return DAG.getNode(ISD::FSUB, DL, VT, N1IsFMul ? N0 : N1, Add, Flags);
}
- // FIXME: Auto-upgrade the target/function-level option.
- if (Options.NoSignedZerosFPMath || N->getFlags().hasNoSignedZeros()) {
- // fold (fadd A, 0) -> A
- if (ConstantFPSDNode *N1C = isConstOrConstSplatFP(N1))
- if (N1C->isZero())
- return N0;
+ ConstantFPSDNode *N1C = isConstOrConstSplatFP(N1);
+ if (N1C && N1C->isZero()) {
+ if (N1C->isNegative() || Options.UnsafeFPMath ||
+ Flags.hasNoSignedZeros()) {
+ // fold (fadd A, 0) -> A
+ return N0;
+ }
}
// No FP constant should be created after legalization as Instruction
// Selection pass has a hard time dealing with FP constants.
bool AllowNewConst = (Level < AfterLegalizeDAG);
- // TODO: fmf test for NaNs could be done here too
- if (Options.UnsafeFPMath && AllowNewConst) {
+ // If 'unsafe math' or nnan is enabled, fold lots of things.
+ if ((Options.UnsafeFPMath || Flags.hasNoNaNs()) && AllowNewConst) {
// If allowed, fold (fadd (fneg x), x) -> 0.0
if (N0.getOpcode() == ISD::FNEG && N0.getOperand(0) == N1)
return DAG.getConstantFP(0.0, DL, VT);
return DAG.getConstantFP(0.0, DL, VT);
}
- // If 'unsafe math' is enabled, fold lots of things.
- // TODO: fmf testing for reassoc/nsz could be done here too
- if (Options.UnsafeFPMath && AllowNewConst) {
+ // If 'unsafe math' or reassoc and nsz, fold lots of things.
+ // TODO: break out portions of the transformations below for which Unsafe is
+ // considered and which do not require both nsz and reassoc
+ if ((Options.UnsafeFPMath ||
+ (Flags.hasAllowReassociation() && Flags.hasNoSignedZeros())) &&
+ AllowNewConst) {
// fadd (fadd x, c1), c2 -> fadd x, c1 + c2
if (N1CFP && N0.getOpcode() == ISD::FADD &&
isConstantFPBuildVectorOrConstantFP(N0.getOperand(1))) {
case ISD::FMUL:
case ISD::FDIV:
case ISD::FREM:
- if (getTarget().Options.UnsafeFPMath) {
- if (Opcode == ISD::FADD) {
- // x+0 --> x
- if (N2CFP && N2CFP->getValueAPF().isZero())
- return N1;
- } else if (Opcode == ISD::FSUB) {
- // x-0 --> x
- if (N2CFP && N2CFP->getValueAPF().isZero())
- return N1;
- } else if (Opcode == ISD::FMUL) {
- // x*0 --> 0
- if (N2CFP && N2CFP->isZero())
- return N2;
- // x*1 --> x
- if (N2CFP && N2CFP->isExactlyValue(1.0))
- return N1;
- }
- }
assert(VT.isFloatingPoint() && "This operator only applies to FP types!");
assert(N1.getValueType() == N2.getValueType() &&
N1.getValueType() == VT && "Binary operator types must match!");
; CHECK-LABEL: fadd_const_multiuse_fmf:
; CHECK: // %bb.0:
; CHECK-NEXT: adrp x8, .LCPI7_0
+; CHECK-NEXT: adrp x9, .LCPI7_1
; CHECK-NEXT: ldr s1, [x8, :lo12:.LCPI7_0]
-; CHECK-NEXT: fadd s0, s0, s1
