[PATCH] D125988: [x86][SelectionDAG] Unroll vectorized FREM instructions which will be lowered to libcalls

[Nabeel Omer via Phabricator via llvm-commits]

n-omer updated this revision to Diff 431371.
n-omer added a comment.

Remove `FIXME` from test.


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D125988/new/

https://reviews.llvm.org/D125988

Files:
  llvm/lib/CodeGen/SelectionDAG/LegalizeVectorTypes.cpp
  llvm/test/CodeGen/X86/frem-libcall.ll


Index: llvm/test/CodeGen/X86/frem-libcall.ll
===================================================================
--- llvm/test/CodeGen/X86/frem-libcall.ll
+++ llvm/test/CodeGen/X86/frem-libcall.ll
@@ -1,49 +1,33 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
 ; RUN: llc -mtriple=x86_64-linux-gnu < %s  | FileCheck %s
 
-; FIXME: Ensure vectorized FREMs are not widened/unrolled such that they get lowered
+; Ensure vectorized FREMs are not widened/unrolled such that they get lowered
 ; into libcalls on undef elements.
 
 define float @frem(<2 x float> %a0, <2 x float> %a1, <2 x float> %a2, <2 x float> *%p3) nounwind {
 ; CHECK-LABEL: frem:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    pushq %rbx
-; CHECK-NEXT:    subq $80, %rsp
+; CHECK-NEXT:    subq $64, %rsp
 ; CHECK-NEXT:    movq %rdi, %rbx
 ; CHECK-NEXT:    movaps %xmm2, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
 ; CHECK-NEXT:    movaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
-; CHECK-NEXT:    movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
-; CHECK-NEXT:    shufps {{.*#+}} xmm0 = xmm0[3,3,3,3]
-; CHECK-NEXT:    shufps {{.*#+}} xmm1 = xmm1[3,3,3,3]
-; CHECK-NEXT:    callq fmodf at PLT
-; CHECK-NEXT:    movaps %xmm0, (%rsp) # 16-byte Spill
-; CHECK-NEXT:    movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
-; CHECK-NEXT:    movhlps {{.*#+}} xmm0 = xmm0[1,1]
-; CHECK-NEXT:    movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Reload
-; CHECK-NEXT:    movhlps {{.*#+}} xmm1 = xmm1[1,1]
-; CHECK-NEXT:    callq fmodf at PLT
-; CHECK-NEXT:    unpcklps (%rsp), %xmm0 # 16-byte Folded Reload
-; CHECK-NEXT:    # xmm0 = xmm0[0],mem[0],xmm0[1],mem[1]
 ; CHECK-NEXT:    movaps %xmm0, (%rsp) # 16-byte Spill
-; CHECK-NEXT:    movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
-; CHECK-NEXT:    movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Reload
 ; CHECK-NEXT:    callq fmodf at PLT
 ; CHECK-NEXT:    movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
-; CHECK-NEXT:    movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
+; CHECK-NEXT:    movaps (%rsp), %xmm0 # 16-byte Reload
 ; CHECK-NEXT:    shufps {{.*#+}} xmm0 = xmm0[1,1,1,1]
 ; CHECK-NEXT:    movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Reload
 ; CHECK-NEXT:    shufps {{.*#+}} xmm1 = xmm1[1,1,1,1]
 ; CHECK-NEXT:    callq fmodf at PLT
 ; CHECK-NEXT:    movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Reload
 ; CHECK-NEXT:    unpcklps {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1]
-; CHECK-NEXT:    unpcklpd (%rsp), %xmm1 # 16-byte Folded Reload
-; CHECK-NEXT:    # xmm1 = xmm1[0],mem[0]
 ; CHECK-NEXT:    divps {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Folded Reload
 ; CHECK-NEXT:    movaps %xmm1, %xmm0
 ; CHECK-NEXT:    shufps {{.*#+}} xmm0 = xmm0[1,1],xmm1[1,1]
 ; CHECK-NEXT:    addss %xmm1, %xmm0
 ; CHECK-NEXT:    movlps %xmm1, (%rbx)
-; CHECK-NEXT:    addq $80, %rsp
+; CHECK-NEXT:    addq $64, %rsp
 ; CHECK-NEXT:    popq %rbx
 ; CHECK-NEXT:    retq
   %frem = frem <2 x float> %a0, %a1
Index: llvm/lib/CodeGen/SelectionDAG/LegalizeVectorTypes.cpp
===================================================================
--- llvm/lib/CodeGen/SelectionDAG/LegalizeVectorTypes.cpp
+++ llvm/lib/CodeGen/SelectionDAG/LegalizeVectorTypes.cpp
@@ -3678,12 +3678,29 @@
     Res = WidenVecRes_Binary(N);
     break;
 
+  case ISD::FREM: {
+    // We're going to widen this vector op to a legal type by padding with undef
+    // elements. If the wide vector op is eventually going to be expanded to
+    // scalar libcalls, then unroll into scalar ops now to avoid unnecessary
+    // libcalls on the undef elements.
+    EVT VT = N->getValueType(0);
+    EVT WideVecVT = TLI.getTypeToTransformTo(*DAG.getContext(), VT);
+    if (!TLI.isOperationLegalOrCustom(N->getOpcode(), WideVecVT) &&
+        TLI.isOperationExpand(N->getOpcode(), VT.getScalarType())) {
+      Res = DAG.UnrollVectorOp(N, WideVecVT.getVectorNumElements());
+      break;
+    }
+    // If the target has custom/legal support for the scalar FP intrinsic ops
+    // (they are probably not destined to become libcalls), then widen those like
+    // any other binary ops.
+  }
+  LLVM_FALLTHROUGH;
+
   case ISD::FADD:
   case ISD::FMUL:
   case ISD::FPOW:
   case ISD::FSUB:
   case ISD::FDIV:
-  case ISD::FREM:
   case ISD::SDIV:
   case ISD::UDIV:
   case ISD::SREM:


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D125988.431371.patch
Type: text/x-patch
Size: 4324 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20220523/e5f90561/attachment.bin>