Google Git
Sign in
llvm / llvm-project / llvm / d42433f828aa47533a213f63bfac32115a62fea2 / . / test / CodeGen / RISCV / sextw-removal.ll
blob: 7b382d30dcd64c7aa714c499616043b46c28c42b [file] [log] [blame]
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=riscv64 -mattr=+m,+f -target-abi=lp64f \
; RUN: | FileCheck %s --check-prefixes=CHECK,RV64I
; RUN: llc < %s -mtriple=riscv64 -mattr=+m,+zbb,+f -target-abi=lp64f \
; RUN: | FileCheck %s --check-prefixes=CHECK,RV64ZBB
; RUN: llc < %s -mtriple=riscv64 -mattr=+m,+zbb,+f -target-abi=lp64f \
; RUN: -riscv-disable-sextw-removal | FileCheck %s --check-prefix=NOREMOVAL
define void @test1(i32 signext %arg, i32 signext %arg1) nounwind {
; CHECK-LABEL: test1:
; CHECK: # %bb.0: # %bb
; CHECK-NEXT: addi sp, sp, -32
; CHECK-NEXT: sd ra, 24(sp) # 8-byte Folded Spill
; CHECK-NEXT: sd s0, 16(sp) # 8-byte Folded Spill
; CHECK-NEXT: sd s1, 8(sp) # 8-byte Folded Spill
; CHECK-NEXT: mv s0, a1
; CHECK-NEXT: sraw s1, a0, a1
; CHECK-NEXT: .LBB0_1: # %bb2
; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
; CHECK-NEXT: mv a0, s1
; CHECK-NEXT: call bar@plt
; CHECK-NEXT: sllw s1, s1, s0
; CHECK-NEXT: bnez a0, .LBB0_1
; CHECK-NEXT: # %bb.2: # %bb7
; CHECK-NEXT: ld ra, 24(sp) # 8-byte Folded Reload
; CHECK-NEXT: ld s0, 16(sp) # 8-byte Folded Reload
; CHECK-NEXT: ld s1, 8(sp) # 8-byte Folded Reload
; CHECK-NEXT: addi sp, sp, 32
; CHECK-NEXT: ret
;
; NOREMOVAL-LABEL: test1:
; NOREMOVAL: # %bb.0: # %bb
; NOREMOVAL-NEXT: addi sp, sp, -32
; NOREMOVAL-NEXT: sd ra, 24(sp) # 8-byte Folded Spill
; NOREMOVAL-NEXT: sd s0, 16(sp) # 8-byte Folded Spill
; NOREMOVAL-NEXT: sd s1, 8(sp) # 8-byte Folded Spill
; NOREMOVAL-NEXT: mv s0, a1
; NOREMOVAL-NEXT: sraw s1, a0, a1
; NOREMOVAL-NEXT: .LBB0_1: # %bb2
; NOREMOVAL-NEXT: # =>This Inner Loop Header: Depth=1
; NOREMOVAL-NEXT: sext.w a0, s1
; NOREMOVAL-NEXT: call bar@plt
; NOREMOVAL-NEXT: sllw s1, s1, s0
; NOREMOVAL-NEXT: bnez a0, .LBB0_1
; NOREMOVAL-NEXT: # %bb.2: # %bb7
; NOREMOVAL-NEXT: ld ra, 24(sp) # 8-byte Folded Reload
; NOREMOVAL-NEXT: ld s0, 16(sp) # 8-byte Folded Reload
; NOREMOVAL-NEXT: ld s1, 8(sp) # 8-byte Folded Reload
; NOREMOVAL-NEXT: addi sp, sp, 32
; NOREMOVAL-NEXT: ret
bb:
%i = ashr i32 %arg, %arg1
br label %bb2
bb2: ; preds = %bb2, %bb
%i3 = phi i32 [ %i, %bb ], [ %i5, %bb2 ]
%i4 = tail call signext i32 @bar(i32 signext %i3)
%i5 = shl i32 %i3, %arg1
%i6 = icmp eq i32 %i4, 0
br i1 %i6, label %bb7, label %bb2
bb7: ; preds = %bb2
ret void
}
declare signext i32 @bar(i32 signext)
; The load here will be an anyext load in isel and sext.w will be emitted for
; the ret. Make sure we can look through logic ops to prove the sext.w is
; unnecessary.
