Revert "[LoongArch] Lowering flog2 to flogb (#162978)"
This reverts commit d9e5e725ed33e462477d5559ffece0d08e9c8dad. The semantics of `flog2(x)` and `logb(x)` are different. Fixes: https://github.com/llvm/llvm-project/issues/176818 Reviewers: zhaoqi5, SixWeining, ylzsx Pull Request: https://github.com/llvm/llvm-project/pull/176850
This commit is contained in:
wanglei
GitHub
parent
55818365cf
commit
009e0ccbbc
@ -375,7 +375,6 @@ def : Pat<(f32 (uint_to_fp (i64 (sexti32 (i64 GPR:$src))))),
|
||||
// FP Rounding
|
||||
let Predicates = [HasBasicF, IsLA64] in {
|
||||
def : PatFpr<frint, FRINT_S, FPR32>;
|
||||
def : PatFpr<flog2, FLOGB_S, FPR32>;
|
||||
} // Predicates = [HasBasicF, IsLA64]
|
||||
|
||||
let Predicates = [HasBasicF, IsLA32] in {
|
||||
|
||||
@ -352,7 +352,6 @@ def : Pat<(bitconvert FPR64:$src), (MOVFR2GR_D FPR64:$src)>;
|
||||
// FP Rounding
|
||||
let Predicates = [HasBasicD, IsLA64] in {
|
||||
def : PatFpr<frint, FRINT_D, FPR64>;
|
||||
def : PatFpr<flog2, FLOGB_D, FPR64>;
|
||||
} // Predicates = [HasBasicD, IsLA64]
|
||||
|
||||
/// Pseudo-instructions needed for the soft-float ABI with LA32D
|
||||
|
||||
@ -245,10 +245,8 @@ LoongArchTargetLowering::LoongArchTargetLowering(const TargetMachine &TM,
|
||||
setOperationAction(ISD::FP_TO_BF16, MVT::f32,
|
||||
Subtarget.isSoftFPABI() ? LibCall : Custom);
|
||||
|
||||
if (Subtarget.is64Bit()) {
|
||||
if (Subtarget.is64Bit())
|
||||
setOperationAction(ISD::FRINT, MVT::f32, Legal);
|
||||
setOperationAction(ISD::FLOG2, MVT::f32, Legal);
|
||||
}
|
||||
|
||||
if (!Subtarget.hasBasicD()) {
|
||||
setOperationAction(ISD::FP_TO_UINT, MVT::i32, Custom);
|
||||
@ -294,10 +292,8 @@ LoongArchTargetLowering::LoongArchTargetLowering(const TargetMachine &TM,
|
||||
setOperationAction(ISD::FP_TO_BF16, MVT::f64,
|
||||
Subtarget.isSoftFPABI() ? LibCall : Custom);
|
||||
|
||||
if (Subtarget.is64Bit()) {
|
||||
if (Subtarget.is64Bit())
|
||||
setOperationAction(ISD::FRINT, MVT::f64, Legal);
|
||||
setOperationAction(ISD::FLOG2, MVT::f64, Legal);
|
||||
}
|
||||
}
|
||||
|
||||
// Set operations for 'LSX' feature.
|
||||
@ -369,7 +365,6 @@ LoongArchTargetLowering::LoongArchTargetLowering(const TargetMachine &TM,
|
||||
setOperationAction(ISD::FMA, VT, Legal);
|
||||
setOperationAction(ISD::FSQRT, VT, Legal);
|
||||
setOperationAction(ISD::FNEG, VT, Legal);
|
||||
setOperationAction(ISD::FLOG2, VT, Legal);
|
||||
setCondCodeAction({ISD::SETGE, ISD::SETGT, ISD::SETOGE, ISD::SETOGT,
|
||||
ISD::SETUGE, ISD::SETUGT},
|
||||
VT, Expand);
|
||||
@ -459,7 +454,6 @@ LoongArchTargetLowering::LoongArchTargetLowering(const TargetMachine &TM,
|
||||
setOperationAction(ISD::FMA, VT, Legal);
|
||||
setOperationAction(ISD::FSQRT, VT, Legal);
|
||||
setOperationAction(ISD::FNEG, VT, Legal);
|
||||
setOperationAction(ISD::FLOG2, VT, Legal);
|
||||
setCondCodeAction({ISD::SETGE, ISD::SETGT, ISD::SETOGE, ISD::SETOGT,
|
||||
ISD::SETUGE, ISD::SETUGT},
|
||||
VT, Expand);
|
||||
|
||||
@ -1606,9 +1606,6 @@ def : Pat<(fma_nsz (fneg v4f64:$xj), v4f64:$xk, v4f64:$xa),
|
||||
// XVFSQRT_{S/D}
|
||||
defm : PatXrF<fsqrt, "XVFSQRT">;
|
||||
|
||||
// XVFLOGB_{S/D}
|
||||
defm : PatXrF<flog2, "XVFLOGB">;
|
||||
|
||||
// XVRECIP_{S/D}
|
||||
def : Pat<(fdiv vsplatf32_fpimm_eq_1, v8f32:$xj),
|
||||
(XVFRECIP_S v8f32:$xj)>;
