[llvm-commits] [llvm] r156196 [1/2] - in /llvm/trunk: ./ autoconf/ include/llvm/ include/llvm/ADT/ lib/Support/ lib/Target/ lib/Target/NVPTX/ lib/Target/NVPTX/InstPrinter/ lib/Target/NVPTX/MCTargetDesc/ lib/Target/NVPTX/TargetInfo/ projects/sampl

Chandler Carruth chandlerc at google.com
Fri May 4 14:37:05 PDT 2012


Just FYI, I fixed a warning in this code with r156209. You'll probably want
to start using a bootstrapped Clang for builds so you get more of the
warnings we care about with LLVM.

Thanks for the great contribution.

On Fri, May 4, 2012 at 1:18 PM, Justin Holewinski <jholewinski at nvidia.com>wrote:

> Author: jholewinski
> Date: Fri May  4 15:18:50 2012
> New Revision: 156196
>
> URL: http://llvm.org/viewvc/llvm-project?rev=156196&view=rev
> Log:
> This patch adds a new NVPTX back-end to LLVM which supports code
> generation for NVIDIA PTX 3.0. This back-end will (eventually) replace the
> current PTX back-end, while maintaining compatibility with it.
>
> The new target machines are:
>
> nvptx (old ptx32) => 32-bit PTX
> nvptx64 (old ptx64) => 64-bit PTX
>
> The sources are based on the internal NVIDIA NVPTX back-end, and
> contain more functionality than the current PTX back-end currently
> provides.
>
> NV_CONTRIB
>
> Added:
>    llvm/trunk/include/llvm/IntrinsicsNVVM.td
>    llvm/trunk/lib/Target/NVPTX/
>    llvm/trunk/lib/Target/NVPTX/CMakeLists.txt
>    llvm/trunk/lib/Target/NVPTX/InstPrinter/
>    llvm/trunk/lib/Target/NVPTX/InstPrinter/CMakeLists.txt
>    llvm/trunk/lib/Target/NVPTX/InstPrinter/LLVMBuild.txt
>    llvm/trunk/lib/Target/NVPTX/InstPrinter/Makefile
>    llvm/trunk/lib/Target/NVPTX/InstPrinter/NVPTXInstPrinter.cpp
>    llvm/trunk/lib/Target/NVPTX/LLVMBuild.txt
>    llvm/trunk/lib/Target/NVPTX/MCTargetDesc/
>    llvm/trunk/lib/Target/NVPTX/MCTargetDesc/CMakeLists.txt
>    llvm/trunk/lib/Target/NVPTX/MCTargetDesc/LLVMBuild.txt
>    llvm/trunk/lib/Target/NVPTX/MCTargetDesc/Makefile
>    llvm/trunk/lib/Target/NVPTX/MCTargetDesc/NVPTXBaseInfo.h
>    llvm/trunk/lib/Target/NVPTX/MCTargetDesc/NVPTXMCAsmInfo.cpp
>    llvm/trunk/lib/Target/NVPTX/MCTargetDesc/NVPTXMCAsmInfo.h
>    llvm/trunk/lib/Target/NVPTX/MCTargetDesc/NVPTXMCTargetDesc.cpp
>    llvm/trunk/lib/Target/NVPTX/MCTargetDesc/NVPTXMCTargetDesc.h
>    llvm/trunk/lib/Target/NVPTX/Makefile
>    llvm/trunk/lib/Target/NVPTX/ManagedStringPool.h
>    llvm/trunk/lib/Target/NVPTX/NVPTX.h
>    llvm/trunk/lib/Target/NVPTX/NVPTX.td
>    llvm/trunk/lib/Target/NVPTX/NVPTXAllocaHoisting.cpp
>    llvm/trunk/lib/Target/NVPTX/NVPTXAllocaHoisting.h
>    llvm/trunk/lib/Target/NVPTX/NVPTXAsmPrinter.cpp
>    llvm/trunk/lib/Target/NVPTX/NVPTXAsmPrinter.h
>    llvm/trunk/lib/Target/NVPTX/NVPTXFrameLowering.cpp
>    llvm/trunk/lib/Target/NVPTX/NVPTXFrameLowering.h
>    llvm/trunk/lib/Target/NVPTX/NVPTXISelDAGToDAG.cpp
>    llvm/trunk/lib/Target/NVPTX/NVPTXISelDAGToDAG.h
>    llvm/trunk/lib/Target/NVPTX/NVPTXISelLowering.cpp
>    llvm/trunk/lib/Target/NVPTX/NVPTXISelLowering.h
>    llvm/trunk/lib/Target/NVPTX/NVPTXInstrFormats.td
>    llvm/trunk/lib/Target/NVPTX/NVPTXInstrInfo.cpp
>    llvm/trunk/lib/Target/NVPTX/NVPTXInstrInfo.h
>    llvm/trunk/lib/Target/NVPTX/NVPTXInstrInfo.td
>    llvm/trunk/lib/Target/NVPTX/NVPTXIntrinsics.td
>    llvm/trunk/lib/Target/NVPTX/NVPTXLowerAggrCopies.cpp
>    llvm/trunk/lib/Target/NVPTX/NVPTXLowerAggrCopies.h
>    llvm/trunk/lib/Target/NVPTX/NVPTXNumRegisters.h
>    llvm/trunk/lib/Target/NVPTX/NVPTXRegisterInfo.cpp
>    llvm/trunk/lib/Target/NVPTX/NVPTXRegisterInfo.h
>    llvm/trunk/lib/Target/NVPTX/NVPTXRegisterInfo.td
>    llvm/trunk/lib/Target/NVPTX/NVPTXSection.h
>    llvm/trunk/lib/Target/NVPTX/NVPTXSplitBBatBar.cpp
>    llvm/trunk/lib/Target/NVPTX/NVPTXSplitBBatBar.h
>    llvm/trunk/lib/Target/NVPTX/NVPTXSubtarget.cpp
>    llvm/trunk/lib/Target/NVPTX/NVPTXSubtarget.h
>    llvm/trunk/lib/Target/NVPTX/NVPTXTargetMachine.cpp
>    llvm/trunk/lib/Target/NVPTX/NVPTXTargetMachine.h
>    llvm/trunk/lib/Target/NVPTX/NVPTXTargetObjectFile.h
>    llvm/trunk/lib/Target/NVPTX/NVPTXUtilities.cpp
>    llvm/trunk/lib/Target/NVPTX/NVPTXUtilities.h
>    llvm/trunk/lib/Target/NVPTX/NVPTXVector.td
>    llvm/trunk/lib/Target/NVPTX/NVPTXutil.cpp
>    llvm/trunk/lib/Target/NVPTX/NVPTXutil.h
>    llvm/trunk/lib/Target/NVPTX/TargetInfo/
>    llvm/trunk/lib/Target/NVPTX/TargetInfo/CMakeLists.txt
>    llvm/trunk/lib/Target/NVPTX/TargetInfo/LLVMBuild.txt
>    llvm/trunk/lib/Target/NVPTX/TargetInfo/Makefile
>    llvm/trunk/lib/Target/NVPTX/TargetInfo/NVPTXTargetInfo.cpp
>    llvm/trunk/lib/Target/NVPTX/VectorElementize.cpp
>    llvm/trunk/lib/Target/NVPTX/cl_common_defines.h
>    llvm/trunk/lib/Target/NVPTX/gen-register-defs.py
>    llvm/trunk/test/CodeGen/NVPTX/
>    llvm/trunk/test/CodeGen/NVPTX/annotations.ll
>    llvm/trunk/test/CodeGen/NVPTX/arithmetic-fp-sm10.ll
>    llvm/trunk/test/CodeGen/NVPTX/arithmetic-fp-sm20.ll
>    llvm/trunk/test/CodeGen/NVPTX/arithmetic-int.ll
>    llvm/trunk/test/CodeGen/NVPTX/calling-conv.ll
>    llvm/trunk/test/CodeGen/NVPTX/compare-int.ll
>    llvm/trunk/test/CodeGen/NVPTX/convert-fp.ll
>    llvm/trunk/test/CodeGen/NVPTX/convert-int-sm10.ll
>    llvm/trunk/test/CodeGen/NVPTX/convert-int-sm20.ll
>    llvm/trunk/test/CodeGen/NVPTX/fma-disable.ll
>    llvm/trunk/test/CodeGen/NVPTX/fma.ll
>    llvm/trunk/test/CodeGen/NVPTX/intrinsic-old.ll
>    llvm/trunk/test/CodeGen/NVPTX/ld-addrspace.ll
>    llvm/trunk/test/CodeGen/NVPTX/ld-generic.ll
>    llvm/trunk/test/CodeGen/NVPTX/lit.local.cfg
>    llvm/trunk/test/CodeGen/NVPTX/st-addrspace.ll
>    llvm/trunk/test/CodeGen/NVPTX/st-generic.ll
> Modified:
>    llvm/trunk/CMakeLists.txt
>    llvm/trunk/autoconf/configure.ac
>    llvm/trunk/configure
>    llvm/trunk/include/llvm/ADT/Triple.h
>    llvm/trunk/include/llvm/Intrinsics.td
>    llvm/trunk/lib/Support/Triple.cpp
>    llvm/trunk/lib/Target/LLVMBuild.txt
>    llvm/trunk/projects/sample/autoconf/configure.ac
>    llvm/trunk/projects/sample/configure
>
> Modified: llvm/trunk/CMakeLists.txt
> URL:
> http://llvm.org/viewvc/llvm-project/llvm/trunk/CMakeLists.txt?rev=156196&r1=156195&r2=156196&view=diff
>
> ==============================================================================
> --- llvm/trunk/CMakeLists.txt (original)
> +++ llvm/trunk/CMakeLists.txt Fri May  4 15:18:50 2012
> @@ -78,6 +78,7 @@
>   Mips
>   MBlaze
>   MSP430
> +  NVPTX
>   PowerPC
>   PTX
>   Sparc
>
> Modified: llvm/trunk/autoconf/configure.ac
> URL:
> http://llvm.org/viewvc/llvm-project/llvm/trunk/autoconf/configure.ac?rev=156196&r1=156195&r2=156196&view=diff
>
> ==============================================================================
> --- llvm/trunk/autoconf/configure.ac (original)
> +++ llvm/trunk/autoconf/configure.ac Fri May  4 15:18:50 2012
> @@ -370,6 +370,7 @@
>   hexagon-*)              llvm_cv_target_arch="Hexagon" ;;
>   mblaze-*)               llvm_cv_target_arch="MBlaze" ;;
>   ptx-*)                  llvm_cv_target_arch="PTX" ;;
> +  nvptx-*)                llvm_cv_target_arch="NVPTX" ;;
>   *)                      llvm_cv_target_arch="Unknown" ;;
>  esac])
>
> @@ -517,6 +518,7 @@
>     Hexagon)     AC_SUBST(TARGET_HAS_JIT,0) ;;
>     MBlaze)      AC_SUBST(TARGET_HAS_JIT,0) ;;
>     PTX)         AC_SUBST(TARGET_HAS_JIT,0) ;;
> +    NVPTX)       AC_SUBST(TARGET_HAS_JIT,0) ;;
>     *)           AC_SUBST(TARGET_HAS_JIT,0) ;;
>   esac
>  fi
> @@ -628,13 +630,13 @@
>  AC_ARG_ENABLE([targets],AS_HELP_STRING([--enable-targets],
>     [Build specific host targets: all or target1,target2,... Valid targets
> are:
>      host, x86, x86_64, sparc, powerpc, arm, mips, spu, hexagon,
> -     xcore, msp430, ptx, and cpp (default=all)]),,
> +     xcore, msp430, ptx, nvptx, and cpp (default=all)]),,
>     enableval=all)
>  if test "$enableval" = host-only ; then
>   enableval=host
>  fi
>  case "$enableval" in
> -  all) TARGETS_TO_BUILD="X86 Sparc PowerPC ARM Mips CellSPU XCore MSP430
> CppBackend MBlaze PTX Hexagon" ;;
> +  all) TARGETS_TO_BUILD="X86 Sparc PowerPC ARM Mips CellSPU XCore MSP430
> CppBackend MBlaze PTX NVPTX Hexagon" ;;
>   *)for a_target in `echo $enableval|sed -e 's/,/ /g' ` ; do
>       case "$a_target" in
>         x86)      TARGETS_TO_BUILD="X86 $TARGETS_TO_BUILD" ;;
> @@ -651,6 +653,7 @@
>         hexagon)  TARGETS_TO_BUILD="Hexagon $TARGETS_TO_BUILD" ;;
>         mblaze)   TARGETS_TO_BUILD="MBlaze $TARGETS_TO_BUILD" ;;
>         ptx)      TARGETS_TO_BUILD="PTX $TARGETS_TO_BUILD" ;;
> +        nvptx)    TARGETS_TO_BUILD="NVPTX $TARGETS_TO_BUILD" ;;
>         host) case "$llvm_cv_target_arch" in
>             x86)         TARGETS_TO_BUILD="X86 $TARGETS_TO_BUILD" ;;
>             x86_64)      TARGETS_TO_BUILD="X86 $TARGETS_TO_BUILD" ;;
> @@ -664,6 +667,7 @@
>             MSP430)      TARGETS_TO_BUILD="MSP430 $TARGETS_TO_BUILD" ;;
>             Hexagon)     TARGETS_TO_BUILD="Hexagon $TARGETS_TO_BUILD" ;;
>             PTX)         TARGETS_TO_BUILD="PTX $TARGETS_TO_BUILD" ;;
> +            NVPTX)       TARGETS_TO_BUILD="NVPTX $TARGETS_TO_BUILD" ;;
>             *)       AC_MSG_ERROR([Can not set target to build]) ;;
>           esac ;;
>         *) AC_MSG_ERROR([Unrecognized target $a_target]) ;;
>
> Modified: llvm/trunk/configure
> URL:
> http://llvm.org/viewvc/llvm-project/llvm/trunk/configure?rev=156196&r1=156195&r2=156196&view=diff
>
> ==============================================================================
> --- llvm/trunk/configure (original)
> +++ llvm/trunk/configure Fri May  4 15:18:50 2012
> @@ -1420,7 +1420,7 @@
>   --enable-targets        Build specific host targets: all or
>                           target1,target2,... Valid targets are: host, x86,
>                           x86_64, sparc, powerpc, arm, mips, spu, hexagon,
> -                          xcore, msp430, ptx, and cpp (default=all)
> +                          xcore, msp430, ptx, nvptx, and cpp (default=all)
>   --enable-bindings       Build specific language bindings:
>                           all,auto,none,{binding-name} (default=auto)
>   --enable-libffi         Check for the presence of libffi (default is NO)
> @@ -3903,6 +3903,7 @@
>   hexagon-*)              llvm_cv_target_arch="Hexagon" ;;
>   mblaze-*)               llvm_cv_target_arch="MBlaze" ;;
>   ptx-*)                  llvm_cv_target_arch="PTX" ;;
> +  nvptx-*)                llvm_cv_target_arch="NVPTX" ;;
>   *)                      llvm_cv_target_arch="Unknown" ;;
>  esac
>  fi
> @@ -5126,6 +5127,8 @@
>  ;;
>     PTX)         TARGET_HAS_JIT=0
>  ;;
> +    NVPTX)       TARGET_HAS_JIT=0
> + ;;
>     *)           TARGET_HAS_JIT=0
>  ;;
>   esac
> @@ -5310,7 +5313,7 @@
>   enableval=host
>  fi
>  case "$enableval" in
> -  all) TARGETS_TO_BUILD="X86 Sparc PowerPC ARM Mips CellSPU XCore MSP430
> CppBackend MBlaze PTX Hexagon" ;;
> +  all) TARGETS_TO_BUILD="X86 Sparc PowerPC ARM Mips CellSPU XCore MSP430
> CppBackend MBlaze PTX NVPTX Hexagon" ;;
>   *)for a_target in `echo $enableval|sed -e 's/,/ /g' ` ; do
>       case "$a_target" in
>         x86)      TARGETS_TO_BUILD="X86 $TARGETS_TO_BUILD" ;;
> @@ -5327,6 +5330,7 @@
>         hexagon)  TARGETS_TO_BUILD="Hexagon $TARGETS_TO_BUILD" ;;
>         mblaze)   TARGETS_TO_BUILD="MBlaze $TARGETS_TO_BUILD" ;;
>         ptx)      TARGETS_TO_BUILD="PTX $TARGETS_TO_BUILD" ;;
> +        nvptx)    TARGETS_TO_BUILD="NVPTX $TARGETS_TO_BUILD" ;;
>         host) case "$llvm_cv_target_arch" in
>             x86)         TARGETS_TO_BUILD="X86 $TARGETS_TO_BUILD" ;;
>             x86_64)      TARGETS_TO_BUILD="X86 $TARGETS_TO_BUILD" ;;
> @@ -5340,6 +5344,7 @@
>             MSP430)      TARGETS_TO_BUILD="MSP430 $TARGETS_TO_BUILD" ;;
>             Hexagon)     TARGETS_TO_BUILD="Hexagon $TARGETS_TO_BUILD" ;;
>             PTX)         TARGETS_TO_BUILD="PTX $TARGETS_TO_BUILD" ;;
> +            NVPTX)       TARGETS_TO_BUILD="NVPTX $TARGETS_TO_BUILD" ;;
>             *)       { { echo "$as_me:$LINENO: error: Can not set target
> to build" >&5
>  echo "$as_me: error: Can not set target to build" >&2;}
>    { (exit 1); exit 1; }; } ;;
> @@ -10401,7 +10406,7 @@
>   lt_dlunknown=0; lt_dlno_uscore=1; lt_dlneed_uscore=2
>   lt_status=$lt_dlunknown
>   cat > conftest.$ac_ext <<EOF
> -#line 10404 "configure"
> +#line 10409 "configure"
>  #include "confdefs.h"
>
>  #if HAVE_DLFCN_H
>
> Modified: llvm/trunk/include/llvm/ADT/Triple.h
> URL:
> http://llvm.org/viewvc/llvm-project/llvm/trunk/include/llvm/ADT/Triple.h?rev=156196&r1=156195&r2=156196&view=diff
>
> ==============================================================================
> --- llvm/trunk/include/llvm/ADT/Triple.h (original)
> +++ llvm/trunk/include/llvm/ADT/Triple.h Fri May  4 15:18:50 2012
> @@ -64,6 +64,8 @@
>     mblaze,  // MBlaze: mblaze
>     ptx32,   // PTX: ptx (32-bit)
>     ptx64,   // PTX: ptx (64-bit)
> +    nvptx,   // NVPTX: 32-bit
> +    nvptx64, // NVPTX: 64-bit
>     le32,    // le32: generic little-endian 32-bit CPU (PNaCl / Emscripten)
>     amdil   // amdil: amd IL
>   };
>
> Modified: llvm/trunk/include/llvm/Intrinsics.td
> URL:
> http://llvm.org/viewvc/llvm-project/llvm/trunk/include/llvm/Intrinsics.td?rev=156196&r1=156195&r2=156196&view=diff
>
> ==============================================================================
> --- llvm/trunk/include/llvm/Intrinsics.td (original)
> +++ llvm/trunk/include/llvm/Intrinsics.td Fri May  4 15:18:50 2012
> @@ -441,3 +441,4 @@
>  include "llvm/IntrinsicsXCore.td"
>  include "llvm/IntrinsicsPTX.td"
>  include "llvm/IntrinsicsHexagon.td"
> +include "llvm/IntrinsicsNVVM.td"
>
> Added: llvm/trunk/include/llvm/IntrinsicsNVVM.td
> URL:
> http://llvm.org/viewvc/llvm-project/llvm/trunk/include/llvm/IntrinsicsNVVM.td?rev=156196&view=auto
>
> ==============================================================================
> --- llvm/trunk/include/llvm/IntrinsicsNVVM.td (added)
> +++ llvm/trunk/include/llvm/IntrinsicsNVVM.td Fri May  4 15:18:50 2012
> @@ -0,0 +1,872 @@
> +//===- IntrinsicsNVVM.td - Defines NVVM intrinsics ---------*- tablegen
> -*-===//
> +//
> +//                     The LLVM Compiler Infrastructure
> +//
> +// This file is distributed under the University of Illinois Open Source
> +// License. See LICENSE.TXT for details.
