[Power9] Exploit vector integer extend instructions

[syzaara]

Summary

This patch adds build vector patterns to exploit the vector integer extend instructions:
vextsb2w - Vector Extend Sign Byte To Word
vextsb2d - Vector Extend Sign Byte To Doubleword
vextsh2w - Vector Extend Sign Halfword To Word
vextsh2d - Vector Extend Sign Halfword To Doubleword
vextsw2d - Vector Extend Sign Word To Doubleword

[kbarton]

LGTM

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

 }
 
 def DblToFlt {
   dag A0 = (f32 (fpround (f64 (extractelt v2f64:$A, 0))));
   dag A1 = (f32 (fpround (f64 (extractelt v2f64:$A, 1))));
   dag B0 = (f32 (fpround (f64 (extractelt v2f64:$B, 0))));
   dag B1 = (f32 (fpround (f64 (extractelt v2f64:$B, 1))));
 }
+
+def ByteToWord {
+  dag A0 = (i32 (sext_inreg (i32 (vector_extract v16i8:$A, 0)), i8));
+  dag A1 = (i32 (sext_inreg (i32 (vector_extract v16i8:$A, 4)), i8));
+  dag A2 = (i32 (sext_inreg (i32 (vector_extract v16i8:$A, 8)), i8));
+  dag A3 = (i32 (sext_inreg (i32 (vector_extract v16i8:$A, 12)), i8));
+}
+
+def ByteToDWord {
+  dag A0 = (i64 (sext_inreg
+            (i64 (anyext (i32 (vector_extract v16i8:$A, 0)))), i8));
+  dag A1 = (i64 (sext_inreg
+            (i64 (anyext (i32 (vector_extract v16i8:$A, 8)))), i8));
+}
+
+def HWordToWord {
+  dag A0 = (i32 (sext_inreg (i32 (vector_extract v8i16:$A, 0)), i16));
+  dag A1 = (i32 (sext_inreg (i32 (vector_extract v8i16:$A, 2)), i16));
+  dag A2 = (i32 (sext_inreg (i32 (vector_extract v8i16:$A, 4)), i16));
+  dag A3 = (i32 (sext_inreg (i32 (vector_extract v8i16:$A, 6)), i16));
+}
+
+def HWordToDWord {
+  dag A0 = (i64 (sext_inreg
+            (i64 (anyext (i32 (vector_extract v8i16:$A, 0)))), i16));
+  dag A1 = (i64 (sext_inreg
+            (i64 (anyext (i32 (vector_extract v8i16:$A, 4)))), i16));
+}
+
+def WordToDWord {
+  dag A0 = (i64 (sext (i32 (vector_extract v4i32:$A, 0))));
+  dag A1 = (i64 (sext (i32 (vector_extract v4i32:$A, 2))));
+}
+
 def FltToIntLoad {
   dag A = (i32 (PPCmfvsr (PPCfctiwz (f64 (extloadf32 xoaddr:$A)))));
 }
 def FltToUIntLoad {
   dag A = (i32 (PPCmfvsr (PPCfctiwuz (f64 (extloadf32 xoaddr:$A)))));
 }
 def FltToLongLoad {
   dag A = (i64 (PPCmfvsr (PPCfctidz (f64 (extloadf32 xoaddr:$A)))));
def : Pat<(i64 (extractelt v2i64:$A, 0)),
               (i64 (MFVSRLD $A))>;
     // Better way to build integer vectors if we have MTVSRDD. Little endian.
     def : Pat<(v2i64 (build_vector i64:$rA, i64:$rB)),
               (v2i64 (MTVSRDD $rB, $rA))>;
     def : Pat<(v4i32 (build_vector i32:$A, i32:$B, i32:$C, i32:$D)),
               (VMRGOW (COPY_TO_REGCLASS (MTVSRDD AnyExts.D, AnyExts.B), VSRC),
                       (COPY_TO_REGCLASS (MTVSRDD AnyExts.C, AnyExts.A), VSRC))>;
   }
+  // P9 Altivec instructions that can be used to build vectors.
+  // Adding them to PPCInstrVSX.td rather than PPCAltivecVSX.td to compete
+  // with complexities of existing build vector patterns in this file.
+  let Predicates = [HasP9Altivec] in {
+    def : Pat<(v2i64 (build_vector WordToDWord.A0, WordToDWord.A1)),
+              (v2i64 (VEXTSW2D $A))>;
+    def : Pat<(v2i64 (build_vector HWordToDWord.A0, HWordToDWord.A1)),
+              (v2i64 (VEXTSH2D $A))>;
+    def : Pat<(v4i32 (build_vector HWordToWord.A0, HWordToWord.A1,
+                      HWordToWord.A2, HWordToWord.A3)),
+              (v4i32 (VEXTSH2W $A))>;
+    def : Pat<(v4i32 (build_vector ByteToWord.A0, ByteToWord.A1,
+                      ByteToWord.A2, ByteToWord.A3)),
+              (v4i32 (VEXTSB2W $A))>;
+    def : Pat<(v2i64 (build_vector ByteToDWord.A0, ByteToDWord.A1)),
+              (v2i64 (VEXTSB2D $A))>;
+  }
 }