|
||||
|
||||
@ -1816,9 +1816,6 @@ def : Pat<(fma_nsz (fneg v2f64:$vj), v2f64:$vk, v2f64:$va),
|
||||
// VFSQRT_{S/D}
|
||||
defm : PatVrF<fsqrt, "VFSQRT">;
|
||||
|
||||
// VFLOGB_{S/D}
|
||||
defm : PatVrF<flog2, "VFLOGB">;
|
||||
|
||||
// VFRECIP_{S/D}
|
||||
def : Pat<(fdiv vsplatf32_fpimm_eq_1, v4f32:$vj),
|
||||
(VFRECIP_S v4f32:$vj)>;
|
||||
|
||||
@ -12,8 +12,8 @@ define float @flog2_s(float %x) nounwind {
|
||||
;
|
||||
; LA64-LABEL: flog2_s:
|
||||
; LA64: # %bb.0:
|
||||
; LA64-NEXT: flogb.s $fa0, $fa0
|
||||
; LA64-NEXT: ret
|
||||
; LA64-NEXT: pcaddu18i $t8, %call36(log2f)
|
||||
; LA64-NEXT: jr $t8
|
||||
%y = call float @llvm.log2.f32(float %x)
|
||||
ret float %y
|
||||
}
|
||||
@ -25,8 +25,8 @@ define double @flog2_d(double %x) nounwind {
|
||||
;
|
||||
; LA64-LABEL: flog2_d:
|
||||
; LA64: # %bb.0:
|
||||
; LA64-NEXT: flogb.d $fa0, $fa0
|
||||
; LA64-NEXT: ret
|
||||
; LA64-NEXT: pcaddu18i $t8, %call36(log2)
|
||||
; LA64-NEXT: jr $t8
|
||||
%y = call double @llvm.log2.f64(double %x)
|
||||
ret double %y
|
||||
}
|
||||
|
||||
@ -1,17 +1,166 @@
|
||||
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 6
|
||||
; RUN: llc --mtriple=loongarch32 --mattr=+32s,+lasx < %s | FileCheck %s
|
||||
; RUN: llc --mtriple=loongarch64 --mattr=+lasx < %s | FileCheck %s
|
||||
; RUN: llc --mtriple=loongarch32 --mattr=+32s,+lasx < %s | FileCheck %s --check-prefix=LA32
|
||||
; RUN: llc --mtriple=loongarch64 --mattr=+lasx < %s | FileCheck %s --check-prefix=LA64
|
||||
|
||||
declare <8 x float> @llvm.log2.v8f32(<8 x float>)
|
||||
declare <4 x double> @llvm.log2.v4f64(<4 x double>)
|
||||
|
||||
define void @flog2_v8f32(ptr %res, ptr %a) nounwind {
|
||||
; CHECK-LABEL: flog2_v8f32:
|
||||
; CHECK: # %bb.0: # %entry
|
||||
; CHECK-NEXT: xvld $xr0, $a1, 0
|
||||
; CHECK-NEXT: xvflogb.s $xr0, $xr0
|
||||
; CHECK-NEXT: xvst $xr0, $a0, 0
|
||||
; CHECK-NEXT: ret
|
||||
; LA32-LABEL: flog2_v8f32:
|
||||
; LA32: # %bb.0: # %entry
|
||||
; LA32-NEXT: addi.w $sp, $sp, -128
|
||||
; LA32-NEXT: st.w $ra, $sp, 124 # 4-byte Folded Spill
|
||||
; LA32-NEXT: st.w $fp, $sp, 120 # 4-byte Folded Spill
|
||||
; LA32-NEXT: xvld $xr0, $a1, 0
|
||||
; LA32-NEXT: xvst $xr0, $sp, 80 # 32-byte Folded Spill
|
||||
; LA32-NEXT: move $fp, $a0
|
||||
; LA32-NEXT: xvpickve.w $xr0, $xr0, 5
|
||||
; LA32-NEXT: # kill: def $f0 killed $f0 killed $xr0
|
||||
; LA32-NEXT: bl log2f
|
||||
; LA32-NEXT: # kill: def $f0 killed $f0 def $vr0
|
||||
; LA32-NEXT: vst $vr0, $sp, 48 # 16-byte Folded Spill
|
||||
; LA32-NEXT: xvld $xr0, $sp, 80 # 32-byte Folded Reload
|
||||
; LA32-NEXT: xvpickve.w $xr0, $xr0, 4
|
||||
; LA32-NEXT: # kill: def $f0 killed $f0 killed $xr0
|
||||
; LA32-NEXT: bl log2f
|
||||
; LA32-NEXT: # kill: def $f0 killed $f0 def $xr0
|
||||
; LA32-NEXT: vld $vr1, $sp, 48 # 16-byte Folded Reload
|
||||
; LA32-NEXT: vextrins.w $vr0, $vr1, 16
|
||||
; LA32-NEXT: xvst $xr0, $sp, 48 # 32-byte Folded Spill
|
||||
; LA32-NEXT: xvld $xr0, $sp, 80 # 32-byte Folded Reload
|
||||
; LA32-NEXT: xvpickve.w $xr0, $xr0, 6
|
||||
; LA32-NEXT: # kill: def $f0 killed $f0 killed $xr0
|
||||
; LA32-NEXT: bl log2f
|
||||
; LA32-NEXT: # kill: def $f0 killed $f0 def $vr0
|
||||
; LA32-NEXT: xvld $xr1, $sp, 48 # 32-byte Folded Reload
|
||||
; LA32-NEXT: vextrins.w $vr1, $vr0, 32