> +//
>
> +//===----------------------------------------------------------------------===//
> +//
> +// This file defines all of the NVVM-specific intrinsics for use with
> NVPTX.
> +//
>
> +//===----------------------------------------------------------------------===//
> +
> +def llvm_anyi64ptr_ty     : LLVMAnyPointerType<llvm_i64_ty>;     //
> (space)i64*
> +
> +//
> +// MISC
> +//
> +
> +  def int_nvvm_clz_i : GCCBuiltin<"__nvvm_clz_i">,
> +      Intrinsic<[llvm_i32_ty], [llvm_i32_ty], [IntrNoMem]>;
> +  def int_nvvm_clz_ll : GCCBuiltin<"__nvvm_clz_ll">,
> +      Intrinsic<[llvm_i32_ty], [llvm_i64_ty], [IntrNoMem]>;
> +
> +  def int_nvvm_popc_i : GCCBuiltin<"__nvvm_popc_i">,
> +      Intrinsic<[llvm_i32_ty], [llvm_i32_ty], [IntrNoMem]>;
> +  def int_nvvm_popc_ll : GCCBuiltin<"__nvvm_popc_ll">,
> +      Intrinsic<[llvm_i32_ty], [llvm_i64_ty], [IntrNoMem]>;
> +
> +  def int_nvvm_prmt : GCCBuiltin<"__nvvm_prmt">,
> +      Intrinsic<[llvm_i32_ty], [llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
> +        [IntrNoMem, Commutative]>;
> +
> +//
> +// Min Max
> +//
> +
> +  def int_nvvm_min_i : GCCBuiltin<"__nvvm_min_i">,
> +      Intrinsic<[llvm_i32_ty], [llvm_i32_ty, llvm_i32_ty],
> +        [IntrNoMem, Commutative]>;
> +  def int_nvvm_min_ui : GCCBuiltin<"__nvvm_min_ui">,
> +      Intrinsic<[llvm_i32_ty], [llvm_i32_ty, llvm_i32_ty],
> +        [IntrNoMem, Commutative]>;
> +
> +  def int_nvvm_min_ll : GCCBuiltin<"__nvvm_min_ll">,
> +      Intrinsic<[llvm_i64_ty], [llvm_i64_ty, llvm_i64_ty],
> +        [IntrNoMem, Commutative]>;
> +  def int_nvvm_min_ull : GCCBuiltin<"__nvvm_min_ull">,
> +      Intrinsic<[llvm_i64_ty], [llvm_i64_ty, llvm_i64_ty],
> +        [IntrNoMem, Commutative]>;
> +
> +  def int_nvvm_max_i : GCCBuiltin<"__nvvm_max_i">,
> +      Intrinsic<[llvm_i32_ty], [llvm_i32_ty, llvm_i32_ty],
> +        [IntrNoMem, Commutative]>;
> +  def int_nvvm_max_ui : GCCBuiltin<"__nvvm_max_ui">,
> +      Intrinsic<[llvm_i32_ty], [llvm_i32_ty, llvm_i32_ty],
> +        [IntrNoMem, Commutative]>;
> +
> +  def int_nvvm_max_ll : GCCBuiltin<"__nvvm_max_ll">,
> +      Intrinsic<[llvm_i64_ty], [llvm_i64_ty, llvm_i64_ty],
> +        [IntrNoMem, Commutative]>;
> +  def int_nvvm_max_ull : GCCBuiltin<"__nvvm_max_ull">,
> +      Intrinsic<[llvm_i64_ty], [llvm_i64_ty, llvm_i64_ty],
> +        [IntrNoMem, Commutative]>;
> +
> +  def int_nvvm_fmin_f : GCCBuiltin<"__nvvm_fmin_f">,
> +      Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_float_ty],
> +        [IntrNoMem, Commutative]>;
> +  def int_nvvm_fmin_ftz_f : GCCBuiltin<"__nvvm_fmin_ftz_f">,
> +      Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_float_ty],
> +        [IntrNoMem, Commutative]>;
> +
> +  def int_nvvm_fmax_f : GCCBuiltin<"__nvvm_fmax_f">,
> +      Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_float_ty]
> +        , [IntrNoMem, Commutative]>;
> +  def int_nvvm_fmax_ftz_f : GCCBuiltin<"__nvvm_fmax_ftz_f">,
> +      Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_float_ty],
> +        [IntrNoMem, Commutative]>;
> +
> +  def int_nvvm_fmin_d : GCCBuiltin<"__nvvm_fmin_d">,
> +      Intrinsic<[llvm_double_ty], [llvm_double_ty, llvm_double_ty],
> +        [IntrNoMem, Commutative]>;
> +  def int_nvvm_fmax_d : GCCBuiltin<"__nvvm_fmax_d">,
> +      Intrinsic<[llvm_double_ty], [llvm_double_ty, llvm_double_ty],
> +        [IntrNoMem, Commutative]>;
> +
> +//
> +// Multiplication
> +//
> +
> +  def int_nvvm_mulhi_i : GCCBuiltin<"__nvvm_mulhi_i">,
> +      Intrinsic<[llvm_i32_ty], [llvm_i32_ty, llvm_i32_ty],
> +        [IntrNoMem, Commutative]>;
> +  def int_nvvm_mulhi_ui : GCCBuiltin<"__nvvm_mulhi_ui">,
> +      Intrinsic<[llvm_i32_ty], [llvm_i32_ty, llvm_i32_ty],
> +        [IntrNoMem, Commutative]>;
> +
> +  def int_nvvm_mulhi_ll : GCCBuiltin<"__nvvm_mulhi_ll">,
> +      Intrinsic<[llvm_i64_ty], [llvm_i64_ty, llvm_i64_ty],
> +        [IntrNoMem, Commutative]>;
> +  def int_nvvm_mulhi_ull : GCCBuiltin<"__nvvm_mulhi_ull">,
> +      Intrinsic<[llvm_i64_ty], [llvm_i64_ty, llvm_i64_ty],
> +        [IntrNoMem, Commutative]>;
> +
> +  def int_nvvm_mul_rn_ftz_f : GCCBuiltin<"__nvvm_mul_rn_ftz_f">,
> +      Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_float_ty],
> +        [IntrNoMem, Commutative]>;
> +  def int_nvvm_mul_rn_f : GCCBuiltin<"__nvvm_mul_rn_f">,
> +      Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_float_ty],
> +        [IntrNoMem, Commutative]>;
> +  def int_nvvm_mul_rz_ftz_f : GCCBuiltin<"__nvvm_mul_rz_ftz_f">,
> +      Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_float_ty],
> +        [IntrNoMem, Commutative]>;
> +  def int_nvvm_mul_rz_f : GCCBuiltin<"__nvvm_mul_rz_f">,
> +      Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_float_ty],
> +        [IntrNoMem, Commutative]>;
> +  def int_nvvm_mul_rm_ftz_f : GCCBuiltin<"__nvvm_mul_rm_ftz_f">,
> +      Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_float_ty],
> +        [IntrNoMem, Commutative]>;
> +  def int_nvvm_mul_rm_f : GCCBuiltin<"__nvvm_mul_rm_f">,
> +      Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_float_ty],
> +        [IntrNoMem, Commutative]>;
> +  def int_nvvm_mul_rp_ftz_f : GCCBuiltin<"__nvvm_mul_rp_ftz_f">,
> +      Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_float_ty],
> +        [IntrNoMem, Commutative]>;
> +  def int_nvvm_mul_rp_f : GCCBuiltin<"__nvvm_mul_rp_f">,
> +      Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_float_ty],
> +        [IntrNoMem, Commutative]>;
> +
> +  def int_nvvm_mul_rn_d : GCCBuiltin<"__nvvm_mul_rn_d">,
> +      Intrinsic<[llvm_double_ty], [llvm_double_ty, llvm_double_ty],
> +        [IntrNoMem, Commutative]>;
> +  def int_nvvm_mul_rz_d : GCCBuiltin<"__nvvm_mul_rz_d">,
> +      Intrinsic<[llvm_double_ty], [llvm_double_ty, llvm_double_ty],
> +        [IntrNoMem, Commutative]>;
> +  def int_nvvm_mul_rm_d : GCCBuiltin<"__nvvm_mul_rm_d">,
> +      Intrinsic<[llvm_double_ty], [llvm_double_ty, llvm_double_ty],
> +        [IntrNoMem, Commutative]>;
> +  def int_nvvm_mul_rp_d : GCCBuiltin<"__nvvm_mul_rp_d">,
> +      Intrinsic<[llvm_double_ty], [llvm_double_ty, llvm_double_ty],
> +        [IntrNoMem, Commutative]>;
> +
> +  def int_nvvm_mul24_i : GCCBuiltin<"__nvvm_mul24_i">,
> +      Intrinsic<[llvm_i32_ty], [llvm_i32_ty, llvm_i32_ty],
> +        [IntrNoMem, Commutative]>;
> +  def int_nvvm_mul24_ui : GCCBuiltin<"__nvvm_mul24_ui">,
> +      Intrinsic<[llvm_i32_ty], [llvm_i32_ty, llvm_i32_ty],
> +        [IntrNoMem, Commutative]>;
> +
> +//
> +// Div
> +//
> +
> +  def int_nvvm_div_approx_ftz_f : GCCBuiltin<"__nvvm_div_approx_ftz_f">,
> +      Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_float_ty],
> +        [IntrNoMem, Commutative]>;
> +  def int_nvvm_div_approx_f : GCCBuiltin<"__nvvm_div_approx_f">,
> +      Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_float_ty],
> +        [IntrNoMem, Commutative]>;
> +
> +  def int_nvvm_div_rn_ftz_f : GCCBuiltin<"__nvvm_div_rn_ftz_f">,
> +      Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_float_ty],
> +        [IntrNoMem, Commutative]>;
> +  def int_nvvm_div_rn_f : GCCBuiltin<"__nvvm_div_rn_f">,
> +      Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_float_ty],
> +        [IntrNoMem, Commutative]>;
> +
> +  def int_nvvm_div_rz_ftz_f : GCCBuiltin<"__nvvm_div_rz_ftz_f">,
> +      Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_float_ty],
> +        [IntrNoMem, Commutative]>;
> +  def int_nvvm_div_rz_f : GCCBuiltin<"__nvvm_div_rz_f">,
> +      Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_float_ty],
> +        [IntrNoMem, Commutative]>;
> +
> +  def int_nvvm_div_rm_ftz_f : GCCBuiltin<"__nvvm_div_rm_ftz_f">,
> +      Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_float_ty],
> +        [IntrNoMem, Commutative]>;
> +  def int_nvvm_div_rm_f : GCCBuiltin<"__nvvm_div_rm_f">,
> +      Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_float_ty],
> +        [IntrNoMem, Commutative]>;
> +
> +  def int_nvvm_div_rp_ftz_f : GCCBuiltin<"__nvvm_div_rp_ftz_f">,
> +      Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_float_ty],
> +        [IntrNoMem, Commutative]>;
> +  def int_nvvm_div_rp_f : GCCBuiltin<"__nvvm_div_rp_f">,
> +      Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_float_ty],
> +        [IntrNoMem, Commutative]>;
> +
> +  def int_nvvm_div_rn_d : GCCBuiltin<"__nvvm_div_rn_d">,
> +      Intrinsic<[llvm_double_ty], [llvm_double_ty, llvm_double_ty],
> +        [IntrNoMem, Commutative]>;
> +  def int_nvvm_div_rz_d : GCCBuiltin<"__nvvm_div_rz_d">,
> +      Intrinsic<[llvm_double_ty], [llvm_double_ty, llvm_double_ty],
> +        [IntrNoMem, Commutative]>;
> +  def int_nvvm_div_rm_d : GCCBuiltin<"__nvvm_div_rm_d">,
> +      Intrinsic<[llvm_double_ty], [llvm_double_ty, llvm_double_ty],
> +        [IntrNoMem, Commutative]>;
> +  def int_nvvm_div_rp_d : GCCBuiltin<"__nvvm_div_rp_d">,
> +      Intrinsic<[llvm_double_ty], [llvm_double_ty, llvm_double_ty],
> +        [IntrNoMem, Commutative]>;
> +
> +//
> +// Brev
> +//
> +
> +  def int_nvvm_brev32 : GCCBuiltin<"__nvvm_brev32">,
> +      Intrinsic<[llvm_i32_ty], [llvm_i32_ty], [IntrNoMem]>;
> +  def int_nvvm_brev64 : GCCBuiltin<"__nvvm_brev64">,
> +      Intrinsic<[llvm_i64_ty], [llvm_i64_ty], [IntrNoMem]>;
> +
> +//
> +// Sad
> +//
> +
> +  def int_nvvm_sad_i : GCCBuiltin<"__nvvm_sad_i">,
> +      Intrinsic<[llvm_i32_ty], [llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
> +        [IntrNoMem, Commutative]>;
> +  def int_nvvm_sad_ui : GCCBuiltin<"__nvvm_sad_ui">,
> +      Intrinsic<[llvm_i32_ty], [llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
> +        [IntrNoMem, Commutative]>;
> +
> +//
> +// Floor  Ceil
> +//
> +
> +  def int_nvvm_floor_ftz_f : GCCBuiltin<"__nvvm_floor_ftz_f">,
> +      Intrinsic<[llvm_float_ty], [llvm_float_ty], [IntrNoMem]>;
> +  def int_nvvm_floor_f : GCCBuiltin<"__nvvm_floor_f">,
> +      Intrinsic<[llvm_float_ty], [llvm_float_ty], [IntrNoMem]>;
> +  def int_nvvm_floor_d : GCCBuiltin<"__nvvm_floor_d">,
> +      Intrinsic<[llvm_double_ty], [llvm_double_ty], [IntrNoMem]>;
> +
> +  def int_nvvm_ceil_ftz_f : GCCBuiltin<"__nvvm_ceil_ftz_f">,
> +      Intrinsic<[llvm_float_ty], [llvm_float_ty], [IntrNoMem]>;
> +  def int_nvvm_ceil_f : GCCBuiltin<"__nvvm_ceil_f">,
> +      Intrinsic<[llvm_float_ty], [llvm_float_ty], [IntrNoMem]>;
> +  def int_nvvm_ceil_d : GCCBuiltin<"__nvvm_ceil_d">,
> +      Intrinsic<[llvm_double_ty], [llvm_double_ty], [IntrNoMem]>;
> +
> +//
> +// Abs
> +//
> +
> +  def int_nvvm_abs_i : GCCBuiltin<"__nvvm_abs_i">,
> +      Intrinsic<[llvm_i32_ty], [llvm_i32_ty], [IntrNoMem]>;
> +  def int_nvvm_abs_ll : GCCBuiltin<"__nvvm_abs_ll">,
> +      Intrinsic<[llvm_i64_ty], [llvm_i64_ty], [IntrNoMem]>;
> +
> +  def int_nvvm_fabs_ftz_f : GCCBuiltin<"__nvvm_fabs_ftz_f">,
> +      Intrinsic<[llvm_float_ty], [llvm_float_ty], [IntrNoMem]>;
> +  def int_nvvm_fabs_f : GCCBuiltin<"__nvvm_fabs_f">,
> +      Intrinsic<[llvm_float_ty], [llvm_float_ty], [IntrNoMem]>;
> +
> +  def int_nvvm_fabs_d : GCCBuiltin<"__nvvm_fabs_d">,
> +      Intrinsic<[llvm_double_ty], [llvm_double_ty], [IntrNoMem]>;
> +
> +//
> +// Round
> +//
> +
> +  def int_nvvm_round_ftz_f : GCCBuiltin<"__nvvm_round_ftz_f">,
> +      Intrinsic<[llvm_float_ty], [llvm_float_ty], [IntrNoMem]>;
> +  def int_nvvm_round_f : GCCBuiltin<"__nvvm_round_f">,
> +      Intrinsic<[llvm_float_ty], [llvm_float_ty], [IntrNoMem]>;
> +
> +  def int_nvvm_round_d : GCCBuiltin<"__nvvm_round_d">,
> +      Intrinsic<[llvm_double_ty], [llvm_double_ty], [IntrNoMem]>;
> +
> +//
> +// Trunc
> +//
> +
> +  def int_nvvm_trunc_ftz_f : GCCBuiltin<"__nvvm_trunc_ftz_f">,
