[llvm] [LegalizeTypes] Expand 128-bit UDIV/UREM by constant via Chunk Addition (PR #146238)
via llvm-commits
llvm-commits at lists.llvm.org
Sat Jun 28 13:41:46 PDT 2025
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-llvm-selectiondag
Author: Shivam Gupta (xgupta)
<details>
<summary>Changes</summary>
This patch improves the lowering of 128-bit unsigned division and remainder by constants (UDIV/UREM) by avoiding a fallback to libcall (__udivti3/uremti3) for specific divisors.
When a divisor D satisfies the condition (1 << ChunkWidth) % D == 1, the 128-bit value is split into fixed-width chunks (e.g., 30-bit) and summed before applying a smaller UDIV/UREM. This transformation is based on the "remainder by summing digits" trick described in Hacker’s Delight.
This fixes PR137514 for some constants.
---
Patch is 36.18 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/146238.diff
8 Files Affected:
- (modified) llvm/lib/CodeGen/SelectionDAG/TargetLowering.cpp (+74-2)
- (modified) llvm/test/CodeGen/RISCV/div-by-constant.ll (+70-10)
- (modified) llvm/test/CodeGen/RISCV/split-udiv-by-constant.ll (+155-28)
- (modified) llvm/test/CodeGen/RISCV/split-urem-by-constant.ll (+107-28)
- (modified) llvm/test/CodeGen/RISCV/urem-vector-lkk.ll (+41-32)
- (modified) llvm/test/CodeGen/X86/divide-by-constant.ll (+35-7)
- (modified) llvm/test/CodeGen/X86/divmod128.ll (+66-15)
- (added) llvm/test/CodeGen/X86/uint128-div-const.ll (+210)
``````````diff
diff --git a/llvm/lib/CodeGen/SelectionDAG/TargetLowering.cpp b/llvm/lib/CodeGen/SelectionDAG/TargetLowering.cpp
index a0b5f67c2e6c7..e8dc9280e8e2b 100644
--- a/llvm/lib/CodeGen/SelectionDAG/TargetLowering.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/TargetLowering.cpp
@@ -7981,8 +7981,6 @@ bool TargetLowering::expandDIVREMByConstant(SDNode *N,
// If (1 << HBitWidth) % divisor == 1, we can add the two halves together and
// then add in the carry.
- // TODO: If we can't split it in half, we might be able to split into 3 or
- // more pieces using a smaller bit width.
if (HalfMaxPlus1.urem(Divisor).isOne()) {
assert(!LL == !LH && "Expected both input halves or no input halves!");
if (!LL)
@@ -8030,6 +8028,80 @@ bool TargetLowering::expandDIVREMByConstant(SDNode *N,
DAG.getConstant(0, dl, HiLoVT));
Sum = DAG.getNode(ISD::ADD, dl, HiLoVT, Sum, Carry);
}
+
+ } else {
+ // If we cannot split in two halves. Let's look for a smaller chunk
+ // width where (1 << ChunkWidth) mod Divisor == 1.
+ // This ensures that the sum of all such chunks modulo Divisor
+ // is equivalent to the original value modulo Divisor.
+ const APInt &Divisor = CN->getAPIntValue();
+ unsigned BitWidth = VT.getScalarSizeInBits();
+ unsigned BestChunkWidth = 0;
+
+ // We restrict to small chunk sizes (e.g., ≤ 32 bits) to ensure that all
+ // operations remain legal on most targets.
+ unsigned MaxChunk = 32;
+ for (int i = MaxChunk; i >= 1; --i) {
+ APInt ChunkMaxPlus1 = APInt::getOneBitSet(BitWidth, i);
+ if (ChunkMaxPlus1.urem(Divisor).isOne()) {
+ BestChunkWidth = i;
+ break;
+ }
+ }
+
+ // If we found a good chunk width, slice the number and sum the pieces.