|
||||
; LA32-NEXT: xvst $xr1, $sp, 48 # 32-byte Folded Spill
|
||||
; LA32-NEXT: xvld $xr0, $sp, 80 # 32-byte Folded Reload
|
||||
; LA32-NEXT: xvpickve.w $xr0, $xr0, 7
|
||||
; LA32-NEXT: # kill: def $f0 killed $f0 killed $xr0
|
||||
; LA32-NEXT: bl log2f
|
||||
; LA32-NEXT: # kill: def $f0 killed $f0 def $vr0
|
||||
; LA32-NEXT: xvld $xr1, $sp, 48 # 32-byte Folded Reload
|
||||
; LA32-NEXT: vextrins.w $vr1, $vr0, 48
|
||||
; LA32-NEXT: xvst $xr1, $sp, 48 # 32-byte Folded Spill
|
||||
; LA32-NEXT: xvld $xr0, $sp, 80 # 32-byte Folded Reload
|
||||
; LA32-NEXT: xvpickve.w $xr0, $xr0, 1
|
||||
; LA32-NEXT: # kill: def $f0 killed $f0 killed $xr0
|
||||
; LA32-NEXT: bl log2f
|
||||
; LA32-NEXT: # kill: def $f0 killed $f0 def $vr0
|
||||
; LA32-NEXT: vst $vr0, $sp, 16 # 16-byte Folded Spill
|
||||
; LA32-NEXT: xvld $xr0, $sp, 80 # 32-byte Folded Reload
|
||||
; LA32-NEXT: xvpickve.w $xr0, $xr0, 0
|
||||
; LA32-NEXT: # kill: def $f0 killed $f0 killed $xr0
|
||||
; LA32-NEXT: bl log2f
|
||||
; LA32-NEXT: # kill: def $f0 killed $f0 def $xr0
|
||||
; LA32-NEXT: vld $vr1, $sp, 16 # 16-byte Folded Reload
|
||||
; LA32-NEXT: vextrins.w $vr0, $vr1, 16
|
||||
; LA32-NEXT: xvst $xr0, $sp, 16 # 32-byte Folded Spill
|
||||
; LA32-NEXT: xvld $xr0, $sp, 80 # 32-byte Folded Reload
|
||||
; LA32-NEXT: xvpickve.w $xr0, $xr0, 2
|
||||
; LA32-NEXT: # kill: def $f0 killed $f0 killed $xr0
|
||||
; LA32-NEXT: bl log2f
|
||||
; LA32-NEXT: # kill: def $f0 killed $f0 def $vr0
|
||||
; LA32-NEXT: xvld $xr1, $sp, 16 # 32-byte Folded Reload
|
||||
; LA32-NEXT: vextrins.w $vr1, $vr0, 32
|
||||
; LA32-NEXT: xvst $xr1, $sp, 16 # 32-byte Folded Spill
|
||||
; LA32-NEXT: xvld $xr0, $sp, 80 # 32-byte Folded Reload
|
||||
; LA32-NEXT: xvpickve.w $xr0, $xr0, 3
|
||||
; LA32-NEXT: # kill: def $f0 killed $f0 killed $xr0
|
||||
; LA32-NEXT: bl log2f
|
||||
; LA32-NEXT: # kill: def $f0 killed $f0 def $vr0
|
||||
; LA32-NEXT: xvld $xr1, $sp, 16 # 32-byte Folded Reload
|
||||
; LA32-NEXT: vextrins.w $vr1, $vr0, 48
|
||||
; LA32-NEXT: xvld $xr0, $sp, 48 # 32-byte Folded Reload
|
||||
; LA32-NEXT: xvpermi.q $xr1, $xr0, 2
|
||||
; LA32-NEXT: xvst $xr1, $fp, 0
|
||||
; LA32-NEXT: ld.w $fp, $sp, 120 # 4-byte Folded Reload
|
||||
; LA32-NEXT: ld.w $ra, $sp, 124 # 4-byte Folded Reload
|
||||
; LA32-NEXT: addi.w $sp, $sp, 128
|
||||
; LA32-NEXT: ret
|
||||
;
|
||||
; LA64-LABEL: flog2_v8f32:
|
||||
; LA64: # %bb.0: # %entry
|
||||
; LA64-NEXT: addi.d $sp, $sp, -128
|
||||
; LA64-NEXT: st.d $ra, $sp, 120 # 8-byte Folded Spill
|
||||
; LA64-NEXT: st.d $fp, $sp, 112 # 8-byte Folded Spill
|
||||
; LA64-NEXT: xvld $xr0, $a1, 0
|
||||
; LA64-NEXT: xvst $xr0, $sp, 80 # 32-byte Folded Spill
|
||||
; LA64-NEXT: move $fp, $a0
|
||||
; LA64-NEXT: xvpickve.w $xr0, $xr0, 5
|
||||
; LA64-NEXT: # kill: def $f0 killed $f0 killed $xr0
|
||||
; LA64-NEXT: pcaddu18i $ra, %call36(log2f)
|
||||
; LA64-NEXT: jirl $ra, $ra, 0
|
||||
; LA64-NEXT: # kill: def $f0 killed $f0 def $vr0
|
||||
; LA64-NEXT: vst $vr0, $sp, 48 # 16-byte Folded Spill
|
||||
; LA64-NEXT: xvld $xr0, $sp, 80 # 32-byte Folded Reload
|
||||
; LA64-NEXT: xvpickve.w $xr0, $xr0, 4
|
||||
; LA64-NEXT: # kill: def $f0 killed $f0 killed $xr0
|
||||
; LA64-NEXT: pcaddu18i $ra, %call36(log2f)
|
||||
; LA64-NEXT: jirl $ra, $ra, 0
|
||||
