[AMDGPU] fix LDS f32 intrinsics

- using qualified pointer addrspace in intrinsics class to avoid .f32 mangling
- changed too common atomic mangling to ds
- added missing intrinsics to AMDGPUTTIImpl::getTgtMemIntrinsic

Reviewed by: b-sumner

Differential Revision: https://reviews.llvm.org/D42383

llvm-svn: 323516

2 files changed, 19 insertions, 16 deletions

diff --git a/llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp b/llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp
index 21088d3e48e..3ad099ca686 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp
@@ -292,7 +292,10 @@ bool AMDGPUTTIImpl::getTgtMemIntrinsic(IntrinsicInst *Inst,
                                        MemIntrinsicInfo &Info) const {
   switch (Inst->getIntrinsicID()) {
   case Intrinsic::amdgcn_atomic_inc:
-  case Intrinsic::amdgcn_atomic_dec: {
+  case Intrinsic::amdgcn_atomic_dec:
+  case Intrinsic::amdgcn_ds_fadd:
+  case Intrinsic::amdgcn_ds_fmin:
+  case Intrinsic::amdgcn_ds_fmax: {
     auto *Ordering = dyn_cast<ConstantInt>(Inst->getArgOperand(2));
     auto *Volatile = dyn_cast<ConstantInt>(Inst->getArgOperand(4));
     if (!Ordering || !Volatile)
@@ -475,9 +478,9 @@ static bool isIntrinsicSourceOfDivergence(const IntrinsicInst *I) {
   case Intrinsic::r600_read_tidig_z:
   case Intrinsic::amdgcn_atomic_inc:
   case Intrinsic::amdgcn_atomic_dec:
-  case Intrinsic::amdgcn_atomic_fadd:
-  case Intrinsic::amdgcn_atomic_fmin:
-  case Intrinsic::amdgcn_atomic_fmax:
+  case Intrinsic::amdgcn_ds_fadd:
+  case Intrinsic::amdgcn_ds_fmin:
+  case Intrinsic::amdgcn_ds_fmax:
   case Intrinsic::amdgcn_image_atomic_swap:
   case Intrinsic::amdgcn_image_atomic_add:
   case Intrinsic::amdgcn_image_atomic_sub:
diff --git a/llvm/lib/Target/AMDGPU/SIISelLowering.cpp b/llvm/lib/Target/AMDGPU/SIISelLowering.cpp
index 7dc9dcf31fc..913bf078679 100644
--- a/llvm/lib/Target/AMDGPU/SIISelLowering.cpp
+++ b/llvm/lib/Target/AMDGPU/SIISelLowering.cpp
@@ -566,9 +566,9 @@ bool SITargetLowering::getTgtMemIntrinsic(IntrinsicInfo &Info,
   switch (IntrID) {
   case Intrinsic::amdgcn_atomic_inc:
   case Intrinsic::amdgcn_atomic_dec:
-  case Intrinsic::amdgcn_atomic_fadd:
-  case Intrinsic::amdgcn_atomic_fmin:
-  case Intrinsic::amdgcn_atomic_fmax: {
+  case Intrinsic::amdgcn_ds_fadd:
+  case Intrinsic::amdgcn_ds_fmin:
+  case Intrinsic::amdgcn_ds_fmax: {
     Info.opc = ISD::INTRINSIC_W_CHAIN;
     Info.memVT = MVT::getVT(CI.getType());
     Info.ptrVal = CI.getOperand(0);
@@ -807,9 +807,9 @@ bool SITargetLowering::getAddrModeArguments(IntrinsicInst *II,
   switch (II->getIntrinsicID()) {
   case Intrinsic::amdgcn_atomic_inc:
   case Intrinsic::amdgcn_atomic_dec:
-  case Intrinsic::amdgcn_atomic_fadd:
-  case Intrinsic::amdgcn_atomic_fmin:
-  case Intrinsic::amdgcn_atomic_fmax: {
+  case Intrinsic::amdgcn_ds_fadd:
+  case Intrinsic::amdgcn_ds_fmin:
+  case Intrinsic::amdgcn_ds_fmax: {
     Value *Ptr = II->getArgOperand(0);
     AccessTy = II->getType();
     Ops.push_back(Ptr);
@@ -4827,9 +4827,9 @@ SDValue SITargetLowering::LowerINTRINSIC_W_CHAIN(SDValue Op,
   switch (IntrID) {
   case Intrinsic::amdgcn_atomic_inc:
   case Intrinsic::amdgcn_atomic_dec:
-  case Intrinsic::amdgcn_atomic_fadd:
-  case Intrinsic::amdgcn_atomic_fmin:
-  case Intrinsic::amdgcn_atomic_fmax: {
+  case Intrinsic::amdgcn_ds_fadd:
+  case Intrinsic::amdgcn_ds_fmin:
+  case Intrinsic::amdgcn_ds_fmax: {
     MemSDNode *M = cast<MemSDNode>(Op);
     unsigned Opc;
     switch (IntrID) {
@@ -4839,13 +4839,13 @@ SDValue SITargetLowering::LowerINTRINSIC_W_CHAIN(SDValue Op,
     case Intrinsic::amdgcn_atomic_dec:
       Opc = AMDGPUISD::ATOMIC_DEC;
       break;
-    case Intrinsic::amdgcn_atomic_fadd:
+    case Intrinsic::amdgcn_ds_fadd:
       Opc = AMDGPUISD::ATOMIC_LOAD_FADD;
       break;
-    case Intrinsic::amdgcn_atomic_fmin:
+    case Intrinsic::amdgcn_ds_fmin:
       Opc = AMDGPUISD::ATOMIC_LOAD_FMIN;
       break;
-    case Intrinsic::amdgcn_atomic_fmax:
+    case Intrinsic::amdgcn_ds_fmax:
       Opc = AMDGPUISD::ATOMIC_LOAD_FMAX;
       break;
     default: