[llvm] [RISCV] Select and/or/xor with certain constants to Zbb ANDN/ORN/XNOR (PR #120221)

Piotr Fusik via llvm-commits llvm-commits at lists.llvm.org
Wed Dec 18 10:21:08 PST 2024


https://github.com/pfusik updated https://github.com/llvm/llvm-project/pull/120221

>From 7fe62f276bee2577ac1b40035a310029e18cf045 Mon Sep 17 00:00:00 2001
From: Piotr Fusik <p.fusik at samsung.com>
Date: Wed, 18 Dec 2024 14:02:22 +0100
Subject: [PATCH 1/4] [RISCV][test] Add zbb-logic-neg-imm.ll

---
 llvm/test/CodeGen/RISCV/zbb-logic-neg-imm.ll | 309 +++++++++++++++++++
 1 file changed, 309 insertions(+)
 create mode 100644 llvm/test/CodeGen/RISCV/zbb-logic-neg-imm.ll

diff --git a/llvm/test/CodeGen/RISCV/zbb-logic-neg-imm.ll b/llvm/test/CodeGen/RISCV/zbb-logic-neg-imm.ll
new file mode 100644
index 00000000000000..f304dbf5eff17b
--- /dev/null
+++ b/llvm/test/CodeGen/RISCV/zbb-logic-neg-imm.ll
@@ -0,0 +1,309 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -mtriple=riscv32 -mattr=+zbb -verify-machineinstrs < %s \
+; RUN:   | FileCheck %s --check-prefixes=CHECK,RV32
+; RUN: llc -mtriple=riscv64 -mattr=+zbb -verify-machineinstrs < %s \
+; RUN:   | FileCheck %s --check-prefixes=CHECK,RV64
+
+define i32 @and0xabcdefff(i32 %x) {
+; RV32-LABEL: and0xabcdefff:
+; RV32:       # %bb.0:
+; RV32-NEXT:    lui a1, 703711
+; RV32-NEXT:    addi a1, a1, -1
+; RV32-NEXT:    and a0, a0, a1
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: and0xabcdefff:
+; RV64:       # %bb.0:
+; RV64-NEXT:    lui a1, 703711
+; RV64-NEXT:    addiw a1, a1, -1
+; RV64-NEXT:    and a0, a0, a1
+; RV64-NEXT:    ret
+  %and = and i32 %x, -1412567041
+  ret i32 %and
+}
+
+define i32 @orlow13(i32 %x) {
+; RV32-LABEL: orlow13:
+; RV32:       # %bb.0:
+; RV32-NEXT:    lui a1, 2
+; RV32-NEXT:    addi a1, a1, -1
+; RV32-NEXT:    or a0, a0, a1
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: orlow13:
+; RV64:       # %bb.0:
+; RV64-NEXT:    lui a1, 2
+; RV64-NEXT:    addiw a1, a1, -1
+; RV64-NEXT:    or a0, a0, a1
+; RV64-NEXT:    ret
+  %or = or i32 %x, 8191
+  ret i32 %or
+}
+
+define i64 @orlow24(i64 %x) {
+; RV32-LABEL: orlow24:
+; RV32:       # %bb.0:
+; RV32-NEXT:    lui a2, 4096
+; RV32-NEXT:    addi a2, a2, -1
+; RV32-NEXT:    or a0, a0, a2
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: orlow24:
+; RV64:       # %bb.0:
+; RV64-NEXT:    lui a1, 4096
+; RV64-NEXT:    addiw a1, a1, -1
+; RV64-NEXT:    or a0, a0, a1
+; RV64-NEXT:    ret
+  %or = or i64 %x, 16777215
+  ret i64 %or
+}
+
+define i32 @xorlow16(i32 %x) {
+; RV32-LABEL: xorlow16:
+; RV32:       # %bb.0:
+; RV32-NEXT:    lui a1, 16
+; RV32-NEXT:    addi a1, a1, -1
+; RV32-NEXT:    xor a0, a0, a1
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: xorlow16:
+; RV64:       # %bb.0:
+; RV64-NEXT:    lui a1, 16
+; RV64-NEXT:    addiw a1, a1, -1
+; RV64-NEXT:    xor a0, a0, a1
+; RV64-NEXT:    ret
+  %xor = xor i32 %x, 65535
+  ret i32 %xor
+}
+
+define i32 @xorlow31(i32 %x) {
+; RV32-LABEL: xorlow31:
+; RV32:       # %bb.0:
+; RV32-NEXT:    lui a1, 524288