; LA64-NEXT: # kill: def $f0 killed $f0 def $xr0
|
||||
; LA64-NEXT: vld $vr1, $sp, 48 # 16-byte Folded Reload
|
||||
; LA64-NEXT: vextrins.w $vr0, $vr1, 16
|
||||
; LA64-NEXT: xvst $xr0, $sp, 48 # 32-byte Folded Spill
|
||||
; LA64-NEXT: xvld $xr0, $sp, 80 # 32-byte Folded Reload
|
||||
; LA64-NEXT: xvpickve.w $xr0, $xr0, 6
|
||||
; LA64-NEXT: # kill: def $f0 killed $f0 killed $xr0
|
||||
; LA64-NEXT: pcaddu18i $ra, %call36(log2f)
|
||||
; LA64-NEXT: jirl $ra, $ra, 0
|
||||
; LA64-NEXT: # kill: def $f0 killed $f0 def $vr0
|
||||
; LA64-NEXT: xvld $xr1, $sp, 48 # 32-byte Folded Reload
|
||||
; LA64-NEXT: vextrins.w $vr1, $vr0, 32
|
||||
; LA64-NEXT: xvst $xr1, $sp, 48 # 32-byte Folded Spill
|
||||
; LA64-NEXT: xvld $xr0, $sp, 80 # 32-byte Folded Reload
|
||||
; LA64-NEXT: xvpickve.w $xr0, $xr0, 7
|
||||
; LA64-NEXT: # kill: def $f0 killed $f0 killed $xr0
|
||||
; LA64-NEXT: pcaddu18i $ra, %call36(log2f)
|
||||
; LA64-NEXT: jirl $ra, $ra, 0
|
||||
; LA64-NEXT: # kill: def $f0 killed $f0 def $vr0
|
||||
; LA64-NEXT: xvld $xr1, $sp, 48 # 32-byte Folded Reload
|
||||
; LA64-NEXT: vextrins.w $vr1, $vr0, 48
|
||||
; LA64-NEXT: xvst $xr1, $sp, 48 # 32-byte Folded Spill
|
||||
; LA64-NEXT: xvld $xr0, $sp, 80 # 32-byte Folded Reload
|
||||
; LA64-NEXT: xvpickve.w $xr0, $xr0, 1
|
||||
; LA64-NEXT: # kill: def $f0 killed $f0 killed $xr0
|
||||
; LA64-NEXT: pcaddu18i $ra, %call36(log2f)
|
||||
; LA64-NEXT: jirl $ra, $ra, 0
|
||||
; LA64-NEXT: # kill: def $f0 killed $f0 def $vr0
|
||||
; LA64-NEXT: vst $vr0, $sp, 16 # 16-byte Folded Spill
|
||||
; LA64-NEXT: xvld $xr0, $sp, 80 # 32-byte Folded Reload
|
||||
; LA64-NEXT: xvpickve.w $xr0, $xr0, 0
|
||||
; LA64-NEXT: # kill: def $f0 killed $f0 killed $xr0
|
||||
; LA64-NEXT: pcaddu18i $ra, %call36(log2f)
|
||||
; LA64-NEXT: jirl $ra, $ra, 0
|
||||
; LA64-NEXT: # kill: def $f0 killed $f0 def $xr0
|
||||
; LA64-NEXT: vld $vr1, $sp, 16 # 16-byte Folded Reload
|
||||
; LA64-NEXT: vextrins.w $vr0, $vr1, 16
|
||||
; LA64-NEXT: xvst $xr0, $sp, 16 # 32-byte Folded Spill
|
||||
; LA64-NEXT: xvld $xr0, $sp, 80 # 32-byte Folded Reload
|
||||
; LA64-NEXT: xvpickve.w $xr0, $xr0, 2
|
||||
; LA64-NEXT: # kill: def $f0 killed $f0 killed $xr0
|
||||
; LA64-NEXT: pcaddu18i $ra, %call36(log2f)
|
||||
; LA64-NEXT: jirl $ra, $ra, 0
|
||||
; LA64-NEXT: # kill: def $f0 killed $f0 def $vr0
|
||||
; LA64-NEXT: xvld $xr1, $sp, 16 # 32-byte Folded Reload
|
||||
; LA64-NEXT: vextrins.w $vr1, $vr0, 32
|
||||
; LA64-NEXT: xvst $xr1, $sp, 16 # 32-byte Folded Spill
|
||||
; LA64-NEXT: xvld $xr0, $sp, 80 # 32-byte Folded Reload
|
||||
; LA64-NEXT: xvpickve.w $xr0, $xr0, 3
|
||||
; LA64-NEXT: # kill: def $f0 killed $f0 killed $xr0
|
||||
; LA64-NEXT: pcaddu18i $ra, %call36(log2f)
|
||||
; LA64-NEXT: jirl $ra, $ra, 0
|
||||
; LA64-NEXT: # kill: def $f0 killed $f0 def $vr0
|
||||
; LA64-NEXT: xvld $xr1, $sp, 16 # 32-byte Folded Reload
|
||||
; LA64-NEXT: vextrins.w $vr1, $vr0, 48
|
||||
; LA64-NEXT: xvld $xr0, $sp, 48 # 32-byte Folded Reload
|
||||
; LA64-NEXT: xvpermi.q $xr1, $xr0, 2
|
||||
; LA64-NEXT: xvst $xr1, $fp, 0
|
||||
; LA64-NEXT: ld.d $fp, $sp, 112 # 8-byte Folded Reload
|
||||
; LA64-NEXT: ld.d $ra, $sp, 120 # 8-byte Folded Reload
|
||||
; LA64-NEXT: addi.d $sp, $sp, 128
|
||||
; LA64-NEXT: ret
|
||||
entry:
|
||||
%v = load <8 x float>, ptr %a
|
