forked from OSchip/llvm-project
Fix bug 9905: Failure in code selection for llvm intrinsics sqrt/exp (fix for FSQRT, FSIN, FCOS, FPOWI, FPOW, FLOG, FLOG2, FLOG10, FEXP, FEXP2).
llvm-svn: 146143
This commit is contained in:
Stepan Dyatkovskiy
parent
221e11e864
commit
a4bcf27dae
|
|
@ -468,13 +468,23 @@ ARMTargetLowering::ARMTargetLowering(TargetMachine &TM)
|
||||||
|
|
||||||
// v2f64 is legal so that QR subregs can be extracted as f64 elements, but
|
// v2f64 is legal so that QR subregs can be extracted as f64 elements, but
|
||||||
// neither Neon nor VFP support any arithmetic operations on it.
|
// neither Neon nor VFP support any arithmetic operations on it.
|
||||||
|
// The same with v4f32. But keep in mind that vadd, vsub, vmul are natively
|
||||||
|
// supported for v4f32.
|
||||||
setOperationAction(ISD::FADD, MVT::v2f64, Expand);
|
setOperationAction(ISD::FADD, MVT::v2f64, Expand);
|
||||||
setOperationAction(ISD::FSUB, MVT::v2f64, Expand);
|
setOperationAction(ISD::FSUB, MVT::v2f64, Expand);
|
||||||
setOperationAction(ISD::FMUL, MVT::v2f64, Expand);
|
setOperationAction(ISD::FMUL, MVT::v2f64, Expand);
|
||||||
|
// FIXME: Code duplication: FDIV and FREM are expanded always, see
|
||||||
|
// ARMTargetLowering::addTypeForNEON method for details.
|
||||||
setOperationAction(ISD::FDIV, MVT::v2f64, Expand);
|
setOperationAction(ISD::FDIV, MVT::v2f64, Expand);
|
||||||
setOperationAction(ISD::FREM, MVT::v2f64, Expand);
|
setOperationAction(ISD::FREM, MVT::v2f64, Expand);
|
||||||
|
// FIXME: Create unittest.
|
||||||
|
// In another words, find a way when "copysign" appears in DAG with vector
|
||||||
|
// operands.
|
||||||
setOperationAction(ISD::FCOPYSIGN, MVT::v2f64, Expand);
|
setOperationAction(ISD::FCOPYSIGN, MVT::v2f64, Expand);
|
||||||
|
// FIXME: Code duplication: SETCC has custom operation action, see
|
||||||
|
// ARMTargetLowering::addTypeForNEON method for details.
|
||||||
setOperationAction(ISD::SETCC, MVT::v2f64, Expand);
|
setOperationAction(ISD::SETCC, MVT::v2f64, Expand);
|
||||||
|
// FIXME: Create unittest for FNEG and for FABS.
|
||||||
setOperationAction(ISD::FNEG, MVT::v2f64, Expand);
|
setOperationAction(ISD::FNEG, MVT::v2f64, Expand);
|
||||||
setOperationAction(ISD::FABS, MVT::v2f64, Expand);
|
setOperationAction(ISD::FABS, MVT::v2f64, Expand);
|
||||||
setOperationAction(ISD::FSQRT, MVT::v2f64, Expand);
|
setOperationAction(ISD::FSQRT, MVT::v2f64, Expand);
|
||||||
|
|
@ -487,11 +497,23 @@ ARMTargetLowering::ARMTargetLowering(TargetMachine &TM)
|
||||||
setOperationAction(ISD::FLOG10, MVT::v2f64, Expand);
|
setOperationAction(ISD::FLOG10, MVT::v2f64, Expand);
|
||||||
setOperationAction(ISD::FEXP, MVT::v2f64, Expand);
|
setOperationAction(ISD::FEXP, MVT::v2f64, Expand);
|
||||||
setOperationAction(ISD::FEXP2, MVT::v2f64, Expand);
|
setOperationAction(ISD::FEXP2, MVT::v2f64, Expand);
|
||||||
|
// FIXME: Create unittest for FCEIL, FTRUNC, FRINT, FNEARBYINT, FFLOOR.
|
||||||
setOperationAction(ISD::FCEIL, MVT::v2f64, Expand);
|
setOperationAction(ISD::FCEIL, MVT::v2f64, Expand);
|
||||||
setOperationAction(ISD::FTRUNC, MVT::v2f64, Expand);
|
setOperationAction(ISD::FTRUNC, MVT::v2f64, Expand);
|
||||||
setOperationAction(ISD::FRINT, MVT::v2f64, Expand);
|
setOperationAction(ISD::FRINT, MVT::v2f64, Expand);
|
||||||
setOperationAction(ISD::FNEARBYINT, MVT::v2f64, Expand);
|
setOperationAction(ISD::FNEARBYINT, MVT::v2f64, Expand);
|
||||||
setOperationAction(ISD::FFLOOR, MVT::v2f64, Expand);
|
setOperationAction(ISD::FFLOOR, MVT::v2f64, Expand);
|
||||||
|
|
||||||
|
setOperationAction(ISD::FSQRT, MVT::v4f32, Expand);
|
||||||
|
setOperationAction(ISD::FSIN, MVT::v4f32, Expand);
|
||||||
|
setOperationAction(ISD::FCOS, MVT::v4f32, Expand);
|
||||||
|
setOperationAction(ISD::FPOWI, MVT::v4f32, Expand);
|
||||||
|
setOperationAction(ISD::FPOW, MVT::v4f32, Expand);
|
||||||
|
setOperationAction(ISD::FLOG, MVT::v4f32, Expand);
|
||||||
|
setOperationAction(ISD::FLOG2, MVT::v4f32, Expand);
|
||||||
|
setOperationAction(ISD::FLOG10, MVT::v4f32, Expand);
|
||||||
|
setOperationAction(ISD::FEXP, MVT::v4f32, Expand);
|
||||||
|
setOperationAction(ISD::FEXP2, MVT::v4f32, Expand);
|
||||||
|
|
||||||
// Neon does not support some operations on v1i64 and v2i64 types.
|
// Neon does not support some operations on v1i64 and v2i64 types.
|
||||||
setOperationAction(ISD::MUL, MVT::v1i64, Expand);
|
setOperationAction(ISD::MUL, MVT::v1i64, Expand);
|
||||||
|
|
|
||||||
|
|
@ -0,0 +1,302 @@
|
||||||
|
; RUN: llc < %s -march=arm -mcpu=cortex-a9 | FileCheck %s
|
||||||
|
|
||||||
|
@A = global <4 x float> <float 0., float 1., float 2., float 3.>
|
||||||
|
|
||||||
|
define void @test_sqrt(<4 x float>* %X) nounwind {
|
||||||
|
|
||||||
|
; CHECK: test_sqrt:
|
||||||
|
|
||||||
|
; CHECK: movw r1, :lower16:A
|
||||||
|
; CHECK-NEXT: movt r1, :upper16:A
|
||||||
|
; CHECK: vldmia r1, {[[short0:s[0-9]+]], [[short1:s[0-9]+]], [[short2:s[0-9]+]], [[short3:s[0-9]+]]}
|
||||||
|
; CHECK: vsqrt.f32 {{s[0-9]+}}, [[short3]]
|
||||||
|
; CHECK: vsqrt.f32 {{s[0-9]+}}, [[short2]]
|
||||||
|
; CHECK: vsqrt.f32 {{s[0-9]+}}, [[short1]]
|
||||||
|
; CHECK: vsqrt.f32 {{s[0-9]+}}, [[short0]]
|
||||||
|
; CHECK-NEXT: vstmia {{.*}}
|
||||||
|
|
||||||
|
L.entry:
|
||||||
|