+; RV32-NEXT:    addi a1, a1, -1
+; RV32-NEXT:    xor a0, a0, a1
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: xorlow31:
+; RV64:       # %bb.0:
+; RV64-NEXT:    lui a1, 524288
+; RV64-NEXT:    addiw a1, a1, -1
+; RV64-NEXT:    xor a0, a0, a1
+; RV64-NEXT:    ret
+  %xor = xor i32 %x, 2147483647
+  ret i32 %xor
+}
+
+define i32 @oraddlow16(i32 %x) {
+; RV32-LABEL: oraddlow16:
+; RV32:       # %bb.0:
+; RV32-NEXT:    lui a1, 16
+; RV32-NEXT:    addi a1, a1, -1
+; RV32-NEXT:    or a0, a0, a1
+; RV32-NEXT:    add a0, a0, a1
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: oraddlow16:
+; RV64:       # %bb.0:
+; RV64-NEXT:    lui a1, 16
+; RV64-NEXT:    addi a1, a1, -1
+; RV64-NEXT:    or a0, a0, a1
+; RV64-NEXT:    addw a0, a0, a1
+; RV64-NEXT:    ret
+  %or = or i32 %x, 65535
+  %add = add nsw i32 %or, 65535
+  ret i32 %add
+}
+
+define i32 @addorlow16(i32 %x) {
+; RV32-LABEL: addorlow16:
+; RV32:       # %bb.0:
+; RV32-NEXT:    lui a1, 16
+; RV32-NEXT:    addi a1, a1, -1
+; RV32-NEXT:    add a0, a0, a1
+; RV32-NEXT:    or a0, a0, a1
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: addorlow16:
+; RV64:       # %bb.0:
+; RV64-NEXT:    lui a1, 16
+; RV64-NEXT:    addiw a1, a1, -1
+; RV64-NEXT:    addw a0, a0, a1
+; RV64-NEXT:    or a0, a0, a1
+; RV64-NEXT:    ret
+  %add = add nsw i32 %x, 65535
+  %or = or i32 %add, 65535
+  ret i32 %or
+}
+
+define i32 @andxorlow16(i32 %x) {
+; RV32-LABEL: andxorlow16:
+; RV32:       # %bb.0:
+; RV32-NEXT:    lui a1, 16
+; RV32-NEXT:    addi a1, a1, -1
+; RV32-NEXT:    andn a0, a1, a0
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: andxorlow16:
+; RV64:       # %bb.0:
+; RV64-NEXT:    lui a1, 16
+; RV64-NEXT:    addiw a1, a1, -1
+; RV64-NEXT:    andn a0, a1, a0
+; RV64-NEXT:    ret
+  %and = and i32 %x, 65535
+  %xor = xor i32 %and, 65535
+  ret i32 %xor
+}
+
+define void @orarray100(ptr %a) {
+; RV32-LABEL: orarray100:
+; RV32:       # %bb.0: # %entry
+; RV32-NEXT:    li a1, 0
+; RV32-NEXT:    li a2, 0
+; RV32-NEXT:    lui a3, 16
+; RV32-NEXT:    addi a3, a3, -1
+; RV32-NEXT:  .LBB8_1: # %for.body
+; RV32-NEXT:    # =>This Inner Loop Header: Depth=1
+; RV32-NEXT:    slli a4, a1, 2
+; RV32-NEXT:    addi a1, a1, 1
+; RV32-NEXT:    add a4, a0, a4
+; RV32-NEXT:    lw a5, 0(a4)
+; RV32-NEXT:    seqz a6, a1
+; RV32-NEXT:    add a2, a2, a6
+; RV32-NEXT:    xori a6, a1, 100
+; RV32-NEXT:    or a5, a5, a3
+; RV32-NEXT:    or a6, a6, a2
+; RV32-NEXT:    sw a5, 0(a4)
+; RV32-NEXT:    bnez a6, .LBB8_1
+; RV32-NEXT:  # %bb.2: # %for.cond.cleanup
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: orarray100:
+; RV64:       # %bb.0: # %entry
+; RV64-NEXT:    addi a1, a0, 400
+; RV64-NEXT:    lui a2, 16
+; RV64-NEXT:    addi a2, a2, -1
+; RV64-NEXT:  .LBB8_1: # %for.body
+; RV64-NEXT:    # =>This Inner Loop Header: Depth=1
+; RV64-NEXT:    lw a3, 0(a0)
+; RV64-NEXT:    or a3, a3, a2
+; RV64-NEXT:    sw a3, 0(a0)
+; RV64-NEXT:    addi a0, a0, 4
+; RV64-NEXT:    bne a0, a1, .LBB8_1
+; RV64-NEXT:  # %bb.2: # %for.cond.cleanup