> +      Intrinsic<[llvm_float_ty], [llvm_float_ty], [IntrNoMem]>;
> +  def int_nvvm_trunc_f : GCCBuiltin<"__nvvm_trunc_f">,
> +      Intrinsic<[llvm_float_ty], [llvm_float_ty], [IntrNoMem]>;
> +
> +  def int_nvvm_trunc_d : GCCBuiltin<"__nvvm_trunc_d">,
> +      Intrinsic<[llvm_double_ty], [llvm_double_ty], [IntrNoMem]>;
> +
> +//
> +// Saturate
> +//
> +
> +  def int_nvvm_saturate_ftz_f : GCCBuiltin<"__nvvm_saturate_ftz_f">,
> +      Intrinsic<[llvm_float_ty], [llvm_float_ty], [IntrNoMem]>;
> +  def int_nvvm_saturate_f : GCCBuiltin<"__nvvm_saturate_f">,
> +      Intrinsic<[llvm_float_ty], [llvm_float_ty], [IntrNoMem]>;
> +
> +  def int_nvvm_saturate_d : GCCBuiltin<"__nvvm_saturate_d">,
> +      Intrinsic<[llvm_double_ty], [llvm_double_ty], [IntrNoMem]>;
> +
> +//
> +// Exp2  Log2
> +//
> +
> +  def int_nvvm_ex2_approx_ftz_f : GCCBuiltin<"__nvvm_ex2_approx_ftz_f">,
> +      Intrinsic<[llvm_float_ty], [llvm_float_ty], [IntrNoMem]>;
> +  def int_nvvm_ex2_approx_f : GCCBuiltin<"__nvvm_ex2_approx_f">,
> +      Intrinsic<[llvm_float_ty], [llvm_float_ty], [IntrNoMem]>;
> +  def int_nvvm_ex2_approx_d : GCCBuiltin<"__nvvm_ex2_approx_d">,
> +      Intrinsic<[llvm_double_ty], [llvm_double_ty], [IntrNoMem]>;
> +
> +  def int_nvvm_lg2_approx_ftz_f : GCCBuiltin<"__nvvm_lg2_approx_ftz_f">,
> +      Intrinsic<[llvm_float_ty], [llvm_float_ty], [IntrNoMem]>;
> +  def int_nvvm_lg2_approx_f : GCCBuiltin<"__nvvm_lg2_approx_f">,
> +      Intrinsic<[llvm_float_ty], [llvm_float_ty], [IntrNoMem]>;
> +  def int_nvvm_lg2_approx_d : GCCBuiltin<"__nvvm_lg2_approx_d">,
> +      Intrinsic<[llvm_double_ty], [llvm_double_ty], [IntrNoMem]>;
> +
> +//
> +// Sin  Cos
> +//
> +
> +  def int_nvvm_sin_approx_ftz_f : GCCBuiltin<"__nvvm_sin_approx_ftz_f">,
> +      Intrinsic<[llvm_float_ty], [llvm_float_ty], [IntrNoMem]>;
> +  def int_nvvm_sin_approx_f : GCCBuiltin<"__nvvm_sin_approx_f">,
> +      Intrinsic<[llvm_float_ty], [llvm_float_ty], [IntrNoMem]>;
> +
> +  def int_nvvm_cos_approx_ftz_f : GCCBuiltin<"__nvvm_cos_approx_ftz_f">,
> +      Intrinsic<[llvm_float_ty], [llvm_float_ty], [IntrNoMem]>;
> +  def int_nvvm_cos_approx_f : GCCBuiltin<"__nvvm_cos_approx_f">,
> +      Intrinsic<[llvm_float_ty], [llvm_float_ty], [IntrNoMem]>;
> +
> +//
> +// Fma
> +//
> +
> +  def int_nvvm_fma_rn_ftz_f : GCCBuiltin<"__nvvm_fma_rn_ftz_f">,
> +      Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_float_ty,
> llvm_float_ty],
> +        [IntrNoMem, Commutative]>;
> +  def int_nvvm_fma_rn_f : GCCBuiltin<"__nvvm_fma_rn_f">,
> +      Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_float_ty,
> llvm_float_ty],
> +        [IntrNoMem, Commutative]>;
> +  def int_nvvm_fma_rz_ftz_f : GCCBuiltin<"__nvvm_fma_rz_ftz_f">,
> +      Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_float_ty,
> llvm_float_ty],
> +        [IntrNoMem, Commutative]>;
> +  def int_nvvm_fma_rz_f : GCCBuiltin<"__nvvm_fma_rz_f">,
> +      Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_float_ty,
> llvm_float_ty],
> +        [IntrNoMem, Commutative]>;
> +  def int_nvvm_fma_rm_ftz_f : GCCBuiltin<"__nvvm_fma_rm_ftz_f">,
> +      Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_float_ty,
> llvm_float_ty],
> +        [IntrNoMem, Commutative]>;
> +  def int_nvvm_fma_rm_f : GCCBuiltin<"__nvvm_fma_rm_f">,
> +      Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_float_ty,
> llvm_float_ty],
> +        [IntrNoMem, Commutative]>;
> +  def int_nvvm_fma_rp_ftz_f : GCCBuiltin<"__nvvm_fma_rp_ftz_f">,
> +      Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_float_ty,
> llvm_float_ty],
> +        [IntrNoMem, Commutative]>;
> +  def int_nvvm_fma_rp_f : GCCBuiltin<"__nvvm_fma_rp_f">,
> +      Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_float_ty,
> llvm_float_ty],
> +        [IntrNoMem, Commutative]>;
> +
> +  def int_nvvm_fma_rn_d : GCCBuiltin<"__nvvm_fma_rn_d">,
> +      Intrinsic<[llvm_double_ty],
> +        [llvm_double_ty, llvm_double_ty, llvm_double_ty],
> +        [IntrNoMem, Commutative]>;
> +  def int_nvvm_fma_rz_d : GCCBuiltin<"__nvvm_fma_rz_d">,
> +      Intrinsic<[llvm_double_ty],
> +        [llvm_double_ty, llvm_double_ty, llvm_double_ty],
> +        [IntrNoMem, Commutative]>;
> +  def int_nvvm_fma_rm_d : GCCBuiltin<"__nvvm_fma_rm_d">,
> +      Intrinsic<[llvm_double_ty],
> +        [llvm_double_ty, llvm_double_ty, llvm_double_ty],
> +        [IntrNoMem, Commutative]>;
> +  def int_nvvm_fma_rp_d : GCCBuiltin<"__nvvm_fma_rp_d">,
> +      Intrinsic<[llvm_double_ty],
> +        [llvm_double_ty, llvm_double_ty, llvm_double_ty],
> +        [IntrNoMem, Commutative]>;
> +
> +//
> +// Rcp
> +//
> +
> +  def int_nvvm_rcp_rn_ftz_f : GCCBuiltin<"__nvvm_rcp_rn_ftz_f">,
> +      Intrinsic<[llvm_float_ty], [llvm_float_ty], [IntrNoMem]>;
> +  def int_nvvm_rcp_rn_f : GCCBuiltin<"__nvvm_rcp_rn_f">,
> +      Intrinsic<[llvm_float_ty], [llvm_float_ty], [IntrNoMem]>;
> +  def int_nvvm_rcp_rz_ftz_f : GCCBuiltin<"__nvvm_rcp_rz_ftz_f">,
> +      Intrinsic<[llvm_float_ty], [llvm_float_ty], [IntrNoMem]>;
> +  def int_nvvm_rcp_rz_f : GCCBuiltin<"__nvvm_rcp_rz_f">,
> +      Intrinsic<[llvm_float_ty], [llvm_float_ty], [IntrNoMem]>;
> +  def int_nvvm_rcp_rm_ftz_f : GCCBuiltin<"__nvvm_rcp_rm_ftz_f">,
> +      Intrinsic<[llvm_float_ty], [llvm_float_ty], [IntrNoMem]>;
> +  def int_nvvm_rcp_rm_f : GCCBuiltin<"__nvvm_rcp_rm_f">,
> +      Intrinsic<[llvm_float_ty], [llvm_float_ty], [IntrNoMem]>;
> +  def int_nvvm_rcp_rp_ftz_f : GCCBuiltin<"__nvvm_rcp_rp_ftz_f">,
> +      Intrinsic<[llvm_float_ty], [llvm_float_ty], [IntrNoMem]>;
> +  def int_nvvm_rcp_rp_f : GCCBuiltin<"__nvvm_rcp_rp_f">,
> +      Intrinsic<[llvm_float_ty], [llvm_float_ty], [IntrNoMem]>;
> +
> +  def int_nvvm_rcp_rn_d : GCCBuiltin<"__nvvm_rcp_rn_d">,
> +      Intrinsic<[llvm_double_ty], [llvm_double_ty], [IntrNoMem]>;
> +  def int_nvvm_rcp_rz_d : GCCBuiltin<"__nvvm_rcp_rz_d">,
> +      Intrinsic<[llvm_double_ty], [llvm_double_ty], [IntrNoMem]>;
> +  def int_nvvm_rcp_rm_d : GCCBuiltin<"__nvvm_rcp_rm_d">,
> +      Intrinsic<[llvm_double_ty], [llvm_double_ty], [IntrNoMem]>;
> +  def int_nvvm_rcp_rp_d : GCCBuiltin<"__nvvm_rcp_rp_d">,
> +      Intrinsic<[llvm_double_ty], [llvm_double_ty], [IntrNoMem]>;
> +
> +  def int_nvvm_rcp_approx_ftz_d : GCCBuiltin<"__nvvm_rcp_approx_ftz_d">,
> +      Intrinsic<[llvm_double_ty], [llvm_double_ty], [IntrNoMem]>;
> +
> +//
> +// Sqrt
> +//
> +
> +  def int_nvvm_sqrt_rn_ftz_f : GCCBuiltin<"__nvvm_sqrt_rn_ftz_f">,
> +      Intrinsic<[llvm_float_ty], [llvm_float_ty], [IntrNoMem]>;
> +  def int_nvvm_sqrt_rn_f : GCCBuiltin<"__nvvm_sqrt_rn_f">,
> +      Intrinsic<[llvm_float_ty], [llvm_float_ty], [IntrNoMem]>;
> +  def int_nvvm_sqrt_rz_ftz_f : GCCBuiltin<"__nvvm_sqrt_rz_ftz_f">,
> +      Intrinsic<[llvm_float_ty], [llvm_float_ty], [IntrNoMem]>;
> +  def int_nvvm_sqrt_rz_f : GCCBuiltin<"__nvvm_sqrt_rz_f">,
> +      Intrinsic<[llvm_float_ty], [llvm_float_ty], [IntrNoMem]>;
> +  def int_nvvm_sqrt_rm_ftz_f : GCCBuiltin<"__nvvm_sqrt_rm_ftz_f">,
> +      Intrinsic<[llvm_float_ty], [llvm_float_ty], [IntrNoMem]>;
> +  def int_nvvm_sqrt_rm_f : GCCBuiltin<"__nvvm_sqrt_rm_f">,
> +      Intrinsic<[llvm_float_ty], [llvm_float_ty], [IntrNoMem]>;
> +  def int_nvvm_sqrt_rp_ftz_f : GCCBuiltin<"__nvvm_sqrt_rp_ftz_f">,
> +      Intrinsic<[llvm_float_ty], [llvm_float_ty], [IntrNoMem]>;
> +  def int_nvvm_sqrt_rp_f : GCCBuiltin<"__nvvm_sqrt_rp_f">,
> +      Intrinsic<[llvm_float_ty], [llvm_float_ty], [IntrNoMem]>;
> +  def int_nvvm_sqrt_approx_ftz_f : GCCBuiltin<"__nvvm_sqrt_approx_ftz_f">,
> +      Intrinsic<[llvm_float_ty], [llvm_float_ty], [IntrNoMem]>;
> +  def int_nvvm_sqrt_approx_f : GCCBuiltin<"__nvvm_sqrt_approx_f">,
> +      Intrinsic<[llvm_float_ty], [llvm_float_ty], [IntrNoMem]>;
> +
> +  def int_nvvm_sqrt_rn_d : GCCBuiltin<"__nvvm_sqrt_rn_d">,
> +      Intrinsic<[llvm_double_ty], [llvm_double_ty], [IntrNoMem]>;
> +  def int_nvvm_sqrt_rz_d : GCCBuiltin<"__nvvm_sqrt_rz_d">,
> +      Intrinsic<[llvm_double_ty], [llvm_double_ty], [IntrNoMem]>;
> +  def int_nvvm_sqrt_rm_d : GCCBuiltin<"__nvvm_sqrt_rm_d">,
> +      Intrinsic<[llvm_double_ty], [llvm_double_ty], [IntrNoMem]>;
> +  def int_nvvm_sqrt_rp_d : GCCBuiltin<"__nvvm_sqrt_rp_d">,
> +      Intrinsic<[llvm_double_ty], [llvm_double_ty], [IntrNoMem]>;
> +
> +//
> +// Rsqrt
> +//
> +
> +  def int_nvvm_rsqrt_approx_ftz_f :
> GCCBuiltin<"__nvvm_rsqrt_approx_ftz_f">,
> +      Intrinsic<[llvm_float_ty], [llvm_float_ty], [IntrNoMem]>;
> +  def int_nvvm_rsqrt_approx_f : GCCBuiltin<"__nvvm_rsqrt_approx_f">,
> +      Intrinsic<[llvm_float_ty], [llvm_float_ty], [IntrNoMem]>;
> +  def int_nvvm_rsqrt_approx_d : GCCBuiltin<"__nvvm_rsqrt_approx_d">,
> +      Intrinsic<[llvm_double_ty], [llvm_double_ty], [IntrNoMem]>;
> +
> +//
> +// Add
> +//
> +
> +  def int_nvvm_add_rn_ftz_f : GCCBuiltin<"__nvvm_add_rn_ftz_f">,
> +      Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_float_ty],
> +        [IntrNoMem, Commutative]>;
> +  def int_nvvm_add_rn_f : GCCBuiltin<"__nvvm_add_rn_f">,
> +      Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_float_ty],
> +        [IntrNoMem, Commutative]>;
> +  def int_nvvm_add_rz_ftz_f : GCCBuiltin<"__nvvm_add_rz_ftz_f">,
> +      Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_float_ty],
> +        [IntrNoMem, Commutative]>;
> +  def int_nvvm_add_rz_f : GCCBuiltin<"__nvvm_add_rz_f">,
> +      Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_float_ty],
> +        [IntrNoMem, Commutative]>;
> +  def int_nvvm_add_rm_ftz_f : GCCBuiltin<"__nvvm_add_rm_ftz_f">,
> +      Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_float_ty],
> +        [IntrNoMem, Commutative]>;
> +  def int_nvvm_add_rm_f : GCCBuiltin<"__nvvm_add_rm_f">,
> +      Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_float_ty],
> +        [IntrNoMem, Commutative]>;
> +  def int_nvvm_add_rp_ftz_f : GCCBuiltin<"__nvvm_add_rp_ftz_f">,
> +      Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_float_ty],
> +        [IntrNoMem, Commutative]>;
> +  def int_nvvm_add_rp_f : GCCBuiltin<"__nvvm_add_rp_f">,
> +      Intrinsic<[llvm_float_ty], [llvm_float_ty, llvm_float_ty],
> +        [IntrNoMem, Commutative]>;
> +
> +  def int_nvvm_add_rn_d : GCCBuiltin<"__nvvm_add_rn_d">,
> +      Intrinsic<[llvm_double_ty], [llvm_double_ty, llvm_double_ty],
> +        [IntrNoMem, Commutative]>;
> +  def int_nvvm_add_rz_d : GCCBuiltin<"__nvvm_add_rz_d">,
> +      Intrinsic<[llvm_double_ty], [llvm_double_ty, llvm_double_ty],
> +        [IntrNoMem, Commutative]>;
> +  def int_nvvm_add_rm_d : GCCBuiltin<"__nvvm_add_rm_d">,
> +      Intrinsic<[llvm_double_ty], [llvm_double_ty, llvm_double_ty],
> +        [IntrNoMem, Commutative]>;
> +  def int_nvvm_add_rp_d : GCCBuiltin<"__nvvm_add_rp_d">,
> +      Intrinsic<[llvm_double_ty], [llvm_double_ty, llvm_double_ty],
> +        [IntrNoMem, Commutative]>;
> +
> +//
> +// Convert
> +//
> +
> +  def int_nvvm_d2f_rn_ftz : GCCBuiltin<"__nvvm_d2f_rn_ftz">,
> +      Intrinsic<[llvm_float_ty], [llvm_double_ty], [IntrNoMem]>;
> +  def int_nvvm_d2f_rn : GCCBuiltin<"__nvvm_d2f_rn">,
> +      Intrinsic<[llvm_float_ty], [llvm_double_ty], [IntrNoMem]>;
> +  def int_nvvm_d2f_rz_ftz : GCCBuiltin<"__nvvm_d2f_rz_ftz">,
> +      Intrinsic<[llvm_float_ty], [llvm_double_ty], [IntrNoMem]>;
> +  def int_nvvm_d2f_rz : GCCBuiltin<"__nvvm_d2f_rz">,
> +      Intrinsic<[llvm_float_ty], [llvm_double_ty], [IntrNoMem]>;
> +  def int_nvvm_d2f_rm_ftz : GCCBuiltin<"__nvvm_d2f_rm_ftz">,
> +      Intrinsic<[llvm_float_ty], [llvm_double_ty], [IntrNoMem]>;
> +  def int_nvvm_d2f_rm : GCCBuiltin<"__nvvm_d2f_rm">,
> +      Intrinsic<[llvm_float_ty], [llvm_double_ty], [IntrNoMem]>;
> +  def int_nvvm_d2f_rp_ftz : GCCBuiltin<"__nvvm_d2f_rp_ftz">,
