6502/llvm-6502
1
0
Fork 0
mirror of https://github.com/c64scene-ar/llvm-6502.git synced 2024-12-21 00:32:23 +00:00
Code Issues Projects Releases Wiki Activity
8a3f50038f
llvm-6502/test/CodeGen/PowerPC/recipest.ll

227 lines
4.0 KiB
LLVM
Raw Normal View History

Use PPC reciprocal estimates with Newton iteration in fast-math mode When unsafe FP math operations are enabled, we can use the fre[s] and frsqrte[s] instructions, which generate reciprocal (sqrt) estimates, together with some Newton iteration, in order to quickly generate floating-point division and sqrt results. All of these instructions are separately optional, and so each has its own feature flag (except for the Altivec instructions, which are covered under the existing Altivec flag). Doing this is not only faster than using the IEEE-compliant fdiv/fsqrt instructions, but allows these computations to be pipelined with other computations in order to hide their overall latency. I've also added a couple of missing fnmsub patterns which turned out to be missing (but are necessary for good code generation of the Newton iterations). Altivec needs a similar fix, but that will probably be more complicated because fneg is expanded for Altivec's v4f32. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@178617 91177308-0d34-0410-b5e6-96231b3b80d8
2013-04-03 04:01:11 +00:00
; RUN: llc < %s -mtriple=powerpc64-unknown-linux-gnu -mcpu=pwr7 -enable-unsafe-fp-math | FileCheck %s
; RUN: llc < %s -mtriple=powerpc64-unknown-linux-gnu -mcpu=pwr7 | FileCheck -check-prefix=CHECK-SAFE %s
target datalayout = "E-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-f128:128:128-v128:128:128-n32:64"
target triple = "powerpc64-unknown-linux-gnu"
declare double @llvm.sqrt.f64(double)
declare float @llvm.sqrt.f32(float)
declare <4 x float> @llvm.sqrt.v4f32(<4 x float>)
define double @foo(double %a, double %b) nounwind {
entry:
%x = call double @llvm.sqrt.f64(double %b)
%r = fdiv double %a, %x
ret double %r
; CHECK: @foo
; CHECK: frsqrte
; CHECK: fnmsub
; CHECK: fmul
; CHECK: fmadd
; CHECK: fmul
; CHECK: fmul
; CHECK: fmadd
; CHECK: fmul
; CHECK: fmul
; CHECK: blr
; CHECK-SAFE: @foo
; CHECK-SAFE: fsqrt
; CHECK-SAFE: fdiv
; CHECK-SAFE: blr
}
PPC: Improve code generation for mixed-precision reciprocal sqrt The DAGCombine logic that recognized a/sqrt(b) and transformed it into a multiplication by the reciprocal sqrt did not handle cases where the sqrt and the division were separated by an fpext or fptrunc. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@178801 91177308-0d34-0410-b5e6-96231b3b80d8
2013-04-04 22:44:12 +00:00
define double @foof(double %a, float %b) nounwind {
entry:
%x = call float @llvm.sqrt.f32(float %b)
%y = fpext float %x to double
%r = fdiv double %a, %y
ret double %r
; CHECK: @foof
; CHECK: frsqrtes
; CHECK: fnmsubs
; CHECK: fmuls
; CHECK: fmadds
; CHECK: fmuls
; CHECK: fmul
; CHECK: blr
; CHECK-SAFE: @foof
; CHECK-SAFE: fsqrts
; CHECK-SAFE: fdiv
; CHECK-SAFE: blr
}
define float @food(float %a, double %b) nounwind {
entry:
%x = call double @llvm.sqrt.f64(double %b)
%y = fptrunc double %x to float
%r = fdiv float %a, %y
ret float %r
; CHECK: @foo
; CHECK: frsqrte
; CHECK: fnmsub
; CHECK: fmul
; CHECK: fmadd
; CHECK: fmul
; CHECK: fmul
; CHECK: fmadd
; CHECK: fmul
; CHECK: frsp
; CHECK: fmuls
; CHECK: blr
; CHECK-SAFE: @foo
; CHECK-SAFE: fsqrt
; CHECK-SAFE: fdivs
; CHECK-SAFE: blr
}
