[PowerPC] Add missing pattern for VSX Scalar Negative Multiply-Subtract Single Precision

[jsji]

Summary

This was found during review of https://reviews.llvm.org/D66050.
In the simple test of fdiv, we miss to fold

fneg 2, 2
xsmaddasp 3, 2, 0

to

xsnmsubasp 3, 2, 0

We have the patterns for Double Precision and vectors, just missing
Single Precision, the patch add that.

[jsji]

Ping..

[steven.zhang]

LGTM with some minor comments. Thank you for the fix.

llvm/lib/Target/PowerPC/PPCInstrVSX.td

1508 ↗

(On Diff #220252)

minor comments. It would be better to write it as follows to align with "-(a*c-b);

def : Pat<(fma (fneg f32:$A), f32:$C, f32:$B),
          (XSNMSUBASP $B, $A, $C)>;

1508 ↗

(On Diff #220252)

Additional XSNMSUBASP patterns ...

And It would be more clear to write it as:
XSNMSUBASP $B, $A, $C

[jsji]

Address Steven's comments. Thanks.

llvm/trunk/lib/Target/PowerPC/PPCInstrVSX.td

let AddedComplexity = 400 in { // Prefer VSX patterns over non-VSX patterns.
   def XSNMSUBMSP : XX3Form<60, 153,
                           (outs vssrc:$XT),
                           (ins vssrc:$XTi, vssrc:$XA, vssrc:$XB),
                           "xsnmsubmsp $XT, $XA, $XB", IIC_VecFP, []>,
                           RegConstraint<"$XTi = $XT">, NoEncode<"$XTi">,
                           AltVSXFMARel;
   }
 
+  // Additional xsnmsubasp patterns: -a*b + c == -(a*b - c)
+  def : Pat<(fma (fneg f32:$A), f32:$B, f32:$C),
+            (XSNMSUBASP $C, $A, $B)>;
+  def : Pat<(fma f32:$A, (fneg f32:$C), f32:$B),
+            (XSNMSUBASP $C, $A, $B)>;
+
   // Single Precision Conversions (FP <-> INT)
   def XSCVSXDSP : XX2Form<60, 312,
                       (outs vssrc:$XT), (ins vsfrc:$XB),
                       "xscvsxdsp $XT, $XB", IIC_VecFP,
                       [(set f32:$XT, (PPCfcfids f64:$XB))]>;
   def XSCVUXDSP : XX2Form<60, 296,
                       (outs vssrc:$XT), (ins vsfrc:$XB),
                       "xscvuxdsp $XT, $XB", IIC_VecFP,

llvm/trunk/test/CodeGen/PowerPC/fdiv.ll

 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
 ; RUN: llc -verify-machineinstrs < %s -mtriple=powerpc64le-unknown-linux-gnu -mcpu=pwr8 | FileCheck %s
 
 define dso_local float @foo(float %0, float %1) local_unnamed_addr {
 ; CHECK-LABEL: foo:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    xsresp 3, 2
-; CHECK-NEXT:    fneg 2, 2
 ; CHECK-NEXT:    xsmulsp 0, 1, 3
-; CHECK-NEXT:    xsmaddasp 1, 2, 0
+; CHECK-NEXT:    xsnmsubasp 1, 2, 0
 ; CHECK-NEXT:    xsmaddasp 0, 3, 1
 ; CHECK-NEXT:    fmr 1, 0
 ; CHECK-NEXT:    blr
   %3 = fdiv fast float %0, %1
   ret float %3
 }