define signext i32 @test2(i32* %p, i32 signext %b) nounwind {
; RV64I-LABEL: test2:
; RV64I: # %bb.0:
; RV64I-NEXT: lw a0, 0(a0)
; RV64I-NEXT: li a2, 1
; RV64I-NEXT: sllw a1, a2, a1
; RV64I-NEXT: not a1, a1
; RV64I-NEXT: and a0, a1, a0
; RV64I-NEXT: ret
;
; RV64ZBB-LABEL: test2:
; RV64ZBB: # %bb.0:
; RV64ZBB-NEXT: lw a0, 0(a0)
; RV64ZBB-NEXT: li a2, -2
; RV64ZBB-NEXT: rolw a1, a2, a1
; RV64ZBB-NEXT: and a0, a1, a0
; RV64ZBB-NEXT: ret
;
; NOREMOVAL-LABEL: test2:
; NOREMOVAL: # %bb.0:
; NOREMOVAL-NEXT: lw a0, 0(a0)
; NOREMOVAL-NEXT: li a2, -2
; NOREMOVAL-NEXT: rolw a1, a2, a1
; NOREMOVAL-NEXT: and a0, a1, a0
; NOREMOVAL-NEXT: sext.w a0, a0
; NOREMOVAL-NEXT: ret
%a = load i32, i32* %p
%shl = shl i32 1, %b
%neg = xor i32 %shl, -1
%and1 = and i32 %neg, %a
ret i32 %and1
}
define signext i32 @test3(i32* %p, i32 signext %b) nounwind {
; RV64I-LABEL: test3:
; RV64I: # %bb.0:
; RV64I-NEXT: lw a0, 0(a0)
; RV64I-NEXT: li a2, 1
; RV64I-NEXT: sllw a1, a2, a1
; RV64I-NEXT: not a1, a1
; RV64I-NEXT: or a0, a1, a0
; RV64I-NEXT: ret
;
; RV64ZBB-LABEL: test3:
; RV64ZBB: # %bb.0:
; RV64ZBB-NEXT: lw a0, 0(a0)
; RV64ZBB-NEXT: li a2, -2
; RV64ZBB-NEXT: rolw a1, a2, a1
; RV64ZBB-NEXT: or a0, a1, a0
; RV64ZBB-NEXT: ret
;
; NOREMOVAL-LABEL: test3:
; NOREMOVAL: # %bb.0:
; NOREMOVAL-NEXT: lw a0, 0(a0)
; NOREMOVAL-NEXT: li a2, -2
; NOREMOVAL-NEXT: rolw a1, a2, a1
; NOREMOVAL-NEXT: or a0, a1, a0
; NOREMOVAL-NEXT: sext.w a0, a0
; NOREMOVAL-NEXT: ret
%a = load i32, i32* %p
%shl = shl i32 1, %b
%neg = xor i32 %shl, -1
%and1 = or i32 %neg, %a
ret i32 %and1
}
define signext i32 @test4(i32* %p, i32 signext %b) nounwind {
; RV64I-LABEL: test4:
; RV64I: # %bb.0:
; RV64I-NEXT: lw a0, 0(a0)
; RV64I-NEXT: li a2, 1
; RV64I-NEXT: sllw a1, a2, a1
; RV64I-NEXT: xor a0, a1, a0
; RV64I-NEXT: not a0, a0
; RV64I-NEXT: ret
;
; RV64ZBB-LABEL: test4:
; RV64ZBB: # %bb.0:
; RV64ZBB-NEXT: lw a0, 0(a0)
; RV64ZBB-NEXT: li a2, 1
; RV64ZBB-NEXT: sllw a1, a2, a1
; RV64ZBB-NEXT: xnor a0, a1, a0
; RV64ZBB-NEXT: ret
;
; NOREMOVAL-LABEL: test4:
; NOREMOVAL: # %bb.0:
; NOREMOVAL-NEXT: lw a0, 0(a0)
; NOREMOVAL-NEXT: li a2, 1
; NOREMOVAL-NEXT: sllw a1, a2, a1
; NOREMOVAL-NEXT: xnor a0, a1, a0
; NOREMOVAL-NEXT: sext.w a0, a0
; NOREMOVAL-NEXT: ret
%a = load i32, i32* %p
%shl = shl i32 1, %b
%neg = xor i32 %shl, -1
%and1 = xor i32 %neg, %a
ret i32 %and1
}
; Make sure we don't put a sext.w before bar when using cpopw.