||||
%r = call <8 x float> @llvm.log2.v8f32(<8 x float> %v)
|
||||
@ -20,12 +169,93 @@ entry:
|
||||
}
|
||||
|
||||
define void @flog2_v4f64(ptr %res, ptr %a) nounwind {
|
||||
; CHECK-LABEL: flog2_v4f64:
|
||||
; CHECK: # %bb.0: # %entry
|
||||
; CHECK-NEXT: xvld $xr0, $a1, 0
|
||||
; CHECK-NEXT: xvflogb.d $xr0, $xr0
|
||||
; CHECK-NEXT: xvst $xr0, $a0, 0
|
||||
; CHECK-NEXT: ret
|
||||
; LA32-LABEL: flog2_v4f64:
|
||||
; LA32: # %bb.0: # %entry
|
||||
; LA32-NEXT: addi.w $sp, $sp, -112
|
||||
; LA32-NEXT: st.w $ra, $sp, 108 # 4-byte Folded Spill
|
||||
; LA32-NEXT: st.w $fp, $sp, 104 # 4-byte Folded Spill
|
||||
; LA32-NEXT: xvld $xr0, $a1, 0
|
||||
; LA32-NEXT: xvst $xr0, $sp, 64 # 32-byte Folded Spill
|
||||
; LA32-NEXT: move $fp, $a0
|
||||
; LA32-NEXT: xvpickve.d $xr0, $xr0, 3
|
||||
; LA32-NEXT: # kill: def $f0_64 killed $f0_64 killed $xr0
|
||||
; LA32-NEXT: bl log2
|
||||
; LA32-NEXT: # kill: def $f0_64 killed $f0_64 def $vr0
|
||||
; LA32-NEXT: vst $vr0, $sp, 32 # 16-byte Folded Spill
|
||||
; LA32-NEXT: xvld $xr0, $sp, 64 # 32-byte Folded Reload
|
||||
; LA32-NEXT: xvpickve.d $xr0, $xr0, 2
|
||||
; LA32-NEXT: # kill: def $f0_64 killed $f0_64 killed $xr0
|
||||
; LA32-NEXT: bl log2
|
||||
; LA32-NEXT: # kill: def $f0_64 killed $f0_64 def $xr0
|
||||
; LA32-NEXT: vld $vr1, $sp, 32 # 16-byte Folded Reload
|
||||
; LA32-NEXT: vextrins.d $vr0, $vr1, 16
|
||||
; LA32-NEXT: xvst $xr0, $sp, 32 # 32-byte Folded Spill
|
||||
; LA32-NEXT: xvld $xr0, $sp, 64 # 32-byte Folded Reload
|
||||
; LA32-NEXT: xvpickve.d $xr0, $xr0, 1
|
||||
; LA32-NEXT: # kill: def $f0_64 killed $f0_64 killed $xr0
|
||||
; LA32-NEXT: bl log2
|
||||
; LA32-NEXT: # kill: def $f0_64 killed $f0_64 def $vr0
|
||||
; LA32-NEXT: vst $vr0, $sp, 16 # 16-byte Folded Spill
|
||||
; LA32-NEXT: xvld $xr0, $sp, 64 # 32-byte Folded Reload
|
||||
; LA32-NEXT: xvpickve.d $xr0, $xr0, 0
|
||||
; LA32-NEXT: # kill: def $f0_64 killed $f0_64 killed $xr0
|
||||
; LA32-NEXT: bl log2
|
||||
; LA32-NEXT: # kill: def $f0_64 killed $f0_64 def $xr0
|
||||
; LA32-NEXT: vld $vr1, $sp, 16 # 16-byte Folded Reload
|
||||
; LA32-NEXT: vextrins.d $vr0, $vr1, 16
|
||||
; LA32-NEXT: xvld $xr1, $sp, 32 # 32-byte Folded Reload
|
||||
; LA32-NEXT: xvpermi.q $xr0, $xr1, 2
|
||||
; LA32-NEXT: xvst $xr0, $fp, 0
|
||||
; LA32-NEXT: ld.w $fp, $sp, 104 # 4-byte Folded Reload
|
||||
; LA32-NEXT: ld.w $ra, $sp, 108 # 4-byte Folded Reload
|
||||
; LA32-NEXT: addi.w $sp, $sp, 112
|
||||
; LA32-NEXT: ret
|
||||
;
|
||||
; LA64-LABEL: flog2_v4f64:
|
||||
; LA64: # %bb.0: # %entry
|
||||
; LA64-NEXT: addi.d $sp, $sp, -112
|
||||
; LA64-NEXT: st.d $ra, $sp, 104 # 8-byte Folded Spill
|
||||
; LA64-NEXT: st.d $fp, $sp, 96 # 8-byte Folded Spill
|
||||
; LA64-NEXT: xvld $xr0, $a1, 0
|
||||
; LA64-NEXT: xvst $xr0, $sp, 64 # 32-byte Folded Spill
|
||||
; LA64-NEXT: move $fp, $a0
|
||||
; LA64-NEXT: xvpickve.d $xr0, $xr0, 3
|
||||
; LA64-NEXT: # kill: def $f0_64 killed $f0_64 killed $xr0
|
||||
; LA64-NEXT: pcaddu18i $ra, %call36(log2)
|
||||
; LA64-NEXT: jirl $ra, $ra, 0
|
||||
; LA64-NEXT: # kill: def $f0_64 killed $f0_64 def $vr0
|
||||
; LA64-NEXT: vst $vr0, $sp, 32 # 16-byte Folded Spill
|
||||
; LA64-NEXT: xvld $xr0, $sp, 64 # 32-byte Folded Reload
|
||||
; LA64-NEXT: xvpickve.d $xr0, $xr0, 2
|
||||
