[X86] Add vector test coverage for or with no common bits tests

Ensure D113970 handles vector types patterns as well. Differential Revision: https://reviews.llvm.org/D114575
2021-11-29 09:55:52 -05:00 · 2021-11-29 09:55:52 -05:00 · a7363067e6
parent 95f34e318c
commit a7363067e6
1 changed files with 161 additions and 0 deletions
--- a/llvm/test/CodeGen/X86/vec_no-common-bits.ll
+++ b/llvm/test/CodeGen/X86/vec_no-common-bits.ll
@ -0,0 +1,161 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc < %s -mtriple=x86_64-unknown -mattr=+sse2 | FileCheck %s --check-prefixes=CHECK
+
+; In the following patterns, lhs and rhs of the or instruction have no common bits.
+; Therefore, "add" and "or" instructions are equal.
+
+define <2 x i32> @or_and_and_rhs_neg_vec_i32(<2 x i32> %x, <2 x i32> %y, <2 x i32> %z) {
+; CHECK-LABEL: or_and_and_rhs_neg_vec_i32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    pand %xmm1, %xmm2
+; CHECK-NEXT:    pandn %xmm0, %xmm1
+; CHECK-NEXT:    movdqa %xmm2, %xmm0
+; CHECK-NEXT:    por %xmm1, %xmm0
+; CHECK-NEXT:    paddd %xmm2, %xmm1
+; CHECK-NEXT:    psubd %xmm1, %xmm0
+; CHECK-NEXT:    retq
+  %and1 = and <2 x i32> %z, %y
+  %xor = xor <2 x i32> %y, <i32 -1, i32 -1>
+  %and2 = and <2 x i32> %x, %xor
+  %or = or <2 x i32> %and1, %and2
+  %add = add <2 x i32> %and1, %and2
+  %sub = sub <2 x i32> %or, %add
+  ret <2 x i32> %sub
+}
+
+define <2 x i32> @or_and_and_lhs_neg_vec_i32(<2 x i32> %x, <2 x i32> %y, <2 x i32> %z) {
+; CHECK-LABEL: or_and_and_lhs_neg_vec_i32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    pand %xmm1, %xmm2
+; CHECK-NEXT:    pandn %xmm0, %xmm1
+; CHECK-NEXT:    movdqa %xmm2, %xmm0
+; CHECK-NEXT:    por %xmm1, %xmm0
+; CHECK-NEXT:    paddd %xmm2, %xmm1
+; CHECK-NEXT:    psubd %xmm1, %xmm0
+; CHECK-NEXT:    retq
+  %and1 = and <2 x i32> %z, %y
+  %xor = xor <2 x i32> %y, <i32 -1, i32 -1>
+  %and2 = and <2 x i32> %xor, %x
+  %or = or <2 x i32> %and1, %and2
+  %add = add <2 x i32> %and1, %and2
+  %sub = sub <2 x i32> %or, %add
+  ret <2 x i32> %sub
+}
+
+define <2 x i32> @or_and_rhs_neg_and_vec_i32(<2 x i32> %x, <2 x i32> %y, <2 x i32> %z) {
+; CHECK-LABEL: or_and_rhs_neg_and_vec_i32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    pand %xmm1, %xmm0
+; CHECK-NEXT:    pandn %xmm2, %xmm1
+; CHECK-NEXT:    movdqa %xmm1, %xmm2
+; CHECK-NEXT:    por %xmm0, %xmm2
+; CHECK-NEXT:    paddd %xmm0, %xmm1
+; CHECK-NEXT:    psubd %xmm1, %xmm2
+; CHECK-NEXT:    movdqa %xmm2, %xmm0
+; CHECK-NEXT:    retq
+  %xor = xor <2 x i32> %y, <i32 -1, i32 -1>
+  %and1 = and <2 x i32> %z, %xor
+  %and2 = and <2 x i32> %x, %y
+  %or = or <2 x i32> %and1, %and2
+  %add = add <2 x i32> %and1, %and2
+  %sub = sub <2 x i32> %or, %add
+  ret <2 x i32> %sub
+}
+
+define <2 x i32> @or_and_lhs_neg_and_vec_i32(<2 x i32> %x, <2 x i32> %y, <2 x i32> %z) {
+; CHECK-LABEL: or_and_lhs_neg_and_vec_i32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    pand %xmm1, %xmm0
+; CHECK-NEXT:    pandn %xmm2, %xmm1
+; CHECK-NEXT:    movdqa %xmm1, %xmm2
+; CHECK-NEXT:    por %xmm0, %xmm2
