[llvm] 5afe29e - [FastIsel] Get the right register type for call instruction (#164565)

[via llvm-commits]

Author: Luo Yuanke
Date: 2025-10-22T17:11:27+08:00
New Revision: 5afe29e0faaee44c44f1daa3e2693fc1ab212530

URL: https://github.com/llvm/llvm-project/commit/5afe29e0faaee44c44f1daa3e2693fc1ab212530
DIFF: https://github.com/llvm/llvm-project/commit/5afe29e0faaee44c44f1daa3e2693fc1ab212530.diff

LOG: [FastIsel] Get the right register type for call instruction (#164565)

When switch from fast isel to dag isel the input value is from llvm IR
instruction.
If the instruction is call we should get the calling convention of the
callee and
pass it to RegsForValue::getCopyFromRegs, so that it can deduce the
right RegisterVT
of the returned value of the callee.

---------

Co-authored-by: Yuanke Luo <ykluo at birentech.com>

Added: 
    llvm/test/CodeGen/X86/bf16-fast-isel.ll

Modified: 
    llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp

Removed: 
    


################################################################################
diff  --git a/llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp b/llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
index 20a0efd3afa1c..dcf2df305d24a 100644
--- a/llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/SelectionDAGBuilder.cpp
@@ -1977,8 +1977,13 @@ SDValue SelectionDAGBuilder::getValueImpl(const Value *V) {
   if (const Instruction *Inst = dyn_cast<Instruction>(V)) {
     Register InReg = FuncInfo.InitializeRegForValue(Inst);
 
+    std::optional<CallingConv::ID> CallConv;
+    auto *CI = dyn_cast<CallInst>(Inst);
+    if (CI && !CI->isInlineAsm())
+      CallConv = CI->getCallingConv();
+
     RegsForValue RFV(*DAG.getContext(), TLI, DAG.getDataLayout(), InReg,
-                     Inst->getType(), std::nullopt);
+                     Inst->getType(), CallConv);
     SDValue Chain = DAG.getEntryNode();
     return RFV.getCopyFromRegs(DAG, FuncInfo, getCurSDLoc(), Chain, nullptr, V);
   }

diff  --git a/llvm/test/CodeGen/X86/bf16-fast-isel.ll b/llvm/test/CodeGen/X86/bf16-fast-isel.ll
new file mode 100644
index 0000000000000..c659e0e647d36
--- /dev/null
+++ b/llvm/test/CodeGen/X86/bf16-fast-isel.ll
@@ -0,0 +1,66 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 6
+; RUN: llc --fast-isel < %s -mtriple=x86_64-unknown-unknown | FileCheck %s
+
+define i8 @test_direct_call(ptr %f) nounwind {
+; CHECK-LABEL: test_direct_call:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    pushq %rax
+; CHECK-NEXT:    callq foo at PLT
+; CHECK-NEXT:    callq bar at PLT
+; CHECK-NEXT:    popq %rcx
+; CHECK-NEXT:    retq
+entry:
+  %call = call bfloat @foo(ptr %f)
+  %call2 = call zeroext i8 @bar(bfloat %call)
+  ret i8 %call2
+}
+
+define i8 @test_fast_direct_call(ptr %f) nounwind {
+; CHECK-LABEL: test_fast_direct_call:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    pushq %rax
+; CHECK-NEXT:    callq foo_fast at PLT
+; CHECK-NEXT:    callq bar at PLT
+; CHECK-NEXT:    popq %rcx
+; CHECK-NEXT:    retq
+entry:
+  %call = call fastcc bfloat @foo_fast(ptr %f)
+  %call2 = call zeroext i8 @bar(bfloat %call)
+  ret i8 %call2
+}
+
+define i8 @test_indirect_all(ptr %fptr, ptr %f) nounwind {
+; CHECK-LABEL: test_indirect_all:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    pushq %rbx
+; CHECK-NEXT:    movq %rdi, %rbx
+; CHECK-NEXT:    movq %rsi, %rdi
+; CHECK-NEXT:    callq foo at PLT
+; CHECK-NEXT:    callq *%rbx
+; CHECK-NEXT:    popq %rbx
+; CHECK-NEXT:    retq
+entry:
+  %call = call bfloat @foo(ptr %f)
+  %call2 = call zeroext i8 %fptr(bfloat %call)
+  ret i8 %call2
+}
+
+define i8 @test_fast_indirect_all(ptr %fptr, ptr %f) nounwind {
+; CHECK-LABEL: test_fast_indirect_all:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    pushq %rbx
+; CHECK-NEXT:    movq %rdi, %rbx
+; CHECK-NEXT:    movq %rsi, %rdi
+; CHECK-NEXT:    callq foo at PLT
+; CHECK-NEXT:    callq *%rbx
+; CHECK-NEXT:    popq %rbx
+; CHECK-NEXT:    retq
+entry:
+  %call = call fastcc bfloat @foo(ptr %f)
+  %call2 = call zeroext i8 %fptr(bfloat %call)
+  ret i8 %call2
+}
+
+declare bfloat @foo(ptr %f)
+declare zeroext i8 @bar(bfloat)
+declare fastcc bfloat @foo_fast(ptr %f)