%0 = load <4 x float>* @A, align 16
|
||||||
|
%1 = call <4 x float> @llvm.sqrt.v4f32(<4 x float> %0)
|
||||||
|
store <4 x float> %1, <4 x float>* %X, align 16
|
||||||
|
ret void
|
||||||
|
}
|
||||||
|
|
||||||
|
declare <4 x float> @llvm.sqrt.v4f32(<4 x float>) nounwind readonly
|
||||||
|
|
||||||
|
|
||||||
|
define void @test_cos(<4 x float>* %X) nounwind {
|
||||||
|
|
||||||
|
; CHECK: test_cos:
|
||||||
|
|
||||||
|
; CHECK: movw [[reg0:r[0-9]+]], :lower16:A
|
||||||
|
; CHECK-NEXT: movt [[reg0]], :upper16:A
|
||||||
|
; CHECK: vldmia [[reg0]], {{.*}}
|
||||||
|
|
||||||
|
; CHECK: {{[v]?mov}} r0, {{[r|s][0-9]+}}
|
||||||
|
; CHECK: bl cosf
|
||||||
|
|
||||||
|
; CHECK: {{[v]?mov}} r0, {{[r|s][0-9]+}}
|
||||||
|
; CHECK: bl cosf
|
||||||
|
|
||||||
|
; CHECK: {{[v]?mov}} r0, {{[r|s][0-9]+}}
|
||||||
|
; CHECK: bl cosf
|
||||||
|
|
||||||
|
; CHECK: {{[v]?mov}} r0, {{[r|s][0-9]+}}
|
||||||
|
; CHECK: bl cosf
|
||||||
|
|
||||||
|
; CHECK: vstmia {{.*}}
|
||||||
|
|
||||||
|
L.entry:
|
||||||
|
%0 = load <4 x float>* @A, align 16
|
||||||
|
%1 = call <4 x float> @llvm.cos.v4f32(<4 x float> %0)
|
||||||
|
store <4 x float> %1, <4 x float>* %X, align 16
|
||||||
|
ret void
|
||||||
|
}
|
||||||
|
|
||||||
|
declare <4 x float> @llvm.cos.v4f32(<4 x float>) nounwind readonly
|
||||||
|
|
||||||
|
define void @test_exp(<4 x float>* %X) nounwind {
|
||||||
|
|
||||||
|
; CHECK: test_exp:
|
||||||
|
|
||||||
|
; CHECK: movw [[reg0:r[0-9]+]], :lower16:A
|
||||||
|
; CHECK-NEXT: movt [[reg0]], :upper16:A
|
||||||
|
; CHECK: vldmia [[reg0]], {{.*}}
|
||||||
|
|
||||||
|
; CHECK: {{[v]?mov}} r0, {{[r|s][0-9]+}}
|
||||||
|
; CHECK: bl expf
|
||||||
|
|
||||||
|
; CHECK: {{[v]?mov}} r0, {{[r|s][0-9]+}}
|
||||||
|
; CHECK: bl expf
|
||||||
|
|
||||||
|
; CHECK: {{[v]?mov}} r0, {{[r|s][0-9]+}}
|
||||||
|
; CHECK: bl expf
|
||||||
|
|
||||||
|
; CHECK: {{[v]?mov}} r0, {{[r|s][0-9]+}}
|
||||||
|
; CHECK: bl expf
|
||||||
|
|
||||||
|
; CHECK: vstmia {{.*}}
|
||||||
|
|
||||||
|
L.entry:
|
||||||
|
%0 = load <4 x float>* @A, align 16
|
||||||
|
%1 = call <4 x float> @llvm.exp.v4f32(<4 x float> %0)
|
||||||
|
store <4 x float> %1, <4 x float>* %X, align 16
|
||||||
|
ret void
|
||||||
|
}
|
||||||
|
|
||||||
|
declare <4 x float> @llvm.exp.v4f32(<4 x float>) nounwind readonly
|
||||||
|
|