> +      Intrinsic<[llvm_float_ty], [llvm_double_ty], [IntrNoMem]>;
> +  def int_nvvm_d2f_rp : GCCBuiltin<"__nvvm_d2f_rp">,
> +      Intrinsic<[llvm_float_ty], [llvm_double_ty], [IntrNoMem]>;
> +
> +  def int_nvvm_d2i_rn : GCCBuiltin<"__nvvm_d2i_rn">,
> +      Intrinsic<[llvm_i32_ty], [llvm_double_ty], [IntrNoMem]>;
> +  def int_nvvm_d2i_rz : GCCBuiltin<"__nvvm_d2i_rz">,
> +      Intrinsic<[llvm_i32_ty], [llvm_double_ty], [IntrNoMem]>;
> +  def int_nvvm_d2i_rm : GCCBuiltin<"__nvvm_d2i_rm">,
> +      Intrinsic<[llvm_i32_ty], [llvm_double_ty], [IntrNoMem]>;
> +  def int_nvvm_d2i_rp : GCCBuiltin<"__nvvm_d2i_rp">,
> +      Intrinsic<[llvm_i32_ty], [llvm_double_ty], [IntrNoMem]>;
> +
> +  def int_nvvm_d2ui_rn : GCCBuiltin<"__nvvm_d2ui_rn">,
> +      Intrinsic<[llvm_i32_ty], [llvm_double_ty], [IntrNoMem]>;
> +  def int_nvvm_d2ui_rz : GCCBuiltin<"__nvvm_d2ui_rz">,
> +      Intrinsic<[llvm_i32_ty], [llvm_double_ty], [IntrNoMem]>;
> +  def int_nvvm_d2ui_rm : GCCBuiltin<"__nvvm_d2ui_rm">,
> +      Intrinsic<[llvm_i32_ty], [llvm_double_ty], [IntrNoMem]>;
> +  def int_nvvm_d2ui_rp : GCCBuiltin<"__nvvm_d2ui_rp">,
> +      Intrinsic<[llvm_i32_ty], [llvm_double_ty], [IntrNoMem]>;
> +
> +  def int_nvvm_i2d_rn : GCCBuiltin<"__nvvm_i2d_rn">,
> +      Intrinsic<[llvm_double_ty], [llvm_i32_ty], [IntrNoMem]>;
> +  def int_nvvm_i2d_rz : GCCBuiltin<"__nvvm_i2d_rz">,
> +      Intrinsic<[llvm_double_ty], [llvm_i32_ty], [IntrNoMem]>;
> +  def int_nvvm_i2d_rm : GCCBuiltin<"__nvvm_i2d_rm">,
> +      Intrinsic<[llvm_double_ty], [llvm_i32_ty], [IntrNoMem]>;
> +  def int_nvvm_i2d_rp : GCCBuiltin<"__nvvm_i2d_rp">,
> +      Intrinsic<[llvm_double_ty], [llvm_i32_ty], [IntrNoMem]>;
> +
> +  def int_nvvm_ui2d_rn : GCCBuiltin<"__nvvm_ui2d_rn">,
> +      Intrinsic<[llvm_double_ty], [llvm_i32_ty], [IntrNoMem]>;
> +  def int_nvvm_ui2d_rz : GCCBuiltin<"__nvvm_ui2d_rz">,
> +      Intrinsic<[llvm_double_ty], [llvm_i32_ty], [IntrNoMem]>;
> +  def int_nvvm_ui2d_rm : GCCBuiltin<"__nvvm_ui2d_rm">,
> +      Intrinsic<[llvm_double_ty], [llvm_i32_ty], [IntrNoMem]>;
> +  def int_nvvm_ui2d_rp : GCCBuiltin<"__nvvm_ui2d_rp">,
> +      Intrinsic<[llvm_double_ty], [llvm_i32_ty], [IntrNoMem]>;
> +
> +  def int_nvvm_f2i_rn_ftz : GCCBuiltin<"__nvvm_f2i_rn_ftz">,
> +      Intrinsic<[llvm_i32_ty], [llvm_float_ty], [IntrNoMem]>;
> +  def int_nvvm_f2i_rn : GCCBuiltin<"__nvvm_f2i_rn">,
> +      Intrinsic<[llvm_i32_ty], [llvm_float_ty], [IntrNoMem]>;
> +  def int_nvvm_f2i_rz_ftz : GCCBuiltin<"__nvvm_f2i_rz_ftz">,
> +      Intrinsic<[llvm_i32_ty], [llvm_float_ty], [IntrNoMem]>;
> +  def int_nvvm_f2i_rz : GCCBuiltin<"__nvvm_f2i_rz">,
> +      Intrinsic<[llvm_i32_ty], [llvm_float_ty], [IntrNoMem]>;
> +  def int_nvvm_f2i_rm_ftz : GCCBuiltin<"__nvvm_f2i_rm_ftz">,
> +      Intrinsic<[llvm_i32_ty], [llvm_float_ty], [IntrNoMem]>;
> +  def int_nvvm_f2i_rm : GCCBuiltin<"__nvvm_f2i_rm">,
> +      Intrinsic<[llvm_i32_ty], [llvm_float_ty], [IntrNoMem]>;
> +  def int_nvvm_f2i_rp_ftz : GCCBuiltin<"__nvvm_f2i_rp_ftz">,
> +      Intrinsic<[llvm_i32_ty], [llvm_float_ty], [IntrNoMem]>;
> +  def int_nvvm_f2i_rp : GCCBuiltin<"__nvvm_f2i_rp">,
> +      Intrinsic<[llvm_i32_ty], [llvm_float_ty], [IntrNoMem]>;
> +
> +  def int_nvvm_f2ui_rn_ftz : GCCBuiltin<"__nvvm_f2ui_rn_ftz">,
> +      Intrinsic<[llvm_i32_ty], [llvm_float_ty], [IntrNoMem]>;
> +  def int_nvvm_f2ui_rn : GCCBuiltin<"__nvvm_f2ui_rn">,
> +      Intrinsic<[llvm_i32_ty], [llvm_float_ty], [IntrNoMem]>;
> +  def int_nvvm_f2ui_rz_ftz : GCCBuiltin<"__nvvm_f2ui_rz_ftz">,
> +      Intrinsic<[llvm_i32_ty], [llvm_float_ty], [IntrNoMem]>;
> +  def int_nvvm_f2ui_rz : GCCBuiltin<"__nvvm_f2ui_rz">,
> +      Intrinsic<[llvm_i32_ty], [llvm_float_ty], [IntrNoMem]>;
> +  def int_nvvm_f2ui_rm_ftz : GCCBuiltin<"__nvvm_f2ui_rm_ftz">,
> +      Intrinsic<[llvm_i32_ty], [llvm_float_ty], [IntrNoMem]>;
> +  def int_nvvm_f2ui_rm : GCCBuiltin<"__nvvm_f2ui_rm">,
> +      Intrinsic<[llvm_i32_ty], [llvm_float_ty], [IntrNoMem]>;
> +  def int_nvvm_f2ui_rp_ftz : GCCBuiltin<"__nvvm_f2ui_rp_ftz">,
> +      Intrinsic<[llvm_i32_ty], [llvm_float_ty], [IntrNoMem]>;
> +  def int_nvvm_f2ui_rp : GCCBuiltin<"__nvvm_f2ui_rp">,
> +      Intrinsic<[llvm_i32_ty], [llvm_float_ty], [IntrNoMem]>;
> +
> +  def int_nvvm_i2f_rn : GCCBuiltin<"__nvvm_i2f_rn">,
> +      Intrinsic<[llvm_float_ty], [llvm_i32_ty], [IntrNoMem]>;
> +  def int_nvvm_i2f_rz : GCCBuiltin<"__nvvm_i2f_rz">,
> +      Intrinsic<[llvm_float_ty], [llvm_i32_ty], [IntrNoMem]>;
> +  def int_nvvm_i2f_rm : GCCBuiltin<"__nvvm_i2f_rm">,
> +      Intrinsic<[llvm_float_ty], [llvm_i32_ty], [IntrNoMem]>;
> +  def int_nvvm_i2f_rp : GCCBuiltin<"__nvvm_i2f_rp">,
> +      Intrinsic<[llvm_float_ty], [llvm_i32_ty], [IntrNoMem]>;
> +
> +  def int_nvvm_ui2f_rn : GCCBuiltin<"__nvvm_ui2f_rn">,
> +      Intrinsic<[llvm_float_ty], [llvm_i32_ty], [IntrNoMem]>;
> +  def int_nvvm_ui2f_rz : GCCBuiltin<"__nvvm_ui2f_rz">,
> +      Intrinsic<[llvm_float_ty], [llvm_i32_ty], [IntrNoMem]>;
> +  def int_nvvm_ui2f_rm : GCCBuiltin<"__nvvm_ui2f_rm">,
> +      Intrinsic<[llvm_float_ty], [llvm_i32_ty], [IntrNoMem]>;
> +  def int_nvvm_ui2f_rp : GCCBuiltin<"__nvvm_ui2f_rp">,
> +      Intrinsic<[llvm_float_ty], [llvm_i32_ty], [IntrNoMem]>;
> +
> +  def int_nvvm_lohi_i2d : GCCBuiltin<"__nvvm_lohi_i2d">,
> +      Intrinsic<[llvm_double_ty], [llvm_i32_ty, llvm_i32_ty],
> +        [IntrNoMem, Commutative]>;
> +
> +  def int_nvvm_d2i_lo : GCCBuiltin<"__nvvm_d2i_lo">,
> +      Intrinsic<[llvm_i32_ty], [llvm_double_ty], [IntrNoMem]>;
> +  def int_nvvm_d2i_hi : GCCBuiltin<"__nvvm_d2i_hi">,
> +      Intrinsic<[llvm_i32_ty], [llvm_double_ty], [IntrNoMem]>;
> +
> +  def int_nvvm_f2ll_rn_ftz : GCCBuiltin<"__nvvm_f2ll_rn_ftz">,
> +      Intrinsic<[llvm_i64_ty], [llvm_float_ty], [IntrNoMem]>;
> +  def int_nvvm_f2ll_rn : GCCBuiltin<"__nvvm_f2ll_rn">,
> +      Intrinsic<[llvm_i64_ty], [llvm_float_ty], [IntrNoMem]>;
> +  def int_nvvm_f2ll_rz_ftz : GCCBuiltin<"__nvvm_f2ll_rz_ftz">,
> +      Intrinsic<[llvm_i64_ty], [llvm_float_ty], [IntrNoMem]>;
> +  def int_nvvm_f2ll_rz : GCCBuiltin<"__nvvm_f2ll_rz">,
> +      Intrinsic<[llvm_i64_ty], [llvm_float_ty], [IntrNoMem]>;
> +  def int_nvvm_f2ll_rm_ftz : GCCBuiltin<"__nvvm_f2ll_rm_ftz">,
> +      Intrinsic<[llvm_i64_ty], [llvm_float_ty], [IntrNoMem]>;
> +  def int_nvvm_f2ll_rm : GCCBuiltin<"__nvvm_f2ll_rm">,
> +      Intrinsic<[llvm_i64_ty], [llvm_float_ty], [IntrNoMem]>;
> +  def int_nvvm_f2ll_rp_ftz : GCCBuiltin<"__nvvm_f2ll_rp_ftz">,
> +      Intrinsic<[llvm_i64_ty], [llvm_float_ty], [IntrNoMem]>;
> +  def int_nvvm_f2ll_rp : GCCBuiltin<"__nvvm_f2ll_rp">,
> +      Intrinsic<[llvm_i64_ty], [llvm_float_ty], [IntrNoMem]>;
> +
> +  def int_nvvm_f2ull_rn_ftz : GCCBuiltin<"__nvvm_f2ull_rn_ftz">,
> +      Intrinsic<[llvm_i64_ty], [llvm_float_ty], [IntrNoMem]>;
> +  def int_nvvm_f2ull_rn : GCCBuiltin<"__nvvm_f2ull_rn">,
> +      Intrinsic<[llvm_i64_ty], [llvm_float_ty], [IntrNoMem]>;
> +  def int_nvvm_f2ull_rz_ftz : GCCBuiltin<"__nvvm_f2ull_rz_ftz">,
> +      Intrinsic<[llvm_i64_ty], [llvm_float_ty], [IntrNoMem]>;
> +  def int_nvvm_f2ull_rz : GCCBuiltin<"__nvvm_f2ull_rz">,
> +      Intrinsic<[llvm_i64_ty], [llvm_float_ty], [IntrNoMem]>;
> +  def int_nvvm_f2ull_rm_ftz : GCCBuiltin<"__nvvm_f2ull_rm_ftz">,
> +      Intrinsic<[llvm_i64_ty], [llvm_float_ty], [IntrNoMem]>;
> +  def int_nvvm_f2ull_rm : GCCBuiltin<"__nvvm_f2ull_rm">,
> +      Intrinsic<[llvm_i64_ty], [llvm_float_ty], [IntrNoMem]>;
> +  def int_nvvm_f2ull_rp_ftz : GCCBuiltin<"__nvvm_f2ull_rp_ftz">,
> +      Intrinsic<[llvm_i64_ty], [llvm_float_ty], [IntrNoMem]>;
> +  def int_nvvm_f2ull_rp : GCCBuiltin<"__nvvm_f2ull_rp">,
> +      Intrinsic<[llvm_i64_ty], [llvm_float_ty], [IntrNoMem]>;
> +
> +  def int_nvvm_d2ll_rn : GCCBuiltin<"__nvvm_d2ll_rn">,
> +      Intrinsic<[llvm_i64_ty], [llvm_double_ty], [IntrNoMem]>;
> +  def int_nvvm_d2ll_rz : GCCBuiltin<"__nvvm_d2ll_rz">,
> +      Intrinsic<[llvm_i64_ty], [llvm_double_ty], [IntrNoMem]>;
> +  def int_nvvm_d2ll_rm : GCCBuiltin<"__nvvm_d2ll_rm">,
> +      Intrinsic<[llvm_i64_ty], [llvm_double_ty], [IntrNoMem]>;
> +  def int_nvvm_d2ll_rp : GCCBuiltin<"__nvvm_d2ll_rp">,
> +      Intrinsic<[llvm_i64_ty], [llvm_double_ty], [IntrNoMem]>;
> +
> +  def int_nvvm_d2ull_rn : GCCBuiltin<"__nvvm_d2ull_rn">,
> +      Intrinsic<[llvm_i64_ty], [llvm_double_ty], [IntrNoMem]>;
> +  def int_nvvm_d2ull_rz : GCCBuiltin<"__nvvm_d2ull_rz">,
> +      Intrinsic<[llvm_i64_ty], [llvm_double_ty], [IntrNoMem]>;
> +  def int_nvvm_d2ull_rm : GCCBuiltin<"__nvvm_d2ull_rm">,
> +      Intrinsic<[llvm_i64_ty], [llvm_double_ty], [IntrNoMem]>;
> +  def int_nvvm_d2ull_rp : GCCBuiltin<"__nvvm_d2ull_rp">,
> +      Intrinsic<[llvm_i64_ty], [llvm_double_ty], [IntrNoMem]>;
> +
> +  def int_nvvm_ll2f_rn : GCCBuiltin<"__nvvm_ll2f_rn">,
> +      Intrinsic<[llvm_float_ty], [llvm_i64_ty], [IntrNoMem]>;
> +  def int_nvvm_ll2f_rz : GCCBuiltin<"__nvvm_ll2f_rz">,
> +      Intrinsic<[llvm_float_ty], [llvm_i64_ty], [IntrNoMem]>;
> +  def int_nvvm_ll2f_rm : GCCBuiltin<"__nvvm_ll2f_rm">,
> +      Intrinsic<[llvm_float_ty], [llvm_i64_ty], [IntrNoMem]>;
> +  def int_nvvm_ll2f_rp : GCCBuiltin<"__nvvm_ll2f_rp">,
> +      Intrinsic<[llvm_float_ty], [llvm_i64_ty], [IntrNoMem]>;
> +  def int_nvvm_ull2f_rn : GCCBuiltin<"__nvvm_ull2f_rn">,
> +      Intrinsic<[llvm_float_ty], [llvm_i64_ty], [IntrNoMem]>;
> +  def int_nvvm_ull2f_rz : GCCBuiltin<"__nvvm_ull2f_rz">,
> +      Intrinsic<[llvm_float_ty], [llvm_i64_ty], [IntrNoMem]>;
> +  def int_nvvm_ull2f_rm : GCCBuiltin<"__nvvm_ull2f_rm">,
> +      Intrinsic<[llvm_float_ty], [llvm_i64_ty], [IntrNoMem]>;
> +  def int_nvvm_ull2f_rp : GCCBuiltin<"__nvvm_ull2f_rp">,
> +      Intrinsic<[llvm_float_ty], [llvm_i64_ty], [IntrNoMem]>;
> +
> +  def int_nvvm_ll2d_rn : GCCBuiltin<"__nvvm_ll2d_rn">,
> +      Intrinsic<[llvm_double_ty], [llvm_i64_ty], [IntrNoMem]>;
> +  def int_nvvm_ll2d_rz : GCCBuiltin<"__nvvm_ll2d_rz">,
> +      Intrinsic<[llvm_double_ty], [llvm_i64_ty], [IntrNoMem]>;
> +  def int_nvvm_ll2d_rm : GCCBuiltin<"__nvvm_ll2d_rm">,
> +      Intrinsic<[llvm_double_ty], [llvm_i64_ty], [IntrNoMem]>;
> +  def int_nvvm_ll2d_rp : GCCBuiltin<"__nvvm_ll2d_rp">,
> +      Intrinsic<[llvm_double_ty], [llvm_i64_ty], [IntrNoMem]>;
> +  def int_nvvm_ull2d_rn : GCCBuiltin<"__nvvm_ull2d_rn">,
> +      Intrinsic<[llvm_double_ty], [llvm_i64_ty], [IntrNoMem]>;
> +  def int_nvvm_ull2d_rz : GCCBuiltin<"__nvvm_ull2d_rz">,
> +      Intrinsic<[llvm_double_ty], [llvm_i64_ty], [IntrNoMem]>;
> +  def int_nvvm_ull2d_rm : GCCBuiltin<"__nvvm_ull2d_rm">,
> +      Intrinsic<[llvm_double_ty], [llvm_i64_ty], [IntrNoMem]>;
> +  def int_nvvm_ull2d_rp : GCCBuiltin<"__nvvm_ull2d_rp">,
> +      Intrinsic<[llvm_double_ty], [llvm_i64_ty], [IntrNoMem]>;
> +
> +  def int_nvvm_f2h_rn_ftz : GCCBuiltin<"__nvvm_f2h_rn_ftz">,
> +      Intrinsic<[llvm_i16_ty], [llvm_float_ty], [IntrNoMem]>;
> +  def int_nvvm_f2h_rn : GCCBuiltin<"__nvvm_f2h_rn">,
> +      Intrinsic<[llvm_i16_ty], [llvm_float_ty], [IntrNoMem]>;
> +
> +  def int_nvvm_h2f : GCCBuiltin<"__nvvm_h2f">,
> +      Intrinsic<[llvm_float_ty], [llvm_i16_ty], [IntrNoMem]>;
> +
> +//
> +// Bitcast
> +//
> +
> +  def int_nvvm_bitcast_f2i : GCCBuiltin<"__nvvm_bitcast_f2i">,
> +      Intrinsic<[llvm_i32_ty], [llvm_float_ty], [IntrNoMem]>;
> +  def int_nvvm_bitcast_i2f : GCCBuiltin<"__nvvm_bitcast_i2f">,
> +      Intrinsic<[llvm_float_ty], [llvm_i32_ty], [IntrNoMem]>;
> +
> +  def int_nvvm_bitcast_ll2d : GCCBuiltin<"__nvvm_bitcast_ll2d">,
> +      Intrinsic<[llvm_double_ty], [llvm_i64_ty], [IntrNoMem]>;
> +  def int_nvvm_bitcast_d2ll : GCCBuiltin<"__nvvm_bitcast_d2ll">,
> +      Intrinsic<[llvm_i64_ty], [llvm_double_ty], [IntrNoMem]>;
> +
> +
> +// Atomic not available as an llvm intrinsic.