; LA64-NEXT: # kill: def $f0_64 killed $f0_64 killed $xr0
|
||||
; LA64-NEXT: pcaddu18i $ra, %call36(log2)
|
||||
; LA64-NEXT: jirl $ra, $ra, 0
|
||||
; LA64-NEXT: # kill: def $f0_64 killed $f0_64 def $xr0
|
||||
; LA64-NEXT: vld $vr1, $sp, 32 # 16-byte Folded Reload
|
||||
; LA64-NEXT: vextrins.d $vr0, $vr1, 16
|
||||
; LA64-NEXT: xvst $xr0, $sp, 32 # 32-byte Folded Spill
|
||||
; LA64-NEXT: xvld $xr0, $sp, 64 # 32-byte Folded Reload
|
||||
; LA64-NEXT: xvpickve.d $xr0, $xr0, 1
|
||||
; LA64-NEXT: # kill: def $f0_64 killed $f0_64 killed $xr0
|
||||
; LA64-NEXT: pcaddu18i $ra, %call36(log2)
|
||||
; LA64-NEXT: jirl $ra, $ra, 0
|
||||
; LA64-NEXT: # kill: def $f0_64 killed $f0_64 def $vr0
|
||||
; LA64-NEXT: vst $vr0, $sp, 16 # 16-byte Folded Spill
|
||||
; LA64-NEXT: xvld $xr0, $sp, 64 # 32-byte Folded Reload
|
||||
; LA64-NEXT: xvpickve.d $xr0, $xr0, 0
|
||||
; LA64-NEXT: # kill: def $f0_64 killed $f0_64 killed $xr0
|
||||
; LA64-NEXT: pcaddu18i $ra, %call36(log2)
|
||||
; LA64-NEXT: jirl $ra, $ra, 0
|
||||
; LA64-NEXT: # kill: def $f0_64 killed $f0_64 def $xr0
|
||||
; LA64-NEXT: vld $vr1, $sp, 16 # 16-byte Folded Reload
|
||||
; LA64-NEXT: vextrins.d $vr0, $vr1, 16
|
||||
; LA64-NEXT: xvld $xr1, $sp, 32 # 32-byte Folded Reload
|
||||
; LA64-NEXT: xvpermi.q $xr0, $xr1, 2
|
||||
; LA64-NEXT: xvst $xr0, $fp, 0
|
||||
; LA64-NEXT: ld.d $fp, $sp, 96 # 8-byte Folded Reload
|
||||
; LA64-NEXT: ld.d $ra, $sp, 104 # 8-byte Folded Reload
|
||||
; LA64-NEXT: addi.d $sp, $sp, 112
|
||||
; LA64-NEXT: ret
|
||||
entry:
|
||||
%v = load <4 x double>, ptr %a
|
||||
%r = call <4 x double> @llvm.log2.v4f64(<4 x double> %v)
|
||||
|
||||
@ -1,17 +1,98 @@
|
||||
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 6
|
||||
; RUN: llc --mtriple=loongarch32 --mattr=+32s,+lsx < %s | FileCheck %s
|
||||
; RUN: llc --mtriple=loongarch64 --mattr=+lsx < %s | FileCheck %s
|
||||
; RUN: llc --mtriple=loongarch32 --mattr=+32s,+lsx < %s | FileCheck %s --check-prefix=LA32
|
||||
; RUN: llc --mtriple=loongarch64 --mattr=+lsx < %s | FileCheck %s --check-prefix=LA64
|
||||
|
||||
declare <4 x float> @llvm.log2.v4f32(<4 x float>)
|
||||
declare <2 x double> @llvm.log2.v2f64(<2 x double>)
|
||||
|
||||
define void @flog2_v4f32(ptr %res, ptr %a) nounwind {
|
||||
; CHECK-LABEL: flog2_v4f32:
|
||||
; CHECK: # %bb.0: # %entry
|
||||
; CHECK-NEXT: vld $vr0, $a1, 0
|
||||
; CHECK-NEXT: vflogb.s $vr0, $vr0
|
||||
; CHECK-NEXT: vst $vr0, $a0, 0
|
||||
; CHECK-NEXT: ret
|
||||
; LA32-LABEL: flog2_v4f32:
|
||||
; LA32: # %bb.0: # %entry
|
||||
; LA32-NEXT: addi.w $sp, $sp, -48
|
||||
; LA32-NEXT: st.w $ra, $sp, 44 # 4-byte Folded Spill
|
||||
; LA32-NEXT: st.w $fp, $sp, 40 # 4-byte Folded Spill
|
||||
; LA32-NEXT: vld $vr0, $a1, 0
|
||||
; LA32-NEXT: vst $vr0, $sp, 16 # 16-byte Folded Spill
|
||||
; LA32-NEXT: move $fp, $a0
|
||||
; LA32-NEXT: vreplvei.w $vr0, $vr0, 1
|
||||
; LA32-NEXT: # kill: def $f0 killed $f0 killed $vr0
|
||||
; LA32-NEXT: bl log2f
|
||||
; LA32-NEXT: # kill: def $f0 killed $f0 def $vr0
|
||||
; LA32-NEXT: vst $vr0, $sp, 0 # 16-byte Folded Spill
|
||||
; LA32-NEXT: vld $vr0, $sp, 16 # 16-byte Folded Reload
|
||||
; LA32-NEXT: vreplvei.w $vr0, $vr0, 0
|
||||
; LA32-NEXT: # kill: def $f0 killed $f0 killed $vr0
|
||||
; LA32-NEXT: bl log2f
|
||||
; LA32-NEXT: # kill: def $f0 killed $f0 def $vr0