+ if (BestChunkWidth > 0) {
+ EVT ChunkVT = EVT::getIntegerVT(*DAG.getContext(), BestChunkWidth);
+
+ if (!LL)
+ std::tie(LL, LH) =
+ DAG.SplitScalar(N->getOperand(0), dl, HiLoVT, HiLoVT);
+ SDValue In = DAG.getNode(ISD::BUILD_PAIR, dl, VT, LL, LH);
+
+ SmallVector<SDValue, 8> Parts;
+ // Split into fixed-size chunks
+ for (unsigned i = 0; i < BitWidth; i += BestChunkWidth) {
+ SDValue Shift = DAG.getShiftAmountConstant(i, VT, dl);
+ SDValue Chunk = DAG.getNode(ISD::SRL, dl, VT, In, Shift);
+ Chunk = DAG.getNode(ISD::TRUNCATE, dl, ChunkVT, Chunk);
+ Parts.push_back(Chunk);
+ }
+ if (Parts.empty())
+ return false;
+ Sum = Parts[0];
+
+ // Use uaddo_carry if we can, otherwise use a compare to detect overflow.
+ // same logic as used in above if condition.
+ SDValue Carry = DAG.getConstant(0, dl, ChunkVT);
+ EVT SetCCType =
+ getSetCCResultType(DAG.getDataLayout(), *DAG.getContext(), ChunkVT);
+ for (unsigned i = 1; i < Parts.size(); ++i) {
+ if (isOperationLegalOrCustom(ISD::UADDO_CARRY, ChunkVT)) {
+ SDVTList VTList = DAG.getVTList(ChunkVT, SetCCType);
+ SDValue UAdd = DAG.getNode(ISD::UADDO, dl, VTList, Sum, Parts[i]);
+ Sum = DAG.getNode(ISD::UADDO_CARRY, dl, VTList, UAdd, Carry,
+ UAdd.getValue(1));
+ } else {
+ SDValue Add = DAG.getNode(ISD::ADD, dl, ChunkVT, Sum, Parts[i]);
+ SDValue NewCarry = DAG.getSetCC(dl, SetCCType, Add, Sum, ISD::SETULT);
+
+ if (getBooleanContents(ChunkVT) ==
+ TargetLoweringBase::ZeroOrOneBooleanContent)
+ NewCarry = DAG.getZExtOrTrunc(NewCarry, dl, ChunkVT);
+ else
+ NewCarry = DAG.getSelect(dl, ChunkVT, NewCarry,
+ DAG.getConstant(1, dl, ChunkVT),
+ DAG.getConstant(0, dl, ChunkVT));
+
+ Sum = DAG.getNode(ISD::ADD, dl, ChunkVT, Add, Carry);
+ Carry = NewCarry;
+ }
+ }
+
+ Sum = DAG.getNode(ISD::ZERO_EXTEND, dl, HiLoVT, Sum);
+ } else {
+ return false;
+ }
}
// If we didn't find a sum, we can't do the expansion.
diff --git a/llvm/test/CodeGen/RISCV/div-by-constant.ll b/llvm/test/CodeGen/RISCV/div-by-constant.ll
index ea8b04d727acf..f2e1979fc4057 100644
--- a/llvm/test/CodeGen/RISCV/div-by-constant.ll
+++ b/llvm/test/CodeGen/RISCV/div-by-constant.ll
@@ -115,16 +115,76 @@ define i64 @udiv64_constant_no_add(i64 %a) nounwind {
}
define i64 @udiv64_constant_add(i64 %a) nounwind {
-; RV32-LABEL: udiv64_constant_add:
-; RV32: # %bb.0:
-; RV32-NEXT: addi sp, sp, -16
-; RV32-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
-; RV32-NEXT: li a2, 7
-; RV32-NEXT: li a3, 0
-; RV32-NEXT: call __udivdi3
