From: Evandro Menezes Date: Tue, 20 Sep 2016 19:02:02 +0000 (+0000) Subject: Revert "[AArch64] Properly validate the reciprocal estimation." X-Git-Url: https://granicus.if.org/sourcecode?a=commitdiff_plain;h=ba27f9fd81fd5253c7bbcc7e91d2213becba8a20;p=llvm Revert "[AArch64] Properly validate the reciprocal estimation." This reverts commit ad8ca1528242e2a4cb363e3779309e70eb7a430e per request by Eric Christopher (v. http://bit.ly/2cmz6kW). git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@281999 91177308-0d34-0410-b5e6-96231b3b80d8 --- diff --git a/lib/Target/AArch64/AArch64ISelLowering.cpp b/lib/Target/AArch64/AArch64ISelLowering.cpp index 7291be33276..1fca58241ed 100644 --- a/lib/Target/AArch64/AArch64ISelLowering.cpp +++ b/lib/Target/AArch64/AArch64ISelLowering.cpp @@ -4594,12 +4594,6 @@ 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/test/CodeGen/AArch64/recp-fastmath.ll b/test/CodeGen/AArch64/recp-fastmath.ll index 1cecdba96ba..710739b2cc5 100644 --- a/test/CodeGen/AArch64/recp-fastmath.ll +++ b/test/CodeGen/AArch64/recp-fastmath.ll @@ -46,23 +46,6 @@ 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> , %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 @@ -93,21 +76,4 @@ 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> , %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/test/CodeGen/AArch64/sqrt-fastmath.ll b/test/CodeGen/AArch64/sqrt-fastmath.ll index 962c7d80a65..0d9533fd27f 100644 --- a/test/CodeGen/AArch64/sqrt-fastmath.ll +++ b/test/CodeGen/AArch64/sqrt-fastmath.ll @@ -1,15 +1,13 @@ -; 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 -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,+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) @@ -55,23 +53,6 @@ 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 @@ -101,23 +82,6 @@ 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 @@ -163,23 +127,6 @@ 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> , %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 @@ -210,21 +157,4 @@ 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> , %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" }