[PATCH] D89404: Preserve param alignment in NVPTXLowerArgs pass.

[Justin Lebar via Phabricator via llvm-commits]

This revision was landed with ongoing or failed builds.
This revision was automatically updated to reflect the committed changes.
Closed by commit rGe9ac1869a82a: Preserve param alignment in NVPTXLowerArgs pass. (authored by jlebar).

Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D89404/new/

https://reviews.llvm.org/D89404

Files:
  llvm/lib/Target/NVPTX/NVPTXLowerArgs.cpp
  llvm/test/CodeGen/NVPTX/lower-args.ll


Index: llvm/test/CodeGen/NVPTX/lower-args.ll
===================================================================
--- /dev/null
+++ llvm/test/CodeGen/NVPTX/lower-args.ll
@@ -0,0 +1,27 @@
+; RUN: opt < %s -S -nvptx-lower-args | FileCheck %s --check-prefix IR
+; RUN: llc < %s -mcpu=sm_20 | FileCheck %s --check-prefix PTX
+
+target datalayout = "e-i64:64-i128:128-v16:16-v32:32-n16:32:64"
+target triple = "nvptx64-nvidia-cuda"
+
+%class.outer = type <{ %class.inner, i32, [4 x i8] }>
+%class.inner = type { i32*, i32* }
+
+; Check that nvptx-lower-args preserves arg alignment
+define void @load_alignment(%class.outer* nocapture readonly byval(%class.outer) align 8 %arg) {
+entry:
+; IR: load %class.outer, %class.outer addrspace(101)*
+; IR-SAME: align 8
+; PTX: ld.param.u64
+; PTX-NOT: ld.param.u8
+  %arg.idx = getelementptr %class.outer, %class.outer* %arg, i64 0, i32 0, i32 0
+  %arg.idx.val = load i32*, i32** %arg.idx, align 8
+  %arg.idx1 = getelementptr %class.outer, %class.outer* %arg, i64 0, i32 0, i32 1
+  %arg.idx1.val = load i32*, i32** %arg.idx1, align 8
+  %arg.idx2 = getelementptr %class.outer, %class.outer* %arg, i64 0, i32 1
+  %arg.idx2.val = load i32, i32* %arg.idx2, align 8
+  %arg.idx.val.val = load i32, i32* %arg.idx.val, align 4
+  %add.i = add nsw i32 %arg.idx.val.val, %arg.idx2.val
+  store i32 %add.i, i32* %arg.idx1.val, align 4
+  ret void
+}
Index: llvm/lib/Target/NVPTX/NVPTXLowerArgs.cpp
===================================================================
--- llvm/lib/Target/NVPTX/NVPTXLowerArgs.cpp
+++ llvm/lib/Target/NVPTX/NVPTXLowerArgs.cpp
@@ -172,8 +172,12 @@
   Value *ArgInParam = new AddrSpaceCastInst(
       Arg, PointerType::get(StructType, ADDRESS_SPACE_PARAM), Arg->getName(),
       FirstInst);
+  // Be sure to propagate alignment to this load; LLVM doesn't know that NVPTX
+  // addrspacecast preserves alignment.  Since params are constant, this load is
+  // definitely not volatile.
   LoadInst *LI =
-      new LoadInst(StructType, ArgInParam, Arg->getName(), FirstInst);
+      new LoadInst(StructType, ArgInParam, Arg->getName(),
+                   /*isVolatile=*/false, AllocA->getAlign(), FirstInst);
   new StoreInst(LI, AllocA, FirstInst);
 }
 


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D89404.298197.patch
Type: text/x-patch
Size: 2217 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20201014/d12bdab7/attachment.bin>