[Statepoint] Constant fold FP deopt args.

[dantrushin]

Summary

We do not have any special handling for constant FP deopt arguments.
They are just spilled to stack or generated in register by MOVS
instruction. This is inefficient and, when we have too many such
constant arguments, may result in register allocation failure.
Instead, we can bitcast such constant Fp operands to appropriately
sized integer and record as constant into statepoint and later, into
StackMap.

[skatkov]

llvm/lib/CodeGen/SelectionDAG/StatepointLowering.cpp

390–391

I guess this comment is for both constant sections.
does it make sense to move up?

llvm/lib/CodeGen/SelectionDAG/StatepointLowering.cpp

 /// statepoint spilling.  If we can find a spill slot for the incoming value,
 /// mark that slot as allocated, and reuse the same slot for this safepoint.
 /// This helps to avoid series of loads and stores that only serve to reshuffle
 /// values on the stack between calls.
 static void reservePreviousStackSlotForValue(const Value *IncomingValue,
                                              SelectionDAGBuilder &Builder) {
   SDValue Incoming = Builder.getValue(IncomingValue);
 
-  if (isa<ConstantSDNode>(Incoming) || isa<FrameIndexSDNode>(Incoming)) {
+  if (isa<ConstantSDNode>(Incoming) || isa<ConstantFPSDNode>(Incoming) ||
+      isa<FrameIndexSDNode>(Incoming)) {
     // We won't need to spill this, so no need to check for previously
     // allocated stack slots
     return;
   }
 
   SDValue OldLocation = Builder.StatepointLowering.getLocation(Incoming);
   if (OldLocation.getNode())
     // Duplicates in input

 lowerIncomingStatepointValue(SDValue Incoming, bool RequireSpillSlot,
                              SmallVectorImpl<SDValue> &Ops,
                              SmallVectorImpl<MachineMemOperand *> &MemRefs,
                              SelectionDAGBuilder &Builder) {
   // Note: We know all of these spills are independent, but don't bother to
   // exploit that chain wise.  DAGCombine will happily do so as needed, so
   // doing it here would be a small compile time win at most.
   SDValue Chain = Builder.getRoot();
 
-  if (ConstantSDNode *C = dyn_cast<ConstantSDNode>(Incoming)) {
-    // If the original value was a constant, make sure it gets recorded as
-    // such in the stackmap.  This is required so that the consumer can
-    // parse any internal format to the deopt state.  It also handles null
-    // pointers and other constant pointers in GC states.  Note the constant
-    // vectors do not appear to actually hit this path and that anything larger
-    // than an i64 value (not type!) will fail asserts here.
+  if (ConstantFPSDNode *C = dyn_cast<ConstantFPSDNode>(Incoming)) {
+    pushStackMapConstant(Ops, Builder,
+                         C->getValueAPF().bitcastToAPInt().getZExtValue());
+  } else if (ConstantSDNode *C = dyn_cast<ConstantSDNode>(Incoming)) {
     pushStackMapConstant(Ops, Builder, C->getSExtValue());
   } else if (FrameIndexSDNode *FI = dyn_cast<FrameIndexSDNode>(Incoming)) {
     // This handles allocas as arguments to the statepoint (this is only
     // really meaningful for a deopt value.  For GC, we'd be trying to
     // relocate the address of the alloca itself?)
     assert(Incoming.getValueType() == Builder.getFrameIndexTy() &&
            "Incoming value is a frame index!");
     Ops.push_back(Builder.DAG.getTargetFrameIndex(FI->getIndex(),

llvm/test/CodeGen/X86/statepoint-regs.ll

 ; CHECK-NEXT:    retq
 entry:
   %a = alloca i32
   store i32 %v, i32* %a
   %statepoint_token1 = call token (i64, i32, void ()*, i32, i32, ...) @llvm.experimental.gc.statepoint.p0f_isVoidf(i64 2882400000, i32 0, void ()* @bar, i32 0, i32 0, i64 0, i64 3, i32* %a, i32* %a, i32* %a)
   ret void
 }
 