-; RV32-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
-; RV32-NEXT: addi sp, sp, 16
-; RV32-NEXT: ret
+; RV32IM-LABEL: udiv64_constant_add:
+; RV32IM: # %bb.0:
+; RV32IM-NEXT: lui a2, 262144
+; RV32IM-NEXT: slli a3, a1, 2
+; RV32IM-NEXT: srli a4, a0, 30
+; RV32IM-NEXT: srli a5, a1, 28
+; RV32IM-NEXT: lui a6, 149797
+; RV32IM-NEXT: addi a2, a2, -1
+; RV32IM-NEXT: or a3, a4, a3
+; RV32IM-NEXT: and a4, a0, a2
+; RV32IM-NEXT: add a3, a0, a3
+; RV32IM-NEXT: add a5, a3, a5
+; RV32IM-NEXT: and a3, a3, a2
+; RV32IM-NEXT: sltu a3, a3, a4
+; RV32IM-NEXT: lui a4, 449390
+; RV32IM-NEXT: add a3, a5, a3
+; RV32IM-NEXT: lui a5, 748983
+; RV32IM-NEXT: addi a6, a6, -1755
+; RV32IM-NEXT: addi a4, a4, -1171
+; RV32IM-NEXT: addi a5, a5, -585
+; RV32IM-NEXT: and a2, a3, a2
+; RV32IM-NEXT: mulhu a3, a2, a6
+; RV32IM-NEXT: slli a6, a3, 3
+; RV32IM-NEXT: add a2, a2, a3
+; RV32IM-NEXT: sub a2, a2, a6
+; RV32IM-NEXT: sub a3, a0, a2
+; RV32IM-NEXT: sltu a0, a0, a2
+; RV32IM-NEXT: mul a2, a3, a4
+; RV32IM-NEXT: mulhu a4, a3, a5
+; RV32IM-NEXT: sub a1, a1, a0
+; RV32IM-NEXT: add a2, a4, a2
+; RV32IM-NEXT: mul a1, a1, a5
+; RV32IM-NEXT: add a1, a2, a1
+; RV32IM-NEXT: mul a0, a3, a5
+; RV32IM-NEXT: ret
+;
+; RV32IMZB-LABEL: udiv64_constant_add:
+; RV32IMZB: # %bb.0:
+; RV32IMZB-NEXT: srli a2, a0, 30
+; RV32IMZB-NEXT: srli a3, a1, 28
+; RV32IMZB-NEXT: lui a4, 786432
+; RV32IMZB-NEXT: slli a5, a0, 2
+; RV32IMZB-NEXT: lui a6, 149797
+; RV32IMZB-NEXT: sh2add a2, a1, a2
+; RV32IMZB-NEXT: srli a5, a5, 2
+; RV32IMZB-NEXT: add a2, a0, a2
+; RV32IMZB-NEXT: add a3, a2, a3
+; RV32IMZB-NEXT: andn a2, a2, a4
+; RV32IMZB-NEXT: sltu a2, a2, a5
+; RV32IMZB-NEXT: lui a5, 449390
+; RV32IMZB-NEXT: add a2, a3, a2
+; RV32IMZB-NEXT: lui a3, 748983
+; RV32IMZB-NEXT: addi a6, a6, -1755
+; RV32IMZB-NEXT: addi a5, a5, -1171
+; RV32IMZB-NEXT: addi a3, a3, -585
+; RV32IMZB-NEXT: andn a2, a2, a4
+; RV32IMZB-NEXT: mulhu a4, a2, a6
+; RV32IMZB-NEXT: slli a6, a4, 3
+; RV32IMZB-NEXT: add a2, a2, a4
+; RV32IMZB-NEXT: sub a2, a2, a6
+; RV32IMZB-NEXT: sub a4, a0, a2
+; RV32IMZB-NEXT: sltu a0, a0, a2
+; RV32IMZB-NEXT: mul a2, a4, a5
+; RV32IMZB-NEXT: mulhu a5, a4, a3
+; RV32IMZB-NEXT: sub a1, a1, a0
+; RV32IMZB-NEXT: add a2, a5, a2
+; RV32IMZB-NEXT: mul a1, a1, a3
+; RV32IMZB-NEXT: add a1, a2, a1
+; RV32IMZB-NEXT: mul a0, a4, a3
+; RV32IMZB-NEXT: ret
;
; RV64-LABEL: udiv64_constant_add:
; RV64: # %bb.0:
diff --git a/llvm/test/CodeGen/RISCV/split-udiv-by-constant.ll b/llvm/test/CodeGen/RISCV/split-udiv-by-constant.ll