||||||
|
define void @test_exp2(<4 x float>* %X) nounwind {
|
||||||
|
|
||||||
|
; CHECK: test_exp2:
|
||||||
|
|
||||||
|
; CHECK: movw [[reg0:r[0-9]+]], :lower16:A
|
||||||
|
; CHECK-NEXT: movt [[reg0]], :upper16:A
|
||||||
|
; CHECK: vldmia [[reg0]], {{.*}}
|
||||||
|
|
||||||
|
; CHECK: {{[v]?mov}} r0, {{[r|s][0-9]+}}
|
||||||
|
; CHECK: bl exp2f
|
||||||
|
|
||||||
|
; CHECK: {{[v]?mov}} r0, {{[r|s][0-9]+}}
|
||||||
|
; CHECK: bl exp2f
|
||||||
|
|
||||||
|
; CHECK: {{[v]?mov}} r0, {{[r|s][0-9]+}}
|
||||||
|
; CHECK: bl exp2f
|
||||||
|
|
||||||
|
; CHECK: {{[v]?mov}} r0, {{[r|s][0-9]+}}
|
||||||
|
; CHECK: bl exp2f
|
||||||
|
|
||||||
|
; CHECK: vstmia {{.*}}
|
||||||
|
|
||||||
|
L.entry:
|
||||||
|
%0 = load <4 x float>* @A, align 16
|
||||||
|
%1 = call <4 x float> @llvm.exp2.v4f32(<4 x float> %0)
|
||||||
|
store <4 x float> %1, <4 x float>* %X, align 16
|
||||||
|
ret void
|
||||||
|
}
|
||||||
|
|
||||||
|
declare <4 x float> @llvm.exp2.v4f32(<4 x float>) nounwind readonly
|
||||||
|
|
||||||
|
define void @test_log10(<4 x float>* %X) nounwind {
|
||||||
|
|
||||||
|
; CHECK: test_log10:
|
||||||
|
|
||||||
|
; CHECK: movw [[reg0:r[0-9]+]], :lower16:A
|
||||||
|
; CHECK-NEXT: movt [[reg0]], :upper16:A
|
||||||
|
; CHECK: vldmia [[reg0]], {{.*}}
|
||||||
|
|
||||||
|
; CHECK: {{[v]?mov}} r0, {{[r|s][0-9]+}}
|
||||||
|
; CHECK: bl log10f
|
||||||
|
|
||||||
|
; CHECK: {{[v]?mov}} r0, {{[r|s][0-9]+}}
|
||||||
|
; CHECK: bl log10f
|
||||||
|
|
||||||
|
; CHECK: {{[v]?mov}} r0, {{[r|s][0-9]+}}
|
||||||
|
; CHECK: bl log10f
|
||||||
|
|
||||||
|
; CHECK: {{[v]?mov}} r0, {{[r|s][0-9]+}}
|
||||||
|
; CHECK: bl log10f
|
||||||
|
|
||||||
|
; CHECK: vstmia {{.*}}
|
||||||
|
|
||||||
|
L.entry:
|
||||||
|
%0 = load <4 x float>* @A, align 16
|
||||||
|
%1 = call <4 x float> @llvm.log10.v4f32(<4 x float> %0)
|
||||||
|
store <4 x float> %1, <4 x float>* %X, align 16
|
||||||
|
ret void
|
||||||
|
}
|
||||||
|
|
||||||
|
declare <4 x float> @llvm.log10.v4f32(<4 x float>) nounwind readonly
|
||||||
|
|
||||||
|
define void @test_log(<4 x float>* %X) nounwind {
|
||||||
|
|
||||||
|
; CHECK: test_log:
|
||||||
|
|
||||||
|
; CHECK: movw [[reg0:r[0-9]+]], :lower16:A
|
||||||
|
; CHECK-NEXT: movt [[reg0]], :upper16:A
|
||||||
|
; CHECK: vldmia [[reg0]], {{.*}}
|
||||||
|
|
||||||