define void @test5(i32 signext %arg, i32 signext %arg1) nounwind {
; RV64I-LABEL: test5:
; RV64I: # %bb.0: # %bb
; RV64I-NEXT: addi sp, sp, -48
; RV64I-NEXT: sd ra, 40(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s0, 32(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s1, 24(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s2, 16(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s3, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: sraw a0, a0, a1
; RV64I-NEXT: lui a1, 349525
; RV64I-NEXT: addiw s0, a1, 1365
; RV64I-NEXT: lui a1, 209715
; RV64I-NEXT: addiw s1, a1, 819
; RV64I-NEXT: lui a1, 61681
; RV64I-NEXT: addiw s2, a1, -241
; RV64I-NEXT: lui a1, 4112
; RV64I-NEXT: addiw s3, a1, 257
; RV64I-NEXT: .LBB4_1: # %bb2
; RV64I-NEXT: # =>This Inner Loop Header: Depth=1
; RV64I-NEXT: call bar@plt
; RV64I-NEXT: mv a1, a0
; RV64I-NEXT: srli a0, a0, 1
; RV64I-NEXT: and a0, a0, s0
; RV64I-NEXT: sub a0, a1, a0
; RV64I-NEXT: and a2, a0, s1
; RV64I-NEXT: srli a0, a0, 2
; RV64I-NEXT: and a0, a0, s1
; RV64I-NEXT: add a0, a2, a0
; RV64I-NEXT: srli a2, a0, 4
; RV64I-NEXT: add a0, a0, a2
; RV64I-NEXT: and a0, a0, s2
; RV64I-NEXT: mulw a0, a0, s3
; RV64I-NEXT: srliw a0, a0, 24
; RV64I-NEXT: bnez a1, .LBB4_1
; RV64I-NEXT: # %bb.2: # %bb7
; RV64I-NEXT: ld ra, 40(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s0, 32(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s1, 24(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s2, 16(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s3, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 48
; RV64I-NEXT: ret
;
; RV64ZBB-LABEL: test5:
; RV64ZBB: # %bb.0: # %bb
; RV64ZBB-NEXT: addi sp, sp, -16
; RV64ZBB-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; RV64ZBB-NEXT: sraw a0, a0, a1
; RV64ZBB-NEXT: .LBB4_1: # %bb2
; RV64ZBB-NEXT: # =>This Inner Loop Header: Depth=1
; RV64ZBB-NEXT: call bar@plt
; RV64ZBB-NEXT: mv a1, a0
; RV64ZBB-NEXT: cpopw a0, a0
; RV64ZBB-NEXT: bnez a1, .LBB4_1
; RV64ZBB-NEXT: # %bb.2: # %bb7
; RV64ZBB-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; RV64ZBB-NEXT: addi sp, sp, 16
; RV64ZBB-NEXT: ret
;
; NOREMOVAL-LABEL: test5:
; NOREMOVAL: # %bb.0: # %bb
; NOREMOVAL-NEXT: addi sp, sp, -16
; NOREMOVAL-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; NOREMOVAL-NEXT: sraw a1, a0, a1
; NOREMOVAL-NEXT: .LBB4_1: # %bb2
; NOREMOVAL-NEXT: # =>This Inner Loop Header: Depth=1
; NOREMOVAL-NEXT: sext.w a0, a1
; NOREMOVAL-NEXT: call bar@plt
; NOREMOVAL-NEXT: cpopw a1, a0
; NOREMOVAL-NEXT: bnez a0, .LBB4_1
; NOREMOVAL-NEXT: # %bb.2: # %bb7
; NOREMOVAL-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; NOREMOVAL-NEXT: addi sp, sp, 16
; NOREMOVAL-NEXT: ret
bb:
%i = ashr i32 %arg, %arg1
br label %bb2
bb2: ; preds = %bb2, %bb
%i3 = phi i32 [ %i, %bb ], [ %i5, %bb2 ]