+; RV64-NEXT:    ret
+entry:
+  br label %for.body
+
+for.cond.cleanup:
+  ret void
+
+for.body:
+  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
+  %arrayidx = getelementptr inbounds nuw i32, ptr %a, i64 %indvars.iv
+  %1 = load i32, ptr %arrayidx, align 4
+  %or = or i32 %1, 65535
+  store i32 %or, ptr %arrayidx, align 4
+  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+  %exitcond.not = icmp eq i64 %indvars.iv.next, 100
+  br i1 %exitcond.not, label %for.cond.cleanup, label %for.body
+}
+
+define void @orarray3(ptr %a) {
+; CHECK-LABEL: orarray3:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    lui a1, 16
+; CHECK-NEXT:    lw a2, 0(a0)
+; CHECK-NEXT:    lw a3, 4(a0)
+; CHECK-NEXT:    lw a4, 8(a0)
+; CHECK-NEXT:    addi a1, a1, -1
+; CHECK-NEXT:    or a2, a2, a1
+; CHECK-NEXT:    or a3, a3, a1
+; CHECK-NEXT:    or a1, a4, a1
+; CHECK-NEXT:    sw a2, 0(a0)
+; CHECK-NEXT:    sw a3, 4(a0)
+; CHECK-NEXT:    sw a1, 8(a0)
+; CHECK-NEXT:    ret
+  %1 = load i32, ptr %a, align 4
+  %or = or i32 %1, 65535
+  store i32 %or, ptr %a, align 4
+  %arrayidx.1 = getelementptr inbounds nuw i8, ptr %a, i64 4
+  %2 = load i32, ptr %arrayidx.1, align 4
+  %or.1 = or i32 %2, 65535
+  store i32 %or.1, ptr %arrayidx.1, align 4
+  %arrayidx.2 = getelementptr inbounds nuw i8, ptr %a, i64 8
+  %3 = load i32, ptr %arrayidx.2, align 4
+  %or.2 = or i32 %3, 65535
+  store i32 %or.2, ptr %arrayidx.2, align 4
+  ret void
+}
+
+define i32 @andlow16(i32 %x) {
+; CHECK-LABEL: andlow16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    zext.h a0, a0
+; CHECK-NEXT:    ret
+  %and = and i32 %x, 65535
+  ret i32 %and
+}
+
+define i32 @andlow24(i32 %x) {
+; RV32-LABEL: andlow24:
+; RV32:       # %bb.0:
+; RV32-NEXT:    slli a0, a0, 8
+; RV32-NEXT:    srli a0, a0, 8
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: andlow24:
+; RV64:       # %bb.0:
+; RV64-NEXT:    slli a0, a0, 40
+; RV64-NEXT:    srli a0, a0, 40
+; RV64-NEXT:    ret
+  %and = and i32 %x, 16777215
+  ret i32 %and
+}
+
+define i32 @compl(i32 %x) {
+; CHECK-LABEL: compl:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    not a0, a0
+; CHECK-NEXT:    ret
+  %not = xor i32 %x, -1
+  ret i32 %not
+}
+
+define i32 @orlow12(i32 %x) {
+; RV32-LABEL: orlow12:
+; RV32:       # %bb.0:
+; RV32-NEXT:    lui a1, 1
+; RV32-NEXT:    addi a1, a1, -1
+; RV32-NEXT:    or a0, a0, a1
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: orlow12:
+; RV64:       # %bb.0:
+; RV64-NEXT:    lui a1, 1
+; RV64-NEXT:    addiw a1, a1, -1
+; RV64-NEXT:    or a0, a0, a1
+; RV64-NEXT:    ret
+  %or = or i32 %x, 4095
+  ret i32 %or
+}
+
+define i32 @xorlow12(i32 %x) {
+; RV32-LABEL: xorlow12:
+; RV32:       # %bb.0:
+; RV32-NEXT:    lui a1, 1
+; RV32-NEXT:    addi a1, a1, -1
+; RV32-NEXT:    xor a0, a0, a1
+; RV32-NEXT:    ret
+;
+; RV64-LABEL: xorlow12:
+; RV64:       # %bb.0:
+; RV64-NEXT:    lui a1, 1
+; RV64-NEXT:    addiw a1, a1, -1
+; RV64-NEXT:    xor a0, a0, a1
+; RV64-NEXT:    ret
+  %xor = xor i32 %x, 4095
+  ret i32 %xor
+}