Use PPC reciprocal estimates with Newton iteration in fast-math mode When unsafe FP math operations are enabled, we can use the fre[s] and frsqrte[s] instructions, which generate reciprocal (sqrt) estimates, together with some Newton iteration, in order to quickly generate floating-point division and sqrt results. All of these instructions are separately optional, and so each has its own feature flag (except for the Altivec instructions, which are covered under the existing Altivec flag). Doing this is not only faster than using the IEEE-compliant fdiv/fsqrt instructions, but allows these computations to be pipelined with other computations in order to hide their overall latency. I've also added a couple of missing fnmsub patterns which turned out to be missing (but are necessary for good code generation of the Newton iterations). Altivec needs a similar fix, but that will probably be more complicated because fneg is expanded for Altivec's v4f32. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@178617 91177308-0d34-0410-b5e6-96231b3b80d8
2013-04-03 04:01:11 +00:00
define float @goo(float %a, float %b) nounwind {
entry:
%x = call float @llvm.sqrt.f32(float %b)
%r = fdiv float %a, %x
ret float %r
; CHECK: @goo
; CHECK: frsqrtes
; CHECK: fnmsubs
; CHECK: fmuls
; CHECK: fmadds
; CHECK: fmuls
; CHECK: fmuls
; CHECK: blr
; CHECK-SAFE: @goo
; CHECK-SAFE: fsqrts
; CHECK-SAFE: fdivs
; CHECK-SAFE: blr
}
define <4 x float> @hoo(<4 x float> %a, <4 x float> %b) nounwind {
entry:
%x = call <4 x float> @llvm.sqrt.v4f32(<4 x float> %b)
%r = fdiv <4 x float> %a, %x
ret <4 x float> %r
; CHECK: @hoo
; CHECK: vrsqrtefp
; CHECK-SAFE: @hoo
; CHECK-SAFE-NOT: vrsqrtefp
; CHECK-SAFE: blr
}
define double @foo2(double %a, double %b) nounwind {
entry:
%r = fdiv double %a, %b
ret double %r
; CHECK: @foo2
; CHECK: fre
; CHECK: fnmsub
; CHECK: fmadd
; CHECK: fnmsub
; CHECK: fmadd
; CHECK: fmul
; CHECK: blr
; CHECK-SAFE: @foo2
; CHECK-SAFE: fdiv
; CHECK-SAFE: blr
}
define float @goo2(float %a, float %b) nounwind {
entry:
%r = fdiv float %a, %b
ret float %r
; CHECK: @goo2
; CHECK: fres
; CHECK: fnmsubs
; CHECK: fmadds
; CHECK: fmuls
; CHECK: blr
; CHECK-SAFE: @goo2
; CHECK-SAFE: fdivs
; CHECK-SAFE: blr
}
define <4 x float> @hoo2(<4 x float> %a, <4 x float> %b) nounwind {
entry:
%r = fdiv <4 x float> %a, %b
ret <4 x float> %r
; CHECK: @hoo2
; CHECK: vrefp
; CHECK-SAFE: @hoo2
; CHECK-SAFE-NOT: vrefp
; CHECK-SAFE: blr
}
define double @foo3(double %a) nounwind {
entry:
%r = call double @llvm.sqrt.f64(double %a)
ret double %r
; CHECK: @foo3
; CHECK: frsqrte
; CHECK: fnmsub
; CHECK: fmul
; CHECK: fmadd
; CHECK: fmul
; CHECK: fmul
; CHECK: fmadd
; CHECK: fmul
; CHECK: fre
; CHECK: fnmsub
; CHECK: fmadd
; CHECK: fnmsub
; CHECK: fmadd
; CHECK: blr
; CHECK-SAFE: @foo3
; CHECK-SAFE: fsqrt
; CHECK-SAFE: blr
}
define float @goo3(float %a) nounwind {
entry:
%r = call float @llvm.sqrt.f32(float %a)
ret float %r
; CHECK: @goo3
; CHECK: frsqrtes
; CHECK: fnmsubs
; CHECK: fmuls
; CHECK: fmadds
; CHECK: fmuls
; CHECK: fres
; CHECK: fnmsubs
; CHECK: fmadds
; CHECK: blr
; CHECK-SAFE: @goo3
; CHECK-SAFE: fsqrts
; CHECK-SAFE: blr
}
define <4 x float> @hoo3(<4 x float> %a) nounwind {
entry:
%r = call <4 x float> @llvm.sqrt.v4f32(<4 x float> %a)
ret <4 x float> %r
; CHECK: @hoo3
; CHECK: vrsqrtefp
; CHECK: vrefp
; CHECK-SAFE: @hoo3
; CHECK-SAFE-NOT: vrsqrtefp
; CHECK-SAFE: blr
}
Reference in New Issue Copy Permalink