%i4 = tail call signext i32 @bar(i32 signext %i3)
%i5 = tail call i32 @llvm.ctpop.i32(i32 %i4)
%i6 = icmp eq i32 %i4, 0
br i1 %i6, label %bb7, label %bb2
bb7: ; preds = %bb2
ret void
}
declare i32 @llvm.ctpop.i32(i32)
define void @test6(i32 signext %arg, i32 signext %arg1) nounwind {
; CHECK-LABEL: test6:
; CHECK: # %bb.0: # %bb
; CHECK-NEXT: addi sp, sp, -16
; CHECK-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; CHECK-NEXT: fsw fs0, 4(sp) # 4-byte Folded Spill
; CHECK-NEXT: sraw a0, a0, a1
; CHECK-NEXT: fmv.w.x fs0, zero
; CHECK-NEXT: .LBB5_1: # %bb2
; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
; CHECK-NEXT: call baz@plt
; CHECK-NEXT: feq.s a1, fa0, fs0
; CHECK-NEXT: fcvt.w.s a0, fa0, rtz
; CHECK-NEXT: beqz a1, .LBB5_1
; CHECK-NEXT: # %bb.2: # %bb7
; CHECK-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; CHECK-NEXT: flw fs0, 4(sp) # 4-byte Folded Reload
; CHECK-NEXT: addi sp, sp, 16
; CHECK-NEXT: ret
;
; NOREMOVAL-LABEL: test6:
; NOREMOVAL: # %bb.0: # %bb
; NOREMOVAL-NEXT: addi sp, sp, -16
; NOREMOVAL-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; NOREMOVAL-NEXT: fsw fs0, 4(sp) # 4-byte Folded Spill
; NOREMOVAL-NEXT: sraw a0, a0, a1
; NOREMOVAL-NEXT: fmv.w.x fs0, zero
; NOREMOVAL-NEXT: .LBB5_1: # %bb2
; NOREMOVAL-NEXT: # =>This Inner Loop Header: Depth=1
; NOREMOVAL-NEXT: sext.w a0, a0
; NOREMOVAL-NEXT: call baz@plt
; NOREMOVAL-NEXT: feq.s a1, fa0, fs0
; NOREMOVAL-NEXT: fcvt.w.s a0, fa0, rtz
; NOREMOVAL-NEXT: beqz a1, .LBB5_1
; NOREMOVAL-NEXT: # %bb.2: # %bb7
; NOREMOVAL-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; NOREMOVAL-NEXT: flw fs0, 4(sp) # 4-byte Folded Reload
; NOREMOVAL-NEXT: addi sp, sp, 16
; NOREMOVAL-NEXT: ret
bb:
%i = ashr i32 %arg, %arg1
br label %bb2
bb2: ; preds = %bb2, %bb
%i3 = phi i32 [ %i, %bb ], [ %i5, %bb2 ]
%i4 = tail call float @baz(i32 signext %i3)
%i5 = fptosi float %i4 to i32
%i6 = fcmp oeq float %i4, zeroinitializer
br i1 %i6, label %bb7, label %bb2
bb7: ; preds = %bb2
ret void
}
declare float @baz(i32 signext %i3)
define void @test7(i32 signext %arg, i32 signext %arg1) nounwind {
; RV64I-LABEL: test7:
; RV64I: # %bb.0: # %bb
; RV64I-NEXT: addi sp, sp, -48
; RV64I-NEXT: sd ra, 40(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s0, 32(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s1, 24(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s2, 16(sp) # 8-byte Folded Spill
; RV64I-NEXT: sd s3, 8(sp) # 8-byte Folded Spill
; RV64I-NEXT: lui a2, %hi(.LCPI6_0)
; RV64I-NEXT: ld s0, %lo(.LCPI6_0)(a2)
; RV64I-NEXT: lui a2, %hi(.LCPI6_1)
; RV64I-NEXT: ld s1, %lo(.LCPI6_1)(a2)
; RV64I-NEXT: lui a2, %hi(.LCPI6_2)
; RV64I-NEXT: ld s2, %lo(.LCPI6_2)(a2)
; RV64I-NEXT: lui a2, %hi(.LCPI6_3)
; RV64I-NEXT: ld s3, %lo(.LCPI6_3)(a2)
; RV64I-NEXT: sraw a0, a0, a1
; RV64I-NEXT: .LBB6_1: # %bb2
; RV64I-NEXT: # =>This Inner Loop Header: Depth=1