-; CHECK-NEXT: fmov s1, #17.00000000
+; CHECK-NEXT: ldr s2, [x9, :lo12:.LCPI7_1]
; CHECK-NEXT: fadd s1, s0, s1
-; CHECK-NEXT: fadd s0, s0, s1
+; CHECK-NEXT: fadd s0, s0, s2
+; CHECK-NEXT: fadd s0, s1, s0
; CHECK-NEXT: ret
%a1 = fadd float %x, 42.0
%a2 = fadd nsz reassoc float %a1, 17.0
; FUNC-LABEL: {{^}}fadd_0_nsz_attr_f32:
; SI-NOT: v_add_f32
define amdgpu_kernel void @fadd_0_nsz_attr_f32(float addrspace(1)* %out, float %a) #1 {
- %add = fadd float %a, 0.0
+ %add = fadd nsz float %a, 0.0
store float %add, float addrspace(1)* %out, align 4
ret void
}
define float @fast_fmuladd_opts(float %a , float %b , float %c) {
; X64-LABEL: fast_fmuladd_opts:
; X64: # %bb.0:
-; X64-NEXT: movaps %xmm0, %xmm1
-; X64-NEXT: addss %xmm0, %xmm1
-; X64-NEXT: addss %xmm0, %xmm1
-; X64-NEXT: movaps %xmm1, %xmm0
+; X64-NEXT: mulss {{.*}}(%rip), %xmm0
; X64-NEXT: retq
;
; X86-LABEL: fast_fmuladd_opts:
; X86: # %bb.0:
; X86-NEXT: flds {{[0-9]+}}(%esp)
-; X86-NEXT: fld %st(0)
-; X86-NEXT: fadd %st(1)
-; X86-NEXT: faddp %st(1)
+; X86-NEXT: fmuls {{.*}}
; X86-NEXT: retl
%res = call fast float @llvm.fmuladd.f32(float %a, float 2.0, float %a)
ret float %res
define double @not_so_fast_mul_add(double %x) {
; X64-LABEL: not_so_fast_mul_add:
; X64: # %bb.0:
-; X64-NEXT: movsd {{.*#+}} xmm1 = mem[0],zero
+; X64-NEXT: movsd {{.*}}(%rip), %xmm1
; X64-NEXT: mulsd %xmm0, %xmm1
-; X64-NEXT: addsd %xmm1, %xmm0
+; X64-NEXT: mulsd {{.*}}(%rip), %xmm0
; X64-NEXT: movsd %xmm1, {{.*}}(%rip)
; X64-NEXT: retq
;
; X86-NEXT: fldl {{[0-9]+}}(%esp)
; X86-NEXT: fld %st(0)
; X86-NEXT: fmull {{\.LCPI.*}}
-; X86-NEXT: fadd %st(0), %st(1)
+; X86-NEXT: fxch %st(1)
+; X86-NEXT: fmull {{\.LCPI.*}}
+; X86-NEXT: fxch %st(1)
; X86-NEXT: fstpl mul1
; X86-NEXT: retl
%m = fmul double %x, 4.2
}
define float @fadd_negzero(float %x) {
-; STRICT-LABEL: fadd_negzero:
-; STRICT: # %bb.0:
-; STRICT-NEXT: addss {{.*}}(%rip), %xmm0
-; STRICT-NEXT: retq
-;
-; UNSAFE-LABEL: fadd_negzero:
-; UNSAFE: # %bb.0:
-; UNSAFE-NEXT: retq
+; ANY-LABEL: fadd_negzero:
+; ANY: # %bb.0:
+; ANY-NEXT: retq
%r = fadd float %x, -0.0
ret float %r
}
+define float @fadd_produce_zero(float %x) {
+; ANY-LABEL: fadd_produce_zero:
+; ANY: # %bb.0:
+; ANY-NEXT: xorps %xmm0, %xmm0
+; ANY-NEXT: retq
+ %neg = fsub nsz float 0.0, %x
+ %r = fadd nnan float %neg, %x
+ ret float %r
+}
+
+define float @fadd_reassociate(float %x) {
+; ANY-LABEL: fadd_reassociate:
+; ANY: # %bb.0:
+; ANY-NEXT: addss {{.*}}(%rip), %xmm0
+; ANY-NEXT: retq
+ %sum = fadd float %x, 8.0
+ %r = fadd reassoc nsz float %sum, 12.0
+ ret float %r
+}
+
define float @fadd_negzero_nsz(float %x) {
; ANY-LABEL: fadd_negzero_nsz:
; ANY: # %bb.0: