[AArch64] Properly validate the reciprocal estimation.

Add check for legal data types when expanding into a Newton series.

Differential Revision: https://reviews.llvm.org/D22267

llvm-svn: 276041

3 files changed, 114 insertions, 4 deletions

diff --git a/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp b/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
index d6f2a190d4c..26e3b21b640 100644
--- a/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
+++ b/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
@@ -4568,6 +4568,12 @@ static SDValue getEstimate(const AArch64Subtarget &ST,
     return SDValue();
 
   EVT VT = Operand.getValueType();
+  if (VT != MVT::f64 && VT != MVT::v1f64 && VT != MVT::v2f64 &&
+      VT != MVT::f32 && VT != MVT::v1f32 &&
+      VT != MVT::v2f32 && VT != MVT::v4f32 &&
+      (!ST.hasFullFP16() ||
+       (VT != MVT::f16 && VT != MVT::v4f16 && VT != MVT::v8f16)))
+    return SDValue();
 
   std::string RecipOp;
   RecipOp = Opcode == (AArch64ISD::FRECPE) ? "div": "sqrt";
diff --git a/llvm/test/CodeGen/AArch64/recp-fastmath.ll b/llvm/test/CodeGen/AArch64/recp-fastmath.ll
index 710739b2cc5..1cecdba96ba 100644
--- a/llvm/test/CodeGen/AArch64/recp-fastmath.ll
+++ b/llvm/test/CodeGen/AArch64/recp-fastmath.ll
@@ -46,6 +46,23 @@ define <4 x float> @f4recp(<4 x float> %x) #0 {
 ; CHECK-NEXT: frecpe
 }
 
+define <8 x float> @f8recp(<8 x float> %x) #0 {
+  %div = fdiv fast <8 x float> <float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0, float 1.0>, %x
+  ret <8 x float> %div
+
+; FAULT-LABEL: f8recp:
+; FAULT-NEXT: BB#0
+; FAULT-NEXT: fmov
+; FAULT-NEXT: fdiv
+; FAULT-NEXT: fdiv
+
+; CHECK-LABEL: f8recp:
+; CHECK-NEXT: BB#0
+; CHECK-NEXT: fmov
+; CHECK-NEXT: frecpe
+; CHECK: frecpe
+}
+
 define double @drecp(double %x) #0 {
   %div = fdiv fast double 1.0, %x
   ret double %div
@@ -76,4 +93,21 @@ define <2 x double> @d2recp(<2 x double> %x) #0 {
 ; CHECK-NEXT: frecpe
 }
 
+define <4 x double> @d4recp(<4 x double> %x) #0 {
+  %div = fdiv fast <4 x double> <double 1.0, double 1.0, double 1.0, double 1.0>, %x
+  ret <4 x double> %div
+
+; FAULT-LABEL: d4recp:
+; FAULT-NEXT: BB#0
+; FAULT-NEXT: fmov
+; FAULT-NEXT: fdiv
+; FAULT-NEXT: fdiv
+
+; CHECK-LABEL: d4recp:
+; CHECK-NEXT: BB#0
+; CHECK-NEXT: fmov
+; CHECK-NEXT: frecpe
+; CHECK: frecpe
+}
+
 attributes #0 = { nounwind "unsafe-fp-math"="true" }
diff --git a/llvm/test/CodeGen/AArch64/sqrt-fastmath.ll b/llvm/test/CodeGen/AArch64/sqrt-fastmath.ll
index 0d9533fd27f..962c7d80a65 100644
--- a/llvm/test/CodeGen/AArch64/sqrt-fastmath.ll
+++ b/llvm/test/CodeGen/AArch64/sqrt-fastmath.ll
@@ -1,13 +1,15 @@
-; RUN: llc < %s -mtriple=aarch64 -mattr=neon -recip=!sqrt,!vec-sqrt | FileCheck %s --check-prefix=FAULT
-; RUN: llc < %s -mtriple=aarch64 -mattr=neon -recip=sqrt,vec-sqrt   | FileCheck %s
-; RUN: llc < %s -mtriple=aarch64 -mattr=neon,-use-reverse-square-root  | FileCheck %s --check-prefix=FAULT
+; RUN: llc < %s -mtriple=aarch64 -mattr=neon -recip=!sqrt,!vec-sqrt   | FileCheck %s --check-prefix=FAULT
+; RUN: llc < %s -mtriple=aarch64 -mattr=neon,-use-reverse-square-root | FileCheck %s --check-prefix=FAULT
+; RUN: llc < %s -mtriple=aarch64 -mattr=neon -recip=sqrt,vec-sqrt     | FileCheck %s
 ; RUN: llc < %s -mtriple=aarch64 -mattr=neon,+use-reverse-square-root | FileCheck %s
 
 declare float @llvm.sqrt.f32(float) #1
-declare double @llvm.sqrt.f64(double) #1
 declare <2 x float> @llvm.sqrt.v2f32(<2 x float>) #1
 declare <4 x float> @llvm.sqrt.v4f32(<4 x float>) #1
+declare <8 x float> @llvm.sqrt.v8f32(<8 x float>) #1
+declare double @llvm.sqrt.f64(double) #1
 declare <2 x double> @llvm.sqrt.v2f64(<2 x double>) #1
+declare <4 x double> @llvm.sqrt.v4f64(<4 x double>) #1
 
 define float @fsqrt(float %a) #0 {
   %1 = tail call fast float @llvm.sqrt.f32(float %a)
@@ -53,6 +55,23 @@ define <4 x float> @f4sqrt(<4 x float> %a) #0 {
 ; CHECK-NEXT: frsqrte
 }
 
+define <8 x float> @f8sqrt(<8 x float> %a) #0 {
+  %1 = tail call fast <8 x float> @llvm.sqrt.v8f32(<8 x float> %a) #2
+  ret <8 x float> %1
+
+; FAULT-LABEL: f8sqrt:
+; FAULT-NEXT: BB#0
+; FAULT-NEXT: fsqrt
+; FAULT-NEXT: fsqrt
+
+; CHECK-LABEL: f8sqrt:
+; CHECK-NEXT: BB#0
+; CHECK-NEXT: fmov
+; CHECK-NEXT: mov
+; CHECK-NEXT: frsqrte
+; CHECK: frsqrte
+}
+
 define double @dsqrt(double %a) #0 {
   %1 = tail call fast double @llvm.sqrt.f64(double %a)
   ret double %1
@@ -82,6 +101,23 @@ define <2 x double> @d2sqrt(<2 x double> %a) #0 {
 ; CHECK-NEXT: frsqrte
 }
 
+define <4 x double> @d4sqrt(<4 x double> %a) #0 {
+  %1 = tail call fast <4 x double> @llvm.sqrt.v4f64(<4 x double> %a) #4
+  ret <4 x double> %1
+
+; FAULT-LABEL: d4sqrt:
+; FAULT-NEXT: BB#0
+; FAULT-NEXT: fsqrt
+; FAULT-NEXT: fsqrt
+
+; CHECK-LABEL: d4sqrt:
+; CHECK-NEXT: BB#0
+; CHECK-NEXT: fmov
+; CHECK-NEXT: mov
+; CHECK-NEXT: frsqrte
+; CHECK: frsqrte
+}
+
 define float @frsqrt(float %a) #0 {
   %1 = tail call fast float @llvm.sqrt.f32(float %a)
   %2 = fdiv fast float 1.000000e+00, %1
@@ -127,6 +163,23 @@ define <4 x float> @f4rsqrt(<4 x float> %a) #0 {
 ; CHECK-NEXT: frsqrte
 }
 
+define <8 x float> @f8rsqrt(<8 x float> %a) #0 {
+  %1 = tail call fast <8 x float> @llvm.sqrt.v8f32(<8 x float> %a) #2
+  %2 = fdiv fast <8 x float> <float 1.000000e+00, float 1.000000e+00, float 1.000000e+00, float 1.000000e+00, float 1.000000e+00, float 1.000000e+00, float 1.000000e+00, float 1.000000e+00>, %1
+  ret <8 x float> %2
+
+; FAULT-LABEL: f8rsqrt:
+; FAULT-NEXT: BB#0
+; FAULT-NEXT: fsqrt
+; FAULT-NEXT: fsqrt
+
+; CHECK-LABEL: f8rsqrt:
+; CHECK-NEXT: BB#0
+; CHECK-NEXT: fmov
+; CHECK-NEXT: frsqrte
+; CHECK: frsqrte
+}
+
 define double @drsqrt(double %a) #0 {
   %1 = tail call fast double @llvm.sqrt.f64(double %a)
   %2 = fdiv fast double 1.000000e+00, %1
@@ -157,4 +210,21 @@ define <2 x double> @d2rsqrt(<2 x double> %a) #0 {
 ; CHECK-NEXT: frsqrte
 }
 
+define <4 x double> @d4rsqrt(<4 x double> %a) #0 {
+  %1 = tail call fast <4 x double> @llvm.sqrt.v4f64(<4 x double> %a) #4
+  %2 = fdiv fast <4 x double> <double 1.000000e+00, double 1.000000e+00, double 1.000000e+00, double 1.000000e+00>, %1
+  ret <4 x double> %2
+
+; FAULT-LABEL: d4rsqrt:
+; FAULT-NEXT: BB#0
+; FAULT-NEXT: fsqrt
+; FAULT-NEXT: fsqrt
+
+; CHECK-LABEL: d4rsqrt:
+; CHECK-NEXT: BB#0
+; CHECK-NEXT: fmov
+; CHECK-NEXT: frsqrte
+; CHECK: frsqrte
+}
+
 attributes #0 = { nounwind "unsafe-fp-math"="true" }