index eb70d7f43c0ef..8250fc3a176e2 100644
--- a/llvm/test/CodeGen/RISCV/split-udiv-by-constant.ll
+++ b/llvm/test/CodeGen/RISCV/split-udiv-by-constant.ll
@@ -117,24 +117,89 @@ define iXLen2 @test_udiv_5(iXLen2 %x) nounwind {
define iXLen2 @test_udiv_7(iXLen2 %x) nounwind {
; RV32-LABEL: test_udiv_7:
; RV32: # %bb.0:
-; RV32-NEXT: addi sp, sp, -16
-; RV32-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
-; RV32-NEXT: li a2, 7
-; RV32-NEXT: li a3, 0
-; RV32-NEXT: call __udivdi3
-; RV32-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
-; RV32-NEXT: addi sp, sp, 16
+; RV32-NEXT: lui a2, 262144
+; RV32-NEXT: slli a3, a1, 2
+; RV32-NEXT: srli a4, a0, 30
+; RV32-NEXT: srli a5, a1, 28
+; RV32-NEXT: lui a6, 149797
+; RV32-NEXT: addi a2, a2, -1
+; RV32-NEXT: or a3, a4, a3
+; RV32-NEXT: and a4, a0, a2
+; RV32-NEXT: add a3, a0, a3
+; RV32-NEXT: add a5, a3, a5
+; RV32-NEXT: and a3, a3, a2
+; RV32-NEXT: sltu a3, a3, a4
+; RV32-NEXT: lui a4, 449390
+; RV32-NEXT: add a3, a5, a3
+; RV32-NEXT: lui a5, 748983
+; RV32-NEXT: addi a6, a6, -1755
+; RV32-NEXT: addi a4, a4, -1171
+; RV32-NEXT: addi a5, a5, -585
+; RV32-NEXT: and a2, a3, a2
+; RV32-NEXT: mulhu a3, a2, a6
+; RV32-NEXT: slli a6, a3, 3
+; RV32-NEXT: add a2, a2, a3
+; RV32-NEXT: sub a2, a2, a6
+; RV32-NEXT: sub a3, a0, a2
+; RV32-NEXT: sltu a0, a0, a2
+; RV32-NEXT: mul a2, a3, a4
+; RV32-NEXT: mulhu a4, a3, a5
+; RV32-NEXT: sub a1, a1, a0
+; RV32-NEXT: add a2, a4, a2
+; RV32-NEXT: mul a1, a1, a5
+; RV32-NEXT: add a1, a2, a1
+; RV32-NEXT: mul a0, a3, a5
; RV32-NEXT: ret
;
; RV64-LABEL: test_udiv_7:
; RV64: # %bb.0:
-; RV64-NEXT: addi sp, sp, -16
-; RV64-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
-; RV64-NEXT: li a2, 7
-; RV64-NEXT: li a3, 0
-; RV64-NEXT: call __udivti3
-; RV64-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
-; RV64-NEXT: addi sp, sp, 16
+; RV64-NEXT: slli a2, a1, 4
+; RV64-NEXT: srli a3, a0, 60
+; RV64-NEXT: slli a4, a1, 34
+; RV64-NEXT: srli a5, a0, 30
+; RV64-NEXT: lui a6, 262144
+; RV64-NEXT: srli a7, a1, 26
+; RV64-NEXT: or a2, a3, a2
+; RV64-NEXT: lui a3, 748983
+; RV64-NEXT: or a4, a5, a4
+; RV64-NEXT: addi a6, a6, -1
+; RV64-NEXT: addi a3, a3, -585
+; RV64-NEXT: add a4, a0, a4
+; RV64-NEXT: slli a5, a3, 33
+; RV64-NEXT: add a3, a3, a5
+; RV64-NEXT: and a5, a0, a6
+; RV64-NEXT: add a2, a4, a2
+; RV64-NEXT: and a4, a4, a6
+; RV64-NEXT: sltu a5, a4, a5
+; RV64-NEXT: add a5, a2, a5
+; RV64-NEXT: and a2, a2, a6
+; RV64-NEXT: sltu a2, a2, a4