|
; CHECK: {{[v]?mov}} r0, {{[r|s][0-9]+}}
|
||||||
|
; CHECK: bl logf
|
||||||
|
|
||||||
|
; CHECK: {{[v]?mov}} r0, {{[r|s][0-9]+}}
|
||||||
|
; CHECK: bl logf
|
||||||
|
|
||||||
|
; CHECK: {{[v]?mov}} r0, {{[r|s][0-9]+}}
|
||||||
|
; CHECK: bl logf
|
||||||
|
|
||||||
|
; CHECK: {{[v]?mov}} r0, {{[r|s][0-9]+}}
|
||||||
|
; CHECK: bl logf
|
||||||
|
|
||||||
|
; CHECK: vstmia {{.*}}
|
||||||
|
|
||||||
|
L.entry:
|
||||||
|
%0 = load <4 x float>* @A, align 16
|
||||||
|
%1 = call <4 x float> @llvm.log.v4f32(<4 x float> %0)
|
||||||
|
store <4 x float> %1, <4 x float>* %X, align 16
|
||||||
|
ret void
|
||||||
|
}
|
||||||
|
|
||||||
|
declare <4 x float> @llvm.log.v4f32(<4 x float>) nounwind readonly
|
||||||
|
|
||||||
|
define void @test_log2(<4 x float>* %X) nounwind {
|
||||||
|
|
||||||
|
; CHECK: test_log2:
|
||||||
|
|
||||||
|
; CHECK: movw [[reg0:r[0-9]+]], :lower16:A
|
||||||
|
; CHECK-NEXT: movt [[reg0]], :upper16:A
|
||||||
|
; CHECK: vldmia [[reg0]], {{.*}}
|
||||||
|
|
||||||
|
; CHECK: {{[v]?mov}} r0, {{[r|s][0-9]+}}
|
||||||
|
; CHECK: bl log2f
|
||||||
|
|
||||||
|
; CHECK: {{[v]?mov}} r0, {{[r|s][0-9]+}}
|
||||||
|
; CHECK: bl log2f
|
||||||
|
|
||||||
|
; CHECK: {{[v]?mov}} r0, {{[r|s][0-9]+}}
|
||||||
|
; CHECK: bl log2f
|
||||||
|
|
||||||
|
; CHECK: {{[v]?mov}} r0, {{[r|s][0-9]+}}
|
||||||
|
; CHECK: bl log2f
|
||||||
|
|
||||||
|
; CHECK: vstmia {{.*}}
|
||||||
|
|
||||||
|
L.entry:
|
||||||
|
%0 = load <4 x float>* @A, align 16
|
||||||
|
%1 = call <4 x float> @llvm.log2.v4f32(<4 x float> %0)
|
||||||
|
store <4 x float> %1, <4 x float>* %X, align 16
|
||||||
|
ret void
|
||||||
|
}
|
||||||
|
|
||||||
|
declare <4 x float> @llvm.log2.v4f32(<4 x float>) nounwind readonly
|
||||||
|
|
||||||
|
|
||||||
|
define void @test_pow(<4 x float>* %X) nounwind {
|
||||||
|
|
||||||
|
; CHECK: test_pow:
|
||||||
|
|
||||||
|
; CHECK: movw [[reg0:r[0-9]+]], :lower16:A
|
||||||
|
; CHECK-NEXT: movt [[reg0]], :upper16:A
|
||||||
|
; CHECK: vldmia [[reg0]], {{.*}}
|
||||||
|
|
||||||
|
; CHECK: {{[v]?mov}} r0, {{[r|s][0-9]+}}
|
||||||
|
; CHECK: bl powf
|
||||||
|
|
||||||
|
; CHECK: {{[v]?mov}} r0, {{[r|s][0-9]+}}
|
||||||
|
; CHECK: bl powf
|
||||||
|
|
||||||
|
; CHECK: {{[v]?mov}} r0, {{[r|s][0-9]+}}
|
||||||
|
; CHECK: bl powf
|
||||||
|
|
||||||
|
