[AMDGPU] add support for hostcall buffer pointer as hidden kernel argument

Hostcall is a service that allows a kernel to submit requests to the
host using shared buffers, and block until a response is
received. This will eventually replace the shared buffer currently
used for printf, and repurposes the same hidden kernel argument. This
change introduces a new ValueKind in the HSA metadata to represent the
hostcall buffer.

Differential Revision: https://reviews.llvm.org/D70038

4 files changed, 23 insertions, 2 deletions

diff --git a/llvm/lib/BinaryFormat/AMDGPUMetadataVerifier.cpp b/llvm/lib/BinaryFormat/AMDGPUMetadataVerifier.cpp
index 3f36dff9f55..d927171d556 100644
--- a/llvm/lib/BinaryFormat/AMDGPUMetadataVerifier.cpp
+++ b/llvm/lib/BinaryFormat/AMDGPUMetadataVerifier.cpp
@@ -119,6 +119,7 @@ bool MetadataVerifier::verifyKernelArgs(msgpack::DocNode &Node) {
                                .Case("hidden_global_offset_z", true)
                                .Case("hidden_none", true)
                                .Case("hidden_printf_buffer", true)
+                               .Case("hidden_hostcall_buffer", true)
                                .Case("hidden_default_queue", true)
                                .Case("hidden_completion_action", true)
                                .Case("hidden_multigrid_sync_arg", true)
diff --git a/llvm/lib/Support/AMDGPUMetadata.cpp b/llvm/lib/Support/AMDGPUMetadata.cpp
index 5f8102299f4..4ea197a9738 100644
--- a/llvm/lib/Support/AMDGPUMetadata.cpp
+++ b/llvm/lib/Support/AMDGPUMetadata.cpp
@@ -62,6 +62,7 @@ struct ScalarEnumerationTraits<ValueKind> {
     YIO.enumCase(EN, "HiddenGlobalOffsetZ", ValueKind::HiddenGlobalOffsetZ);
     YIO.enumCase(EN, "HiddenNone", ValueKind::HiddenNone);
     YIO.enumCase(EN, "HiddenPrintfBuffer", ValueKind::HiddenPrintfBuffer);
+    YIO.enumCase(EN, "HiddenHostcallBuffer", ValueKind::HiddenHostcallBuffer);
     YIO.enumCase(EN, "HiddenDefaultQueue", ValueKind::HiddenDefaultQueue);
     YIO.enumCase(EN, "HiddenCompletionAction",
                  ValueKind::HiddenCompletionAction);
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUHSAMetadataStreamer.cpp b/llvm/lib/Target/AMDGPU/AMDGPUHSAMetadataStreamer.cpp
index 9f5bcd8ff5f..511d6294318 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPUHSAMetadataStreamer.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUHSAMetadataStreamer.cpp
@@ -421,7 +421,12 @@ void MetadataStreamerV2::emitHiddenKernelArgs(const Function &Func) {
   if (HiddenArgNumBytes >= 32) {
     if (Func.getParent()->getNamedMetadata("llvm.printf.fmts"))
       emitKernelArg(DL, Int8PtrTy, ValueKind::HiddenPrintfBuffer);
-    else
+    else if (Func.getParent()->getFunction("__ockl_hostcall_internal")) {
+      // The printf runtime binding pass should have ensured that hostcall and
+      // printf are not used in the same module.
+      assert(!Func.getParent()->getNamedMetadata("llvm.printf.fmts"));
+      emitKernelArg(DL, Int8PtrTy, ValueKind::HiddenHostcallBuffer);
+    } else
       emitKernelArg(DL, Int8PtrTy, ValueKind::HiddenNone);
   }
 
@@ -854,7 +859,12 @@ void MetadataStreamerV3::emitHiddenKernelArgs(const Function &Func,
   if (HiddenArgNumBytes >= 32) {
     if (Func.getParent()->getNamedMetadata("llvm.printf.fmts"))
       emitKernelArg(DL, Int8PtrTy, "hidden_printf_buffer", Offset, Args);
-    else
+    else if (Func.getParent()->getFunction("__ockl_hostcall_internal")) {
+      // The printf runtime binding pass should have ensured that hostcall and
+      // printf are not used in the same module.
+      assert(!Func.getParent()->getNamedMetadata("llvm.printf.fmts"));
+      emitKernelArg(DL, Int8PtrTy, "hidden_hostcall_buffer", Offset, Args);
+    } else
       emitKernelArg(DL, Int8PtrTy, "hidden_none", Offset, Args);
   }
 
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUPrintfRuntimeBinding.cpp b/llvm/lib/Target/AMDGPU/AMDGPUPrintfRuntimeBinding.cpp
index 1f44012a7c0..511de96b5f7 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPUPrintfRuntimeBinding.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUPrintfRuntimeBinding.cpp
@@ -582,6 +582,15 @@ bool AMDGPUPrintfRuntimeBinding::runOnModule(Module &M) {
   if (Printfs.empty())
     return false;
 
+  if (auto HostcallFunction = M.getFunction("__ockl_hostcall_internal")) {
+    for (auto &U : HostcallFunction->uses()) {
+      if (auto *CI = dyn_cast<CallInst>(U.getUser())) {
+        M.getContext().emitError(
+            CI, "Cannot use both printf and hostcall in the same module");
+      }
+    }
+  }
+
   TD = &M.getDataLayout();
   auto DTWP = getAnalysisIfAvailable<DominatorTreeWrapperPass>();
   DT = DTWP ? &DTWP->getDomTree() : nullptr;