[PowerPC] Exploit VSX rounding instrs for rint

Exploit native VSX rounding instruction, x(v|s)r(d|s)pic, which does
rounding using current rounding mode.

According to C standard library, rint may raise INEXACT exception while
nearbyint won't.

Reviewed By: lkail

Differential Revision: https://reviews.llvm.org/D72685

Author: ecnelises

llvm/lib/Target/PowerPC/PPCISelLowering.cpp

@@ -799,12 +799,16 @@ PPCTargetLowering::PPCTargetLowering(const PPCTargetMachine &TM,
       setOperationAction(ISD::FCEIL, MVT::v2f64, Legal);
       setOperationAction(ISD::FTRUNC, MVT::v2f64, Legal);
       setOperationAction(ISD::FNEARBYINT, MVT::v2f64, Legal);
+      setOperationAction(ISD::FRINT, MVT::v2f64, Legal);
       setOperationAction(ISD::FROUND, MVT::v2f64, Legal);
       setOperationAction(ISD::FROUND, MVT::f64, Legal);
+      setOperationAction(ISD::FRINT, MVT::f64, Legal);
 
       setOperationAction(ISD::FNEARBYINT, MVT::v4f32, Legal);
+      setOperationAction(ISD::FRINT, MVT::v4f32, Legal);
       setOperationAction(ISD::FROUND, MVT::v4f32, Legal);
       setOperationAction(ISD::FROUND, MVT::f32, Legal);
+      setOperationAction(ISD::FRINT, MVT::f32, Legal);
 
       setOperationAction(ISD::MUL, MVT::v2f64, Legal);
       setOperationAction(ISD::FMA, MVT::v2f64, Legal);

llvm/lib/Target/PowerPC/PPCInstrVSX.td

@@ -2563,6 +2563,14 @@ def : Pat<(f32 (fceil f32:$S)),
 def : Pat<(f32 (ftrunc f32:$S)),
           (f32 (COPY_TO_REGCLASS (XSRDPIZ
                                    (COPY_TO_REGCLASS $S, VSFRC)), VSSRC))>;
+def : Pat<(f32 (frint f32:$S)),
+          (f32 (COPY_TO_REGCLASS (XSRDPIC
+                                   (COPY_TO_REGCLASS $S, VSFRC)), VSSRC))>;
+def : Pat<(v4f32 (frint v4f32:$S)), (v4f32 (XVRSPIC $S))>;
+
+// Rounding for double precision.
+def : Pat<(f64 (frint f64:$S)), (f64 (XSRDPIC $S))>;
+def : Pat<(v2f64 (frint v2f64:$S)), (v2f64 (XVRDPIC $S))>;
 }
 
