[NFC][PowerPC] Optimize vector compares for not equal to non zero vectors

Author: himadhith

llvm/test/CodeGen/PowerPC/optimize-vector-not-equal.ll

@@ -0,0 +1,71 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 6
+; RUN: llc -verify-machineinstrs -mcpu=pwr9 -mtriple=powerpc64le-unknown-linux-gnu \
+; RUN:     -ppc-asm-full-reg-names --ppc-vsr-nums-as-vr < %s | FileCheck %s --check-prefix=POWERPC_64LE
+
+; RUN: llc -verify-machineinstrs -mcpu=pwr9 -mtriple=powerpc64-ibm-aix \
+; RUN:     -ppc-asm-full-reg-names --ppc-vsr-nums-as-vr < %s | FileCheck %s --check-prefix=POWERPC_64
+
+; RUN: llc -verify-machineinstrs -mcpu=pwr9 -mtriple=powerpc-ibm-aix \
+; RUN:     -ppc-asm-full-reg-names --ppc-vsr-nums-as-vr < %s | FileCheck %s --check-prefix=POWERPC_32
+
+; The current implementation is comparing vector of non-zeros in register v2 with v3. v3 is then negated and converts:
+; 0XFFFF -> 0
+; 0 -> 1
+; An optimized version is to follow this NFC patch
+
+define i32 @cols_needed(<4 x i16> %wide.load) {
+; POWERPC_64LE-LABEL: cols_needed:
+; POWERPC_64LE:       # %bb.0: # %entry
+; POWERPC_64LE-NEXT:    xxlxor v3, v3, v3
+; POWERPC_64LE-NEXT:    li r3, 0
+; POWERPC_64LE-NEXT:    vcmpequh v2, v2, v3
+; POWERPC_64LE-NEXT:    xxleqv v3, v3, v3
+; POWERPC_64LE-NEXT:    vmrglh v2, v2, v2
+; POWERPC_64LE-NEXT:    vsubuwm v2, v2, v3
+; POWERPC_64LE-NEXT:    xxswapd v3, v2
+; POWERPC_64LE-NEXT:    vadduwm v2, v2, v3
+; POWERPC_64LE-NEXT:    xxspltw v3, v2, 2
+; POWERPC_64LE-NEXT:    vadduwm v2, v2, v3
+; POWERPC_64LE-NEXT:    vextuwrx r3, r3, v2
+; POWERPC_64LE-NEXT:    blr
+;
+; POWERPC_64-LABEL: cols_needed:
+; POWERPC_64:       # %bb.0: # %entry
+; POWERPC_64-NEXT:    xxlxor v3, v3, v3
+; POWERPC_64-NEXT:    li r3, 0
+; POWERPC_64-NEXT:    vcmpequh v2, v2, v3
+; POWERPC_64-NEXT:    xxleqv v3, v3, v3
+; POWERPC_64-NEXT:    vmrghh v2, v2, v2
+; POWERPC_64-NEXT:    vsubuwm v2, v2, v3
+; POWERPC_64-NEXT:    xxswapd v3, v2
+; POWERPC_64-NEXT:    vadduwm v2, v2, v3
+; POWERPC_64-NEXT:    xxspltw v3, v2, 1
+; POWERPC_64-NEXT:    vadduwm v2, v2, v3
+; POWERPC_64-NEXT:    vextuwlx r3, r3, v2
+; POWERPC_64-NEXT:    blr
+;
+; POWERPC_32-LABEL: cols_needed:
+; POWERPC_32:       # %bb.0: # %entry
+; POWERPC_32-NEXT:    xxlxor v3, v3, v3
+; POWERPC_32-NEXT:    vcmpequh v2, v2, v3
+; POWERPC_32-NEXT:    xxleqv v3, v3, v3
+; POWERPC_32-NEXT:    vmrghh v2, v2, v2
+; POWERPC_32-NEXT:    vsubuwm v2, v2, v3
+; POWERPC_32-NEXT:    xxswapd v3, v2
+; POWERPC_32-NEXT:    vadduwm v2, v2, v3
+; POWERPC_32-NEXT:    xxspltw v3, v2, 1
+; POWERPC_32-NEXT:    vadduwm v2, v2, v3
+; POWERPC_32-NEXT:    stxv v2, -16(r1)
+; POWERPC_32-NEXT:    lwz r3, -16(r1)
+; POWERPC_32-NEXT:    blr
+entry:
+  %0 = icmp ne <4 x i16> %wide.load, zeroinitializer
+  %1 = zext <4 x i1> %0 to <4 x i32>
+  %2 = tail call i32 @llvm.vector.reduce.add.v4i32(<4 x i32> %1)
+  ret i32 %2
+}
+
+; Function Attrs: nocallback nofree nosync nounwind speculatable willreturn memory(none)
+declare i32 @llvm.vector.reduce.add.v4i32(<4 x i32>) #0
+
+attributes #0 = { nocallback nofree nosync nounwind speculatable willreturn memory(none) }