; RV64I-NEXT: call foo@plt
; RV64I-NEXT: srli a1, a0, 1
; RV64I-NEXT: and a1, a1, s0
; RV64I-NEXT: sub a0, a0, a1
; RV64I-NEXT: and a1, a0, s1
; RV64I-NEXT: srli a0, a0, 2
; RV64I-NEXT: and a0, a0, s1
; RV64I-NEXT: add a0, a1, a0
; RV64I-NEXT: srli a1, a0, 4
; RV64I-NEXT: add a0, a0, a1
; RV64I-NEXT: and a0, a0, s2
; RV64I-NEXT: mul a0, a0, s3
; RV64I-NEXT: srli a0, a0, 56
; RV64I-NEXT: bnez a0, .LBB6_1
; RV64I-NEXT: # %bb.2: # %bb7
; RV64I-NEXT: ld ra, 40(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s0, 32(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s1, 24(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s2, 16(sp) # 8-byte Folded Reload
; RV64I-NEXT: ld s3, 8(sp) # 8-byte Folded Reload
; RV64I-NEXT: addi sp, sp, 48
; RV64I-NEXT: ret
;
; RV64ZBB-LABEL: test7:
; RV64ZBB: # %bb.0: # %bb
; RV64ZBB-NEXT: addi sp, sp, -16
; RV64ZBB-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; RV64ZBB-NEXT: sraw a0, a0, a1
; RV64ZBB-NEXT: .LBB6_1: # %bb2
; RV64ZBB-NEXT: # =>This Inner Loop Header: Depth=1
; RV64ZBB-NEXT: call foo@plt
; RV64ZBB-NEXT: cpop a0, a0
; RV64ZBB-NEXT: bnez a0, .LBB6_1
; RV64ZBB-NEXT: # %bb.2: # %bb7
; RV64ZBB-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; RV64ZBB-NEXT: addi sp, sp, 16
; RV64ZBB-NEXT: ret
;
; NOREMOVAL-LABEL: test7:
; NOREMOVAL: # %bb.0: # %bb
; NOREMOVAL-NEXT: addi sp, sp, -16
; NOREMOVAL-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; NOREMOVAL-NEXT: sraw a0, a0, a1
; NOREMOVAL-NEXT: .LBB6_1: # %bb2
; NOREMOVAL-NEXT: # =>This Inner Loop Header: Depth=1
; NOREMOVAL-NEXT: sext.w a0, a0
; NOREMOVAL-NEXT: call foo@plt
; NOREMOVAL-NEXT: cpop a0, a0
; NOREMOVAL-NEXT: bnez a0, .LBB6_1
; NOREMOVAL-NEXT: # %bb.2: # %bb7
; NOREMOVAL-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; NOREMOVAL-NEXT: addi sp, sp, 16
; NOREMOVAL-NEXT: ret
bb:
%i = ashr i32 %arg, %arg1
br label %bb2
bb2: ; preds = %bb2, %bb
%i3 = phi i32 [ %i, %bb ], [ %i6, %bb2 ]
%i4 = tail call signext i64 @foo(i32 signext %i3)
%i5 = tail call i64 @llvm.ctpop.i64(i64 %i4)
%i6 = trunc i64 %i5 to i32
%i7 = icmp eq i32 %i6, 0
br i1 %i7, label %bb7, label %bb2
bb7: ; preds = %bb2
ret void
}
declare i64 @llvm.ctpop.i64(i64)
define void @test8(i32 signext %arg, i32 signext %arg1) nounwind {
; CHECK-LABEL: test8:
; CHECK: # %bb.0: # %bb
; CHECK-NEXT: addi sp, sp, -16
; CHECK-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; CHECK-NEXT: sraw a0, a0, a1
; CHECK-NEXT: .LBB7_1: # %bb2
; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
; CHECK-NEXT: call foo@plt
; CHECK-NEXT: ori a0, a0, -256
; CHECK-NEXT: bnez a0, .LBB7_1
; CHECK-NEXT: # %bb.2: # %bb7
; CHECK-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; CHECK-NEXT: addi sp, sp, 16
; CHECK-NEXT: ret
;
; NOREMOVAL-LABEL: test8:
; NOREMOVAL: # %bb.0: # %bb
; NOREMOVAL-NEXT: addi sp, sp, -16
; NOREMOVAL-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; NOREMOVAL-NEXT: sraw a0, a0, a1
; NOREMOVAL-NEXT: .LBB7_1: # %bb2
; NOREMOVAL-NEXT: # =>This Inner Loop Header: Depth=1
; NOREMOVAL-NEXT: sext.w a0, a0
; NOREMOVAL-NEXT: call foo@plt
; NOREMOVAL-NEXT: ori a0, a0, -256
; NOREMOVAL-NEXT: bnez a0, .LBB7_1
; NOREMOVAL-NEXT: # %bb.2: # %bb7
; NOREMOVAL-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; NOREMOVAL-NEXT: addi sp, sp, 16
; NOREMOVAL-NEXT: ret
bb:
%i = ashr i32 %arg, %arg1
br label %bb2
bb2: ; preds = %bb2, %bb
%i3 = phi i32 [ %i, %bb ], [ %i6, %bb2 ]
%i4 = tail call signext i64 @foo(i32 signext %i3)
%i5 = or i64 %i4, -256
%i6 = trunc i64 %i5 to i32
%i7 = icmp eq i32 %i6, 0
br i1 %i7, label %bb7, label %bb2
bb7: ; preds = %bb2
ret void
}
declare i64 @foo(i32 signext)
define void @test9(i32 signext %arg, i32 signext %arg1) nounwind {
; CHECK-LABEL: test9:
; CHECK: # %bb.0: # %bb
; CHECK-NEXT: addi sp, sp, -16
; CHECK-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; CHECK-NEXT: sd s0, 0(sp) # 8-byte Folded Spill
; CHECK-NEXT: sraw a0, a0, a1
; CHECK-NEXT: li s0, 254
; CHECK-NEXT: .LBB8_1: # %bb2
; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
; CHECK-NEXT: call bar@plt
; CHECK-NEXT: mv a1, a0
; CHECK-NEXT: slti a0, a0, 255
; CHECK-NEXT: blt s0, a1, .LBB8_1
; CHECK-NEXT: # %bb.2: # %bb7
; CHECK-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; CHECK-NEXT: ld s0, 0(sp) # 8-byte Folded Reload
; CHECK-NEXT: addi sp, sp, 16
; CHECK-NEXT: ret
;
; NOREMOVAL-LABEL: test9:
; NOREMOVAL: # %bb.0: # %bb
; NOREMOVAL-NEXT: addi sp, sp, -16
; NOREMOVAL-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; NOREMOVAL-NEXT: sd s0, 0(sp) # 8-byte Folded Spill
; NOREMOVAL-NEXT: sraw a1, a0, a1
; NOREMOVAL-NEXT: li s0, 254
; NOREMOVAL-NEXT: .LBB8_1: # %bb2
; NOREMOVAL-NEXT: # =>This Inner Loop Header: Depth=1
; NOREMOVAL-NEXT: sext.w a0, a1
; NOREMOVAL-NEXT: call bar@plt
; NOREMOVAL-NEXT: slti a1, a0, 255
; NOREMOVAL-NEXT: blt s0, a0, .LBB8_1
; NOREMOVAL-NEXT: # %bb.2: # %bb7
; NOREMOVAL-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; NOREMOVAL-NEXT: ld s0, 0(sp) # 8-byte Folded Reload
; NOREMOVAL-NEXT: addi sp, sp, 16
; NOREMOVAL-NEXT: ret
bb:
%i = ashr i32 %arg, %arg1
br label %bb2
bb2: ; preds = %bb2, %bb
%i3 = phi i32 [ %i, %bb ], [ %i7, %bb2 ]
%i4 = tail call signext i32 @bar(i32 signext %i3)
%i5 = icmp slt i32 %i4, 255
%i6 = sext i1 %i5 to i32
%i7 = sub i32 0, %i6
br i1 %i5, label %bb7, label %bb2
bb7: ; preds = %bb2
ret void
}
define void @test10(i32 signext %arg, i32 signext %arg1) nounwind {
; CHECK-LABEL: test10:
; CHECK: # %bb.0: # %bb
; CHECK-NEXT: addi sp, sp, -16
; CHECK-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; CHECK-NEXT: fsw fs0, 4(sp) # 4-byte Folded Spill
; CHECK-NEXT: sraw a0, a0, a1