+define i32 addrspace(1)*  @test_fpconst_deopt(i32 addrspace(1)* %in) gc "statepoint-example" {
+; CHECK-LABEL: test_fpconst_deopt:
+; CHECK:       ## %bb.0:
+; CHECK-NEXT:    pushq %rax
+; CHECK-NEXT:    .cfi_def_cfa_offset 16
+; CHECK-NEXT:    movq %rdi, (%rsp)
+; CHECK-NEXT:    nopl 8(%rax,%rax)
+; CHECK-NEXT:  Ltmp18:
+; CHECK-NEXT:    movq (%rsp), %rax
+; CHECK-NEXT:    popq %rcx
+; CHECK-NEXT:    retq
+    %statepoint_token = call token (i64, i32, void ()*, i32, i32, ...) @llvm.experimental.gc.statepoint.p0f_isVoidf(i64 2, i32 5, void ()* nonnull @bar, i32 0, i32 0, i32 0, i32 20,
+    float 0x40421A1CA0000000, float 0x40459A1CA0000000, float 0x40401A1CA0000000, float 0x40479A1CA0000000, float 0x403C343940000000,
+    float 0x403E343940000000, float 0x40469A1CA0000000, float 0x40489A1CA0000000, float 0x404A9A1CA0000000, float 0x40499A1CA0000000,
+    float 0xC05FCD2F20000000, float 0xC05C0D2F20000000, float 0xC060269780000000, float 0xC05B8D2F20000000, float 0xC060669780000000,
+    float 0xC05B0D2F20000000, float 0xC060A69780000000, float 0xC05A8D2F20000000, float 0xC060E69780000000, float 0x40439A1CA0000000, i32 addrspace(1)* %in)
+    %out = call coldcc i32 addrspace(1)* @llvm.experimental.gc.relocate.p1i32(token %statepoint_token, i32 27, i32 27)
+    ret i32 addrspace(1)* %out
+}
+; CHECK-LABEL: __LLVM_StackMaps:
+; CHECK: .long   Ltmp18-_test_fpconst_deopt
+; CHECK-NEXT: .short  0
+; CHECK-NEXT: .short  25
+; CHECK-NEXT: .byte 4
+; CHECK-NEXT: .byte 0
+; CHECK-NEXT: .short  8
+; CHECK-NEXT: .short  0
+; CHECK-NEXT: .short  0
+; CHECK-NEXT: .long 0
+; CHECK-NEXT: .byte 4
+; CHECK-NEXT: .byte 0
+; CHECK-NEXT: .short  8
+; CHECK-NEXT: .short  0
+; CHECK-NEXT: .short  0
+; CHECK-NEXT: .long 0
+; CHECK-NEXT: .byte 4
+; CHECK-NEXT: .byte 0
+; CHECK-NEXT: .short  8
+; CHECK-NEXT: .short  0
+; CHECK-NEXT: .short  0
+; CHECK-NEXT: .long 20
+; CHECK: .byte  4
+; CHECK: .byte  0
+; CHECK: .short 8
+; CHECK: .short 0
+; CHECK: .short 0
+; CHECK: .long  1108398309
+; CHECK: .byte  4
+; CHECK: .byte  0
+; CHECK: .short 8
+; CHECK: .short 0
+; CHECK: .short 0
+; CHECK: .long  1110233317
+; CHECK: .byte  4
+; CHECK: .byte  0
+; CHECK: .short 8
+; CHECK: .short 0
+; CHECK: .short 0
+; CHECK: .long  1107349733
+; CHECK: .byte  4
+; CHECK: .byte  0
+; CHECK: .short 8
+; CHECK: .short 0
+; CHECK: .short 0
+; CHECK: .long  1111281893
+; CHECK: .byte  4
+; CHECK: .byte  0
+; CHECK: .short 8
+; CHECK: .short 0
+; CHECK: .short 0
+; CHECK: .long  1105306058
+; CHECK: .byte  4
+; CHECK: .byte  0
+; CHECK: .short 8
+; CHECK: .short 0
+; CHECK: .short 0
+; CHECK: .long  1106354634
+; CHECK: .byte  4
+; CHECK: .byte  0
+; CHECK: .short 8
+; CHECK: .short 0
+; CHECK: .short 0
+; CHECK: .long  1110757605
+; CHECK: .byte  4
+; CHECK: .byte  0
+; CHECK: .short 8
+; CHECK: .short 0
+; CHECK: .short 0
+; CHECK: .long  1111806181
+; CHECK: .byte  4
+; CHECK: .byte  0
+; CHECK: .short 8
+; CHECK: .short 0
+; CHECK: .short 0
+; CHECK: .long  1112854757
+; CHECK: .byte  4
+; CHECK: .byte  0
+; CHECK: .short 8
+; CHECK: .short 0
+; CHECK: .short 0
+; CHECK: .long  1112330469
+; CHECK: .byte  5
+; CHECK: .byte  0
+; CHECK: .short 8
+; CHECK: .short 0
+; CHECK: .short 0
+; CHECK: .long  0
+; CHECK: .byte  5
+; CHECK: .byte  0
+; CHECK: .short 8
+; CHECK: .short 0
+; CHECK: .short 0
+; CHECK: .long  1
+; CHECK: .byte  5
+; CHECK: .byte  0
+; CHECK: .short 8
+; CHECK: .short 0
+; CHECK: .short 0
+; CHECK: .long  2
+; CHECK: .byte  5
+; CHECK: .byte  0
+; CHECK: .short 8
+; CHECK: .short 0
+; CHECK: .short 0
+; CHECK: .long  3
+; CHECK: .byte  5
+; CHECK: .byte  0
+; CHECK: .short 8
+; CHECK: .short 0
+; CHECK: .short 0
+; CHECK: .long  4
+; CHECK: .byte  5
+; CHECK: .byte  0
+; CHECK: .short 8
+; CHECK: .short 0
+; CHECK: .short 0
+; CHECK: .long  5
+; CHECK: .byte  5
+; CHECK: .byte  0
+; CHECK: .short 8
+; CHECK: .short 0
+; CHECK: .short 0
+; CHECK: .long  6
+; CHECK: .byte  5
+; CHECK: .byte  0
+; CHECK: .short 8
+; CHECK: .short 0
+; CHECK: .short 0
+; CHECK: .long  7
+; CHECK: .byte  5
+; CHECK: .byte  0
+; CHECK: .short 8
+; CHECK: .short 0
+; CHECK: .short 0
+; CHECK: .long  8
+; CHECK: .byte  4
+; CHECK: .byte  0
+; CHECK: .short 8
+; CHECK: .short 0
+; CHECK: .short 0
+; CHECK: .long  1109184741
+
 declare token @llvm.experimental.gc.statepoint.p0f_isVoidf(i64, i32, void ()*, i32, i32, ...)
 declare i32 addrspace(1)* @llvm.experimental.gc.relocate.p1i32(token, i32, i32)
 
 attributes #0 = { "deopt-lowering"="live-in" }
 attributes #1 = { "deopt-lowering"="live-through" }