocapture %varray) {
+  ; CHECK-LABEL: @log2_f64(
+  ; CHECK:    [[TMP5:%.*]] = call <2 x double> @_ZGVnN2v_log2(<2 x double> [[TMP4:%.*]])
+  ; CHECK:    ret void
+  ;
+  entry:
+  br label %for.body
+
+  for.body:
+  %iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
+  %tmp = trunc i64 %iv to i32
+  %conv = sitofp i32 %tmp to double
+  %call = tail call double @log2(double %conv)
+  %arrayidx = getelementptr inbounds double, double* %varray, i64 %iv
+  store double %call, double* %arrayidx, align 8
+  %iv.next = add nuw nsw i64 %iv, 1
+  %exitcond = icmp eq i64 %iv.next, 1000
+  br i1 %exitcond, label %for.end, label %for.body
+
+  for.end:
+  ret void
+}
+
+define void @log2_f32(float* nocapture %varray) {
+  ; CHECK-LABEL: @log2_f32(
+  ; CHECK:    [[TMP5:%.*]] = call <4 x float> @_ZGVnN4v_log2f(<4 x float> [[TMP4:%.*]])
+  ; CHECK:    ret void
+  ;
+  entry:
+  br label %for.body
+
+  for.body:
+  %iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
+  %tmp = trunc i64 %iv to i32
+  %conv = sitofp i32 %tmp to float
+  %call = tail call float @log2f(float %conv)
+  %arrayidx = getelementptr inbounds float, float* %varray, i64 %iv
+  store float %call, float* %arrayidx, align 4
+  %iv.next = add nuw nsw i64 %iv, 1
+  %exitcond = icmp eq i64 %iv.next, 1000
+  br i1 %exitcond, label %for.end, label %for.body
+
+  for.end:
+  ret void
+}
+
+declare double @log(double) #0
+declare float @logf(float) #0
+declare double @llvm.log.f64(double) #0
+declare float @llvm.log.f32(float) #0
+
+define void @log_f64(double* nocapture %varray) {
+  ; CHECK-LABEL: @log_f64(
+  ; CHECK:    [[TMP5:%.*]] = call <2 x double> @_ZGVnN2v_log(<2 x double> [[TMP4:%.*]])
+  ; CHECK:    ret void
+  ;
+  entry:
+  br label %for.body
+
+  for.body:
+  %iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
+  %tmp = trunc i64 %iv to i32
+  %conv = sitofp i32 %tmp to double
+  %call = tail call double @log(double %conv)
+  %arrayidx = getelementptr inbounds double, double* %varray, i64 %iv
+  store double %call, double* %arrayidx, align 8
+  %iv.next = add nuw nsw i64 %iv, 1
+  %exitcond = icmp eq i64 %iv.next, 1000
+  br i1 %exitcond, label %for.end, label %for.body
+
+  for.end:
+  ret void
+}
+
+define void @log_f32(float* nocapture %varray) {
+  ; CHECK-LABEL: @log_f32(
+  ; CHECK:    [[TMP5:%.*]] = call <4 x float> @_ZGVnN4v_logf(<4 x float> [[TMP4:%.*]])
+  ; CHECK:    ret void
+  ;
+  entry:
+  br label %for.body
+
+  for.body:
+  %iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
+  %tmp = trunc i64 %iv to i32
+  %conv = sitofp i32 %tmp to float
+  %call = tail call float @logf(float %conv)
+  %arrayidx = getelementptr inbounds float, float* %varray, i64 %iv
+  store float %call, float* %arrayidx, align 4
+  %iv.next = add nuw nsw i64 %iv, 1
+  %exitcond = icmp eq i64 %iv.next, 1000
+  br i1 %exitcond, label %for.end, label %for.body
+
+  for.end:
+  ret void
+}
+
+declare double @pow(double, double) #0
+declare float @powf(float, float) #0
+declare double @llvm.pow.f64(double, double) #0
+declare float @llvm.pow.f32(float, float) #0
+
+define void @pow_f64(double* nocapture %varray) {
+  ; CHECK-LABEL: @pow_f64(
+  ; CHECK:    [[TMP5:%.*]] = call <2 x double> @_ZGVnN2vv_pow(<2 x double> [[TMP4:%.*]], <2 x double> [[TMP4:%.*]])
+  ; CHECK:    ret void
+  ;
+  entry:
+  br label %for.body
+
+  for.body:
+  %iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
+  %tmp = trunc i64 %iv to i32
+  %conv = sitofp i32 %tmp to double
