[llvm] 1c729d7 - [NVPTX] Use align attribute for kernel pointer arg alignment

[Nikita Popov via llvm-commits]

Author: Nikita Popov
Date: 2022-02-10T11:56:48+01:00
New Revision: 1c729d719a344c1dbe8c507118fcfbf2eeab85fd

URL: https://github.com/llvm/llvm-project/commit/1c729d719a344c1dbe8c507118fcfbf2eeab85fd
DIFF: https://github.com/llvm/llvm-project/commit/1c729d719a344c1dbe8c507118fcfbf2eeab85fd.diff

LOG: [NVPTX] Use align attribute for kernel pointer arg alignment

Instead of determining the alignment based on the pointer element
type (which is incompatible with opaque pointers), make use of
alignment annotations added by the frontend.

In particular, clang will add alignment attributes to OpenCL kernels
since D118894. Other frontends might need to be adjusted to add
the attribute as well.

Differential Revision: https://reviews.llvm.org/D119247

Added: 
    

Modified: 
    llvm/lib/Target/NVPTX/NVPTXAsmPrinter.cpp
    llvm/test/CodeGen/NVPTX/nvcl-param-align.ll

Removed: 
    


################################################################################
diff  --git a/llvm/lib/Target/NVPTX/NVPTXAsmPrinter.cpp b/llvm/lib/Target/NVPTX/NVPTXAsmPrinter.cpp
index 7392cd8be4028..558ca6879cdbd 100644
--- a/llvm/lib/Target/NVPTX/NVPTXAsmPrinter.cpp
+++ b/llvm/lib/Target/NVPTX/NVPTXAsmPrinter.cpp
@@ -1335,34 +1335,6 @@ void NVPTXAsmPrinter::emitPTXGlobalVariable(const GlobalVariable *GVar,
   }
 }
 
-static unsigned int getOpenCLAlignment(const DataLayout &DL, Type *Ty) {
-  if (Ty->isSingleValueType())
-    return DL.getPrefTypeAlignment(Ty);
-
-  auto *ATy = dyn_cast<ArrayType>(Ty);
-  if (ATy)
-    return getOpenCLAlignment(DL, ATy->getElementType());
-
-  auto *STy = dyn_cast<StructType>(Ty);
-  if (STy) {
-    unsigned int alignStruct = 1;
-    // Go through each element of the struct and find the
-    // largest alignment.
-    for (unsigned i = 0, e = STy->getNumElements(); i != e; i++) {
-      Type *ETy = STy->getElementType(i);
-      unsigned int align = getOpenCLAlignment(DL, ETy);
-      if (align > alignStruct)
-        alignStruct = align;
-    }
-    return alignStruct;
-  }
-
-  auto *FTy = dyn_cast<FunctionType>(Ty);
-  if (FTy)
-    return DL.getPointerPrefAlignment().value();
-  return DL.getPrefTypeAlignment(Ty);
-}
-
 void NVPTXAsmPrinter::printParamName(Function::const_arg_iterator I,
                                      int paramIndex, raw_ostream &O) {
   getSymbol(I->getParent())->print(O, MAI);
@@ -1454,7 +1426,6 @@ void NVPTXAsmPrinter::emitFunctionParamList(const Function *F, raw_ostream &O) {
 
           if (static_cast<NVPTXTargetMachine &>(TM).getDrvInterface() !=
               NVPTX::CUDA) {
-            Type *ETy = PTy->getPointerElementType();
             int addrSpace = PTy->getAddressSpace();
             switch (addrSpace) {
             default:
@@ -1470,7 +1441,8 @@ void NVPTXAsmPrinter::emitFunctionParamList(const Function *F, raw_ostream &O) {
               O << ".ptr .global ";
               break;
             }
-            O << ".align " << (int)getOpenCLAlignment(DL, ETy) << " ";
+            Align ParamAlign = I->getParamAlign().valueOrOne();
+            O << ".align " << ParamAlign.value() << " ";
           }
           printParamName(I, paramIndex, O);
           continue;

diff  --git a/llvm/test/CodeGen/NVPTX/nvcl-param-align.ll b/llvm/test/CodeGen/NVPTX/nvcl-param-align.ll
index c1a489f1fc422..d1eecc855fcb4 100644
--- a/llvm/test/CodeGen/NVPTX/nvcl-param-align.ll
+++ b/llvm/test/CodeGen/NVPTX/nvcl-param-align.ll
@@ -2,15 +2,15 @@
 
 target triple = "nvptx-unknown-nvcl"
 
+define void @foo(i64 %img, i64 %sampler, <5 x float>* align 32 %v1, i32* %v2) {
+; The parameter alignment is determined by the align attribute (default 1).
 ; CHECK-LABEL: .entry foo(
-define void @foo(i64 %img, i64 %sampler, <5 x float>* %v) {
-; The parameter alignment should be the next power of 2 of 5xsizeof(float),
-; which is 32.
 ; CHECK: .param .u32 .ptr .align 32 foo_param_2
+; CHECK: .param .u32 .ptr .align 1 foo_param_3
   ret void
 }
 
 !nvvm.annotations = !{!1, !2, !3}
-!1 = !{void (i64, i64, <5 x float>*)* @foo, !"kernel", i32 1}
-!2 = !{void (i64, i64, <5 x float>*)* @foo, !"rdoimage", i32 0}
-!3 = !{void (i64, i64, <5 x float>*)* @foo, !"sampler", i32 1}
+!1 = !{void (i64, i64, <5 x float>*, i32*)* @foo, !"kernel", i32 1}
+!2 = !{void (i64, i64, <5 x float>*, i32*)* @foo, !"rdoimage", i32 0}
+!3 = !{void (i64, i64, <5 x float>*, i32*)* @foo, !"sampler", i32 1}