+; RV64-NEXT: srli a4, a1, 56
+; RV64-NEXT: add a2, a2, a4
+; RV64-NEXT: lui a4, %hi(.LCPI2_0)
+; RV64-NEXT: add a7, a5, a7
+; RV64-NEXT: and a5, a5, a6
+; RV64-NEXT: add a2, a7, a2
+; RV64-NEXT: and a7, a7, a6
+; RV64-NEXT: sltu a5, a7, a5
+; RV64-NEXT: lui a7, %hi(.LCPI2_1)
+; RV64-NEXT: ld a4, %lo(.LCPI2_0)(a4)
+; RV64-NEXT: ld a7, %lo(.LCPI2_1)(a7)
+; RV64-NEXT: add a2, a2, a5
+; RV64-NEXT: and a2, a2, a6
+; RV64-NEXT: mulhu a4, a2, a4
+; RV64-NEXT: slli a5, a4, 3
+; RV64-NEXT: add a2, a2, a4
+; RV64-NEXT: sub a2, a2, a5
+; RV64-NEXT: sub a4, a0, a2
+; RV64-NEXT: sltu a0, a0, a2
+; RV64-NEXT: mul a2, a4, a7
+; RV64-NEXT: mulhu a5, a4, a3
+; RV64-NEXT: sub a1, a1, a0
+; RV64-NEXT: add a2, a5, a2
+; RV64-NEXT: mul a1, a1, a3
+; RV64-NEXT: add a1, a2, a1
+; RV64-NEXT: mul a0, a4, a3
; RV64-NEXT: ret
%a = udiv iXLen2 %x, 7
ret iXLen2 %a
@@ -143,24 +208,86 @@ define iXLen2 @test_udiv_7(iXLen2 %x) nounwind {
define iXLen2 @test_udiv_9(iXLen2 %x) nounwind {
; RV32-LABEL: test_udiv_9:
; RV32: # %bb.0:
-; RV32-NEXT: addi sp, sp, -16
-; RV32-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
-; RV32-NEXT: li a2, 9
-; RV32-NEXT: li a3, 0
-; RV32-NEXT: call __udivdi3
-; RV32-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
-; RV32-NEXT: addi sp, sp, 16
+; RV32-NEXT: lui a2, 262144
+; RV32-NEXT: slli a3, a1, 2
+; RV32-NEXT: srli a4, a0, 30
+; RV32-NEXT: srli a5, a1, 28
+; RV32-NEXT: lui a6, 233017
+; RV32-NEXT: addi a2, a2, -1
+; RV32-NEXT: or a3, a4, a3
+; RV32-NEXT: and a4, a0, a2
+; RV32-NEXT: add a3, a0, a3
+; RV32-NEXT: add a5, a3, a5
+; RV32-NEXT: and a3, a3, a2
+; RV32-NEXT: sltu a3, a3, a4
+; RV32-NEXT: lui a4, 582542
+; RV32-NEXT: addi a6, a6, -455
+; RV32-NEXT: addi a4, a4, 910
+; RV32-NEXT: add a3, a5, a3
+; RV32-NEXT: and a2, a3, a2
+; RV32-NEXT: mulhu a3, a2, a6
+; RV32-NEXT: srli a3, a3, 1
+; RV32-NEXT: slli a5, a3, 3
+; RV32-NEXT: sub a2, a2, a3
+; RV32-NEXT: sub a2, a2, a5
+; RV32-NEXT: sub a3, a0, a2
+; RV32-NEXT: sltu a0, a0, a2
+; RV32-NEXT: mul a2, a3, a4
+; RV32-NEXT: mulhu a4, a3, a6
+; RV32-NEXT: sub a1, a1, a0
+; RV32-NEXT: add a2, a4, a2
+; RV32-NEXT: mul a1, a1, a6
+; RV32-NEXT: add a1, a2, a1
+; RV32-NEXT: mul a0, a3, a6
; RV32-NEXT: ret
;
; RV64-LABEL: test_udiv_9:
; RV64: # %bb.0:
-; RV64-NEXT: addi sp, sp, -16
-; RV64-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
-; RV64-NEXT: li a2, 9
-; RV64-NEXT: li a3, 0
-; RV64-NEXT: call __udivti3
-; RV64-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
-; RV64-NEXT: addi sp, sp, 16