 // Materialize a zero-vector of long long

llvm/test/CodeGen/PowerPC/mi-peephole-splat.ll

@@ -11,118 +11,34 @@
 define double @splat_swap(<2 x double> %x, <2 x double> %y) nounwind  {
 ; CHECK-LE-LABEL: splat_swap:
 ; CHECK-LE:       # %bb.0:
-; CHECK-LE-NEXT:    mflr 0
-; CHECK-LE-NEXT:    std 0, 16(1)
-; CHECK-LE-NEXT:    stdu 1, -80(1)
-; CHECK-LE-NEXT:    li 3, 64
-; CHECK-LE-NEXT:    stxvd2x 63, 1, 3 # 16-byte Folded Spill
-; CHECK-LE-NEXT:    xvadddp 63, 34, 35
-; CHECK-LE-NEXT:    xxlor 1, 63, 63
-; CHECK-LE-NEXT:    bl rint
-; CHECK-LE-NEXT:    nop
-; CHECK-LE-NEXT:    xxswapd 0, 63
-; CHECK-LE-NEXT:    # kill: def $f1 killed $f1 def $vsl1
-; CHECK-LE-NEXT:    li 3, 48
-; CHECK-LE-NEXT:    stxvd2x 1, 1, 3 # 16-byte Folded Spill
-; CHECK-LE-NEXT:    fmr 1, 0
-; CHECK-LE-NEXT:    bl rint
-; CHECK-LE-NEXT:    nop
-; CHECK-LE-NEXT:    li 3, 48
-; CHECK-LE-NEXT:    # kill: def $f1 killed $f1 def $vsl1
-; CHECK-LE-NEXT:    lxvd2x 0, 1, 3 # 16-byte Folded Reload
-; CHECK-LE-NEXT:    li 3, 64
-; CHECK-LE-NEXT:    lxvd2x 63, 1, 3 # 16-byte Folded Reload
-; CHECK-LE-NEXT:    xxmrghd 0, 0, 1
+; CHECK-LE-NEXT:    xvadddp 0, 34, 35
+; CHECK-LE-NEXT:    xvrdpic 0, 0
 ; CHECK-LE-NEXT:    xxswapd 1, 0
 ; CHECK-LE-NEXT:    xssubdp 1, 1, 0
-; CHECK-LE-NEXT:    addi 1, 1, 80
-; CHECK-LE-NEXT:    ld 0, 16(1)
-; CHECK-LE-NEXT:    mtlr 0
 ; CHECK-LE-NEXT:    blr
 ;
 ; CHECK-BE-LABEL: splat_swap:
 ; CHECK-BE:       # %bb.0:
-; CHECK-BE-NEXT:    mflr 0
-; CHECK-BE-NEXT:    std 0, 16(1)
-; CHECK-BE-NEXT:    stdu 1, -160(1)
-; CHECK-BE-NEXT:    li 3, 144
-; CHECK-BE-NEXT:    stxvd2x 63, 1, 3 # 16-byte Folded Spill
-; CHECK-BE-NEXT:    xvadddp 63, 34, 35
-; CHECK-BE-NEXT:    xxlor 1, 63, 63
-; CHECK-BE-NEXT:    bl rint
-; CHECK-BE-NEXT:    nop
-; CHECK-BE-NEXT:    # kill: def $f1 killed $f1 def $vsl1
-; CHECK-BE-NEXT:    li 3, 128
-; CHECK-BE-NEXT:    stxvd2x 1, 1, 3 # 16-byte Folded Spill
-; CHECK-BE-NEXT:    xxswapd 1, 63
-; CHECK-BE-NEXT:    # kill: def $f1 killed $f1 killed $vsl1
-; CHECK-BE-NEXT:    bl rint
-; CHECK-BE-NEXT:    nop
-; CHECK-BE-NEXT:    li 3, 128
-; CHECK-BE-NEXT:    lxvd2x 0, 1, 3 # 16-byte Folded Reload
-; CHECK-BE-NEXT:    # kill: def $f1 killed $f1 def $vsl1
-; CHECK-BE-NEXT:    li 3, 144
-; CHECK-BE-NEXT:    lxvd2x 63, 1, 3 # 16-byte Folded Reload
-; CHECK-BE-NEXT:    xxmrghd 0, 0, 1
+; CHECK-BE-NEXT:    xvadddp 0, 34, 35
+; CHECK-BE-NEXT:    xvrdpic 0, 0
 ; CHECK-BE-NEXT:    xxswapd 1, 0
 ; CHECK-BE-NEXT:    xssubdp 1, 0, 1
-; CHECK-BE-NEXT:    addi 1, 1, 160
-; CHECK-BE-NEXT:    ld 0, 16(1)
-; CHECK-BE-NEXT:    mtlr 0
 ; CHECK-BE-NEXT:    blr
 ;
 ; CHECK-P9LE-LABEL: splat_swap:
 ; CHECK-P9LE:       # %bb.0:
-; CHECK-P9LE-NEXT:    mflr 0
-; CHECK-P9LE-NEXT:    std 0, 16(1)
-; CHECK-P9LE-NEXT:    stdu 1, -64(1)
-; CHECK-P9LE-NEXT:    stxv 63, 48(1) # 16-byte Folded Spill
-; CHECK-P9LE-NEXT:    xvadddp 63, 34, 35
-; CHECK-P9LE-NEXT:    xscpsgndp 1, 63, 63
-; CHECK-P9LE-NEXT:    bl rint
-; CHECK-P9LE-NEXT:    nop
-; CHECK-P9LE-NEXT:    # kill: def $f1 killed $f1 def $vsl1
-; CHECK-P9LE-NEXT:    stxv 1, 32(1) # 16-byte Folded Spill
-; CHECK-P9LE-NEXT:    xxswapd 1, 63
-; CHECK-P9LE-NEXT:    # kill: def $f1 killed $f1 killed $vsl1
-; CHECK-P9LE-NEXT:    bl rint
-; CHECK-P9LE-NEXT:    nop
-; CHECK-P9LE-NEXT:    lxv 0, 32(1) # 16-byte Folded Reload
-; CHECK-P9LE-NEXT:    # kill: def $f1 killed $f1 def $vsl1
-; CHECK-P9LE-NEXT:    xxmrghd 0, 0, 1
-; CHECK-P9LE-NEXT:    lxv 63, 48(1) # 16-byte Folded Reload
+; CHECK-P9LE-NEXT:    xvadddp 0, 34, 35
+; CHECK-P9LE-NEXT:    xvrdpic 0, 0
 ; CHECK-P9LE-NEXT:    xxswapd 1, 0
 ; CHECK-P9LE-NEXT:    xssubdp 1, 1, 0
-; CHECK-P9LE-NEXT:    addi 1, 1, 64
-; CHECK-P9LE-NEXT:    ld 0, 16(1)
-; CHECK-P9LE-NEXT:    mtlr 0
 ; CHECK-P9LE-NEXT:    blr
 ;
 ; CHECK-P9BE-LABEL: splat_swap:
 ; CHECK-P9BE:       # %bb.0:
-; CHECK-P9BE-NEXT:    mflr 0
-; CHECK-P9BE-NEXT:    std 0, 16(1)
-; CHECK-P9BE-NEXT:    stdu 1, -144(1)
-; CHECK-P9BE-NEXT:    stxv 63, 128(1) # 16-byte Folded Spill
-; CHECK-P9BE-NEXT:    xvadddp 63, 34, 35
-; CHECK-P9BE-NEXT:    xscpsgndp 1, 63, 63
-; CHECK-P9BE-NEXT:    bl rint
-; CHECK-P9BE-NEXT:    nop
-; CHECK-P9BE-NEXT:    # kill: def $f1 killed $f1 def $vsl1
-; CHECK-P9BE-NEXT:    stxv 1, 112(1) # 16-byte Folded Spill
-; CHECK-P9BE-NEXT:    xxswapd 1, 63
-; CHECK-P9BE-NEXT:    # kill: def $f1 killed $f1 killed $vsl1
-; CHECK-P9BE-NEXT:    bl rint
-; CHECK-P9BE-NEXT:    nop
-; CHECK-P9BE-NEXT:    lxv 0, 112(1) # 16-byte Folded Reload
-; CHECK-P9BE-NEXT:    # kill: def $f1 killed $f1 def $vsl1
-; CHECK-P9BE-NEXT:    xxmrghd 0, 0, 1
-; CHECK-P9BE-NEXT:    lxv 63, 128(1) # 16-byte Folded Reload
+; CHECK-P9BE-NEXT:    xvadddp 0, 34, 35
+; CHECK-P9BE-NEXT:    xvrdpic 0, 0
 ; CHECK-P9BE-NEXT:    xxswapd 1, 0
 ; CHECK-P9BE-NEXT:    xssubdp 1, 0, 1
-; CHECK-P9BE-NEXT:    addi 1, 1, 144
-; CHECK-P9BE-NEXT:    ld 0, 16(1)
-; CHECK-P9BE-NEXT:    mtlr 0
 ; CHECK-P9BE-NEXT:    blr
   %added = fadd <2 x double> %x, %y
   %call = tail call <2 x double> @llvm.rint.v2f64(<2 x double> %added) nounwind readnone