+; CHECK-NEXT:    paddd %xmm0, %xmm1
+; CHECK-NEXT:    psubd %xmm1, %xmm2
+; CHECK-NEXT:    movdqa %xmm2, %xmm0
+; CHECK-NEXT:    retq
+  %xor = xor <2 x i32> %y, <i32 -1, i32 -1>
+  %and1 = and <2 x i32> %xor, %z
+  %and2 = and <2 x i32> %x, %y
+  %or = or <2 x i32> %and1, %and2
+  %add = add <2 x i32> %and1, %and2
+  %sub = sub <2 x i32> %or, %add
+  ret <2 x i32> %sub
+}
+
+define <2 x i64> @or_and_and_rhs_neg_vec_i64(<2 x i64> %x, <2 x i64> %y, <2 x i64> %z) {
+; CHECK-LABEL: or_and_and_rhs_neg_vec_i64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    pand %xmm1, %xmm2
+; CHECK-NEXT:    pandn %xmm0, %xmm1
+; CHECK-NEXT:    movdqa %xmm2, %xmm0
+; CHECK-NEXT:    por %xmm1, %xmm0
+; CHECK-NEXT:    paddq %xmm2, %xmm1
+; CHECK-NEXT:    psubq %xmm1, %xmm0
+; CHECK-NEXT:    retq
+  %and1 = and <2 x i64> %z, %y
+  %xor = xor <2 x i64> %y, <i64 -1, i64 -1>
+  %and2 = and <2 x i64> %x, %xor
+  %or = or <2 x i64> %and1, %and2
+  %add = add <2 x i64> %and1, %and2
+  %sub = sub <2 x i64> %or, %add
+  ret <2 x i64> %sub
+}
+
+define <2 x i64> @or_and_and_lhs_neg_vec_i64(<2 x i64> %x, <2 x i64> %y, <2 x i64> %z) {
+; CHECK-LABEL: or_and_and_lhs_neg_vec_i64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    pand %xmm1, %xmm2
+; CHECK-NEXT:    pandn %xmm0, %xmm1
+; CHECK-NEXT:    movdqa %xmm2, %xmm0
+; CHECK-NEXT:    por %xmm1, %xmm0
+; CHECK-NEXT:    paddq %xmm2, %xmm1
+; CHECK-NEXT:    psubq %xmm1, %xmm0
+; CHECK-NEXT:    retq
+  %and1 = and <2 x i64> %z, %y
+  %xor = xor <2 x i64> %y, <i64 -1, i64 -1>
+  %and2 = and <2 x i64> %xor, %x
+  %or = or <2 x i64> %and1, %and2
+  %add = add <2 x i64> %and1, %and2
+  %sub = sub <2 x i64> %or, %add
+  ret <2 x i64> %sub
+}
+
+define <2 x i64> @or_and_rhs_neg_and_vec_i64(<2 x i64> %x, <2 x i64> %y, <2 x i64> %z) {
+; CHECK-LABEL: or_and_rhs_neg_and_vec_i64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    pand %xmm1, %xmm0
+; CHECK-NEXT:    pandn %xmm2, %xmm1
+; CHECK-NEXT:    movdqa %xmm1, %xmm2
+; CHECK-NEXT:    por %xmm0, %xmm2
+; CHECK-NEXT:    paddq %xmm0, %xmm1
+; CHECK-NEXT:    psubq %xmm1, %xmm2
+; CHECK-NEXT:    movdqa %xmm2, %xmm0
+; CHECK-NEXT:    retq
+  %xor = xor <2 x i64> %y, <i64 -1, i64 -1>
+  %and1 = and <2 x i64> %z, %xor
+  %and2 = and <2 x i64> %x, %y
+  %or = or <2 x i64> %and1, %and2
+  %add = add <2 x i64> %and1, %and2
+  %sub = sub <2 x i64> %or, %add
+  ret <2 x i64> %sub
+}
+
+define <2 x i64> @or_and_lhs_neg_and_vec_i64(<2 x i64> %x, <2 x i64> %y, <2 x i64> %z) {
+; CHECK-LABEL: or_and_lhs_neg_and_vec_i64:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    pand %xmm1, %xmm0
+; CHECK-NEXT:    pandn %xmm2, %xmm1
+; CHECK-NEXT:    movdqa %xmm1, %xmm2
+; CHECK-NEXT:    por %xmm0, %xmm2
+; CHECK-NEXT:    paddq %xmm0, %xmm1
+; CHECK-NEXT:    psubq %xmm1, %xmm2
+; CHECK-NEXT:    movdqa %xmm2, %xmm0
+; CHECK-NEXT:    retq
+  %xor = xor <2 x i64> %y, <i64 -1, i64 -1>
+  %and1 = and <2 x i64> %xor, %z
+  %and2 = and <2 x i64> %x, %y
+  %or = or <2 x i64> %and1, %and2
+  %add = add <2 x i64> %and1, %and2
+  %sub = sub <2 x i64> %or, %add
+  ret <2 x i64> %sub
+}