>From 70c470925169e04a24a43bff4e648df574fde92f Mon Sep 17 00:00:00 2001
From: Piotr Fusik <p.fusik at samsung.com>
Date: Tue, 17 Dec 2024 13:07:20 +0100
Subject: [PATCH 2/4] [RISCV] Select and/or/xor with some constants to Zbb
 ANDN/ORN/XNOR

    (and X, (C<<12|0xfff)) -> (ANDN X, ~C<<12)
    (or  X, (C<<12|0xfff)) -> (ORN  X, ~C<<12)
    (xor X, (C<<12|0xfff)) -> (XNOR X, ~C<<12)

Saves an `ADDI HI, -1` instruction.

Co-authored-by: Craig Topper <craig.topper at sifive.com>
---
 llvm/lib/Target/RISCV/RISCVISelDAGToDAG.cpp  |  12 ++
 llvm/lib/Target/RISCV/RISCVISelDAGToDAG.h    |   2 +
 llvm/lib/Target/RISCV/RISCVInstrInfoZb.td    |   6 +
 llvm/test/CodeGen/RISCV/pr84653_pr85190.ll   |   6 +-
 llvm/test/CodeGen/RISCV/zbb-logic-neg-imm.ll | 163 +++++++------------
 5 files changed, 79 insertions(+), 110 deletions(-)

diff --git a/llvm/lib/Target/RISCV/RISCVISelDAGToDAG.cpp b/llvm/lib/Target/RISCV/RISCVISelDAGToDAG.cpp
index ccf34b8a6b2b02..d77e2b1421b136 100644
--- a/llvm/lib/Target/RISCV/RISCVISelDAGToDAG.cpp
+++ b/llvm/lib/Target/RISCV/RISCVISelDAGToDAG.cpp
@@ -3236,6 +3236,18 @@ bool RISCVDAGToDAGISel::selectSHXADD_UWOp(SDValue N, unsigned ShAmt,
   return false;
 }
 
+bool RISCVDAGToDAGISel::selectSImm32fff(SDValue N, SDValue &Val) {
+  if (!isa<ConstantSDNode>(N))
+    return false;
+
+  int64_t Imm = cast<ConstantSDNode>(N)->getSExtValue();
+  if (!(isInt<32>(Imm) && (Imm & 0xfff) == 0xfff && Imm != -1))
+    return false;
+
+  Val = selectImm(CurDAG, SDLoc(N), N->getSimpleValueType(0), ~Imm, *Subtarget);
+  return true;
+}
+
 static bool vectorPseudoHasAllNBitUsers(SDNode *User, unsigned UserOpNo,
                                         unsigned Bits,
                                         const TargetInstrInfo *TII) {
diff --git a/llvm/lib/Target/RISCV/RISCVISelDAGToDAG.h b/llvm/lib/Target/RISCV/RISCVISelDAGToDAG.h
index 2e738d8d25a6dc..cfe07277fd9ddf 100644
--- a/llvm/lib/Target/RISCV/RISCVISelDAGToDAG.h
+++ b/llvm/lib/Target/RISCV/RISCVISelDAGToDAG.h
@@ -119,6 +119,8 @@ class RISCVDAGToDAGISel : public SelectionDAGISel {
     return selectSHXADD_UWOp(N, ShAmt, Val);
   }
 
+  bool selectSImm32fff(SDValue N, SDValue &Val);
+
   bool hasAllNBitUsers(SDNode *Node, unsigned Bits,
                        const unsigned Depth = 0) const;
   bool hasAllBUsers(SDNode *Node) const { return hasAllNBitUsers(Node, 8); }
diff --git a/llvm/lib/Target/RISCV/RISCVInstrInfoZb.td b/llvm/lib/Target/RISCV/RISCVInstrInfoZb.td
index a78091cd02a35f..e2050d100e4f88 100644
--- a/llvm/lib/Target/RISCV/RISCVInstrInfoZb.td
+++ b/llvm/lib/Target/RISCV/RISCVInstrInfoZb.td
@@ -475,10 +475,16 @@ def : InstAlias<"zext.h $rd, $rs", (PACKW GPR:$rd, GPR:$rs, X0)>;
 // Codegen patterns
 //===----------------------------------------------------------------------===//
 
+def simm32fff : ComplexPattern<XLenVT, 1, "selectSImm32fff", [], [], 0>;
+
 let Predicates = [HasStdExtZbbOrZbkb] in {
 def : Pat<(XLenVT (and GPR:$rs1, (not GPR:$rs2))), (ANDN GPR:$rs1, GPR:$rs2)>;
 def : Pat<(XLenVT (or  GPR:$rs1, (not GPR:$rs2))), (ORN  GPR:$rs1, GPR:$rs2)>;
 def : Pat<(XLenVT (xor GPR:$rs1, (not GPR:$rs2))), (XNOR GPR:$rs1, GPR:$rs2)>;
+
+def : Pat<(XLenVT (and GPR:$rs1, simm32fff:$rs2)), (ANDN GPR:$rs1, simm32fff:$rs2)>;
+def : Pat<(XLenVT (or  GPR:$rs1, simm32fff:$rs2)), (ORN  GPR:$rs1, simm32fff:$rs2)>;
+def : Pat<(XLenVT (xor GPR:$rs1, simm32fff:$rs2)), (XNOR GPR:$rs1, simm32fff:$rs2)>;
 } // Predicates = [HasStdExtZbbOrZbkb]
 