+  %call = tail call double @pow(double %conv, double %conv)
+  %arrayidx = getelementptr inbounds double, double* %varray, i64 %iv
+  store double %call, double* %arrayidx, align 8
+  %iv.next = add nuw nsw i64 %iv, 1
+  %exitcond = icmp eq i64 %iv.next, 1000
+  br i1 %exitcond, label %for.end, label %for.body
+
+  for.end:
+  ret void
+}
+
+define void @pow_f32(float* nocapture %varray) {
+  ; CHECK-LABEL: @pow_f32(
+  ; CHECK:    [[TMP5:%.*]] = call <4 x float> @_ZGVnN4vv_powf(<4 x float> [[TMP4:%.*]], <4 x float> [[TMP4:%.*]])
+  ; CHECK:    ret void
+  ;
+  entry:
+  br label %for.body
+
+  for.body:
+  %iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
+  %tmp = trunc i64 %iv to i32
+  %conv = sitofp i32 %tmp to float
+  %call = tail call float @powf(float %conv, float %conv)
+  %arrayidx = getelementptr inbounds float, float* %varray, i64 %iv
+  store float %call, float* %arrayidx, align 4
+  %iv.next = add nuw nsw i64 %iv, 1
+  %exitcond = icmp eq i64 %iv.next, 1000
+  br i1 %exitcond, label %for.end, label %for.body
+
+  for.end:
+  ret void
+}
+
+declare double @sin(double) #0
+declare float @sinf(float) #0
+declare double @llvm.sin.f64(double) #0
+declare float @llvm.sin.f32(float) #0
+
+define void @sin_f64(double* nocapture %varray) {
+  ; CHECK-LABEL: @sin_f64(
+  ; CHECK:    [[TMP5:%.*]] = call <2 x double> @_ZGVnN2v_sin(<2 x double> [[TMP4:%.*]])
+  ; CHECK:    ret void
+  ;
+  entry:
+  br label %for.body
+
+  for.body:
+  %iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
+  %tmp = trunc i64 %iv to i32
+  %conv = sitofp i32 %tmp to double
+  %call = tail call double @sin(double %conv)
+  %arrayidx = getelementptr inbounds double, double* %varray, i64 %iv
+  store double %call, double* %arrayidx, align 8
+  %iv.next = add nuw nsw i64 %iv, 1
+  %exitcond = icmp eq i64 %iv.next, 1000
+  br i1 %exitcond, label %for.end, label %for.body
+
+  for.end:
+  ret void
+}
+
+define void @sin_f32(float* nocapture %varray) {
+  ; CHECK-LABEL: @sin_f32(
+  ; CHECK:    [[TMP5:%.*]] = call <4 x float> @_ZGVnN4v_sinf(<4 x float> [[TMP4:%.*]])
+  ; CHECK:    ret void
+  ;
+  entry:
+  br label %for.body
+
+  for.body:
+  %iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
+  %tmp = trunc i64 %iv to i32
+  %conv = sitofp i32 %tmp to float
+  %call = tail call float @sinf(float %conv)
+  %arrayidx = getelementptr inbounds float, float* %varray, i64 %iv
+  store float %call, float* %arrayidx, align 4
+  %iv.next = add nuw nsw i64 %iv, 1
+  %exitcond = icmp eq i64 %iv.next, 1000
+  br i1 %exitcond, label %for.end, label %for.body
+
+  for.end:
+  ret void
+}
+
+declare double @sinh(double) #0
+declare float @sinhf(float) #0
+declare double @llvm.sinh.f64(double) #0
+declare float @llvm.sinh.f32(float) #0
+
+define void @sinh_f64(double* nocapture %varray) {
+  ; CHECK-LABEL: @sinh_f64(
+  ; CHECK:    [[TMP5:%.*]] = call <2 x double> @_ZGVnN2v_sinh(<2 x double> [[TMP4:%.*]])
+  ; CHECK:    ret void
+  ;
+  entry:
+  br label %for.body
+
+  for.body:
+  %iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
+  %tmp = trunc i64 %iv to i32
+  %conv = sitofp i32 %tmp to double
+  %call = tail call double @sinh(double %conv)
+  %arrayidx = getelementptr inbounds double, double* %varray, i64 %iv
+  store double %call, double* %arrayidx, align 8
+  %iv.next = add nuw nsw i64 %iv, 1
+  %exitcond = icmp eq i64 %iv.next, 1000
+  br i1 %exitcond, label %for.end, label %for.body
+
+  for.end:
+  ret void
+}
+
+define void @sinh_f32(float* nocapture %varray) {
+  ; CHECK-LABEL: @sinh_f32(
+  ; CHECK:    [[TMP5:%.*]] = call <4 x float> @_ZGVnN4v_sinhf(<4 x float> [[TMP4:%.*]])
+  ; CHECK:    ret void
+  ;
+  entry:
+  br label %for.body
+
+  for.body:
+  %iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
+  %tmp = trunc i64 %iv to i32
+  %conv = sitofp i32 %tmp to float
+  %call = tail call float @sinhf(float %conv)
+  %arrayidx = getelementptr inbounds float, float* %varray, i64 %iv
+  store float %call, float* %arrayidx, align 4
+  %iv.next = add nuw nsw i64 %iv, 1
+  %exitcond = icmp eq i64 %iv.next, 1000
+  br i1 %exitcond, label %for.end, label %for.body
+
+  for.end:
+  ret void
+}
+
+declare double @sqrt(double) #0
+declare float @sqrtf(float) #0
+declare double @llvm.sqrt.f64(double) #0
+declare float @llvm.sqrt.f32(float) #0
+
+define void @sqrt_f64(double* nocapture %varray) {
+  ; CHECK-LABEL: @sqrt_f64(
+  ; CHECK:    [[TMP5:%.*]] = call <2 x double> @_ZGVnN2v_sqrt(<2 x double> [[TMP4:%.*]])
+  ; CHECK:    ret void
+  ;
+  entry:
+  br label %for.body
+
+  for.body:
+  %iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
+  %tmp = trunc i64 %iv to i32
+  %conv = sitofp i32 %tmp to double
+  %call = tail call double @sqrt(double %conv)
+  %arrayidx = getelementptr inbounds double, double* %varray, i64 %iv
+  store double %call, double* %arrayidx, align 8
+  %iv.next = add nuw nsw i64 %iv, 1
+  %exitcond = icmp eq i64 %iv.next, 1000
+  br i1 %exitcond, label %for.end, label %for.body
+
+  for.end:
+  ret void
+}
+
+define void @sqrt_f32(float* nocapture %varray) {
+  ; CHECK-LABEL: @sqrt_f32(
+  ; CHECK:    [[TMP5:%.*]] = call <4 x float> @_ZGVnN4v_sqrtf(<4 x float> [[TMP4:%.*]])
+  ; CHECK:    ret void
+  ;
+  entry:
+  br label %for.body
+
+  for.body:
+  %iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
+  %tmp = trunc i64 %iv to i32
+  %conv = sitofp i32 %tmp to float
+  %call = tail call float @sqrtf(float %conv)
+  %arrayidx = getelementptr inbounds float, float* %varray, i64 %iv
+  store float %call, float* %arrayidx, align 4
+  %iv.next = add nuw nsw i64 %iv, 1
+  %exitcond = icmp eq i64 %iv.next, 1000
+  br i1 %exitcond, label %for.end, label %for.body
+
+  for.end:
+  ret void
+}
+
+declare double @tan(double) #0
+declare float @tanf(float) #0
+declare double @llvm.tan.f64(double) #0
+declare float @llvm.tan.f32(float) #0
+
+define void @tan_f64(double* nocapture %varray) {
+  ; CHECK-LABEL: @tan_f64(
+  ; CHECK:    [[TMP5:%.*]] = call <2 x double> @_ZGVnN2v_tan(<2 x double> [[TMP4:%.*]])
+  ; CHECK:    ret void
+  ;
+  entry:
+  br label %for.body
+
+  for.body:
+  %iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
+  %tmp = trunc i64 %iv to i32
+  %conv = sitofp i32 %tmp to double
+  %call = tail call double @tan(double %conv)
+  %arrayidx = getelementptr inbounds double, double* %varray, i64 %iv
+  store double %call, double* %arrayidx, align 8
+  %iv.next = add nuw nsw i64 %iv, 1
+  %exitcond = icmp eq i64 %iv.next, 1000
+  br i1 %exitcond, label %for.end, label %for.body
+
+  for.end:
+  ret void
+}
+
+define void @tan_f32(float* nocapture %varray) {
+  ; CHECK-LABEL: @tan_f32(
+  ; CHECK:    [[TMP5:%.*]] = call <4 x float> @_ZGVnN4v_tanf(<4 x float> [[TMP4:%.*]])
+  ; CHECK:    ret void
+  ;
+  entry:
+  br label %for.body
+
+  for.body:
+  %iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
+  %tmp = trunc i64 %iv to i32
+  %conv = sitofp i32 %tmp to float