+; RV64-NEXT: slli a2, a1, 4
+; RV64-NEXT: srli a3, a0, 60
+; RV64-NEXT: slli a4, a1, 34
+; RV64-NEXT: srli a5, a0, 30
+; RV64-NEXT: lui a6, 262144
+; RV64-NEXT: srli a7, a1, 26
+; RV64-NEXT: or a2, a3, a2
+; RV64-NEXT: srli a3, a1, 56
+; RV64-NEXT: or a4, a5, a4
+; RV64-NEXT: addi a6, a6, -1
+; RV64-NEXT: add a4, a0, a4
+; RV64-NEXT: and a5, a0, a6
+; RV64-NEXT: add a2, a4, a2
+; RV64-NEXT: and a4, a4, a6
+; RV64-NEXT: sltu a5, a4, a5
+; RV64-NEXT: add a5, a2, a5
+; RV64-NEXT: and a2, a2, a6
+; RV64-NEXT: sltu a2, a2, a4
+; RV64-NEXT: lui a4, %hi(.LCPI3_0)
+; RV64-NEXT: add a2, a2, a3
+; RV64-NEXT: lui a3, %hi(.LCPI3_1)
+; RV64-NEXT: add a7, a5, a7
+; RV64-NEXT: and a5, a5, a6
+; RV64-NEXT: add a2, a7, a2
+; RV64-NEXT: and a7, a7, a6
+; RV64-NEXT: sltu a5, a7, a5
+; RV64-NEXT: lui a7, %hi(.LCPI3_2)
+; RV64-NEXT: ld a4, %lo(.LCPI3_0)(a4)
+; RV64-NEXT: ld a3, %lo(.LCPI3_1)(a3)
+; RV64-NEXT: ld a7, %lo(.LCPI3_2)(a7)
+; RV64-NEXT: add a2, a2, a5
+; RV64-NEXT: and a2, a2, a6
+; RV64-NEXT: mulhu a4, a2, a4
+; RV64-NEXT: slli a5, a4, 3
+; RV64-NEXT: sub a2, a2, a4
+; RV64-NEXT: sub a2, a2, a5
+; RV64-NEXT: sub a4, a0, a2
+; RV64-NEXT: sltu a0, a0, a2
+; RV64-NEXT: mul a2, a4, a3
+; RV64-NEXT: mulhu a3, a4, a7
+; RV64-NEXT: sub a1, a1, a0
+; RV64-NEXT: add a2, a3, a2
+; RV64-NEXT: mul a1, a1, a7
+; RV64-NEXT: add a1, a2, a1
+; RV64-NEXT: mul a0, a4, a7
; RV64-NEXT: ret
%a = udiv iXLen2 %x, 9
ret iXLen2 %a
diff --git a/llvm/test/CodeGen/RISCV/split-urem-by-constant.ll b/llvm/test/CodeGen/RISCV/split-urem-by-constant.ll
index bc4a99a00ac64..1680ea7d8da30 100644
--- a/llvm/test/CodeGen/RISCV/split-urem-by-constant.ll
+++ b/llvm/test/CodeGen/RISCV/split-urem-by-constant.ll
@@ -79,24 +79,63 @@ define iXLen2 @test_urem_5(iXLen2 %x) nounwind {
define iXLen2 @test_urem_7(iXLen2 %x) nounwind {
; RV32-LABEL: test_urem_7:
; RV32: # %bb.0:
-; RV32-NEXT: addi sp, sp, -16
-; RV32-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
-; RV32-NEXT: li a2, 7
-; RV32-NEXT: li a3, 0
-; RV32-NEXT: call __umoddi3
-; RV32-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
-; RV32-NEXT: addi sp, sp, 16
+; RV32-NEXT: lui a2, 262144
+; RV32-NEXT: slli a3, a1, 2
+; RV32-NEXT: srli a4, a0, 30
+; RV32-NEXT: srli a1, a1, 28
+; RV32-NEXT: lui a5, 149797
+; RV32-NEXT: addi a2, a2, -1
+; RV32-NEXT: or a3, a4, a3
+; RV32-NEXT: addi a4, a5, -1755
+; RV32-NEXT: and a5, a0, a2
+; RV32-NEXT: add a0, a0, a3
+; RV32-NEXT: and a3, a0, a2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: sltu a1, a3, a5