> +  def int_nvvm_atomic_load_add_f32 : Intrinsic<[llvm_float_ty],
> +          [LLVMAnyPointerType<llvm_float_ty>, llvm_float_ty],
> +                                      [IntrReadWriteArgMem,
> NoCapture<0>]>;
> +  def int_nvvm_atomic_load_inc_32 : Intrinsic<[llvm_i32_ty],
> +          [LLVMAnyPointerType<llvm_i32_ty>, llvm_i32_ty],
> +                                      [IntrReadWriteArgMem,
> NoCapture<0>]>;
> +  def int_nvvm_atomic_load_dec_32 : Intrinsic<[llvm_i32_ty],
> +          [LLVMAnyPointerType<llvm_i32_ty>, llvm_i32_ty],
> +                                      [IntrReadWriteArgMem,
> NoCapture<0>]>;
> +
> +// Bar.Sync
> +  def int_cuda_syncthreads : GCCBuiltin<"__syncthreads">,
> +      Intrinsic<[], [], []>;
> +  def int_nvvm_barrier0 : GCCBuiltin<"__nvvm_bar0">,
> +      Intrinsic<[], [], []>;
> +  def int_nvvm_barrier0_popc : GCCBuiltin<"__nvvm_bar0_popc">,
> +      Intrinsic<[llvm_i32_ty], [llvm_i32_ty], []>;
> +  def int_nvvm_barrier0_and : GCCBuiltin<"__nvvm_bar0_and">,
> +      Intrinsic<[llvm_i32_ty], [llvm_i32_ty], []>;
> +  def int_nvvm_barrier0_or : GCCBuiltin<"__nvvm_bar0_or">,
> +      Intrinsic<[llvm_i32_ty], [llvm_i32_ty], []>;
> +
> +  // Membar
> +  def int_nvvm_membar_cta : GCCBuiltin<"__nvvm_membar_cta">,
> +      Intrinsic<[], [], []>;
> +  def int_nvvm_membar_gl : GCCBuiltin<"__nvvm_membar_gl">,
> +      Intrinsic<[], [], []>;
> +  def int_nvvm_membar_sys : GCCBuiltin<"__nvvm_membar_sys">,
> +      Intrinsic<[], [], []>;
> +
> +
> +// Accessing special registers
> +  def int_nvvm_read_ptx_sreg_tid_x :
> +      Intrinsic<[llvm_i32_ty], [], [IntrNoMem]>,
> +      GCCBuiltin<"__nvvm_read_ptx_sreg_tid_x">;
> +  def int_nvvm_read_ptx_sreg_tid_y :
> +      Intrinsic<[llvm_i32_ty], [], [IntrNoMem]>,
> +      GCCBuiltin<"__nvvm_read_ptx_sreg_tid_y">;
> +  def int_nvvm_read_ptx_sreg_tid_z :
> +      Intrinsic<[llvm_i32_ty], [], [IntrNoMem]>,
> +      GCCBuiltin<"__nvvm_read_ptx_sreg_tid_z">;
> +
> +  def int_nvvm_read_ptx_sreg_ntid_x :
> +      Intrinsic<[llvm_i32_ty], [], [IntrNoMem]>,
> +      GCCBuiltin<"__nvvm_read_ptx_sreg_ntid_x">;
> +  def int_nvvm_read_ptx_sreg_ntid_y :
> +      Intrinsic<[llvm_i32_ty], [], [IntrNoMem]>,
> +      GCCBuiltin<"__nvvm_read_ptx_sreg_ntid_y">;
> +  def int_nvvm_read_ptx_sreg_ntid_z :
> +      Intrinsic<[llvm_i32_ty], [], [IntrNoMem]>,
> +      GCCBuiltin<"__nvvm_read_ptx_sreg_ntid_z">;
> +
> +  def int_nvvm_read_ptx_sreg_ctaid_x :
> +      Intrinsic<[llvm_i32_ty], [], [IntrNoMem]>,
> +      GCCBuiltin<"__nvvm_read_ptx_sreg_ctaid_x">;
> +  def int_nvvm_read_ptx_sreg_ctaid_y :
> +      Intrinsic<[llvm_i32_ty], [], [IntrNoMem]>,
> +      GCCBuiltin<"__nvvm_read_ptx_sreg_ctaid_y">;
> +  def int_nvvm_read_ptx_sreg_ctaid_z :
> +      Intrinsic<[llvm_i32_ty], [], [IntrNoMem]>,
> +      GCCBuiltin<"__nvvm_read_ptx_sreg_ctaid_z">;
> +
> +  def int_nvvm_read_ptx_sreg_nctaid_x :
> +      Intrinsic<[llvm_i32_ty], [], [IntrNoMem]>,
> +      GCCBuiltin<"__nvvm_read_ptx_sreg_nctaid_x">;
> +  def int_nvvm_read_ptx_sreg_nctaid_y :
> +      Intrinsic<[llvm_i32_ty], [], [IntrNoMem]>,
> +      GCCBuiltin<"__nvvm_read_ptx_sreg_nctaid_y">;
> +  def int_nvvm_read_ptx_sreg_nctaid_z :
> +      Intrinsic<[llvm_i32_ty], [], [IntrNoMem]>,
> +      GCCBuiltin<"__nvvm_read_ptx_sreg_nctaid_z">;
> +
> +  def int_nvvm_read_ptx_sreg_warpsize :
> +      Intrinsic<[llvm_i32_ty], [], [IntrNoMem]>,
> +      GCCBuiltin<"__nvvm_read_ptx_sreg_warpsize">;
> +
> +
> +// Generated within nvvm. Use for ldu on sm_20 or later
> +// @TODO: Revisit this, Changed LLVMAnyPointerType to LLVMPointerType
> +def int_nvvm_ldu_global_i : Intrinsic<[llvm_anyint_ty],
> +  [LLVMPointerType<LLVMMatchType<0>>], [IntrReadMem, NoCapture<0>],
> +  "llvm.nvvm.ldu.global.i">;
> +def int_nvvm_ldu_global_f : Intrinsic<[llvm_anyfloat_ty],
> +  [LLVMPointerType<LLVMMatchType<0>>], [IntrReadMem, NoCapture<0>],
> +  "llvm.nvvm.ldu.global.f">;
> +def int_nvvm_ldu_global_p : Intrinsic<[llvm_anyptr_ty],
> +  [LLVMPointerType<LLVMMatchType<0>>], [IntrReadMem, NoCapture<0>],
> +  "llvm.nvvm.ldu.global.p">;
> +
> +
> +// Use for generic pointers
> +// - These intrinsics are used to convert address spaces.
> +// - The input pointer and output pointer must have the same type, except
> for
> +//   the address-space. (This restriction is not enforced here as there is
> +//   currently no way to describe it).
> +// - This complements the llvm bitcast, which can be used to cast one type
> +//   of pointer to another type of pointer, while the address space
> remains
> +//   the same.
> +def int_nvvm_ptr_local_to_gen: Intrinsic<[llvm_anyptr_ty],
> +                 [llvm_anyptr_ty], [IntrNoMem, NoCapture<0>],
> +                 "llvm.nvvm.ptr.local.to.gen">;
> +def int_nvvm_ptr_shared_to_gen: Intrinsic<[llvm_anyptr_ty],
> +                 [llvm_anyptr_ty], [IntrNoMem, NoCapture<0>],
> +                 "llvm.nvvm.ptr.shared.to.gen">;
> +def int_nvvm_ptr_global_to_gen: Intrinsic<[llvm_anyptr_ty],
> +                 [llvm_anyptr_ty], [IntrNoMem, NoCapture<0>],
> +                 "llvm.nvvm.ptr.global.to.gen">;
> +def int_nvvm_ptr_constant_to_gen: Intrinsic<[llvm_anyptr_ty],
> +                 [llvm_anyptr_ty], [IntrNoMem, NoCapture<0>],
> +                 "llvm.nvvm.ptr.constant.to.gen">;
> +
> +def int_nvvm_ptr_gen_to_global: Intrinsic<[llvm_anyptr_ty],
> +                 [llvm_anyptr_ty], [IntrNoMem, NoCapture<0>],
> +                 "llvm.nvvm.ptr.gen.to.global">;
> +def int_nvvm_ptr_gen_to_shared: Intrinsic<[llvm_anyptr_ty],
> +                 [llvm_anyptr_ty], [IntrNoMem, NoCapture<0>],
> +                 "llvm.nvvm.ptr.gen.to.shared">;
> +def int_nvvm_ptr_gen_to_local: Intrinsic<[llvm_anyptr_ty],
> +                 [llvm_anyptr_ty], [IntrNoMem, NoCapture<0>],
> +                 "llvm.nvvm.ptr.gen.to.local">;
> +def int_nvvm_ptr_gen_to_constant: Intrinsic<[llvm_anyptr_ty],
> +                 [llvm_anyptr_ty], [IntrNoMem, NoCapture<0>],
> +                 "llvm.nvvm.ptr.gen.to.constant">;
> +
> +// Used in nvvm internally to help address space opt and ptx code
> generation
> +// This is for params that are passed to kernel functions by pointer
> by-val.
> +def int_nvvm_ptr_gen_to_param: Intrinsic<[llvm_anyptr_ty],
> +                                     [llvm_anyptr_ty],
> +                                   [IntrNoMem, NoCapture<0>],
> +                                   "llvm.nvvm.ptr.gen.to.param">;
> +
> +// Move intrinsics, used in nvvm internally
> +
> +def int_nvvm_move_i8 : Intrinsic<[llvm_i8_ty], [llvm_i8_ty], [IntrNoMem],
> +  "llvm.nvvm.move.i8">;
> +def int_nvvm_move_i16 : Intrinsic<[llvm_i16_ty], [llvm_i16_ty],
> [IntrNoMem],
> +  "llvm.nvvm.move.i16">;
> +def int_nvvm_move_i32 : Intrinsic<[llvm_i32_ty], [llvm_i32_ty],
> [IntrNoMem],
> +  "llvm.nvvm.move.i32">;
> +def int_nvvm_move_i64 : Intrinsic<[llvm_i64_ty], [llvm_i64_ty],
> [IntrNoMem],
> +  "llvm.nvvm.move.i64">;
> +def int_nvvm_move_float : Intrinsic<[llvm_float_ty], [llvm_float_ty],
> +  [IntrNoMem], "llvm.nvvm.move.float">;
> +def int_nvvm_move_double : Intrinsic<[llvm_double_ty], [llvm_double_ty],
> +  [IntrNoMem], "llvm.nvvm.move.double">;
> +def int_nvvm_move_ptr : Intrinsic<[llvm_anyptr_ty], [llvm_anyptr_ty],
> +  [IntrNoMem, NoCapture<0>], "llvm.nvvm.move.ptr">;
> +
> +
> +/// Error / Warn
> +def int_nvvm_compiler_error :
> +    Intrinsic<[], [llvm_anyptr_ty], [], "llvm.nvvm.compiler.error">;
> +def int_nvvm_compiler_warn :
> +    Intrinsic<[], [llvm_anyptr_ty], [], "llvm.nvvm.compiler.warn">;
>
> Modified: llvm/trunk/lib/Support/Triple.cpp
> URL:
> http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Support/Triple.cpp?rev=156196&r1=156195&r2=156196&view=diff
>
> ==============================================================================
> --- llvm/trunk/lib/Support/Triple.cpp (original)
> +++ llvm/trunk/lib/Support/Triple.cpp Fri May  4 15:18:50 2012
> @@ -40,6 +40,8 @@
>   case mblaze:  return "mblaze";
>   case ptx32:   return "ptx32";
>   case ptx64:   return "ptx64";
> +  case nvptx:   return "nvptx";
> +  case nvptx64: return "nvptx64";
>   case le32:    return "le32";
>   case amdil:   return "amdil";
>   }
> @@ -76,6 +78,8 @@
>
>   case ptx32:   return "ptx";
>   case ptx64:   return "ptx";
> +  case nvptx:   return "nvptx";
> +  case nvptx64: return "nvptx";
>   case le32:    return "le32";
>   case amdil:   return "amdil";
>   }
> @@ -162,6 +166,8 @@
>     .Case("xcore", xcore)
>     .Case("ptx32", ptx32)
>     .Case("ptx64", ptx64)
> +    .Case("nvptx", nvptx)
> +    .Case("nvptx64", nvptx64)
>     .Case("le32", le32)
>     .Case("amdil", amdil)
>     .Default(UnknownArch);
> @@ -194,6 +200,8 @@
>     .Case("r600", Triple::r600)
>     .Case("ptx32", Triple::ptx32)
>     .Case("ptx64", Triple::ptx64)
> +    .Case("nvptx", Triple::nvptx)
> +    .Case("nvptx64", Triple::nvptx64)
>     .Case("amdil", Triple::amdil)
>     .Default(Triple::UnknownArch);
>  }
> @@ -217,6 +225,8 @@
>     .Case("r600", "r600")
>     .Case("ptx32", "ptx32")
>     .Case("ptx64", "ptx64")
> +    .Case("nvptx", "nvptx")
> +    .Case("nvptx64", "nvptx64")
>     .Case("le32", "le32")
>     .Case("amdil", "amdil")
>     .Default(NULL);
> @@ -251,6 +261,8 @@
>     .Case("xcore", Triple::xcore)
>     .Case("ptx32", Triple::ptx32)
>     .Case("ptx64", Triple::ptx64)
> +    .Case("nvptx", Triple::nvptx)
> +    .Case("nvptx64", Triple::nvptx64)
>     .Case("le32", Triple::le32)
>     .Case("amdil", Triple::amdil)
>     .Default(Triple::UnknownArch);
> @@ -652,6 +664,7 @@
>   case llvm::Triple::mblaze:
>   case llvm::Triple::mips:
>   case llvm::Triple::mipsel:
> +  case llvm::Triple::nvptx:
>   case llvm::Triple::ppc:
>   case llvm::Triple::ptx32:
>   case llvm::Triple::r600:
> @@ -664,6 +677,7 @@
>
>   case llvm::Triple::mips64:
>   case llvm::Triple::mips64el:
> +  case llvm::Triple::nvptx64:
>   case llvm::Triple::ppc64:
>   case llvm::Triple::ptx64:
>   case llvm::Triple::sparcv9:
> @@ -701,6 +715,7 @@
>   case Triple::mblaze:
>   case Triple::mips:
>   case Triple::mipsel:
> +  case Triple::nvptx:
>   case Triple::ppc:
>   case Triple::ptx32:
>   case Triple::r600:
> @@ -714,6 +729,7 @@
>
>   case Triple::mips64:    T.setArch(Triple::mips);    break;
>   case Triple::mips64el:  T.setArch(Triple::mipsel);  break;
> +  case Triple::nvptx64:   T.setArch(Triple::nvptx);   break;
>   case Triple::ppc64:     T.setArch(Triple::ppc);   break;
>   case Triple::ptx64:     T.setArch(Triple::ptx32);   break;
>   case Triple::sparcv9:   T.setArch(Triple::sparc);   break;
> @@ -742,6 +758,7 @@
>
>   case Triple::mips64:
>   case Triple::mips64el:
> +  case Triple::nvptx64:
>   case Triple::ppc64:
>   case Triple::ptx64:
>   case Triple::sparcv9:
> @@ -751,6 +768,7 @@
>
>   case Triple::mips:    T.setArch(Triple::mips64);    break;
>   case Triple::mipsel:  T.setArch(Triple::mips64el);  break;
> +  case Triple::nvptx:   T.setArch(Triple::nvptx64);   break;
>   case Triple::ppc:     T.setArch(Triple::ppc64);     break;
>   case Triple::ptx32:   T.setArch(Triple::ptx64);     break;
>   case Triple::sparc:   T.setArch(Triple::sparcv9);   break;
>
> Modified: llvm/trunk/lib/Target/LLVMBuild.txt
> URL:
> http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/LLVMBuild.txt?rev=156196&r1=156195&r2=156196&view=diff
>
> ==============================================================================
> --- llvm/trunk/lib/Target/LLVMBuild.txt (original)
> +++ llvm/trunk/lib/Target/LLVMBuild.txt Fri May  4 15:18:50 2012
> @@ -16,7 +16,7 @@
>
>  ;===------------------------------------------------------------------------===;
>
>  [common]
> -subdirectories = ARM CellSPU CppBackend Hexagon MBlaze MSP430 Mips PTX
> PowerPC Sparc X86 XCore
> +subdirectories = ARM CellSPU CppBackend Hexagon MBlaze MSP430 NVPTX Mips
> PTX PowerPC Sparc X86 XCore
>
>  ; This is a special group whose required libraries are extended (by
> llvm-build)
>  ; with the best execution engine (the native JIT, if available, or the
>
> Added: llvm/trunk/lib/Target/NVPTX/CMakeLists.txt
> URL:
> http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/NVPTX/CMakeLists.txt?rev=156196&view=auto
>
> ==============================================================================
> --- llvm/trunk/lib/Target/NVPTX/CMakeLists.txt (added)
> +++ llvm/trunk/lib/Target/NVPTX/CMakeLists.txt Fri May  4 15:18:50 2012
> @@ -0,0 +1,33 @@
> +set(LLVM_TARGET_DEFINITIONS NVPTX.td)
> +
> +
> +tablegen(LLVM NVPTXGenRegisterInfo.inc -gen-register-info)
> +tablegen(LLVM NVPTXGenInstrInfo.inc -gen-instr-info)
> +tablegen(LLVM NVPTXGenAsmWriter.inc -gen-asm-writer)
> +tablegen(LLVM NVPTXGenDAGISel.inc -gen-dag-isel)
> +tablegen(LLVM NVPTXGenSubtargetInfo.inc -gen-subtarget)
> +add_public_tablegen_target(NVPTXCommonTableGen)
> +
> +set(NVPTXCodeGen_sources
> +  NVPTXFrameLowering.cpp
> +  NVPTXInstrInfo.cpp
> +  NVPTXISelDAGToDAG.cpp
> +  NVPTXISelLowering.cpp
> +  NVPTXRegisterInfo.cpp
> +  NVPTXSubtarget.cpp
> +  NVPTXTargetMachine.cpp
> +  NVPTXSplitBBatBar.cpp
> +  NVPTXLowerAggrCopies.cpp
> +  NVPTXutil.cpp
> +  NVPTXAllocaHoisting.cpp
> +  NVPTXAsmPrinter.cpp
> +  NVPTXUtilities.cpp
> +  VectorElementize.cpp
> +  )
> +
> +add_llvm_target(NVPTXCodeGen ${NVPTXCodeGen_sources})
> +
> +
> +add_subdirectory(TargetInfo)
> +add_subdirectory(InstPrinter)
> +add_subdirectory(MCTargetDesc)
>
> Added: llvm/trunk/lib/Target/NVPTX/InstPrinter/CMakeLists.txt
> URL:
> http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/NVPTX/InstPrinter/CMakeLists.txt?rev=156196&view=auto
>
> ==============================================================================
> --- llvm/trunk/lib/Target/NVPTX/InstPrinter/CMakeLists.txt (added)
> +++ llvm/trunk/lib/Target/NVPTX/InstPrinter/CMakeLists.txt Fri May  4
> 15:18:50 2012
> @@ -0,0 +1,7 @@
> +include_directories( ${CMAKE_CURRENT_BINARY_DIR}/..