|
||||
; LA32-NEXT: vld $vr1, $sp, 0 # 16-byte Folded Reload
|
||||
; LA32-NEXT: vextrins.w $vr0, $vr1, 16
|
||||
; LA32-NEXT: vst $vr0, $sp, 0 # 16-byte Folded Spill
|
||||
; LA32-NEXT: vld $vr0, $sp, 16 # 16-byte Folded Reload
|
||||
; LA32-NEXT: vreplvei.w $vr0, $vr0, 2
|
||||
; LA32-NEXT: # kill: def $f0 killed $f0 killed $vr0
|
||||
; LA32-NEXT: bl log2f
|
||||
; LA32-NEXT: # kill: def $f0 killed $f0 def $vr0
|
||||
; LA32-NEXT: vld $vr1, $sp, 0 # 16-byte Folded Reload
|
||||
; LA32-NEXT: vextrins.w $vr1, $vr0, 32
|
||||
; LA32-NEXT: vst $vr1, $sp, 0 # 16-byte Folded Spill
|
||||
; LA32-NEXT: vld $vr0, $sp, 16 # 16-byte Folded Reload
|
||||
; LA32-NEXT: vreplvei.w $vr0, $vr0, 3
|
||||
; LA32-NEXT: # kill: def $f0 killed $f0 killed $vr0
|
||||
; LA32-NEXT: bl log2f
|
||||
; LA32-NEXT: # kill: def $f0 killed $f0 def $vr0
|
||||
; LA32-NEXT: vld $vr1, $sp, 0 # 16-byte Folded Reload
|
||||
; LA32-NEXT: vextrins.w $vr1, $vr0, 48
|
||||
; LA32-NEXT: vst $vr1, $fp, 0
|
||||
; LA32-NEXT: ld.w $fp, $sp, 40 # 4-byte Folded Reload
|
||||
; LA32-NEXT: ld.w $ra, $sp, 44 # 4-byte Folded Reload
|
||||
; LA32-NEXT: addi.w $sp, $sp, 48
|
||||
; LA32-NEXT: ret
|
||||
;
|
||||
; LA64-LABEL: flog2_v4f32:
|
||||
; LA64: # %bb.0: # %entry
|
||||
; LA64-NEXT: addi.d $sp, $sp, -48
|
||||
; LA64-NEXT: st.d $ra, $sp, 40 # 8-byte Folded Spill
|
||||
; LA64-NEXT: st.d $fp, $sp, 32 # 8-byte Folded Spill
|
||||
; LA64-NEXT: vld $vr0, $a1, 0
|
||||
; LA64-NEXT: vst $vr0, $sp, 16 # 16-byte Folded Spill
|
||||
; LA64-NEXT: move $fp, $a0
|
||||
; LA64-NEXT: vreplvei.w $vr0, $vr0, 1
|
||||
; LA64-NEXT: # kill: def $f0 killed $f0 killed $vr0
|
||||
; LA64-NEXT: pcaddu18i $ra, %call36(log2f)
|
||||
; LA64-NEXT: jirl $ra, $ra, 0
|
||||
; LA64-NEXT: # kill: def $f0 killed $f0 def $vr0
|
||||
; LA64-NEXT: vst $vr0, $sp, 0 # 16-byte Folded Spill
|
||||
; LA64-NEXT: vld $vr0, $sp, 16 # 16-byte Folded Reload
|
||||
; LA64-NEXT: vreplvei.w $vr0, $vr0, 0
|
||||
; LA64-NEXT: # kill: def $f0 killed $f0 killed $vr0
|
||||
; LA64-NEXT: pcaddu18i $ra, %call36(log2f)
|
||||
; LA64-NEXT: jirl $ra, $ra, 0
|
||||
; LA64-NEXT: # kill: def $f0 killed $f0 def $vr0
|
||||
; LA64-NEXT: vld $vr1, $sp, 0 # 16-byte Folded Reload
|
||||
; LA64-NEXT: vextrins.w $vr0, $vr1, 16
|
||||
; LA64-NEXT: vst $vr0, $sp, 0 # 16-byte Folded Spill
|
||||
; LA64-NEXT: vld $vr0, $sp, 16 # 16-byte Folded Reload
|
||||
; LA64-NEXT: vreplvei.w $vr0, $vr0, 2
|
||||
; LA64-NEXT: # kill: def $f0 killed $f0 killed $vr0
|
||||
; LA64-NEXT: pcaddu18i $ra, %call36(log2f)
|
||||
; LA64-NEXT: jirl $ra, $ra, 0
|
||||
; LA64-NEXT: # kill: def $f0 killed $f0 def $vr0
|
||||
; LA64-NEXT: vld $vr1, $sp, 0 # 16-byte Folded Reload
|
||||
; LA64-NEXT: vextrins.w $vr1, $vr0, 32
|
||||
; LA64-NEXT: vst $vr1, $sp, 0 # 16-byte Folded Spill
|
||||
; LA64-NEXT: vld $vr0, $sp, 16 # 16-byte Folded Reload
|
||||
; LA64-NEXT: vreplvei.w $vr0, $vr0, 3
|
||||
; LA64-NEXT: # kill: def $f0 killed $f0 killed $vr0
|
||||
; LA64-NEXT: pcaddu18i $ra, %call36(log2f)
|
||||
; LA64-NEXT: jirl $ra, $ra, 0
|
||||
; LA64-NEXT: # kill: def $f0 killed $f0 def $vr0
|
||||
; LA64-NEXT: vld $vr1, $sp, 0 # 16-byte Folded Reload
|
||||
; LA64-NEXT: vextrins.w $vr1, $vr0, 48
|
||||
; LA64-NEXT: vst $vr1, $fp, 0
|
||||
; LA64-NEXT: ld.d $fp, $sp, 32 # 8-byte Folded Reload