; CHECK-NEXT: fmv.w.x fs0, zero
; CHECK-NEXT: .LBB9_1: # %bb2
; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
; CHECK-NEXT: call baz@plt
; CHECK-NEXT: feq.s a1, fa0, fs0
; CHECK-NEXT: fmv.x.w a0, fa0
; CHECK-NEXT: beqz a1, .LBB9_1
; CHECK-NEXT: # %bb.2: # %bb7
; CHECK-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; CHECK-NEXT: flw fs0, 4(sp) # 4-byte Folded Reload
; CHECK-NEXT: addi sp, sp, 16
; CHECK-NEXT: ret
;
; NOREMOVAL-LABEL: test10:
; NOREMOVAL: # %bb.0: # %bb
; NOREMOVAL-NEXT: addi sp, sp, -16
; NOREMOVAL-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; NOREMOVAL-NEXT: fsw fs0, 4(sp) # 4-byte Folded Spill
; NOREMOVAL-NEXT: sraw a0, a0, a1
; NOREMOVAL-NEXT: fmv.w.x fs0, zero
; NOREMOVAL-NEXT: .LBB9_1: # %bb2
; NOREMOVAL-NEXT: # =>This Inner Loop Header: Depth=1
; NOREMOVAL-NEXT: sext.w a0, a0
; NOREMOVAL-NEXT: call baz@plt
; NOREMOVAL-NEXT: feq.s a1, fa0, fs0
; NOREMOVAL-NEXT: fmv.x.w a0, fa0
; NOREMOVAL-NEXT: beqz a1, .LBB9_1
; NOREMOVAL-NEXT: # %bb.2: # %bb7
; NOREMOVAL-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; NOREMOVAL-NEXT: flw fs0, 4(sp) # 4-byte Folded Reload
; NOREMOVAL-NEXT: addi sp, sp, 16
; NOREMOVAL-NEXT: ret
bb:
%i = ashr i32 %arg, %arg1
br label %bb2
bb2: ; preds = %bb2, %bb
%i3 = phi i32 [ %i, %bb ], [ %i5, %bb2 ]
%i4 = tail call float @baz(i32 signext %i3)
%i5 = bitcast float %i4 to i32
%i6 = fcmp oeq float %i4, zeroinitializer
br i1 %i6, label %bb7, label %bb2
bb7: ; preds = %bb2
ret void
}
; simple test for forward-searching. (and 1234) only uses lower word of input
define signext i32 @test11(i64 %arg1, i64 %arg2, i64 %arg3) {
; CHECK-LABEL: test11:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: addi a2, a2, -1
; CHECK-NEXT: li a3, 256
; CHECK-NEXT: .LBB10_1: # %bb2
; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
; CHECK-NEXT: andi a0, a0, 1234
; CHECK-NEXT: addi a2, a2, 1
; CHECK-NEXT: addw a0, a0, a1
; CHECK-NEXT: bltu a2, a3, .LBB10_1
; CHECK-NEXT: # %bb.2: # %bb7
; CHECK-NEXT: ret
;
; NOREMOVAL-LABEL: test11:
; NOREMOVAL: # %bb.0: # %entry
; NOREMOVAL-NEXT: addi a2, a2, -1
; NOREMOVAL-NEXT: li a3, 256
; NOREMOVAL-NEXT: .LBB10_1: # %bb2
; NOREMOVAL-NEXT: # =>This Inner Loop Header: Depth=1
; NOREMOVAL-NEXT: andi a0, a0, 1234
; NOREMOVAL-NEXT: addi a2, a2, 1
; NOREMOVAL-NEXT: add a0, a0, a1
; NOREMOVAL-NEXT: bltu a2, a3, .LBB10_1
; NOREMOVAL-NEXT: # %bb.2: # %bb7
; NOREMOVAL-NEXT: sext.w a0, a0
; NOREMOVAL-NEXT: ret
entry:
br label %bb2
bb2: ; preds = %bb2, %entry
%i1 = phi i64 [ %arg1, %entry ], [ %i5, %bb2 ]
%i2 = phi i64 [ %arg3, %entry ], [ %i3, %bb2 ]
%i3 = add i64 %i2, 1
%i4 = and i64 %i1, 1234
%i5 = add i64 %i4, %arg2
%i6 = icmp ugt i64 %i2, 255
br i1 %i6, label %bb7, label %bb2
bb7: ; preds = %bb2
%i7 = trunc i64 %i5 to i32
ret i32 %i7
}
; circular use-dependency and multiple transformations.