 let Predicates = [HasStdExtZbbOrZbkb] in {
diff --git a/llvm/test/CodeGen/RISCV/pr84653_pr85190.ll b/llvm/test/CodeGen/RISCV/pr84653_pr85190.ll
index b1bba5fdc92116..30a93557347727 100644
--- a/llvm/test/CodeGen/RISCV/pr84653_pr85190.ll
+++ b/llvm/test/CodeGen/RISCV/pr84653_pr85190.ll
@@ -21,8 +21,7 @@ define i1 @pr84653(i32 %x) {
 ; CHECK-ZBB:       # %bb.0:
 ; CHECK-ZBB-NEXT:    sext.w a1, a0
 ; CHECK-ZBB-NEXT:    lui a2, 524288
-; CHECK-ZBB-NEXT:    addi a2, a2, -1
-; CHECK-ZBB-NEXT:    xor a0, a0, a2
+; CHECK-ZBB-NEXT:    xnor a0, a0, a2
 ; CHECK-ZBB-NEXT:    sext.w a0, a0
 ; CHECK-ZBB-NEXT:    max a0, a0, zero
 ; CHECK-ZBB-NEXT:    slt a0, a0, a1
@@ -82,8 +81,7 @@ define i1 @select_to_or(i32 %x) {
 ; CHECK-ZBB:       # %bb.0:
 ; CHECK-ZBB-NEXT:    sext.w a1, a0
 ; CHECK-ZBB-NEXT:    lui a2, 524288
-; CHECK-ZBB-NEXT:    addi a2, a2, -1
-; CHECK-ZBB-NEXT:    xor a0, a0, a2
+; CHECK-ZBB-NEXT:    xnor a0, a0, a2
 ; CHECK-ZBB-NEXT:    sext.w a0, a0
 ; CHECK-ZBB-NEXT:    min a0, a0, zero
 ; CHECK-ZBB-NEXT:    slt a0, a0, a1
diff --git a/llvm/test/CodeGen/RISCV/zbb-logic-neg-imm.ll b/llvm/test/CodeGen/RISCV/zbb-logic-neg-imm.ll
index f304dbf5eff17b..86c9676bec1280 100644
--- a/llvm/test/CodeGen/RISCV/zbb-logic-neg-imm.ll
+++ b/llvm/test/CodeGen/RISCV/zbb-logic-neg-imm.ll
@@ -5,37 +5,21 @@
 ; RUN:   | FileCheck %s --check-prefixes=CHECK,RV64
 
 define i32 @and0xabcdefff(i32 %x) {
-; RV32-LABEL: and0xabcdefff:
-; RV32:       # %bb.0:
-; RV32-NEXT:    lui a1, 703711
-; RV32-NEXT:    addi a1, a1, -1
-; RV32-NEXT:    and a0, a0, a1
-; RV32-NEXT:    ret
-;
-; RV64-LABEL: and0xabcdefff:
-; RV64:       # %bb.0:
-; RV64-NEXT:    lui a1, 703711
-; RV64-NEXT:    addiw a1, a1, -1
-; RV64-NEXT:    and a0, a0, a1
-; RV64-NEXT:    ret
+; CHECK-LABEL: and0xabcdefff:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    lui a1, 344865
+; CHECK-NEXT:    andn a0, a0, a1
+; CHECK-NEXT:    ret
   %and = and i32 %x, -1412567041
   ret i32 %and
 }
 
 define i32 @orlow13(i32 %x) {
-; RV32-LABEL: orlow13:
-; RV32:       # %bb.0:
-; RV32-NEXT:    lui a1, 2
-; RV32-NEXT:    addi a1, a1, -1
-; RV32-NEXT:    or a0, a0, a1
-; RV32-NEXT:    ret
-;
-; RV64-LABEL: orlow13:
-; RV64:       # %bb.0:
-; RV64-NEXT:    lui a1, 2
-; RV64-NEXT:    addiw a1, a1, -1
-; RV64-NEXT:    or a0, a0, a1
-; RV64-NEXT:    ret
+; CHECK-LABEL: orlow13:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    lui a1, 1048574
+; CHECK-NEXT:    orn a0, a0, a1
+; CHECK-NEXT:    ret
   %or = or i32 %x, 8191
   ret i32 %or
 }
@@ -43,53 +27,35 @@ define i32 @orlow13(i32 %x) {
 define i64 @orlow24(i64 %x) {
 ; RV32-LABEL: orlow24:
 ; RV32:       # %bb.0:
-; RV32-NEXT:    lui a2, 4096
-; RV32-NEXT:    addi a2, a2, -1
-; RV32-NEXT:    or a0, a0, a2
+; RV32-NEXT:    lui a2, 1044480
+; RV32-NEXT:    orn a0, a0, a2
 ; RV32-NEXT:    ret
 ;
 ; RV64-LABEL: orlow24:
 ; RV64:       # %bb.0:
-; RV64-NEXT:    lui a1, 4096
-; RV64-NEXT:    addiw a1, a1, -1
-; RV64-NEXT:    or a0, a0, a1
+; RV64-NEXT:    lui a1, 1044480
+; RV64-NEXT:    orn a0, a0, a1
 ; RV64-NEXT:    ret
   %or = or i64 %x, 16777215
   ret i64 %or
 }
 
 define i32 @xorlow16(i32 %x) {
-; RV32-LABEL: xorlow16:
-; RV32:       # %bb.0:
-; RV32-NEXT:    lui a1, 16
-; RV32-NEXT:    addi a1, a1, -1
-; RV32-NEXT:    xor a0, a0, a1
-; RV32-NEXT:    ret
-;
-; RV64-LABEL: xorlow16:
-; RV64:       # %bb.0:
-; RV64-NEXT:    lui a1, 16
-; RV64-NEXT:    addiw a1, a1, -1
-; RV64-NEXT:    xor a0, a0, a1
-; RV64-NEXT:    ret
+; CHECK-LABEL: xorlow16:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    lui a1, 1048560
+; CHECK-NEXT:    xnor a0, a0, a1
+; CHECK-NEXT:    ret
   %xor = xor i32 %x, 65535
   ret i32 %xor
 }
 
