[Libclc-dev] [PATCH 1/1] R600: Add new intrinsic to read work dimensions

[Jan Vesely]

CC: Tom Stellard <tom at stellard.net>
CC: Matt Arsenault <Matthew.Arsenault at amd.com>

Signed-off-by: Jan Vesely <jan.vesely at rutgers.edu>
---
 include/llvm/IR/IntrinsicsR600.td    | 2 ++
 lib/Target/R600/R600ISelLowering.cpp | 6 ++++--
 2 files changed, 6 insertions(+), 2 deletions(-)

diff --git a/include/llvm/IR/IntrinsicsR600.td b/include/llvm/IR/IntrinsicsR600.td
index ba69eaa..37a9771 100644
--- a/include/llvm/IR/IntrinsicsR600.td
+++ b/include/llvm/IR/IntrinsicsR600.td
@@ -33,6 +33,8 @@ defm int_r600_read_tgid : R600ReadPreloadRegisterIntrinsic_xyz <
                                        "__builtin_r600_read_tgid">;
 defm int_r600_read_tidig : R600ReadPreloadRegisterIntrinsic_xyz <
                                        "__builtin_r600_read_tidig">;
+def int_r600_read_workdim : R600ReadPreloadRegisterIntrinsic <
+                                       "__builtin_r600_read_workdim">;
 
 } // End TargetPrefix = "r600"
 
diff --git a/lib/Target/R600/R600ISelLowering.cpp b/lib/Target/R600/R600ISelLowering.cpp
index 4c603f8..1c59684 100644
--- a/lib/Target/R600/R600ISelLowering.cpp
+++ b/lib/Target/R600/R600ISelLowering.cpp
@@ -805,6 +805,8 @@ SDValue R600TargetLowering::LowerOperation(SDValue Op, SelectionDAG &DAG) const
       return LowerImplicitParameter(DAG, VT, DL, 7);
     case Intrinsic::r600_read_local_size_z:
       return LowerImplicitParameter(DAG, VT, DL, 8);
+    case Intrinsic::r600_read_workdim:
+      return LowerImplicitParameter(DAG, VT, DL, 9);
 
     case Intrinsic::r600_read_tgid_x:
       return CreateLiveInRegister(DAG, &AMDGPU::R600_TReg32RegClass,
@@ -1722,7 +1724,7 @@ SDValue R600TargetLowering::LowerFormalArguments(
     // being invalid. Somehow this seems to work with i64 arguments, but breaks
     // for <1 x i64>.
 
-    // The first 36 bytes of the input buffer contains information about
+    // The first 40 bytes of the input buffer contains information about
     // thread group and global sizes.
 
     // FIXME: This should really check the extload type, but the handling of
@@ -1730,7 +1732,7 @@ SDValue R600TargetLowering::LowerFormalArguments(
     //ISD::LoadExtType Ext = Ins[i].Flags.isSExt() ? ISD::SEXTLOAD : ISD::ZEXTLOAD;
     ISD::LoadExtType Ext = ISD::SEXTLOAD;
     SDValue Arg = DAG.getExtLoad(Ext, DL, VT, Chain,
-                                 DAG.getConstant(36 + VA.getLocMemOffset(), MVT::i32),
+                                 DAG.getConstant(40 + VA.getLocMemOffset(), MVT::i32),
                                  MachinePointerInfo(UndefValue::get(PtrTy)),
                                  MemVT, false, false, 4);
 
-- 
1.9.3