; CHECK: {{[v]?mov}} r0, {{[r|s][0-9]+}}
|
||||||
|
; CHECK: bl powf
|
||||||
|
|
||||||
|
; CHECK: vstmia {{.*}}
|
||||||
|
|
||||||
|
L.entry:
|
||||||
|
|
||||||
|
%0 = load <4 x float>* @A, align 16
|
||||||
|
%1 = call <4 x float> @llvm.pow.v4f32(<4 x float> %0, <4 x float> <float 2., float 2., float 2., float 2.>)
|
||||||
|
|
||||||
|
store <4 x float> %1, <4 x float>* %X, align 16
|
||||||
|
|
||||||
|
ret void
|
||||||
|
}
|
||||||
|
|
||||||
|
declare <4 x float> @llvm.pow.v4f32(<4 x float>, <4 x float>) nounwind readonly
|
||||||
|
|
||||||
|
define void @test_powi(<4 x float>* %X) nounwind {
|
||||||
|
|
||||||
|
; CHECK: test_powi:
|
||||||
|
|
||||||
|
; CHECK: movw [[reg0:r[0-9]+]], :lower16:A
|
||||||
|
; CHECK-NEXT: movt [[reg0]], :upper16:A
|
||||||
|
; CHECK-NEXT: vldmia [[reg0]], {{.*}}
|
||||||
|
; CHECK: vmul.f32 {{.*}}
|
||||||
|
|
||||||
|
; CHECK: vstmia {{.*}}
|
||||||
|
|
||||||
|
L.entry:
|
||||||
|
|
||||||
|
%0 = load <4 x float>* @A, align 16
|
||||||
|
%1 = call <4 x float> @llvm.powi.v4f32(<4 x float> %0, i32 2)
|
||||||
|
|
||||||
|
store <4 x float> %1, <4 x float>* %X, align 16
|
||||||
|
|
||||||
|
ret void
|
||||||
|
}
|
||||||
|
|
||||||
|
declare <4 x float> @llvm.powi.v4f32(<4 x float>, i32) nounwind readonly
|
||||||
|
|
||||||
|
define void @test_sin(<4 x float>* %X) nounwind {
|
||||||
|
|
||||||
|
; CHECK: test_sin:
|
||||||
|
|
||||||
|
; CHECK: movw [[reg0:r[0-9]+]], :lower16:A
|
||||||
|
; CHECK-NEXT: movt [[reg0]], :upper16:A
|
||||||
|
; CHECK: vldmia [[reg0]], {{.*}}
|
||||||
|
|
||||||
|
; CHECK: {{[v]?mov}} r0, {{[r|s][0-9]+}}
|
||||||
|
; CHECK: bl sinf
|
||||||
|
|
||||||
|
; CHECK: {{[v]?mov}} r0, {{[r|s][0-9]+}}
|
||||||
|
; CHECK: bl sinf
|
||||||
|
|
||||||
|
; CHECK: {{[v]?mov}} r0, {{[r|s][0-9]+}}
|
||||||
|
; CHECK: bl sinf
|
||||||
|
|
||||||
|
; CHECK: {{[v]?mov}} r0, {{[r|s][0-9]+}}
|
||||||
|
; CHECK: bl sinf
|
||||||
|
|
||||||
|
; CHECK: vstmia {{.*}}
|
||||||
|
|
||||||
|
L.entry:
|
||||||
|
%0 = load <4 x float>* @A, align 16
|
||||||
|
%1 = call <4 x float> @llvm.sin.v4f32(<4 x float> %0)
|
||||||
|
store <4 x float> %1, <4 x float>* %X, align 16
|
||||||
|
ret void
|
||||||
|
}
|
||||||
|
|
||||||
|
declare <4 x float> @llvm.sin.v4f32(<4 x float>) nounwind readonly
|
||||||
|
|
||||||
Loading…
Reference in New Issue