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: and a0, a0, a2
+; RV32-NEXT: mulhu a1, a0, a4
+; RV32-NEXT: slli a2, a1, 3
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: sub a0, a0, a2
+; RV32-NEXT: li a1, 0
; RV32-NEXT: ret
;
; RV64-LABEL: test_urem_7:
; RV64: # %bb.0:
-; RV64-NEXT: addi sp, sp, -16
-; RV64-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
-; RV64-NEXT: li a2, 7
-; RV64-NEXT: li a3, 0
-; RV64-NEXT: call __umodti3
-; RV64-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
-; RV64-NEXT: addi sp, sp, 16
+; RV64-NEXT: slli a2, a1, 4
+; RV64-NEXT: srli a3, a0, 60
+; RV64-NEXT: slli a4, a1, 34
+; RV64-NEXT: srli a5, a0, 30
+; RV64-NEXT: lui a6, 262144
+; RV64-NEXT: or a2, a3, a2
+; RV64-NEXT: srli a3, a1, 26
+; RV64-NEXT: srli a1, a1, 56
+; RV64-NEXT: or a4, a5, a4
+; RV64-NEXT: lui a5, %hi(.LCPI2_0)
+; RV64-NEXT: addi a6, a6, -1
+; RV64-NEXT: ld a5, %lo(.LCPI2_0)(a5)
+; RV64-NEXT: add a4, a0, a4
+; RV64-NEXT: and a0, a0, a6
+; RV64-NEXT: add a2, a4, a2
+; RV64-NEXT: and a4, a4, a6
+; RV64-NEXT: sltu a0, a4, a0
+; RV64-NEXT: add a0, a2, a0
+; RV64-NEXT: and a2, a2, a6
+; RV64-NEXT: sltu a2, a2, a4
+; RV64-NEXT: and a4, a0, a6
+; RV64-NEXT: add a0, a0, a3
+; RV64-NEXT: add a1, a2, a1
+; RV64-NEXT: and a2, a0, a6
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: sltu a1, a2, a4
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: and a0, a0, a6
+; RV64-NEXT: mulhu a1, a0, a5
+; RV64-NEXT: slli a2, a1, 3
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: sub a0, a0, a2
+; RV64-NEXT: li a1, 0
; RV64-NEXT: ret
%a = urem iXLen2 %x, 7
ret iXLen2 %a
@@ -105,24 +144,64 @@ define iXLen2 @test_urem_7(iXLen2 %x) nounwind {
define iXLen2 @test_urem_9(iXLen2 %x) nounwind {
; RV32-LABEL: test_urem_9:
; RV32: # %bb.0:
-; RV32-NEXT: addi sp, sp, -16
-; RV32-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
-; RV32-NEXT: li a2, 9
-; RV32-NEXT: li a3, 0
-; RV32-NEXT: call __umoddi3
-; RV32-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
-; RV32-NEXT: addi sp, sp, 16
+; RV32-NEXT: lui a2, 262144
+; RV32-NEXT: slli a3, a1, 2
+; RV32-NEXT: srli a4, a0, 30
+; RV32-NEXT: srli a1, a1, 28
+; RV32-NEXT: lui a5, 233017
+; RV32-NEXT: addi a2, a2, -1
+; RV32-NEXT: or a3, a4, a3
+; RV32-NEXT: addi a4, a5, -455
+; RV32-NEXT: and a5, a0, a2
+; RV32-NEXT: add a0, a0, a3
+; RV32-NEXT: and a3, a0, a2
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: sltu a1, a3, a5