define signext i32 @test12(i64 %arg1, i64 %arg2, i64 %arg3) {
; CHECK-LABEL: test12:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: addi a3, a2, -1
; CHECK-NEXT: li a4, 256
; CHECK-NEXT: .LBB11_1: # %bb2
; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
; CHECK-NEXT: xor a0, a0, a1
; CHECK-NEXT: mulw a2, a0, a1
; CHECK-NEXT: addw a0, a0, a2
; CHECK-NEXT: and a2, a2, a0
; CHECK-NEXT: addi a3, a3, 1
; CHECK-NEXT: add a0, a2, a1
; CHECK-NEXT: bltu a3, a4, .LBB11_1
; CHECK-NEXT: # %bb.2: # %bb7
; CHECK-NEXT: mv a0, a2
; CHECK-NEXT: ret
;
; NOREMOVAL-LABEL: test12:
; NOREMOVAL: # %bb.0: # %entry
; NOREMOVAL-NEXT: addi a2, a2, -1
; NOREMOVAL-NEXT: li a3, 256
; NOREMOVAL-NEXT: .LBB11_1: # %bb2
; NOREMOVAL-NEXT: # =>This Inner Loop Header: Depth=1
; NOREMOVAL-NEXT: xor a0, a0, a1
; NOREMOVAL-NEXT: mul a4, a0, a1
; NOREMOVAL-NEXT: add a0, a0, a4
; NOREMOVAL-NEXT: and a4, a4, a0
; NOREMOVAL-NEXT: addi a2, a2, 1
; NOREMOVAL-NEXT: add a0, a4, a1
; NOREMOVAL-NEXT: bltu a2, a3, .LBB11_1
; NOREMOVAL-NEXT: # %bb.2: # %bb7
; NOREMOVAL-NEXT: sext.w a0, a4
; NOREMOVAL-NEXT: ret
entry:
br label %bb2
bb2: ; preds = %bb2, %entry
%i1 = phi i64 [ %arg1, %entry ], [ %i6, %bb2 ]
%i2 = phi i64 [ %arg3, %entry ], [ %i3, %bb2 ]
%i3 = add i64 %i2, 1
%i4 = xor i64 %i1, %arg2
%i5 = mul i64 %i4, %arg2
%i9 = add i64 %i4, %i5
%i8 = and i64 %i5, %i9
%i6 = add i64 %i8, %arg2
%i7 = icmp ugt i64 %i2, 255
br i1 %i7, label %bb7, label %bb2
bb7: ; preds = %bb2
%r = trunc i64 %i8 to i32
ret i32 %r
}
; Not optimized. sdiv doesn't only use lower word
define signext i32 @test13(i64 %arg1, i64 %arg2, i64 %arg3) {
; CHECK-LABEL: test13:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: addi a2, a2, -1
; CHECK-NEXT: li a3, 256
; CHECK-NEXT: .LBB12_1: # %bb2
; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
; CHECK-NEXT: div a0, a0, a1
; CHECK-NEXT: addi a2, a2, 1
; CHECK-NEXT: add a0, a0, a1
; CHECK-NEXT: bltu a2, a3, .LBB12_1
; CHECK-NEXT: # %bb.2: # %bb7
; CHECK-NEXT: sext.w a0, a0
; CHECK-NEXT: ret
;
; NOREMOVAL-LABEL: test13:
; NOREMOVAL: # %bb.0: # %entry
; NOREMOVAL-NEXT: addi a2, a2, -1
; NOREMOVAL-NEXT: li a3, 256
; NOREMOVAL-NEXT: .LBB12_1: # %bb2
; NOREMOVAL-NEXT: # =>This Inner Loop Header: Depth=1
; NOREMOVAL-NEXT: div a0, a0, a1
; NOREMOVAL-NEXT: addi a2, a2, 1
; NOREMOVAL-NEXT: add a0, a0, a1
; NOREMOVAL-NEXT: bltu a2, a3, .LBB12_1
; NOREMOVAL-NEXT: # %bb.2: # %bb7
; NOREMOVAL-NEXT: sext.w a0, a0
; NOREMOVAL-NEXT: ret
entry:
br label %bb2
bb2: ; preds = %bb2, %entry
%i1 = phi i64 [ %arg1, %entry ], [ %i5, %bb2 ]
%i2 = phi i64 [ %arg3, %entry ], [ %i3, %bb2 ]
%i3 = add i64 %i2, 1
%i4 = sdiv i64 %i1, %arg2
%i5 = add i64 %i4, %arg2
%i6 = icmp ugt i64 %i2, 255
br i1 %i6, label %bb7, label %bb2
bb7: ; preds = %bb2
%i8 = trunc i64 %i5 to i32
ret i32 %i8
}