[RISCV] Constant materialisation for RV64I

This commit introduces support for materialising 64-bit constants for RV64I,
making use of the RISCVMatInt::generateInstSeq helper in order to share logic
for immediate materialisation with the MC layer (where it's used for the li
pseudoinstruction).

test/CodeGen/RISCV/imm.ll is updated to test RV64, and gains new 64-bit
constant tests. It would be preferable if anyext constant returns were sign
rather than zero extended (see PR39092). This patch simply adds an explicit
signext to the returns in imm.ll.

Further optimisations for constant materialisation are possible, most notably
for mask-like values which can be generated my loading -1 and shifting right.
A future patch will standardise on the C++ codepath for immediate selection on
RV32 as well as RV64, and then add further such optimisations to
RISCVMatInt::generateInstSeq in order to benefit both RV32 and RV64 for
codegen and li expansion.

Differential Revision: https://reviews.llvm.org/D52962

llvm-svn: 347042

2 files changed, 232 insertions, 8 deletions

diff --git a/llvm/lib/Target/RISCV/RISCVISelDAGToDAG.cpp b/llvm/lib/Target/RISCV/RISCVISelDAGToDAG.cpp
index e355b20..b153946 100644
--- a/llvm/lib/Target/RISCV/RISCVISelDAGToDAG.cpp
+++ b/llvm/lib/Target/RISCV/RISCVISelDAGToDAG.cpp
@@ -11,9 +11,10 @@
 //
 //===----------------------------------------------------------------------===//
 
-#include "RISCV.h"
 #include "MCTargetDesc/RISCVMCTargetDesc.h"
+#include "RISCV.h"
 #include "RISCVTargetMachine.h"
+#include "Utils/RISCVMatInt.h"
 #include "llvm/CodeGen/MachineFrameInfo.h"
 #include "llvm/CodeGen/SelectionDAGISel.h"
 #include "llvm/Support/Debug.h"
@@ -63,6 +64,27 @@ void RISCVDAGToDAGISel::PostprocessISelDAG() {
   doPeepholeLoadStoreADDI();
 }
 
+static SDNode *selectImm(SelectionDAG *CurDAG, const SDLoc &DL, int64_t Imm,
+                         MVT XLenVT) {
+  RISCVMatInt::InstSeq Seq;
+  RISCVMatInt::generateInstSeq(Imm, XLenVT == MVT::i64, Seq);
+
+  SDNode *Result;
+  SDValue SrcReg = CurDAG->getRegister(RISCV::X0, XLenVT);
+  for (RISCVMatInt::Inst &Inst : Seq) {
+    SDValue SDImm = CurDAG->getTargetConstant(Inst.Imm, DL, XLenVT);
+    if (Inst.Opc == RISCV::LUI)
+      Result = CurDAG->getMachineNode(RISCV::LUI, DL, XLenVT, SDImm);
+    else
+      Result = CurDAG->getMachineNode(Inst.Opc, DL, XLenVT, SrcReg, SDImm);
+
+    // Only the first instruction has X0 as its source.
+    SrcReg = SDValue(Result, 0);
+  }
+
+  return Result;
+}
+
 void RISCVDAGToDAGISel::Select(SDNode *Node) {
   // If we have a custom node, we have already selected.
   if (Node->isMachineOpcode()) {
@@ -87,6 +109,11 @@ void RISCVDAGToDAGISel::Select(SDNode *Node) {
       ReplaceNode(Node, New.getNode());
       return;
     }
+    int64_t Imm = ConstNode->getSExtValue();
+    if (XLenVT == MVT::i64) {
+      ReplaceNode(Node, selectImm(CurDAG, SDLoc(Node), Imm, XLenVT));
+      return;
+    }
     break;
   }
   case ISD::FrameIndex: {
diff --git a/llvm/test/CodeGen/RISCV/imm.ll b/llvm/test/CodeGen/RISCV/imm.ll
index b9e2f8a..872b6d5 100644
--- a/llvm/test/CodeGen/RISCV/imm.ll
+++ b/llvm/test/CodeGen/RISCV/imm.ll
@@ -1,63 +1,260 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
 ; RUN: llc -mtriple=riscv32 -verify-machineinstrs < %s \
 ; RUN:   | FileCheck %s -check-prefix=RV32I
+; RUN: llc -mtriple=riscv64 -verify-machineinstrs < %s \
+; RUN:   | FileCheck %s -check-prefix=RV64I
 