 define i32 @xorlow31(i32 %x) {
-; RV32-LABEL: xorlow31:
-; RV32:       # %bb.0:
-; RV32-NEXT:    lui a1, 524288
-; RV32-NEXT:    addi a1, a1, -1
-; RV32-NEXT:    xor a0, a0, a1
-; RV32-NEXT:    ret
-;
-; RV64-LABEL: xorlow31:
-; RV64:       # %bb.0:
-; RV64-NEXT:    lui a1, 524288
-; RV64-NEXT:    addiw a1, a1, -1
-; RV64-NEXT:    xor a0, a0, a1
-; RV64-NEXT:    ret
+; CHECK-LABEL: xorlow31:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    lui a1, 524288
+; CHECK-NEXT:    xnor a0, a0, a1
+; CHECK-NEXT:    ret
   %xor = xor i32 %x, 2147483647
   ret i32 %xor
 }
@@ -97,17 +63,19 @@ define i32 @xorlow31(i32 %x) {
 define i32 @oraddlow16(i32 %x) {
 ; RV32-LABEL: oraddlow16:
 ; RV32:       # %bb.0:
+; RV32-NEXT:    lui a1, 1048560
+; RV32-NEXT:    orn a0, a0, a1
 ; RV32-NEXT:    lui a1, 16
 ; RV32-NEXT:    addi a1, a1, -1
-; RV32-NEXT:    or a0, a0, a1
 ; RV32-NEXT:    add a0, a0, a1
 ; RV32-NEXT:    ret
 ;
 ; RV64-LABEL: oraddlow16:
 ; RV64:       # %bb.0:
+; RV64-NEXT:    lui a1, 1048560
+; RV64-NEXT:    orn a0, a0, a1
 ; RV64-NEXT:    lui a1, 16
 ; RV64-NEXT:    addi a1, a1, -1
-; RV64-NEXT:    or a0, a0, a1
 ; RV64-NEXT:    addw a0, a0, a1
 ; RV64-NEXT:    ret
   %or = or i32 %x, 65535
@@ -121,15 +89,17 @@ define i32 @addorlow16(i32 %x) {
 ; RV32-NEXT:    lui a1, 16
 ; RV32-NEXT:    addi a1, a1, -1
 ; RV32-NEXT:    add a0, a0, a1
-; RV32-NEXT:    or a0, a0, a1
+; RV32-NEXT:    lui a1, 1048560
+; RV32-NEXT:    orn a0, a0, a1
 ; RV32-NEXT:    ret
 ;
 ; RV64-LABEL: addorlow16:
 ; RV64:       # %bb.0:
 ; RV64-NEXT:    lui a1, 16
-; RV64-NEXT:    addiw a1, a1, -1
+; RV64-NEXT:    addi a1, a1, -1
 ; RV64-NEXT:    addw a0, a0, a1
-; RV64-NEXT:    or a0, a0, a1
+; RV64-NEXT:    lui a1, 1048560
+; RV64-NEXT:    orn a0, a0, a1
 ; RV64-NEXT:    ret
   %add = add nsw i32 %x, 65535
   %or = or i32 %add, 65535
@@ -160,8 +130,7 @@ define void @orarray100(ptr %a) {
 ; RV32:       # %bb.0: # %entry
 ; RV32-NEXT:    li a1, 0
 ; RV32-NEXT:    li a2, 0
-; RV32-NEXT:    lui a3, 16
-; RV32-NEXT:    addi a3, a3, -1
+; RV32-NEXT:    lui a3, 1048560
 ; RV32-NEXT:  .LBB8_1: # %for.body
 ; RV32-NEXT:    # =>This Inner Loop Header: Depth=1
 ; RV32-NEXT:    slli a4, a1, 2
@@ -171,7 +140,7 @@ define void @orarray100(ptr %a) {
 ; RV32-NEXT:    seqz a6, a1
 ; RV32-NEXT:    add a2, a2, a6
 ; RV32-NEXT:    xori a6, a1, 100
-; RV32-NEXT:    or a5, a5, a3
+; RV32-NEXT:    orn a5, a5, a3
 ; RV32-NEXT:    or a6, a6, a2
 ; RV32-NEXT:    sw a5, 0(a4)
 ; RV32-NEXT:    bnez a6, .LBB8_1
@@ -181,12 +150,11 @@ define void @orarray100(ptr %a) {
 ; RV64-LABEL: orarray100:
 ; RV64:       # %bb.0: # %entry
 ; RV64-NEXT:    addi a1, a0, 400
-; RV64-NEXT:    lui a2, 16
-; RV64-NEXT:    addi a2, a2, -1
+; RV64-NEXT:    lui a2, 1048560
 ; RV64-NEXT:  .LBB8_1: # %for.body
 ; RV64-NEXT:    # =>This Inner Loop Header: Depth=1
 ; RV64-NEXT:    lw a3, 0(a0)
-; RV64-NEXT:    or a3, a3, a2
+; RV64-NEXT:    orn a3, a3, a2
 ; RV64-NEXT:    sw a3, 0(a0)
 ; RV64-NEXT:    addi a0, a0, 4
 ; RV64-NEXT:    bne a0, a1, .LBB8_1
@@ -212,17 +180,16 @@ for.body:
 define void @orarray3(ptr %a) {
 ; CHECK-LABEL: orarray3:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    lui a1, 16
-; CHECK-NEXT:    lw a2, 0(a0)
-; CHECK-NEXT:    lw a3, 4(a0)
-; CHECK-NEXT:    lw a4, 8(a0)
-; CHECK-NEXT:    addi a1, a1, -1
-; CHECK-NEXT:    or a2, a2, a1
-; CHECK-NEXT:    or a3, a3, a1
-; CHECK-NEXT:    or a1, a4, a1
-; CHECK-NEXT:    sw a2, 0(a0)
-; CHECK-NEXT:    sw a3, 4(a0)
-; CHECK-NEXT:    sw a1, 8(a0)
+; CHECK-NEXT:    lw a1, 0(a0)
+; CHECK-NEXT:    lw a2, 4(a0)
+; CHECK-NEXT:    lw a3, 8(a0)
+; CHECK-NEXT:    lui a4, 1048560
+; CHECK-NEXT:    orn a1, a1, a4
+; CHECK-NEXT:    orn a2, a2, a4
+; CHECK-NEXT:    orn a3, a3, a4
+; CHECK-NEXT:    sw a1, 0(a0)
+; CHECK-NEXT:    sw a2, 4(a0)
+; CHECK-NEXT:    sw a3, 8(a0)
 ; CHECK-NEXT:    ret
   %1 = load i32, ptr %a, align 4
   %or = or i32 %1, 65535
@@ -273,37 +240,21 @@ define i32 @compl(i32 %x) {
 }
 