+  %call = tail call float @tanf(float %conv)
+  %arrayidx = getelementptr inbounds float, float* %varray, i64 %iv
+  store float %call, float* %arrayidx, align 4
+  %iv.next = add nuw nsw i64 %iv, 1
+  %exitcond = icmp eq i64 %iv.next, 1000
+  br i1 %exitcond, label %for.end, label %for.body
+
+  for.end:
+  ret void
+}
+
+declare double @tanh(double) #0
+declare float @tanhf(float) #0
+declare double @llvm.tanh.f64(double) #0
+declare float @llvm.tanh.f32(float) #0
+
+define void @tanh_f64(double* nocapture %varray) {
+  ; CHECK-LABEL: @tanh_f64(
+  ; CHECK:    [[TMP5:%.*]] = call <2 x double> @_ZGVnN2v_tanh(<2 x double> [[TMP4:%.*]])
+  ; CHECK:    ret void
+  ;
+  entry:
+  br label %for.body
+
+  for.body:
+  %iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
+  %tmp = trunc i64 %iv to i32
+  %conv = sitofp i32 %tmp to double
+  %call = tail call double @tanh(double %conv)
+  %arrayidx = getelementptr inbounds double, double* %varray, i64 %iv
+  store double %call, double* %arrayidx, align 8
+  %iv.next = add nuw nsw i64 %iv, 1
+  %exitcond = icmp eq i64 %iv.next, 1000
+  br i1 %exitcond, label %for.end, label %for.body
+
+  for.end:
+  ret void
+}
+
+define void @tanh_f32(float* nocapture %varray) {
+  ; CHECK-LABEL: @tanh_f32(
+  ; CHECK:    [[TMP5:%.*]] = call <4 x float> @_ZGVnN4v_tanhf(<4 x float> [[TMP4:%.*]])
+  ; CHECK:    ret void
+  ;
+  entry:
+  br label %for.body
+
+  for.body:
+  %iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
+  %tmp = trunc i64 %iv to i32
+  %conv = sitofp i32 %tmp to float
+  %call = tail call float @tanhf(float %conv)
+  %arrayidx = getelementptr inbounds float, float* %varray, i64 %iv
+  store float %call, float* %arrayidx, align 4
+  %iv.next = add nuw nsw i64 %iv, 1
+  %exitcond = icmp eq i64 %iv.next, 1000
+  br i1 %exitcond, label %for.end, label %for.body
+
+  for.end:
+  ret void
+}
+
+declare double @tgamma(double) #0
+declare float @tgammaf(float) #0
+declare double @llvm.tgamma.f64(double) #0
+declare float @llvm.tgamma.f32(float) #0
+
+define void @tgamma_f64(double* nocapture %varray) {
+  ; CHECK-LABEL: @tgamma_f64(
+  ; CHECK:    [[TMP5:%.*]] = call <2 x double> @_ZGVnN2v_tgamma(<2 x double> [[TMP4:%.*]])
+  ; CHECK:    ret void
+  ;
+  entry:
+  br label %for.body
+
+  for.body:
+  %iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
+  %tmp = trunc i64 %iv to i32
+  %conv = sitofp i32 %tmp to double
+  %call = tail call double @tgamma(double %conv)
+  %arrayidx = getelementptr inbounds double, double* %varray, i64 %iv
+  store double %call, double* %arrayidx, align 8
+  %iv.next = add nuw nsw i64 %iv, 1
+  %exitcond = icmp eq i64 %iv.next, 1000
+  br i1 %exitcond, label %for.end, label %for.body
+
+  for.end:
+  ret void
+}
+
+define void @tgamma_f32(float* nocapture %varray) {
+  ; CHECK-LABEL: @tgamma_f32(
+  ; CHECK:    [[TMP5:%.*]] = call <4 x float> @_ZGVnN4v_tgammaf(<4 x float> [[TMP4:%.*]])
+  ; CHECK:    ret void
+  ;
+  entry:
+  br label %for.body
+
+  for.body:
+  %iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
+  %tmp = trunc i64 %iv to i32
+  %conv = sitofp i32 %tmp to float
+  %call = tail call float @tgammaf(float %conv)
+  %arrayidx = getelementptr inbounds float, float* %varray, i64 %iv
+  store float %call, float* %arrayidx, align 4
+  %iv.next = add nuw nsw i64 %iv, 1
+  %exitcond = icmp eq i64 %iv.next, 1000
+  br i1 %exitcond, label %for.end, label %for.body
+
+  for.end:
+  ret void
+}