r261779 - [CUDA] Mark all CUDA device-side function defs, decls, and calls as convergent.

[Justin Lebar via cfe-commits]

Author: jlebar
Date: Wed Feb 24 15:55:11 2016
New Revision: 261779

URL: http://llvm.org/viewvc/llvm-project?rev=261779&view=rev
Log:
[CUDA] Mark all CUDA device-side function defs, decls, and calls as convergent.

Summary:
This is important for e.g. the following case:

  void sync() { __syncthreads(); }
  void foo() {
    do_something();
    sync();
    do_something_else():
  }

Without this change, if the optimizer does not inline sync() (which it
won't because __syncthreads is also marked as noduplicate, for now
anyway), it is free to perform optimizations on sync() that it would not
be able to perform on __syncthreads(), because sync() is not marked as
convergent.

Similarly, we need a notion of convergent calls, since in the case when
we can't statically determine a call's target(s), we need to know
whether it's safe to perform optimizations around the call.

This change is conservative; the optimizer will remove these attrs where
it can, see r260318, r260319.

Reviewers: majnemer

Subscribers: cfe-commits, jhen, echristo, tra

Differential Revision: http://reviews.llvm.org/D17056

Added:
    cfe/trunk/test/CodeGenCUDA/convergent.cu
Modified:
    cfe/trunk/lib/CodeGen/CGCall.cpp
    cfe/trunk/test/CodeGenCUDA/device-var-init.cu

Modified: cfe/trunk/lib/CodeGen/CGCall.cpp
URL: http://llvm.org/viewvc/llvm-project/cfe/trunk/lib/CodeGen/CGCall.cpp?rev=261779&r1=261778&r2=261779&view=diff
==============================================================================
--- cfe/trunk/lib/CodeGen/CGCall.cpp (original)
+++ cfe/trunk/lib/CodeGen/CGCall.cpp Wed Feb 24 15:55:11 2016
@@ -1595,6 +1595,14 @@ void CodeGenModule::ConstructAttributeLi
     }
   }
 
+  if (getLangOpts().CUDA && getLangOpts().CUDAIsDevice) {
+    // Conservatively, mark all functions and calls in CUDA as convergent
+    // (meaning, they may call an intrinsically convergent op, such as
+    // __syncthreads(), and so can't have certain optimizations applied around
+    // them).  LLVM will remove this attribute where it safely can.
+    FuncAttrs.addAttribute(llvm::Attribute::Convergent);
+  }
+
   ClangToLLVMArgMapping IRFunctionArgs(getContext(), FI);
 
   QualType RetTy = FI.getReturnType();

Added: cfe/trunk/test/CodeGenCUDA/convergent.cu
URL: http://llvm.org/viewvc/llvm-project/cfe/trunk/test/CodeGenCUDA/convergent.cu?rev=261779&view=auto
==============================================================================
--- cfe/trunk/test/CodeGenCUDA/convergent.cu (added)
+++ cfe/trunk/test/CodeGenCUDA/convergent.cu Wed Feb 24 15:55:11 2016
@@ -0,0 +1,39 @@
+// REQUIRES: x86-registered-target
+// REQUIRES: nvptx-registered-target
+
+// RUN: %clang_cc1 -fcuda-is-device -triple nvptx-nvidia-cuda -emit-llvm \
+// RUN:   -disable-llvm-passes -o - %s | FileCheck -check-prefix DEVICE %s
+
+// RUN: %clang_cc1 -triple x86_64-unknown-linux-gnu -emit-llvm \
+// RUN:   -disable-llvm-passes -o - %s | \
+// RUN:  FileCheck -check-prefix HOST %s
+
+#include "Inputs/cuda.h"
+
+// DEVICE: Function Attrs:
+// DEVICE-SAME: convergent
+// DEVICE-NEXT: define void @_Z3foov
+__device__ void foo() {}
+
+// HOST: Function Attrs:
+// HOST-NOT: convergent
+// HOST-NEXT: define void @_Z3barv
+// DEVICE: Function Attrs:
+// DEVICE-SAME: convergent
+// DEVICE-NEXT: define void @_Z3barv
+__host__ __device__ void baz();
+__host__ __device__ void bar() {
+  // DEVICE: call void @_Z3bazv() [[CALL_ATTR:#[0-9]+]]
+  baz();
+}
+
+// DEVICE: declare void @_Z3bazv() [[BAZ_ATTR:#[0-9]+]]
+// DEVICE: attributes [[BAZ_ATTR]] = {
+// DEVICE-SAME: convergent
+// DEVICE-SAME: }
+// DEVICE: attributes [[CALL_ATTR]] = { convergent }
+
+// HOST: declare void @_Z3bazv() [[BAZ_ATTR:#[0-9]+]]
+// HOST: attributes [[BAZ_ATTR]] = {
+// HOST-NOT: convergent
+// NOST-SAME: }

Modified: cfe/trunk/test/CodeGenCUDA/device-var-init.cu
URL: http://llvm.org/viewvc/llvm-project/cfe/trunk/test/CodeGenCUDA/device-var-init.cu?rev=261779&r1=261778&r2=261779&view=diff
==============================================================================
--- cfe/trunk/test/CodeGenCUDA/device-var-init.cu (original)
+++ cfe/trunk/test/CodeGenCUDA/device-var-init.cu Wed Feb 24 15:55:11 2016
@@ -382,7 +382,7 @@ __device__ void df() {
 // CHECK:   call void @_ZN4NETCC1IJEEEDpT_(%struct.NETC* %netc)
 // CHECK:   call void @_ZN7EC_I_ECC1Ev(%struct.EC_I_EC* %ec_i_ec)
 // CHECK:   call void @_ZN8EC_I_EC1C1Ev(%struct.EC_I_EC1* %ec_i_ec1)
-// CHECK:   call void @_ZN5T_V_TC1Ev(%struct.T_V_T* %t_v_t) #3
+// CHECK:   call void @_ZN5T_V_TC1Ev(%struct.T_V_T* %t_v_t)
 // CHECK:   call void @_ZN7T_B_NECC1Ev(%struct.T_B_NEC* %t_b_nec)
 // CHECK:   call void @_ZN7T_F_NECC1Ev(%struct.T_F_NEC* %t_f_nec)
 // CHECK:   call void @_ZN8T_FA_NECC1Ev(%struct.T_FA_NEC* %t_fa_nec)