 define i32 @orlow12(i32 %x) {
-; RV32-LABEL: orlow12:
-; RV32:       # %bb.0:
-; RV32-NEXT:    lui a1, 1
-; RV32-NEXT:    addi a1, a1, -1
-; RV32-NEXT:    or a0, a0, a1
-; RV32-NEXT:    ret
-;
-; RV64-LABEL: orlow12:
-; RV64:       # %bb.0:
-; RV64-NEXT:    lui a1, 1
-; RV64-NEXT:    addiw a1, a1, -1
-; RV64-NEXT:    or a0, a0, a1
-; RV64-NEXT:    ret
+; CHECK-LABEL: orlow12:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    lui a1, 1048575
+; CHECK-NEXT:    orn a0, a0, a1
+; CHECK-NEXT:    ret
   %or = or i32 %x, 4095
   ret i32 %or
 }
 
 define i32 @xorlow12(i32 %x) {
-; RV32-LABEL: xorlow12:
-; RV32:       # %bb.0:
-; RV32-NEXT:    lui a1, 1
-; RV32-NEXT:    addi a1, a1, -1
-; RV32-NEXT:    xor a0, a0, a1
-; RV32-NEXT:    ret
-;
-; RV64-LABEL: xorlow12:
-; RV64:       # %bb.0:
-; RV64-NEXT:    lui a1, 1
-; RV64-NEXT:    addiw a1, a1, -1
-; RV64-NEXT:    xor a0, a0, a1
-; RV64-NEXT:    ret
+; CHECK-LABEL: xorlow12:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    lui a1, 1048575
+; CHECK-NEXT:    xnor a0, a0, a1
+; CHECK-NEXT:    ret
   %xor = xor i32 %x, 4095
   ret i32 %xor
 }

>From d8340ac1be29462c3a68962f7dec0b30a91a60dd Mon Sep 17 00:00:00 2001
From: Piotr Fusik <p.fusik at samsung.com>
Date: Wed, 18 Dec 2024 18:29:59 +0100
Subject: [PATCH 3/4] [RISCV] Keep and/or/xor if there is another user of the
 constant

---
 llvm/lib/Target/RISCV/RISCVISelDAGToDAG.cpp  |  4 ++++
 llvm/test/CodeGen/RISCV/zbb-logic-neg-imm.ll | 14 +++++---------
 2 files changed, 9 insertions(+), 9 deletions(-)

diff --git a/llvm/lib/Target/RISCV/RISCVISelDAGToDAG.cpp b/llvm/lib/Target/RISCV/RISCVISelDAGToDAG.cpp
index d77e2b1421b136..072cc1e8f47921 100644
--- a/llvm/lib/Target/RISCV/RISCVISelDAGToDAG.cpp
+++ b/llvm/lib/Target/RISCV/RISCVISelDAGToDAG.cpp
@@ -3244,6 +3244,10 @@ bool RISCVDAGToDAGISel::selectSImm32fff(SDValue N, SDValue &Val) {
   if (!(isInt<32>(Imm) && (Imm & 0xfff) == 0xfff && Imm != -1))
     return false;
 