+; RV32-NEXT: add a0, a0, a1
+; RV32-NEXT: and a0, a0, a2
+; RV32-NEXT: mulhu a1, a0, a4
+; RV32-NEXT: srli a1, a1, 1
+; RV32-NEXT: slli a2, a1, 3
+; RV32-NEXT: sub a0, a0, a1
+; RV32-NEXT: sub a0, a0, a2
+; RV32-NEXT: li a1, 0
; RV32-NEXT: ret
;
; RV64-LABEL: test_urem_9:
; RV64: # %bb.0:
-; RV64-NEXT: addi sp, sp, -16
-; RV64-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
-; RV64-NEXT: li a2, 9
-; RV64-NEXT: li a3, 0
-; RV64-NEXT: call __umodti3
-; RV64-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
-; RV64-NEXT: addi sp, sp, 16
+; RV64-NEXT: slli a2, a1, 4
+; RV64-NEXT: srli a3, a0, 60
+; RV64-NEXT: slli a4, a1, 34
+; RV64-NEXT: srli a5, a0, 30
+; RV64-NEXT: lui a6, 262144
+; RV64-NEXT: or a2, a3, a2
+; RV64-NEXT: srli a3, a1, 26
+; RV64-NEXT: srli a1, a1, 56
+; RV64-NEXT: or a4, a5, a4
+; RV64-NEXT: lui a5, %hi(.LCPI3_0)
+; RV64-NEXT: addi a6, a6, -1
+; RV64-NEXT: ld a5, %lo(.LCPI3_0)(a5)
+; RV64-NEXT: add a4, a0, a4
+; RV64-NEXT: and a0, a0, a6
+; RV64-NEXT: add a2, a4, a2
+; RV64-NEXT: and a4, a4, a6
+; RV64-NEXT: sltu a0, a4, a0
+; RV64-NEXT: add a0, a2, a0
+; RV64-NEXT: and a2, a2, a6
+; RV64-NEXT: sltu a2, a2, a4
+; RV64-NEXT: and a4, a0, a6
+; RV64-NEXT: add a0, a0, a3
+; RV64-NEXT: add a1, a2, a1
+; RV64-NEXT: and a2, a0, a6
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: sltu a1, a2, a4
+; RV64-NEXT: add a0, a0, a1
+; RV64-NEXT: and a0, a0, a6
+; RV64-NEXT: mulhu a1, a0, a5
+; RV64-NEXT: slli a2, a1, 3
+; RV64-NEXT: sub a0, a0, a1
+; RV64-NEXT: sub a0, a0, a2
+; RV64-NEXT: li a1, 0
; RV64-NEXT: ret
%a = urem iXLen2 %x, 9
ret iXLen2 %a
diff --git a/llvm/test/CodeGen/RISCV/urem-vector-lkk.ll b/llvm/test/CodeGen/RISCV/urem-vector-lkk.ll
index 3ef9f3f945108..77a026669c51d 100644
--- a/llvm/test/CodeGen/RISCV/urem-vector-lkk.ll
+++ b/llvm/test/CodeGen/RISCV/urem-vector-lkk.ll
@@ -862,51 +862,61 @@ define <4 x i64> @dont_fold_urem_i64(<4 x i64> %x) nounwind {
; RV32IM-NEXT: sw s5, 20(sp) # 4-byte Folded Spill
; RV32IM-NEXT: sw s6, 16(sp) # 4-byte Folded Spill
; RV32IM-NEXT: sw s7, 12(sp) # 4-byte Folded Spill
-; RV32IM-NEXT: sw s8, 8(sp) # 4-byte Folded Spill
-; RV32IM-NEXT: lw s1, 16(a1)
-; RV32IM-NEXT: lw s2, 20(a1)
-; RV32IM-NEXT: lw s3, 24(a1)
-; RV32IM-NEXT: lw s4, 28(a1)
-; RV32IM-NEXT: lw a3, 0(a1)
-; RV32IM-NEXT: lw a4, 4(a1)
-; RV32IM-NEXT: lw s5, 8(a1)
-; RV32IM-NEXT: lw s6, 12(...
[truncated]
``````````
</details>
https://github.com/llvm/llvm-project/pull/146238
More information about the llvm-commits
mailing list