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

+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -verify-machineinstrs -mcpu=pwr9 < %s | FileCheck %s -check-prefix=PWR9
+target triple = "powerpc64le-unknown-linux-gnu"
+
+define <4 x i32> @vextsb2w(<16 x i8> %a) {
+; PWR9-LABEL: vextsb2w:
+; PWR9:       # BB#0: # %entry
+; PWR9-NEXT:    vextsb2w 2, 2
+; PWR9-NEXT:    blr
+entry:
+  %vecext = extractelement <16 x i8> %a, i32 0
+  %conv = sext i8 %vecext to i32
+  %vecinit = insertelement <4 x i32> undef, i32 %conv, i32 0
+  %vecext1 = extractelement <16 x i8> %a, i32 4
+  %conv2 = sext i8 %vecext1 to i32
+  %vecinit3 = insertelement <4 x i32> %vecinit, i32 %conv2, i32 1
+  %vecext4 = extractelement <16 x i8> %a, i32 8
+  %conv5 = sext i8 %vecext4 to i32
+  %vecinit6 = insertelement <4 x i32> %vecinit3, i32 %conv5, i32 2
+  %vecext7 = extractelement <16 x i8> %a, i32 12
+  %conv8 = sext i8 %vecext7 to i32
+  %vecinit9 = insertelement <4 x i32> %vecinit6, i32 %conv8, i32 3
+  ret <4 x i32> %vecinit9
+}
+
+define <2 x i64> @vextsb2d(<16 x i8> %a) {
+; PWR9-LABEL: vextsb2d:
+; PWR9:       # BB#0: # %entry
+; PWR9-NEXT:    vextsb2d 2, 2
+; PWR9-NEXT:    blr
+entry:
+  %vecext = extractelement <16 x i8> %a, i32 0
+  %conv = sext i8 %vecext to i64
+  %vecinit = insertelement <2 x i64> undef, i64 %conv, i32 0
+  %vecext1 = extractelement <16 x i8> %a, i32 8
+  %conv2 = sext i8 %vecext1 to i64
+  %vecinit3 = insertelement <2 x i64> %vecinit, i64 %conv2, i32 1
+  ret <2 x i64> %vecinit3
+}
+
+define <4 x i32> @vextsh2w(<8 x i16> %a) {
+; PWR9-LABEL: vextsh2w:
+; PWR9:       # BB#0: # %entry
+; PWR9-NEXT:    vextsh2w 2, 2
+; PWR9-NEXT:    blr
+entry:
+  %vecext = extractelement <8 x i16> %a, i32 0
+  %conv = sext i16 %vecext to i32
+  %vecinit = insertelement <4 x i32> undef, i32 %conv, i32 0
+  %vecext1 = extractelement <8 x i16> %a, i32 2
+  %conv2 = sext i16 %vecext1 to i32
+  %vecinit3 = insertelement <4 x i32> %vecinit, i32 %conv2, i32 1
+  %vecext4 = extractelement <8 x i16> %a, i32 4
+  %conv5 = sext i16 %vecext4 to i32
+  %vecinit6 = insertelement <4 x i32> %vecinit3, i32 %conv5, i32 2
+  %vecext7 = extractelement <8 x i16> %a, i32 6
+  %conv8 = sext i16 %vecext7 to i32
+  %vecinit9 = insertelement <4 x i32> %vecinit6, i32 %conv8, i32 3
+  ret <4 x i32> %vecinit9
+}
+
+define <2 x i64> @vextsh2d(<8 x i16> %a) {
+; PWR9-LABEL: vextsh2d:
+; PWR9:       # BB#0: # %entry
+; PWR9-NEXT:    vextsh2d 2, 2
+; PWR9-NEXT:    blr
+entry:
+  %vecext = extractelement <8 x i16> %a, i32 0
+  %conv = sext i16 %vecext to i64
+  %vecinit = insertelement <2 x i64> undef, i64 %conv, i32 0
+  %vecext1 = extractelement <8 x i16> %a, i32 4
+  %conv2 = sext i16 %vecext1 to i64
+  %vecinit3 = insertelement <2 x i64> %vecinit, i64 %conv2, i32 1
+  ret <2 x i64> %vecinit3
+}
+
+define <2 x i64> @vextsw2d(<4 x i32> %a) {
+; PWR9-LABEL: vextsw2d:
+; PWR9:       # BB#0: # %entry
+; PWR9-NEXT:    vextsw2d 2, 2
+; PWR9-NEXT:    blr
+entry:
+  %vecext = extractelement <4 x i32> %a, i32 0
+  %conv = sext i32 %vecext to i64
+  %vecinit = insertelement <2 x i64> undef, i64 %conv, i32 0
+  %vecext1 = extractelement <4 x i32> %a, i32 2
+  %conv2 = sext i32 %vecext1 to i64
+  %vecinit3 = insertelement <2 x i64> %vecinit, i64 %conv2, i32 1
+  ret <2 x i64> %vecinit3
+}