> ${CMAKE_CURRENT_SOURCE_DIR}/.. )
> +
> +add_llvm_library(LLVMNVPTXAsmPrinter
> +  NVPTXInstPrinter.cpp
> +  )
> +
> +add_dependencies(LLVMNVPTXAsmPrinter NVPTXCommonTableGen)
>
> Added: llvm/trunk/lib/Target/NVPTX/InstPrinter/LLVMBuild.txt
> URL:
> http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/NVPTX/InstPrinter/LLVMBuild.txt?rev=156196&view=auto
>
> ==============================================================================
> --- llvm/trunk/lib/Target/NVPTX/InstPrinter/LLVMBuild.txt (added)
> +++ llvm/trunk/lib/Target/NVPTX/InstPrinter/LLVMBuild.txt Fri May  4
> 15:18:50 2012
> @@ -0,0 +1,23 @@
> +;===- ./lib/Target/NVPTX/InstPrinter/LLVMBuild.txt -------------*- Conf
> -*--===;
> +;
> +;                     The LLVM Compiler Infrastructure
> +;
> +; This file is distributed under the University of Illinois Open Source
> +; License. See LICENSE.TXT for details.
> +;
>
> +;===------------------------------------------------------------------------===;
> +;
> +; This is an LLVMBuild description file for the components in this
> subdirectory.
> +;
> +; For more information on the LLVMBuild system, please see:
> +;
> +;   http://llvm.org/docs/LLVMBuild.html
> +;
>
> +;===------------------------------------------------------------------------===;
> +
> +[component_0]
> +type = Library
> +name = NVPTXAsmPrinter
> +parent = NVPTX
> +required_libraries = MC Support
> +add_to_library_groups = NVPTX
>
> Added: llvm/trunk/lib/Target/NVPTX/InstPrinter/Makefile
> URL:
> http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/NVPTX/InstPrinter/Makefile?rev=156196&view=auto
>
> ==============================================================================
> --- llvm/trunk/lib/Target/NVPTX/InstPrinter/Makefile (added)
> +++ llvm/trunk/lib/Target/NVPTX/InstPrinter/Makefile Fri May  4 15:18:50
> 2012
> @@ -0,0 +1,15 @@
> +##===- lib/Target/NVPTX/AsmPrinter/Makefile ----------------*- Makefile
> -*-===##
> +#
> +#
>              The LLVM Compiler Infrastructure
> +#
> +# This file is distributed under the University of Illinois Open Source
> +# License. See LICENSE.TXT for details.
> +#
>
> +##===----------------------------------------------------------------------===##
> +LEVEL = ../../../..
> +LIBRARYNAME = LLVMNVPTXAsmPrinter
> +
> +# Hack: we need to include 'main' ptx target directory to grab private
> headers
> +CPP.Flags += -I$(PROJ_OBJ_DIR)/.. -I$(PROJ_SRC_DIR)/..
> +
> +include $(LEVEL)/Makefile.common
>
> Added: llvm/trunk/lib/Target/NVPTX/InstPrinter/NVPTXInstPrinter.cpp
> URL:
> http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/NVPTX/InstPrinter/NVPTXInstPrinter.cpp?rev=156196&view=auto
>
> ==============================================================================
> --- llvm/trunk/lib/Target/NVPTX/InstPrinter/NVPTXInstPrinter.cpp (added)
> +++ llvm/trunk/lib/Target/NVPTX/InstPrinter/NVPTXInstPrinter.cpp Fri May
>  4 15:18:50 2012
> @@ -0,0 +1 @@
> +// Placeholder
>
> Added: llvm/trunk/lib/Target/NVPTX/LLVMBuild.txt
> URL:
> http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/NVPTX/LLVMBuild.txt?rev=156196&view=auto
>
> ==============================================================================
> --- llvm/trunk/lib/Target/NVPTX/LLVMBuild.txt (added)
> +++ llvm/trunk/lib/Target/NVPTX/LLVMBuild.txt Fri May  4 15:18:50 2012
> @@ -0,0 +1,32 @@
> +;===- ./lib/Target/NVPTX/LLVMBuild.txt -------------------------*- Conf
> -*--===;
> +;
> +;                     The LLVM Compiler Infrastructure
> +;
> +; This file is distributed under the University of Illinois Open Source
> +; License. See LICENSE.TXT for details.
> +;
>
> +;===------------------------------------------------------------------------===;
> +;
> +; This is an LLVMBuild description file for the components in this
> subdirectory.
> +;
> +; For more information on the LLVMBuild system, please see:
> +;
> +;   http://llvm.org/docs/LLVMBuild.html
> +;
>
> +;===------------------------------------------------------------------------===;
> +
> +[common]
> +subdirectories = InstPrinter MCTargetDesc TargetInfo
> +
> +[component_0]
> +type = TargetGroup
> +name = NVPTX
> +parent = Target
> +has_asmprinter = 1
> +
> +[component_1]
> +type = Library
> +name = NVPTXCodeGen
> +parent = NVPTX
> +required_libraries = Analysis AsmPrinter CodeGen Core MC NVPTXDesc
> NVPTXInfo SelectionDAG Support Target TransformUtils
> +add_to_library_groups = NVPTX
>
> Added: llvm/trunk/lib/Target/NVPTX/MCTargetDesc/CMakeLists.txt
> URL:
> http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/NVPTX/MCTargetDesc/CMakeLists.txt?rev=156196&view=auto
>
> ==============================================================================
> --- llvm/trunk/lib/Target/NVPTX/MCTargetDesc/CMakeLists.txt (added)
> +++ llvm/trunk/lib/Target/NVPTX/MCTargetDesc/CMakeLists.txt Fri May  4
> 15:18:50 2012
> @@ -0,0 +1,9 @@
> +add_llvm_library(LLVMNVPTXDesc
> +  NVPTXMCAsmInfo.cpp
> +  NVPTXMCTargetDesc.cpp
> +  )
> +
> +add_dependencies(LLVMNVPTXDesc NVPTXCommonTableGen)
> +
> +# Hack: we need to include 'main' target directory to grab private headers
> +#include_directories(${CMAKE_CURRENT_SOURCE_DIR}/..
> ${CMAKE_CURRENT_BINARY_DIR}/..)
>
> Added: llvm/trunk/lib/Target/NVPTX/MCTargetDesc/LLVMBuild.txt
> URL:
> http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/NVPTX/MCTargetDesc/LLVMBuild.txt?rev=156196&view=auto
>
> ==============================================================================
> --- llvm/trunk/lib/Target/NVPTX/MCTargetDesc/LLVMBuild.txt (added)
> +++ llvm/trunk/lib/Target/NVPTX/MCTargetDesc/LLVMBuild.txt Fri May  4
> 15:18:50 2012
> @@ -0,0 +1,23 @@
> +;===- ./lib/Target/NVPTX/MCTargetDesc/LLVMBuild.txt ------------*- Conf
> -*--===;
> +;
> +;                     The LLVM Compiler Infrastructure
> +;
> +; This file is distributed under the University of Illinois Open Source
> +; License. See LICENSE.TXT for details.
> +;
>
> +;===------------------------------------------------------------------------===;
> +;
> +; This is an LLVMBuild description file for the components in this
> subdirectory.
> +;
> +; For more information on the LLVMBuild system, please see:
> +;
> +;   http://llvm.org/docs/LLVMBuild.html
> +;
>
> +;===------------------------------------------------------------------------===;
> +
> +[component_0]
> +type = Library
> +name = NVPTXDesc
> +parent = NVPTX
> +required_libraries = MC NVPTXAsmPrinter NVPTXInfo Support
> +add_to_library_groups = NVPTX
>
> Added: llvm/trunk/lib/Target/NVPTX/MCTargetDesc/Makefile
> URL:
> http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/NVPTX/MCTargetDesc/Makefile?rev=156196&view=auto
>
> ==============================================================================
> --- llvm/trunk/lib/Target/NVPTX/MCTargetDesc/Makefile (added)
> +++ llvm/trunk/lib/Target/NVPTX/MCTargetDesc/Makefile Fri May  4 15:18:50
> 2012
> @@ -0,0 +1,16 @@
> +##===- lib/Target/NVPTX/TargetDesc/Makefile ----------------*- Makefile
> -*-===##
> +#
> +#                     The LLVM Compiler Infrastructure
> +#
> +# This file is distributed under the University of Illinois Open Source
> +# License. See LICENSE.TXT for details.
> +#
>
> +##===----------------------------------------------------------------------===##
> +
> +LEVEL = ../../../..
> +LIBRARYNAME = LLVMNVPTXDesc
> +
> +# Hack: we need to include 'main' target directory to grab private headers
> +CPP.Flags += -I$(PROJ_OBJ_DIR)/.. -I$(PROJ_SRC_DIR)/..
> +
> +include $(LEVEL)/Makefile.common
>
> Added: llvm/trunk/lib/Target/NVPTX/MCTargetDesc/NVPTXBaseInfo.h
> URL:
> http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/NVPTX/MCTargetDesc/NVPTXBaseInfo.h?rev=156196&view=auto
>
> ==============================================================================
> --- llvm/trunk/lib/Target/NVPTX/MCTargetDesc/NVPTXBaseInfo.h (added)
> +++ llvm/trunk/lib/Target/NVPTX/MCTargetDesc/NVPTXBaseInfo.h Fri May  4
> 15:18:50 2012
> @@ -0,0 +1,88 @@
> +//===-- NVPTXBaseInfo.h - Top-level definitions for NVPTX -------*- C++
> -*-===//
> +//
> +//                     The LLVM Compiler Infrastructure
> +//
> +// This file is distributed under the University of Illinois Open Source
> +// License. See LICENSE.TXT for details.
> +//
>
> +//===----------------------------------------------------------------------===//
> +//
> +// This file contains small standalone helper functions and enum
> definitions for
> +// the NVPTX target useful for the compiler back-end and the MC libraries.
> +// As such, it deliberately does not include references to LLVM core
> +// code gen types, passes, etc..
> +//
>
> +//===----------------------------------------------------------------------===//
> +
> +#ifndef NVPTXBASEINFO_H
> +#define NVPTXBASEINFO_H
> +
> +namespace llvm {
> +
> +enum AddressSpace {
> +  ADDRESS_SPACE_GENERIC = 0,
> +  ADDRESS_SPACE_GLOBAL = 1,
> +  ADDRESS_SPACE_CONST_NOT_GEN = 2, // Not part of generic space
> +  ADDRESS_SPACE_SHARED = 3,
> +  ADDRESS_SPACE_CONST = 4,
> +  ADDRESS_SPACE_LOCAL = 5,
> +
> +  // NVVM Internal
> +  ADDRESS_SPACE_PARAM = 101
> +};
> +
> +enum PropertyAnnotation {
> +  PROPERTY_MAXNTID_X = 0,
> +  PROPERTY_MAXNTID_Y,
> +  PROPERTY_MAXNTID_Z,
> +  PROPERTY_REQNTID_X,
> +  PROPERTY_REQNTID_Y,
> +  PROPERTY_REQNTID_Z,
> +  PROPERTY_MINNCTAPERSM,
> +  PROPERTY_ISTEXTURE,
> +  PROPERTY_ISSURFACE,
> +  PROPERTY_ISSAMPLER,
> +  PROPERTY_ISREADONLY_IMAGE_PARAM,
> +  PROPERTY_ISWRITEONLY_IMAGE_PARAM,
> +  PROPERTY_ISKERNEL_FUNCTION,
> +  PROPERTY_ALIGN,
> +
> +  // last property
> +  PROPERTY_LAST
> +};
> +
> +const unsigned AnnotationNameLen = 8; // length of each annotation name
> +const char
> +PropertyAnnotationNames[PROPERTY_LAST + 1][AnnotationNameLen + 1] = {
> +  "maxntidx",               // PROPERTY_MAXNTID_X
> +  "maxntidy",               // PROPERTY_MAXNTID_Y
> +  "maxntidz",               // PROPERTY_MAXNTID_Z
> +  "reqntidx",               // PROPERTY_REQNTID_X
> +  "reqntidy",               // PROPERTY_REQNTID_Y
> +  "reqntidz",               // PROPERTY_REQNTID_Z
> +  "minctasm",               // PROPERTY_MINNCTAPERSM
> +  "texture",                // PROPERTY_ISTEXTURE
> +  "surface",                // PROPERTY_ISSURFACE
> +  "sampler",                // PROPERTY_ISSAMPLER
> +  "rdoimage",               // PROPERTY_ISREADONLY_IMAGE_PARAM
> +  "wroimage",               // PROPERTY_ISWRITEONLY_IMAGE_PARAM
> +  "kernel",                 // PROPERTY_ISKERNEL_FUNCTION
> +  "align",                  // PROPERTY_ALIGN
> +
> +  // last property
> +  "proplast",               // PROPERTY_LAST
> +};
> +
> +// name of named metadata used for global annotations
> +#if defined(__GNUC__)
> +// As this is declared to be static but some of the .cpp files that
> +// include NVVM.h do not use this array, gcc gives a warning when
> +// compiling those .cpp files, hence __attribute__((unused)).
> +__attribute__((unused))
> +#endif
> +static const char* NamedMDForAnnotations = "nvvm.annotations";
> +
> +}
> +
> +
> +#endif
>
> Added: llvm/trunk/lib/Target/NVPTX/MCTargetDesc/NVPTXMCAsmInfo.cpp
> URL:
> http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/NVPTX/MCTargetDesc/NVPTXMCAsmInfo.cpp?rev=156196&view=auto
>
> ==============================================================================
> --- llvm/trunk/lib/Target/NVPTX/MCTargetDesc/NVPTXMCAsmInfo.cpp (added)
> +++ llvm/trunk/lib/Target/NVPTX/MCTargetDesc/NVPTXMCAsmInfo.cpp Fri May  4
> 15:18:50 2012
> @@ -0,0 +1,63 @@
> +//===-- NVPTXMCAsmInfo.cpp - NVPTX asm properties
> -------------------------===//
> +//
> +//                     The LLVM Compiler Infrastructure
> +//
> +// This file is distributed under the University of Illinois Open Source
> +// License. See LICENSE.TXT for details.
> +//
>
> +//===----------------------------------------------------------------------===//
> +//
> +// This file contains the declarations of the NVPTXMCAsmInfo properties.