 ; Materializing constants
 
-define i32 @zero() nounwind {
+; TODO: It would be preferable if anyext constant returns were sign rather
+; than zero extended. See PR39092. For now, mark returns as explicitly signext
+; (this matches what Clang would generate for equivalent C/C++ anyway).
+
+define signext i32 @zero() nounwind {
 ; RV32I-LABEL: zero:
 ; RV32I:       # %bb.0:
 ; RV32I-NEXT:    mv a0, zero
 ; RV32I-NEXT:    ret
+;
+; RV64I-LABEL: zero:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    mv a0, zero
+; RV64I-NEXT:    ret
   ret i32 0
 }
 
-define i32 @pos_small() nounwind {
+define signext i32 @pos_small() nounwind {
 ; RV32I-LABEL: pos_small:
 ; RV32I:       # %bb.0:
 ; RV32I-NEXT:    addi a0, zero, 2047
 ; RV32I-NEXT:    ret
+;
+; RV64I-LABEL: pos_small:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    addi a0, zero, 2047
+; RV64I-NEXT:    ret
   ret i32 2047
 }
 
-define i32 @neg_small() nounwind {
+define signext i32 @neg_small() nounwind {
 ; RV32I-LABEL: neg_small:
 ; RV32I:       # %bb.0:
 ; RV32I-NEXT:    addi a0, zero, -2048
 ; RV32I-NEXT:    ret
+;
+; RV64I-LABEL: neg_small:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    addi a0, zero, -2048
+; RV64I-NEXT:    ret
   ret i32 -2048
 }
 
-define i32 @pos_i32() nounwind {
+define signext i32 @pos_i32() nounwind {
 ; RV32I-LABEL: pos_i32:
 ; RV32I:       # %bb.0:
 ; RV32I-NEXT:    lui a0, 423811
 ; RV32I-NEXT:    addi a0, a0, -1297
 ; RV32I-NEXT:    ret
+;
+; RV64I-LABEL: pos_i32:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    lui a0, 423811
+; RV64I-NEXT:    addiw a0, a0, -1297
+; RV64I-NEXT:    ret
   ret i32 1735928559
 }
 
-define i32 @neg_i32() nounwind {
+define signext i32 @neg_i32() nounwind {
 ; RV32I-LABEL: neg_i32:
 ; RV32I:       # %bb.0:
 ; RV32I-NEXT:    lui a0, 912092
 ; RV32I-NEXT:    addi a0, a0, -273
 ; RV32I-NEXT:    ret
+;
+; RV64I-LABEL: neg_i32:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    lui a0, 912092
+; RV64I-NEXT:    addiw a0, a0, -273
+; RV64I-NEXT:    ret
   ret i32 -559038737
 }
 
-define i32 @pos_i32_hi20_only() nounwind {
+define signext i32 @pos_i32_hi20_only() nounwind {
 ; RV32I-LABEL: pos_i32_hi20_only:
 ; RV32I:       # %bb.0:
 ; RV32I-NEXT:    lui a0, 16
 ; RV32I-NEXT:    ret
+;
+; RV64I-LABEL: pos_i32_hi20_only:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    lui a0, 16
+; RV64I-NEXT:    ret
   ret i32 65536
 }
 
