blob: d00208ef6803b00df9850c58f1b35a4f9900a4db [file] [log] [blame]
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=riscv32 -mattr=+m | FileCheck %s --check-prefixes=RISCV32
define { i128, i8 } @muloti_test(i128 %l, i128 %r) unnamed_addr #0 {
; RISCV32-LABEL: muloti_test:
; RISCV32: # %bb.0: # %start
; RISCV32-NEXT: addi sp, sp, -96
; RISCV32-NEXT: sw ra, 92(sp)
; RISCV32-NEXT: sw s1, 88(sp)
; RISCV32-NEXT: sw s2, 84(sp)
; RISCV32-NEXT: sw s3, 80(sp)
; RISCV32-NEXT: sw s4, 76(sp)
; RISCV32-NEXT: sw s5, 72(sp)
; RISCV32-NEXT: sw s6, 68(sp)
; RISCV32-NEXT: sw s7, 64(sp)
; RISCV32-NEXT: sw s8, 60(sp)
; RISCV32-NEXT: mv s3, a2
; RISCV32-NEXT: mv s1, a1
; RISCV32-NEXT: mv s2, a0
; RISCV32-NEXT: mv s4, zero
; RISCV32-NEXT: sw zero, 20(sp)
; RISCV32-NEXT: sw zero, 16(sp)
; RISCV32-NEXT: sw zero, 36(sp)
; RISCV32-NEXT: sw zero, 32(sp)
; RISCV32-NEXT: lw s5, 4(a2)
; RISCV32-NEXT: sw s5, 12(sp)
; RISCV32-NEXT: lw s7, 0(a2)
; RISCV32-NEXT: sw s7, 8(sp)
; RISCV32-NEXT: lw s6, 4(a1)
; RISCV32-NEXT: sw s6, 28(sp)
; RISCV32-NEXT: lw s8, 0(a1)
; RISCV32-NEXT: sw s8, 24(sp)
; RISCV32-NEXT: addi a0, sp, 40
; RISCV32-NEXT: addi a1, sp, 24
; RISCV32-NEXT: addi a2, sp, 8
; RISCV32-NEXT: call __multi3
; RISCV32-NEXT: lw t2, 12(s1)
; RISCV32-NEXT: lw a1, 8(s1)
; RISCV32-NEXT: mul a0, s5, a1
; RISCV32-NEXT: mul a2, t2, s7
; RISCV32-NEXT: add a0, a2, a0
; RISCV32-NEXT: lw t3, 12(s3)
; RISCV32-NEXT: lw a3, 8(s3)
; RISCV32-NEXT: mul a2, s6, a3
; RISCV32-NEXT: mul a4, t3, s8
; RISCV32-NEXT: add a2, a4, a2
; RISCV32-NEXT: mul a4, a3, s8
; RISCV32-NEXT: mul a5, a1, s7
; RISCV32-NEXT: add a4, a5, a4
; RISCV32-NEXT: sltu a5, a4, a5
; RISCV32-NEXT: mulhu a6, a3, s8
; RISCV32-NEXT: add a7, a6, a2
; RISCV32-NEXT: mulhu t0, a1, s7
; RISCV32-NEXT: add t1, t0, a0
; RISCV32-NEXT: add a0, t1, a7
; RISCV32-NEXT: add a2, a0, a5
; RISCV32-NEXT: lw a0, 52(sp)
; RISCV32-NEXT: add a5, a0, a2
; RISCV32-NEXT: lw a2, 48(sp)
; RISCV32-NEXT: add t4, a2, a4
; RISCV32-NEXT: sltu s1, t4, a2
; RISCV32-NEXT: add a4, a5, s1
; RISCV32-NEXT: beq a4, a0, .LBB0_2
; RISCV32-NEXT: # %bb.1: # %start
; RISCV32-NEXT: sltu s1, a4, a0
; RISCV32-NEXT: .LBB0_2: # %start
; RISCV32-NEXT: xor a0, a4, a0
; RISCV32-NEXT: xor a2, t4, a2
; RISCV32-NEXT: or a0, a2, a0
; RISCV32-NEXT: beq a0, s4, .LBB0_4
; RISCV32-NEXT: # %bb.3: # %start
; RISCV32-NEXT: mv s4, s1
; RISCV32-NEXT: .LBB0_4: # %start
; RISCV32-NEXT: snez a0, s5
; RISCV32-NEXT: snez a2, t2
; RISCV32-NEXT: and a0, a2, a0
; RISCV32-NEXT: snez a2, s6
; RISCV32-NEXT: snez a5, t3
; RISCV32-NEXT: and a2, a5, a2
; RISCV32-NEXT: mulhu a5, t3, s8
; RISCV32-NEXT: snez a5, a5
; RISCV32-NEXT: or a2, a2, a5
; RISCV32-NEXT: mulhu a5, t2, s7
; RISCV32-NEXT: snez a5, a5
; RISCV32-NEXT: or a0, a0, a5
; RISCV32-NEXT: sltu t0, t1, t0
; RISCV32-NEXT: mulhu s1, s5, a1
; RISCV32-NEXT: snez s1, s1
; RISCV32-NEXT: or a0, a0, s1
; RISCV32-NEXT: sltu s1, a7, a6
; RISCV32-NEXT: mulhu a5, s6, a3
; RISCV32-NEXT: snez a5, a5
; RISCV32-NEXT: or a2, a2, a5
; RISCV32-NEXT: lw a5, 44(sp)
; RISCV32-NEXT: sw a5, 4(s2)
; RISCV32-NEXT: lw a5, 40(sp)
; RISCV32-NEXT: sw a5, 0(s2)
; RISCV32-NEXT: sw t4, 8(s2)
; RISCV32-NEXT: sw a4, 12(s2)
; RISCV32-NEXT: or a2, a2, s1
; RISCV32-NEXT: or a0, a0, t0
; RISCV32-NEXT: or a1, a1, t2
; RISCV32-NEXT: or a3, a3, t3
; RISCV32-NEXT: snez a3, a3
; RISCV32-NEXT: snez a1, a1
; RISCV32-NEXT: and a1, a1, a3
; RISCV32-NEXT: or a0, a1, a0
; RISCV32-NEXT: or a0, a0, a2
; RISCV32-NEXT: or a0, a0, s4
; RISCV32-NEXT: andi a0, a0, 1
; RISCV32-NEXT: sb a0, 16(s2)
; RISCV32-NEXT: lw s8, 60(sp)
; RISCV32-NEXT: lw s7, 64(sp)
; RISCV32-NEXT: lw s6, 68(sp)
; RISCV32-NEXT: lw s5, 72(sp)
; RISCV32-NEXT: lw s4, 76(sp)
; RISCV32-NEXT: lw s3, 80(sp)
; RISCV32-NEXT: lw s2, 84(sp)
; RISCV32-NEXT: lw s1, 88(sp)
; RISCV32-NEXT: lw ra, 92(sp)
; RISCV32-NEXT: addi sp, sp, 96
; RISCV32-NEXT: ret
start:
%0 = tail call { i128, i1 } @llvm.umul.with.overflow.i128(i128 %l, i128 %r) #2
%1 = extractvalue { i128, i1 } %0, 0
%2 = extractvalue { i128, i1 } %0, 1
%3 = zext i1 %2 to i8
%4 = insertvalue { i128, i8 } undef, i128 %1, 0
%5 = insertvalue { i128, i8 } %4, i8 %3, 1
ret { i128, i8 } %5
}
; Function Attrs: nounwind readnone speculatable
declare { i128, i1 } @llvm.umul.with.overflow.i128(i128, i128) #1
attributes #0 = { nounwind readnone uwtable }
attributes #1 = { nounwind readnone speculatable }
attributes #2 = { nounwind }