> +//
>
> +//===----------------------------------------------------------------------===//
> +
> +#include "NVPTXMCAsmInfo.h"
> +#include "llvm/ADT/Triple.h"
> +#include "llvm/Support/CommandLine.h"
> +
> +using namespace llvm;
> +
> +bool CompileForDebugging;
> +
> +// -debug-compile - Command line option to inform opt and llc passes to
> +// compile for debugging
> +static cl::opt<bool, true>
> +Debug("debug-compile", cl::desc("Compile for debugging"), cl::Hidden,
> +      cl::location(CompileForDebugging),
> +      cl::init(false));
> +
> +void NVPTXMCAsmInfo::anchor() { }
> +
> +NVPTXMCAsmInfo::NVPTXMCAsmInfo(const Target &T, const StringRef &TT) {
> +  Triple TheTriple(TT);
> +  if (TheTriple.getArch() == Triple::nvptx64)
> +    PointerSize = 8;
> +
> +  CommentString = "//";
> +
> +  PrivateGlobalPrefix = "$L__";
> +
> +  AllowPeriodsInName = false;
> +
> +  HasSetDirective = false;
> +
> +  HasSingleParameterDotFile = false;
> +
> +  InlineAsmStart = " inline asm";
> +  InlineAsmEnd = " inline asm";
> +
> +  SupportsDebugInformation = CompileForDebugging;
> +  HasDotTypeDotSizeDirective = false;
> +
> +  Data8bitsDirective = " .b8 ";
> +  Data16bitsDirective = " .b16 ";
> +  Data32bitsDirective = " .b32 ";
> +  Data64bitsDirective = " .b64 ";
> +  PrivateGlobalPrefix = "";
> +  ZeroDirective =  " .b8";
> +  AsciiDirective = " .b8";
> +  AscizDirective = " .b8";
> +
> +  // @TODO: Can we just disable this?
> +  GlobalDirective = "\t// .globl\t";
> +}
>
> Added: llvm/trunk/lib/Target/NVPTX/MCTargetDesc/NVPTXMCAsmInfo.h
> URL:
> http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/NVPTX/MCTargetDesc/NVPTXMCAsmInfo.h?rev=156196&view=auto
>
> ==============================================================================
> --- llvm/trunk/lib/Target/NVPTX/MCTargetDesc/NVPTXMCAsmInfo.h (added)
> +++ llvm/trunk/lib/Target/NVPTX/MCTargetDesc/NVPTXMCAsmInfo.h Fri May  4
> 15:18:50 2012
> @@ -0,0 +1,30 @@
> +//===-- NVPTXMCAsmInfo.h - NVPTX asm properties ----------------*- C++
> -*--===//
> +//
> +//                     The LLVM Compiler Infrastructure
> +//
> +// This file is distributed under the University of Illinois Open Source
> +// License. See LICENSE.TXT for details.
> +//
>
> +//===----------------------------------------------------------------------===//
> +//
> +// This file contains the declaration of the NVPTXMCAsmInfo class.
> +//
>
> +//===----------------------------------------------------------------------===//
> +
> +#ifndef NVPTX_MCASM_INFO_H
> +#define NVPTX_MCASM_INFO_H
> +
> +#include "llvm/MC/MCAsmInfo.h"
> +
> +namespace llvm {
> +class Target;
> +class StringRef;
> +
> +class NVPTXMCAsmInfo : public MCAsmInfo {
> +  virtual void anchor();
> +public:
> +  explicit NVPTXMCAsmInfo(const Target &T, const StringRef &TT);
> +};
> +} // namespace llvm
> +
> +#endif // NVPTX_MCASM_INFO_H
>
> Added: llvm/trunk/lib/Target/NVPTX/MCTargetDesc/NVPTXMCTargetDesc.cpp
> URL:
> http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/NVPTX/MCTargetDesc/NVPTXMCTargetDesc.cpp?rev=156196&view=auto
>
> ==============================================================================
> --- llvm/trunk/lib/Target/NVPTX/MCTargetDesc/NVPTXMCTargetDesc.cpp (added)
> +++ llvm/trunk/lib/Target/NVPTX/MCTargetDesc/NVPTXMCTargetDesc.cpp Fri May
>  4 15:18:50 2012
> @@ -0,0 +1,91 @@
> +//===-- NVPTXMCTargetDesc.cpp - NVPTX Target Descriptions -------*- C++
> -*-===//
> +//
> +//                     The LLVM Compiler Infrastructure
> +//
> +// This file is distributed under the University of Illinois Open Source
> +// License. See LICENSE.TXT for details.
> +//
>
> +//===----------------------------------------------------------------------===//
> +//
> +// This file provides NVPTX specific target descriptions.
> +//
>
> +//===----------------------------------------------------------------------===//
> +
> +#include "NVPTXMCTargetDesc.h"
> +#include "NVPTXMCAsmInfo.h"
> +#include "llvm/MC/MCCodeGenInfo.h"
> +#include "llvm/MC/MCInstrInfo.h"
> +#include "llvm/MC/MCRegisterInfo.h"
> +#include "llvm/MC/MCSubtargetInfo.h"
> +#include "llvm/Support/TargetRegistry.h"
> +
> +#define GET_INSTRINFO_MC_DESC
> +#include "NVPTXGenInstrInfo.inc"
> +
> +#define GET_SUBTARGETINFO_MC_DESC
> +#include "NVPTXGenSubtargetInfo.inc"
> +
> +#define GET_REGINFO_MC_DESC
> +#include "NVPTXGenRegisterInfo.inc"
> +
> +
> +using namespace llvm;
> +
> +static MCInstrInfo *createNVPTXMCInstrInfo() {
> +  MCInstrInfo *X = new MCInstrInfo();
> +  InitNVPTXMCInstrInfo(X);
> +  return X;
> +}
> +
> +static MCRegisterInfo *createNVPTXMCRegisterInfo(StringRef TT) {
> +  MCRegisterInfo *X = new MCRegisterInfo();
> +  // PTX does not have a return address register.
> +  InitNVPTXMCRegisterInfo(X, 0);
> +  return X;
> +}
> +
> +static MCSubtargetInfo *createNVPTXMCSubtargetInfo(StringRef TT,
> StringRef CPU,
> +                                                   StringRef FS) {
> +  MCSubtargetInfo *X = new MCSubtargetInfo();
> +  InitNVPTXMCSubtargetInfo(X, TT, CPU, FS);
> +  return X;
> +}
> +
> +static MCCodeGenInfo *createNVPTXMCCodeGenInfo(StringRef TT, Reloc::Model
> RM,
> +                                               CodeModel::Model CM,
> +                                               CodeGenOpt::Level OL) {
> +  MCCodeGenInfo *X = new MCCodeGenInfo();
> +  X->InitMCCodeGenInfo(RM, CM, OL);
> +  return X;
> +}
> +
> +
> +// Force static initialization.
> +extern "C" void LLVMInitializeNVPTXTargetMC() {
> +  // Register the MC asm info.
> +  RegisterMCAsmInfo<NVPTXMCAsmInfo> X(TheNVPTXTarget32);
> +  RegisterMCAsmInfo<NVPTXMCAsmInfo> Y(TheNVPTXTarget64);
> +
> +  // Register the MC codegen info.
> +  TargetRegistry::RegisterMCCodeGenInfo(TheNVPTXTarget32,
> +                                        createNVPTXMCCodeGenInfo);
> +  TargetRegistry::RegisterMCCodeGenInfo(TheNVPTXTarget64,
> +                                        createNVPTXMCCodeGenInfo);
> +
> +  // Register the MC instruction info.
> +  TargetRegistry::RegisterMCInstrInfo(TheNVPTXTarget32,
> createNVPTXMCInstrInfo);
> +  TargetRegistry::RegisterMCInstrInfo(TheNVPTXTarget64,
> createNVPTXMCInstrInfo);
> +
> +  // Register the MC register info.
> +  TargetRegistry::RegisterMCRegInfo(TheNVPTXTarget32,
> +                                    createNVPTXMCRegisterInfo);
> +  TargetRegistry::RegisterMCRegInfo(TheNVPTXTarget64,
> +                                    createNVPTXMCRegisterInfo);
> +
> +  // Register the MC subtarget info.
> +  TargetRegistry::RegisterMCSubtargetInfo(TheNVPTXTarget32,
> +                                          createNVPTXMCSubtargetInfo);
> +  TargetRegistry::RegisterMCSubtargetInfo(TheNVPTXTarget64,
> +                                          createNVPTXMCSubtargetInfo);
> +
> +}
>
> Added: llvm/trunk/lib/Target/NVPTX/MCTargetDesc/NVPTXMCTargetDesc.h
> URL:
> http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/NVPTX/MCTargetDesc/NVPTXMCTargetDesc.h?rev=156196&view=auto
>
> ==============================================================================
> --- llvm/trunk/lib/Target/NVPTX/MCTargetDesc/NVPTXMCTargetDesc.h (added)
> +++ llvm/trunk/lib/Target/NVPTX/MCTargetDesc/NVPTXMCTargetDesc.h Fri May
>  4 15:18:50 2012
> @@ -0,0 +1,36 @@
> +//===-- NVPTXMCTargetDesc.h - NVPTX Target Descriptions ---------*- C++
> -*-===//
> +//
> +//                     The LLVM Compiler Infrastructure
> +//
> +// This file is distributed under the University of Illinois Open Source
> +// License. See LICENSE.TXT for details.
> +//
>
> +//===----------------------------------------------------------------------===//
> +//
> +// This file provides NVPTX specific target descriptions.
> +//
>
> +//===----------------------------------------------------------------------===//
> +
> +#ifndef NVPTXMCTARGETDESC_H
> +#define NVPTXMCTARGETDESC_H
> +
> +namespace llvm {
> +class Target;
> +
> +extern Target TheNVPTXTarget32;
> +extern Target TheNVPTXTarget64;
> +
> +} // End llvm namespace
> +
> +// Defines symbolic names for PTX registers.
> +#define GET_REGINFO_ENUM
> +#include "NVPTXGenRegisterInfo.inc"
> +
> +// Defines symbolic names for the PTX instructions.
> +#define GET_INSTRINFO_ENUM
> +#include "NVPTXGenInstrInfo.inc"
> +
> +#define GET_SUBTARGETINFO_ENUM
> +#include "NVPTXGenSubtargetInfo.inc"
> +
> +#endif
>
> Added: llvm/trunk/lib/Target/NVPTX/Makefile
> URL:
> http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/NVPTX/Makefile?rev=156196&view=auto
>
> ==============================================================================
> --- llvm/trunk/lib/Target/NVPTX/Makefile (added)
> +++ llvm/trunk/lib/Target/NVPTX/Makefile Fri May  4 15:18:50 2012
> @@ -0,0 +1,23 @@
> +##===- lib/Target/NVPTX/Makefile ---------------------------*- Makefile
> -*-===##
> +#
> +#                     The LLVM Compiler Infrastructure
> +#
> +# This file is distributed under the University of Illinois Open Source
> +# License. See LICENSE.TXT for details.
> +#
>
> +##===----------------------------------------------------------------------===##
> +
> +LEVEL = ../../..
> +LIBRARYNAME = LLVMNVPTXCodeGen
> +TARGET = NVPTX
> +
> +# Make sure that tblgen is run, first thing.
> +BUILT_SOURCES = NVPTXGenAsmWriter.inc \
> +               NVPTXGenDAGISel.inc \
> +               NVPTXGenInstrInfo.inc \
> +               NVPTXGenRegisterInfo.inc \
> +               NVPTXGenSubtargetInfo.inc
> +
> +DIRS = InstPrinter TargetInfo MCTargetDesc
> +
> +include $(LEVEL)/Makefile.common
>
> Added: llvm/trunk/lib/Target/NVPTX/ManagedStringPool.h
> URL:
> http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/NVPTX/ManagedStringPool.h?rev=156196&view=auto
>
> ==============================================================================
> --- llvm/trunk/lib/Target/NVPTX/ManagedStringPool.h (added)
> +++ llvm/trunk/lib/Target/NVPTX/ManagedStringPool.h Fri May  4 15:18:50
> 2012
> @@ -0,0 +1,49 @@
> +//===-- ManagedStringPool.h - Managed String Pool ---------------*- C++
> -*-===//
> +//
> +//                     The LLVM Compiler Infrastructure
> +//
> +// This file is distributed under the University of Illinois Open Source
> +// License. See LICENSE.TXT for details.
> +//
>
> +//===----------------------------------------------------------------------===//
> +//
> +// The strings allocated from a managed string pool are owned by the
> string
> +// pool and will be deleted together with the managed string pool.
> +//
>
> +//===----------------------------------------------------------------------===//
> +
> +
> +#ifndef LLVM_SUPPORT_MANAGED_STRING_H
> +#define LLVM_SUPPORT_MANAGED_STRING_H
> +
> +#include "llvm/ADT/SmallVector.h"
> +#include <string>
> +
> +namespace llvm {
> +
> +/// ManagedStringPool - The strings allocated from a managed string pool
> are
> +/// owned by the string pool and will be deleted together with the managed
> +/// string pool.
> +class ManagedStringPool {
> +  SmallVector<std::string *, 8> Pool;
> +
> +public:
> +  ManagedStringPool() {}
> +  ~ManagedStringPool() {
> +    SmallVector<std::string *, 8>::iterator Current = Pool.begin();
> +    while (Current != Pool.end()) {
> +      delete *Current;
> +      Current++;
> +    }
> +  }
> +
> +  std::string *getManagedString(const char *S) {
> +    std::string *Str = new std::string(S);
> +    Pool.push_back(Str);
> +    return Str;
> +  }
> +};
> +
> +}
> +
> +#endif
>
> Added: llvm/trunk/lib/Target/NVPTX/NVPTX.h
> URL:
> http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/NVPTX/NVPTX.h?rev=156196&view=auto
>
> ==============================================================================
> --- llvm/trunk/lib/Target/NVPTX/NVPTX.h (added)
> +++ llvm/trunk/lib/Target/NVPTX/NVPTX.h Fri May  4 15:18:50 2012
> @@ -0,0 +1,137 @@
> +//===-- NVPTX.h - Top-level interface for NVPTX representation --*- C++
> -*-===//
> +//
> +//                     The LLVM Compiler Infrastructure
> +//
> +// This file is distributed under the University of Illinois Open Source
> +// License. See LICENSE.TXT for details.
> +//
>
> +//===----------------------------------------------------------------------===//
> +//
> +// This file contains the entry points for global functions defined in
> +// the LLVM NVPTX back-end.
> +//
>
> +//===----------------------------------------------------------------------===//
> +
> +#ifndef LLVM_TARGET_NVPTX_H
> +#define LLVM_TARGET_NVPTX_H
> +
> +#include <cassert>
> +#include <iosfwd>
> +#include "llvm/Value.h"
> +#include "llvm/Module.h"
> +#include "llvm/Support/ErrorHandling.h"
> +#include "llvm/Target/TargetMachine.h"
> +#include "MCTargetDesc/NVPTXBaseInfo.h"
> +
> +namespace llvm {
> +class NVPTXTargetMachine;
> +class FunctionPass;
> +class formatted_raw_ostream;
> +
> +namespace NVPTXCC {
> +enum CondCodes {
> +  EQ,
> +  NE,
> +  LT,
> +  LE,
> +  GT,
> +  GE
> +};
> +}
> +
> +inline static const char *NVPTXCondCodeToString(NVPTXCC::CondCodes CC) {
> +  switch (CC) {
> +  default: assert(0 && "Unknown condition code");
> +  case NVPTXCC::NE:  return "ne";
> +  case NVPTXCC::EQ:   return "eq";
> +  case NVPTXCC::LT:   return "lt";
> +  case NVPTXCC::LE:  return "le";
> +  case NVPTXCC::GT:  return "gt";
> +  case NVPTXCC::GE:   return "ge";
> +  }
> +}
> +
> +FunctionPass *createNVPTXISelDag(NVPTXTargetMachine &TM,
> +                                 llvm::CodeGenOpt::Level OptLevel);
> +FunctionPass *createVectorElementizePass(NVPTXTargetMachine &);
> +FunctionPass *createLowerStructArgsPass(NVPTXTargetMachine &);
> +FunctionPass *createNVPTXReMatPass(NVPTXTargetMachine &);
> +FunctionPass *createNVPTXReMatBlockPass(NVPTXTargetMachine &);
> +
> +bool isImageOrSamplerVal(const Value *, const Module *);
> +
> +extern Target TheNVPTXTarget32;
> +extern Target TheNVPTXTarget64;
> +
> +namespace NVPTX
> +{
> +enum DrvInterface {
> +  NVCL,
> +  CUDA,
> +  TEST
> +};
> +
> +// A field inside TSFlags needs a shift and a mask. The usage is
> +// always as follows :
> +// ((TSFlags & fieldMask) >> fieldShift)
> +// The enum keeps the mask, the shift, and all valid values of the
> +// field in one place.
> +enum VecInstType {
> +  VecInstTypeShift = 0,
> +  VecInstTypeMask = 0xF,
> +
> +  VecNOP = 0,
> +  VecLoad = 1,
> +  VecStore = 2,
> +  VecBuild = 3,
> +  VecShuffle = 4,
> +  VecExtract = 5,
> +  VecInsert = 6,
> +  VecDest = 7,
> +  VecOther = 15
> +};
> +
> +enum SimpleMove {
> +  SimpleMoveMask = 0x10,
> +  SimpleMoveShift = 4
> +};
> +enum LoadStore {
> +  isLoadMask = 0x20,
> +  isLoadShift = 5,
> +  isStoreMask = 0x40,
> +  isStoreShift = 6
> +};
> +
> +namespace PTXLdStInstCode {
> +enum AddressSpace{
> +  GENERIC = 0,
> +  GLOBAL = 1,
> +  CONSTANT = 2,
> +  SHARED = 3,
> +  PARAM = 4,
> +  LOCAL = 5
> +};
> +enum FromType {
> +  Unsigned = 0,
> +  Signed,
> +  Float
> +};
> +enum VecType {
> +  Scalar = 1,
> +  V2 = 2,
> +  V4 = 4
> +};
> +}
> +}
> +} // end namespace llvm;
> +
> +// Defines symbolic names for NVPTX registers.  This defines a mapping
> from
> +// register name to register number.
> +#define GET_REGINFO_ENUM
> +#include "NVPTXGenRegisterInfo.inc"
> +
> +// Defines symbolic names for the NVPTX instructions.