|
||||
; LA64-NEXT: ld.d $ra, $sp, 40 # 8-byte Folded Reload
|
||||
; LA64-NEXT: addi.d $sp, $sp, 48
|
||||
; LA64-NEXT: ret
|
||||
entry:
|
||||
%v = load <4 x float>, ptr %a
|
||||
%r = call <4 x float> @llvm.log2.v4f32(<4 x float> %v)
|
||||
@ -20,12 +101,59 @@ entry:
|
||||
}
|
||||
|
||||
define void @flog2_v2f64(ptr %res, ptr %a) nounwind {
|
||||
; CHECK-LABEL: flog2_v2f64:
|
||||
; CHECK: # %bb.0: # %entry
|
||||
; CHECK-NEXT: vld $vr0, $a1, 0
|
||||
; CHECK-NEXT: vflogb.d $vr0, $vr0
|
||||
; CHECK-NEXT: vst $vr0, $a0, 0
|
||||
; CHECK-NEXT: ret
|
||||
; LA32-LABEL: flog2_v2f64:
|
||||
; LA32: # %bb.0: # %entry
|
||||
; LA32-NEXT: addi.w $sp, $sp, -48
|
||||
; LA32-NEXT: st.w $ra, $sp, 44 # 4-byte Folded Spill
|
||||
; LA32-NEXT: st.w $fp, $sp, 40 # 4-byte Folded Spill
|
||||
; LA32-NEXT: vld $vr0, $a1, 0
|
||||
; LA32-NEXT: vst $vr0, $sp, 0 # 16-byte Folded Spill
|
||||
; LA32-NEXT: move $fp, $a0
|
||||
; LA32-NEXT: vreplvei.d $vr0, $vr0, 1
|
||||
; LA32-NEXT: # kill: def $f0_64 killed $f0_64 killed $vr0
|
||||
; LA32-NEXT: bl log2
|
||||
; LA32-NEXT: # kill: def $f0_64 killed $f0_64 def $vr0
|
||||
; LA32-NEXT: vst $vr0, $sp, 16 # 16-byte Folded Spill
|
||||
; LA32-NEXT: vld $vr0, $sp, 0 # 16-byte Folded Reload
|
||||
; LA32-NEXT: vreplvei.d $vr0, $vr0, 0
|
||||
; LA32-NEXT: # kill: def $f0_64 killed $f0_64 killed $vr0
|
||||
; LA32-NEXT: bl log2
|
||||
; LA32-NEXT: # kill: def $f0_64 killed $f0_64 def $vr0
|
||||
; LA32-NEXT: vld $vr1, $sp, 16 # 16-byte Folded Reload
|
||||
; LA32-NEXT: vextrins.d $vr0, $vr1, 16
|
||||
; LA32-NEXT: vst $vr0, $fp, 0
|
||||
; LA32-NEXT: ld.w $fp, $sp, 40 # 4-byte Folded Reload
|
||||
; LA32-NEXT: ld.w $ra, $sp, 44 # 4-byte Folded Reload
|
||||
; LA32-NEXT: addi.w $sp, $sp, 48
|
||||
; LA32-NEXT: ret
|
||||
;
|
||||
; LA64-LABEL: flog2_v2f64:
|
||||
; LA64: # %bb.0: # %entry
|
||||
; LA64-NEXT: addi.d $sp, $sp, -48
|
||||
; LA64-NEXT: st.d $ra, $sp, 40 # 8-byte Folded Spill
|
||||
; LA64-NEXT: st.d $fp, $sp, 32 # 8-byte Folded Spill
|
||||
; LA64-NEXT: vld $vr0, $a1, 0
|
||||
; LA64-NEXT: vst $vr0, $sp, 0 # 16-byte Folded Spill
|
||||
; LA64-NEXT: move $fp, $a0
|
||||
; LA64-NEXT: vreplvei.d $vr0, $vr0, 1
|
||||
; LA64-NEXT: # kill: def $f0_64 killed $f0_64 killed $vr0
|
||||
; LA64-NEXT: pcaddu18i $ra, %call36(log2)
|
||||
; LA64-NEXT: jirl $ra, $ra, 0
|
||||
; LA64-NEXT: # kill: def $f0_64 killed $f0_64 def $vr0
|
||||
; LA64-NEXT: vst $vr0, $sp, 16 # 16-byte Folded Spill
|
||||
; LA64-NEXT: vld $vr0, $sp, 0 # 16-byte Folded Reload
|
||||
; LA64-NEXT: vreplvei.d $vr0, $vr0, 0
|
||||
; LA64-NEXT: # kill: def $f0_64 killed $f0_64 killed $vr0
|
||||
; LA64-NEXT: pcaddu18i $ra, %call36(log2)
|
||||
; LA64-NEXT: jirl $ra, $ra, 0
|
||||
; LA64-NEXT: # kill: def $f0_64 killed $f0_64 def $vr0
|
||||
; LA64-NEXT: vld $vr1, $sp, 16 # 16-byte Folded Reload
|
||||
; LA64-NEXT: vextrins.d $vr0, $vr1, 16
|
||||
; LA64-NEXT: vst $vr0, $fp, 0
|
||||
; LA64-NEXT: ld.d $fp, $sp, 32 # 8-byte Folded Reload
|
||||
; LA64-NEXT: ld.d $ra, $sp, 40 # 8-byte Folded Reload
|
||||
; LA64-NEXT: addi.d $sp, $sp, 48
|
||||
; LA64-NEXT: ret
|
||||
entry:
|
||||
%v = load <2 x double>, ptr %a
|
||||
%r = call <2 x double> @llvm.log2.v2f64(<2 x double> %v)
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user