+  if (!std::all_of(N->use_begin(), N->use_end(), [](const SDNode *U) {
+	return ISD::isBitwiseLogicOp(U->getOpcode()); }))
+    return false;
+
   Val = selectImm(CurDAG, SDLoc(N), N->getSimpleValueType(0), ~Imm, *Subtarget);
   return true;
 }
diff --git a/llvm/test/CodeGen/RISCV/zbb-logic-neg-imm.ll b/llvm/test/CodeGen/RISCV/zbb-logic-neg-imm.ll
index 86c9676bec1280..604d1b0d7506fe 100644
--- a/llvm/test/CodeGen/RISCV/zbb-logic-neg-imm.ll
+++ b/llvm/test/CodeGen/RISCV/zbb-logic-neg-imm.ll
@@ -63,19 +63,17 @@ define i32 @xorlow31(i32 %x) {
 define i32 @oraddlow16(i32 %x) {
 ; RV32-LABEL: oraddlow16:
 ; RV32:       # %bb.0:
-; RV32-NEXT:    lui a1, 1048560
-; RV32-NEXT:    orn a0, a0, a1
 ; RV32-NEXT:    lui a1, 16
 ; RV32-NEXT:    addi a1, a1, -1
+; RV32-NEXT:    or a0, a0, a1
 ; RV32-NEXT:    add a0, a0, a1
 ; RV32-NEXT:    ret
 ;
 ; RV64-LABEL: oraddlow16:
 ; RV64:       # %bb.0:
-; RV64-NEXT:    lui a1, 1048560
-; RV64-NEXT:    orn a0, a0, a1
 ; RV64-NEXT:    lui a1, 16
 ; RV64-NEXT:    addi a1, a1, -1
+; RV64-NEXT:    or a0, a0, a1
 ; RV64-NEXT:    addw a0, a0, a1
 ; RV64-NEXT:    ret
   %or = or i32 %x, 65535
@@ -89,17 +87,15 @@ define i32 @addorlow16(i32 %x) {
 ; RV32-NEXT:    lui a1, 16
 ; RV32-NEXT:    addi a1, a1, -1
 ; RV32-NEXT:    add a0, a0, a1
-; RV32-NEXT:    lui a1, 1048560
-; RV32-NEXT:    orn a0, a0, a1
+; RV32-NEXT:    or a0, a0, a1
 ; RV32-NEXT:    ret
 ;
 ; RV64-LABEL: addorlow16:
 ; RV64:       # %bb.0:
 ; RV64-NEXT:    lui a1, 16
-; RV64-NEXT:    addi a1, a1, -1
+; RV64-NEXT:    addiw a1, a1, -1
 ; RV64-NEXT:    addw a0, a0, a1
-; RV64-NEXT:    lui a1, 1048560
-; RV64-NEXT:    orn a0, a0, a1
+; RV64-NEXT:    or a0, a0, a1
 ; RV64-NEXT:    ret
   %add = add nsw i32 %x, 65535
   %or = or i32 %add, 65535

>From 2bbf1a15a5f16e623999ca0e399366bcc1333cf3 Mon Sep 17 00:00:00 2001
From: Piotr Fusik <p.fusik at samsung.com>
Date: Wed, 18 Dec 2024 19:20:13 +0100
Subject: [PATCH 4/4] Address review comment. Fix formatting.

---
 llvm/lib/Target/RISCV/RISCVISelDAGToDAG.cpp | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/llvm/lib/Target/RISCV/RISCVISelDAGToDAG.cpp b/llvm/lib/Target/RISCV/RISCVISelDAGToDAG.cpp
index 072cc1e8f47921..a12b4c79f70804 100644
--- a/llvm/lib/Target/RISCV/RISCVISelDAGToDAG.cpp
+++ b/llvm/lib/Target/RISCV/RISCVISelDAGToDAG.cpp
@@ -3241,12 +3241,13 @@ bool RISCVDAGToDAGISel::selectSImm32fff(SDValue N, SDValue &Val) {
     return false;
 
   int64_t Imm = cast<ConstantSDNode>(N)->getSExtValue();
-  if (!(isInt<32>(Imm) && (Imm & 0xfff) == 0xfff && Imm != -1))
+  if (!isInt<32>(Imm) || (Imm & 0xfff) != 0xfff || Imm == -1)
     return false;
 
-  if (!std::all_of(N->use_begin(), N->use_end(), [](const SDNode *U) {
-	return ISD::isBitwiseLogicOp(U->getOpcode()); }))
-    return false;
+  for (const SDNode *U : N->uses()) {
+    if (!ISD::isBitwiseLogicOp(U->getOpcode()))
+      return false;
+  }
 
   Val = selectImm(CurDAG, SDLoc(N), N->getSimpleValueType(0), ~Imm, *Subtarget);
   return true;



More information about the llvm-commits mailing list