> +#define GET_INSTRINFO_ENUM
> +#include "NVPTXGenInstrInfo.inc"
> +
> +#endif
>
> Added: llvm/trunk/lib/Target/NVPTX/NVPTX.td
> URL:
> http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/NVPTX/NVPTX.td?rev=156196&view=auto
>
> ==============================================================================
> --- llvm/trunk/lib/Target/NVPTX/NVPTX.td (added)
> +++ llvm/trunk/lib/Target/NVPTX/NVPTX.td Fri May  4 15:18:50 2012
> @@ -0,0 +1,44 @@
> +//===- NVPTX.td - Describe the NVPTX Target Machine -----------*- tblgen
> -*-==//
> +//
> +//                     The LLVM Compiler Infrastructure
> +//
> +// This file is distributed under the University of Illinois Open Source
> +// License. See LICENSE.TXT for details.
> +//
>
> +//===----------------------------------------------------------------------===//
> +// This is the top level entry point for the NVPTX target.
>
> +//===----------------------------------------------------------------------===//
> +
>
> +//===----------------------------------------------------------------------===//
> +// Target-independent interfaces
>
> +//===----------------------------------------------------------------------===//
> +
> +include "llvm/Target/Target.td"
> +
> +include "NVPTXRegisterInfo.td"
> +include "NVPTXInstrInfo.td"
> +
>
> +//===----------------------------------------------------------------------===//
> +// Subtarget Features.
> +// - We use the SM version number instead of explicit feature table.
> +// - Need at least one feature to avoid generating zero sized array by
> +//   TableGen in NVPTXGenSubtarget.inc.
>
> +//===----------------------------------------------------------------------===//
> +def FeatureDummy  : SubtargetFeature<"dummy", "dummy", "true", "">;
> +
>
> +//===----------------------------------------------------------------------===//
> +// NVPTX supported processors.
>
> +//===----------------------------------------------------------------------===//
> +
> +class Proc<string Name, list<SubtargetFeature> Features>
> + : Processor<Name, NoItineraries, Features>;
> +
> +def : Proc<"sm_10", [FeatureDummy]>;
> +
> +
> +def NVPTXInstrInfo : InstrInfo {
> +}
> +
> +def NVPTX : Target {
> +  let InstructionSet = NVPTXInstrInfo;
> +}
>
> Added: llvm/trunk/lib/Target/NVPTX/NVPTXAllocaHoisting.cpp
> URL:
> http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/NVPTX/NVPTXAllocaHoisting.cpp?rev=156196&view=auto
>
> ==============================================================================
> --- llvm/trunk/lib/Target/NVPTX/NVPTXAllocaHoisting.cpp (added)
> +++ llvm/trunk/lib/Target/NVPTX/NVPTXAllocaHoisting.cpp Fri May  4
> 15:18:50 2012
> @@ -0,0 +1,48 @@
> +//===-- AllocaHoisting.cpp - Hosist allocas to the entry block --*- C++
> -*-===//
> +//
> +//                     The LLVM Compiler Infrastructure
> +//
> +// This file is distributed under the University of Illinois Open Source
> +// License. See LICENSE.TXT for details.
> +//
>
> +//===----------------------------------------------------------------------===//
> +//
> +// Hoist the alloca instructions in the non-entry blocks to the entry
> blocks.
> +//
>
> +//===----------------------------------------------------------------------===//
> +
> +#include "llvm/Function.h"
> +#include "llvm/Instructions.h"
> +#include "llvm/Constants.h"
> +#include "NVPTXAllocaHoisting.h"
> +
> +namespace llvm {
> +
> +bool NVPTXAllocaHoisting::runOnFunction(Function &function) {
> +  bool               functionModified    = false;
> +  Function::iterator I                   = function.begin();
> +  TerminatorInst    *firstTerminatorInst = (I++)->getTerminator();
> +
> +  for (Function::iterator E = function.end(); I != E; ++I) {
> +    for (BasicBlock::iterator BI = I->begin(), BE = I->end(); BI != BE;) {
> +      AllocaInst *allocaInst = dyn_cast<AllocaInst>(BI++);
> +      if (allocaInst && isa<ConstantInt>(allocaInst->getArraySize())) {
> +        allocaInst->moveBefore(firstTerminatorInst);
> +        functionModified = true;
> +      }
> +    }
> +  }
> +
> +  return functionModified;
> +}
> +
> +char NVPTXAllocaHoisting::ID = 1;
> +RegisterPass<NVPTXAllocaHoisting> X("alloca-hoisting",
> +                                    "Hoisting alloca instructsion in
> non-entry "
> +                                    "blocks to the entry block");
> +
> +FunctionPass *createAllocaHoisting() {
> +  return new NVPTXAllocaHoisting();
> +}
> +
> +} // end namespace llvm
>
> Added: llvm/trunk/lib/Target/NVPTX/NVPTXAllocaHoisting.h
> URL:
> http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/NVPTX/NVPTXAllocaHoisting.h?rev=156196&view=auto
>
> ==============================================================================
> --- llvm/trunk/lib/Target/NVPTX/NVPTXAllocaHoisting.h (added)
> +++ llvm/trunk/lib/Target/NVPTX/NVPTXAllocaHoisting.h Fri May  4 15:18:50
> 2012
> @@ -0,0 +1,49 @@
> +//===-- AllocaHoisting.h - Hosist allocas to the entry block ----*- C++
> -*-===//
> +//
> +//                     The LLVM Compiler Infrastructure
> +//
> +// This file is distributed under the University of Illinois Open Source
> +// License. See LICENSE.TXT for details.
> +//
>
> +//===----------------------------------------------------------------------===//
> +//
> +// Hoist the alloca instructions in the non-entry blocks to the entry
> blocks.
> +//
>
> +//===----------------------------------------------------------------------===//
> +
> +#ifndef NVPTX_ALLOCA_HOISTING_H_
> +#define NVPTX_ALLOCA_HOISTING_H_
> +
> +#include "llvm/CodeGen/MachineFunctionAnalysis.h"
> +#include "llvm/Pass.h"
> +#include "llvm/Target/TargetData.h"
> +
> +namespace llvm {
> +
> +class FunctionPass;
> +class Function;
> +
> +// Hoisting the alloca instructions in the non-entry blocks to the entry
> +// block.
> +class NVPTXAllocaHoisting : public FunctionPass {
> +public:
> +  static char ID; // Pass ID
> +  NVPTXAllocaHoisting() : FunctionPass(ID) {}
> +
> +  void getAnalysisUsage(AnalysisUsage &AU) const {
> +    AU.addRequired<TargetData>();
> +    AU.addPreserved<MachineFunctionAnalysis>();
> +  }
> +
> +  virtual const char *getPassName() const {
> +    return "NVPTX specific alloca hoisting";
> +  }
> +
> +  virtual bool runOnFunction(Function &function);
> +};
> +
> +extern FunctionPass *createAllocaHoisting();
> +
> +} // end namespace llvm
> +
> +#endif // NVPTX_ALLOCA_HOISTING_H_
>
> Added: llvm/trunk/lib/Target/NVPTX/NVPTXAsmPrinter.cpp
> URL:
> http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/NVPTX/NVPTXAsmPrinter.cpp?rev=156196&view=auto
>
> ==============================================================================
> --- llvm/trunk/lib/Target/NVPTX/NVPTXAsmPrinter.cpp (added)
> +++ llvm/trunk/lib/Target/NVPTX/NVPTXAsmPrinter.cpp Fri May  4 15:18:50
> 2012
> @@ -0,0 +1,2068 @@
> +//===-- NVPTXAsmPrinter.cpp - NVPTX LLVM assembly writer
> ------------------===//
> +//
> +//                     The LLVM Compiler Infrastructure
> +//
> +// This file is distributed under the University of Illinois Open Source
> +// License. See LICENSE.TXT for details.
> +//
>
> +//===----------------------------------------------------------------------===//
> +//
> +// This file contains a printer that converts from our internal
> representation
> +// of machine-dependent LLVM code to NVPTX assembly language.
> +//
>
> +//===----------------------------------------------------------------------===//
> +
> +#include "NVPTX.h"
> +#include "NVPTXInstrInfo.h"
> +#include "NVPTXTargetMachine.h"
> +#include "NVPTXRegisterInfo.h"
> +#include "NVPTXAsmPrinter.h"
> +#include "MCTargetDesc/NVPTXMCAsmInfo.h"
> +#include "NVPTXNumRegisters.h"
> +#include "../lib/CodeGen/AsmPrinter/DwarfDebug.h"
> +#include "llvm/ADT/StringExtras.h"
> +#include "llvm/GlobalVariable.h"
> +#include "llvm/Function.h"
> +#include "llvm/Module.h"
> +#include "llvm/CodeGen/Analysis.h"
> +#include "llvm/CodeGen/MachineRegisterInfo.h"
> +#include "llvm/CodeGen/MachineFrameInfo.h"
> +#include "llvm/CodeGen/MachineModuleInfo.h"
> +#include "llvm/MC/MCStreamer.h"
> +#include "llvm/MC/MCSymbol.h"
> +#include "llvm/Target/Mangler.h"
> +#include "llvm/Target/TargetLoweringObjectFile.h"
> +#include "llvm/Support/TargetRegistry.h"
> +#include "llvm/Support/ErrorHandling.h"
> +#include "llvm/Support/FormattedStream.h"
> +#include "llvm/DerivedTypes.h"
> +#include "NVPTXUtilities.h"
> +#include "llvm/Support/TimeValue.h"
> +#include <sstream>
> +#include "llvm/Support/CommandLine.h"
> +#include "llvm/Analysis/DebugInfo.h"
> +#include "llvm/Analysis/ConstantFolding.h"
> +#include "llvm/Support/Path.h"
> +#include "llvm/Assembly/Writer.h"
> +#include "cl_common_defines.h"
> +
> +
> +using namespace llvm;
> +
> +
> +#include "NVPTXGenAsmWriter.inc"
> +
> +bool RegAllocNilUsed = true;
> +
> +#define DEPOTNAME "__local_depot"
> +
> +static cl::opt<bool>
> +EmitLineNumbers("nvptx-emit-line-numbers",
> +                cl::desc("NVPTX Specific: Emit Line numbers even without
> -G"),
> +                cl::init(true));
> +
> +namespace llvm  {
> +bool InterleaveSrcInPtx = false;
> +}
> +
> +static cl::opt<bool, true>InterleaveSrc("nvptx-emit-src",
> +                                        cl::ZeroOrMore,
> +                       cl::desc("NVPTX Specific: Emit source line in ptx
> file"),
> +
>  cl::location(llvm::InterleaveSrcInPtx));
> +
> +
> +
> +
> +// @TODO: This is a copy from AsmPrinter.cpp.  The function is static, so
> we
> +// cannot just link to the existing version.
> +/// LowerConstant - Lower the specified LLVM Constant to an MCExpr.
> +///
> +using namespace nvptx;
> +const MCExpr *nvptx::LowerConstant(const Constant *CV, AsmPrinter &AP) {
> +  MCContext &Ctx = AP.OutContext;
> +
> +  if (CV->isNullValue() || isa<UndefValue>(CV))
> +    return MCConstantExpr::Create(0, Ctx);
> +
> +  if (const ConstantInt *CI = dyn_cast<ConstantInt>(CV))
> +    return MCConstantExpr::Create(CI->getZExtValue(), Ctx);
> +
> +  if (const GlobalValue *GV = dyn_cast<GlobalValue>(CV))
> +    return MCSymbolRefExpr::Create(AP.Mang->getSymbol(GV), Ctx);
> +
> +  if (const BlockAddress *BA = dyn_cast<BlockAddress>(CV))
> +    return MCSymbolRefExpr::Create(AP.GetBlockAddressSymbol(BA), Ctx);
> +
> +  const ConstantExpr *CE = dyn_cast<ConstantExpr>(CV);
> +  if (CE == 0)
> +    llvm_unreachable("Unknown constant value to lower!");
> +
> +
> +  switch (CE->getOpcode()) {
> +  default:
> +    // If the code isn't optimized, there may be outstanding folding
> +    // opportunities. Attempt to fold the expression using TargetData as a
> +    // last resort before giving up.
> +    if (Constant *C =
> +        ConstantFoldConstantExpression(CE, AP.TM.getTargetData()))
> +      if (C != CE)
> +        return LowerConstant(C, AP);
> +
> +    // Otherwise report the problem to the user.
> +    {
> +        std::string S;
> +        raw_string_ostream OS(S);
> +        OS << "Unsupported expression in static initializer: ";
> +        WriteAsOperand(OS, CE, /*PrintType=*/false,
> +                       !AP.MF ? 0 : AP.MF->getFunction()->getParent());
> +        report_fatal_error(OS.str());
> +    }
> +  case Instruction::GetElementPtr: {
> +    const TargetData &TD = *AP.TM.getTargetData();
> +    // Generate a symbolic expression for the byte address
> +    const Constant *PtrVal = CE->getOperand(0);
> +    SmallVector<Value*, 8> IdxVec(CE->op_begin()+1, CE->op_end());
> +    int64_t Offset = TD.getIndexedOffset(PtrVal->getType(), IdxVec);
> +
> +    const MCExpr *Base = LowerConstant(CE->getOperand(0), AP);
> +    if (Offset == 0)
> +      return Base;
> +
> +    // Truncate/sext the offset to the pointer size.
> +    if (TD.getPointerSizeInBits() != 64) {
> +      int SExtAmount = 64-TD.getPointerSizeInBits();
> +      Offset = (Offset << SExtAmount) >> SExtAmount;
> +    }
> +
> +    return MCBinaryExpr::CreateAdd(Base, MCConstantExpr::Create(Offset,
> Ctx),
> +                                   Ctx);
> +  }
> +
> +  case Instruction::Trunc:
> +    // We emit the value and depend on the assembler to truncate the
> generated
> +    // expression properly.  This is important for differences between
> +    // blockaddress labels.  Since the two labels are in the same
> function, it
> +    // is reasonable to treat their delta as a 32-bit value.
> +    // FALL THROUGH.
> +  case Instruction::BitCast:
> +    return LowerConstant(CE->getOperand(0), AP);
> +
> +  case Instruction::IntToPtr: {
> +    const TargetData &TD = *AP.TM.getTargetData();
> +    // Handle casts to pointers by changing them into casts to the
> appropriate
> +    // integer type.  This promotes constant folding and simplifies this
> code.
> +    Constant *Op = CE->getOperand(0);
> +    Op = ConstantExpr::getIntegerCast(Op,
> TD.getIntPtrType(CV->getContext()),
> +                                      false/*ZExt*/);
> +    return LowerConstant(Op, AP);
> +  }
> +
> +  case Instruction::PtrToInt: {
> +    const TargetData &TD = *AP.TM.getTargetData();
> +    // Support only foldable casts to/from pointers that can be
> eliminated by
> +    // changing the pointer to the appropriately sized integer type.
> +    Constant *Op = CE->getOperand(0);
> +    Type *Ty = CE->getType();
> +
> +    const MCExpr *OpExpr = LowerConstant(Op, AP);
> +
> +    // We can emit the pointer value into this slot if the slot is an
> +    // integer slot equal to the size of the pointer.
> +    if (TD.getTypeAllocSize(Ty) == TD.getTypeAllocSize(Op->getType()))
> +      return OpExpr;
> +
> +    // Otherwise the pointer is smaller than the resultant integer, mask
> off
> +    // the high bits so we are sure to get a proper truncation if the
> input is
> +    // a constant expr.
> +    unsigned InBits = TD.getTypeAllocSizeInBits(Op->getType());
> +    const MCExpr *MaskExpr = MCConstantExpr::Create(~0ULL >> (64-InBits),
> Ctx);
> +    return MCBinaryExpr::CreateAnd(OpExpr, MaskExpr, Ctx);
> +  }
> +
> +  // The MC library also has a right-shift operator, but it isn't
> consistently
> +  // signed or unsigned between different targets.
> +  case Instruction::Add:
> +  case Instruction::Sub:
> +  case Instruction::Mul:
> +  case Instruction::SDiv:
> +  case Instruction::SRem:
> +  case Instruction::Shl:
> +  case Instruction::And:
> +  case Instruction::Or:
> +  case Instruction::Xor: {
> +    const MCExpr *LHS = LowerConstant(CE->getOperand(0), AP);
> +    const MCExpr *RHS = LowerConstant(CE->getOperand(1), AP);
> +    switch (CE->getOpcode()) {
> +    default: llvm_unreachable("Unknown binary operator constant cast
> expr");
> +    case Instruction::Add: return MCBinaryExpr::CreateAdd(LHS, RHS, Ctx);
> +    case Instruction::Sub: return MCBinaryExpr::CreateSub(LHS, RHS, Ctx);
> +    case Instruction::Mul: return MCBinaryExpr::CreateMul(LHS, RHS, Ctx);
> +    case Instruction::SDiv: return MCBinaryExpr::CreateDiv(LHS, RHS, Ctx);
> +    case Instruction::SRem: return MCBinaryExpr::CreateMod(LHS, RHS, Ctx);
> +    case Instruction::Shl: return MCBinaryExpr::CreateShl(LHS, RHS, Ctx);
> +    case Instruction::And: return MCBinaryExpr::CreateAnd(LHS, RHS, Ctx);
> +    case Instruction::Or:  return MCBinaryExpr::CreateOr (LHS, RHS, Ctx);
> +    case Instruction::Xor: return MCBinaryExpr::CreateXor(LHS, RHS, Ctx);
> +    }
> +  }
> +  }
> +}
> +
> +
> +void NVPTXAsmPrinter::emitLineNumberAsDotLoc(const MachineInstr &MI)
> +{
> +  if (!EmitLineNumbers)
> +    return;
> +  if (ignoreLoc(MI))
> +    return;
> +
> +  DebugLoc curLoc = MI.getDebugLoc();
> +
> +  if (prevDebugLoc.isUnknown() && curLoc.isUnknown())
> +    return;
> +
> +  if (prevDebugLoc == curLoc)
> +    return;
> +
> +  prevDebugLoc = curLoc;
> +
> +  if (curLoc.isUnknown())
> +    return;
> +
> +
> +  const MachineFunction *MF = MI.getParent()->getParent();
> +  //const TargetMachine &TM = MF->getTarget();
> +
> +  const LLVMContext &ctx = MF->getFunction()->getContext();
> +  DIScope Scope(curLoc.getSc...
>
> [Message clipped]
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20120504/ecd776e5/attachment.html>


More information about the llvm-commits mailing list