-define i32 @neg_i32_hi20_only() nounwind {
+define signext i32 @neg_i32_hi20_only() nounwind {
 ; RV32I-LABEL: neg_i32_hi20_only:
 ; RV32I:       # %bb.0:
 ; RV32I-NEXT:    lui a0, 1048560
 ; RV32I-NEXT:    ret
+;
+; RV64I-LABEL: neg_i32_hi20_only:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    lui a0, 1048560
+; RV64I-NEXT:    ret
   ret i32 -65536
 }
+
+define i64 @imm64_1() nounwind {
+; RV32I-LABEL: imm64_1:
+; RV32I:       # %bb.0:
+; RV32I-NEXT:    lui a0, 524288
+; RV32I-NEXT:    mv a1, zero
+; RV32I-NEXT:    ret
+;
+; RV64I-LABEL: imm64_1:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    addi a0, zero, 1
+; RV64I-NEXT:    slli a0, a0, 31
+; RV64I-NEXT:    ret
+  ret i64 2147483648
+}
+
+; TODO: This and similar constants with all 0s in the upper bits and all 1s in
+; the lower bits could be lowered to addi a0, zero, -1 followed by a logical
+; right shift.
+define i64 @imm64_2() nounwind {
+; RV32I-LABEL: imm64_2:
+; RV32I:       # %bb.0:
+; RV32I-NEXT:    addi a0, zero, -1
+; RV32I-NEXT:    mv a1, zero
+; RV32I-NEXT:    ret
+;
+; RV64I-LABEL: imm64_2:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    addi a0, zero, 1
+; RV64I-NEXT:    slli a0, a0, 32
+; RV64I-NEXT:    addi a0, a0, -1
+; RV64I-NEXT:    ret
+  ret i64 4294967295
+}
+
+define i64 @imm64_3() nounwind {
+; RV32I-LABEL: imm64_3:
+; RV32I:       # %bb.0:
+; RV32I-NEXT:    addi a1, zero, 1
+; RV32I-NEXT:    mv a0, zero
+; RV32I-NEXT:    ret
+;
+; RV64I-LABEL: imm64_3:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    addi a0, zero, 1
+; RV64I-NEXT:    slli a0, a0, 32
+; RV64I-NEXT:    ret
+  ret i64 4294967296
+}
+
+define i64 @imm64_4() nounwind {
+; RV32I-LABEL: imm64_4:
+; RV32I:       # %bb.0:
+; RV32I-NEXT:    lui a1, 524288
+; RV32I-NEXT:    mv a0, zero
+; RV32I-NEXT:    ret
+;
+; RV64I-LABEL: imm64_4:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    addi a0, zero, -1
+; RV64I-NEXT:    slli a0, a0, 63
+; RV64I-NEXT:    ret
+  ret i64 9223372036854775808
+}
+
+define i64 @imm64_5() nounwind {
+; RV32I-LABEL: imm64_5:
+; RV32I:       # %bb.0:
+; RV32I-NEXT:    lui a1, 524288
+; RV32I-NEXT:    mv a0, zero
+; RV32I-NEXT:    ret
+;
+; RV64I-LABEL: imm64_5:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    addi a0, zero, -1
+; RV64I-NEXT:    slli a0, a0, 63
+; RV64I-NEXT:    ret
+  ret i64 -9223372036854775808
+}
+
+define i64 @imm64_6() nounwind {
+; RV32I-LABEL: imm64_6:
+; RV32I:       # %bb.0:
+; RV32I-NEXT:    lui a0, 74565
+; RV32I-NEXT:    addi a1, a0, 1656
+; RV32I-NEXT:    mv a0, zero
+; RV32I-NEXT:    ret
+;
+; RV64I-LABEL: imm64_6:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    lui a0, 9321
+; RV64I-NEXT:    addiw a0, a0, -1329
+; RV64I-NEXT:    slli a0, a0, 35
+; RV64I-NEXT:    ret
+  ret i64 1311768464867721216
+}
+
+define i64 @imm64_7() nounwind {
+; RV32I-LABEL: imm64_7:
+; RV32I:       # %bb.0:
+; RV32I-NEXT:    lui a0, 45056
+; RV32I-NEXT:    addi a0, a0, 15
+; RV32I-NEXT:    lui a1, 458752
+; RV32I-NEXT:    ret
+;
+; RV64I-LABEL: imm64_7:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    addi a0, zero, 7
+; RV64I-NEXT:    slli a0, a0, 36
+; RV64I-NEXT:    addi a0, a0, 11
+; RV64I-NEXT:    slli a0, a0, 24
+; RV64I-NEXT:    addi a0, a0, 15
+; RV64I-NEXT:    ret
+  ret i64 8070450532432478223
+}
+
+; TODO: it can be preferable to put constants that are expensive to materialise
+; into the constant pool, especially for -Os.
+define i64 @imm64_8() nounwind {
+; RV32I-LABEL: imm64_8:
+; RV32I:       # %bb.0:
+; RV32I-NEXT:    lui a0, 633806
+; RV32I-NEXT:    addi a0, a0, -272
+; RV32I-NEXT:    lui a1, 74565
+; RV32I-NEXT:    addi a1, a1, 1656
+; RV32I-NEXT:    ret
+;
+; RV64I-LABEL: imm64_8:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    lui a0, 583
+; RV64I-NEXT:    addiw a0, a0, -1875
+; RV64I-NEXT:    slli a0, a0, 14
+; RV64I-NEXT:    addi a0, a0, -947
+; RV64I-NEXT:    slli a0, a0, 12
+; RV64I-NEXT:    addi a0, a0, 1511
+; RV64I-NEXT:    slli a0, a0, 13
+; RV64I-NEXT:    addi a0, a0, -272
+; RV64I-NEXT:    ret
+  ret i64 1311768467463790320
+}
+
+define i64 @imm64_9() nounwind {
+; RV32I-LABEL: imm64_9:
+; RV32I:       # %bb.0:
+; RV32I-NEXT:    addi a0, zero, -1
+; RV32I-NEXT:    mv a1, a0
+; RV32I-NEXT:    ret
+;
+; RV64I-LABEL: imm64_9:
+; RV64I:       # %bb.0:
+; RV64I-NEXT:    addi a0, zero, -1
+; RV64I-NEXT:    ret
+  ret i64 -1
+}