llvm/test/CodeGen/PowerPC/scalar-rounding-ops.ll

@@ -559,3 +559,47 @@ entry:
 }
 
 declare float @llvm.ceil.f32(float)
+
+define dso_local double @test_rint(double %d) local_unnamed_addr {
+; BE-LABEL: test_rint:
+; BE:       # %bb.0: # %entry
+; BE-NEXT:    xsrdpic f1, f1
+; BE-NEXT:    blr
+;
+; CHECK-LABEL: test_rint:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    xsrdpic f1, f1
+; CHECK-NEXT:    blr
+;
+; FAST-LABEL: test_rint:
+; FAST:       # %bb.0: # %entry
+; FAST-NEXT:    xsrdpic f1, f1
+; FAST-NEXT:    blr
+entry:
+  %0 = tail call double @llvm.rint.f64(double %d)
+  ret double %0
+}
+
+declare double @llvm.rint.f64(double)
+
+define dso_local float @test_rintf(float %f) local_unnamed_addr {
+; BE-LABEL: test_rintf:
+; BE:       # %bb.0: # %entry
+; BE-NEXT:    xsrdpic f1, f1
+; BE-NEXT:    blr
+;
+; CHECK-LABEL: test_rintf:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    xsrdpic f1, f1
+; CHECK-NEXT:    blr
+;
+; FAST-LABEL: test_rintf:
+; FAST:       # %bb.0: # %entry
+; FAST-NEXT:    xsrdpic f1, f1
+; FAST-NEXT:    blr
+entry:
+  %0 = tail call float @llvm.rint.f32(float %f)
+  ret float %0
+}
+
+declare float @llvm.rint.f32(float)