[test][AArch64] Adjust vector insertion lit tests (llvm#143101)

The test cases test_insert_v16i8_insert_2_undef_base and
test_insert_v16i8_insert_2_undef_base_different_valeus in
CodeGen/AArch64/arm64-vector-insertion.ll was leaving element 8 in the
vector as "undef" without any real explanation. It kind of looked like a
typo as the input IR looked like this
   %v.8 = insertelement <16 x i8> %v.7, i8 %a, i32 8
   %v.10 = insertelement <16 x i8> %v.7, i8 %a, i32 10
leaving %v.8 as unused.

This patch is cleaning up the tests a bit by adding separate test cases
to validate what is happening when skipping insert at index 8, while
amending the original tests cases to use %v.8 instead of %v.7 when
creating %v.10.

Author: bjope

llvm/test/CodeGen/AArch64/arm64-vector-insertion.ll

@@ -66,6 +66,35 @@ define <16 x i8> @test_insert_v16i8_insert_2_undef_base(i8 %a) {
   %v.6 = insertelement <16 x i8> %v.4, i8 %a, i32 6
   %v.7 = insertelement <16 x i8> %v.6, i8 %a, i32 7
   %v.8 = insertelement <16 x i8> %v.7, i8 %a, i32 8
+  %v.10 = insertelement <16 x i8> %v.8, i8 %a, i32 10
+  %v.11 = insertelement <16 x i8> %v.10, i8 %a, i32 11
+  %v.12 = insertelement <16 x i8> %v.11, i8 %a, i32 12
+  %v.13 = insertelement <16 x i8> %v.12, i8 %a, i32 13
+  %v.14 = insertelement <16 x i8> %v.13, i8 %a, i32 14
+  %v.15 = insertelement <16 x i8> %v.14, i8 %a, i32 15
+  ret <16 x i8> %v.15
+}
+
+; Similar to above, but we leave element 8 as undef. One interesting part with
+; this test case is that %a may be poison, so simply inserting %a also at
+; index 8 would make the result vector more poisonous.
+define <16 x i8> @test_insert_v16i8_insert_2_undef_base_skip8(i32 %a0) {
+; CHECK-LABEL: test_insert_v16i8_insert_2_undef_base_skip8:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    lsr w8, w0, #5
+; CHECK-NEXT:    dup.16b v0, w8
+; CHECK-NEXT:    mov.b v0[5], wzr
+; CHECK-NEXT:    mov.b v0[9], wzr
+; CHECK-NEXT:    ret
+  %a1 = lshr exact i32 %a0, 5
+  %a = trunc i32 %a1 to i8
+  %v.0 = insertelement <16 x i8> <i8 undef, i8 undef, i8 undef, i8 undef, i8 undef, i8 0, i8 undef, i8 undef, i8 undef, i8 0, i8 undef, i8 undef, i8 undef, i8 undef, i8 undef, i8 undef>  , i8 %a, i32 0
+  %v.1 = insertelement <16 x i8> %v.0, i8 %a, i32 1
+  %v.2 = insertelement <16 x i8> %v.1, i8 %a, i32 2
+  %v.3 = insertelement <16 x i8> %v.2, i8 %a, i32 3
+  %v.4 = insertelement <16 x i8> %v.3, i8 %a, i32 4
+  %v.6 = insertelement <16 x i8> %v.4, i8 %a, i32 6
+  %v.7 = insertelement <16 x i8> %v.6, i8 %a, i32 7
   %v.10 = insertelement <16 x i8> %v.7, i8 %a, i32 10
   %v.11 = insertelement <16 x i8> %v.10, i8 %a, i32 11
   %v.12 = insertelement <16 x i8> %v.11, i8 %a, i32 12
@@ -75,8 +104,8 @@ define <16 x i8> @test_insert_v16i8_insert_2_undef_base(i8 %a) {
   ret <16 x i8> %v.15
 }
 
-define <16 x i8> @test_insert_v16i8_insert_2_undef_base_different_valeus(i8 %a, i8 %b) {
-; CHECK-LABEL: test_insert_v16i8_insert_2_undef_base_different_valeus:
+define <16 x i8> @test_insert_v16i8_insert_2_undef_base_different_values(i8 %a, i8 %b) {
+; CHECK-LABEL: test_insert_v16i8_insert_2_undef_base_different_values:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    dup.16b v0, w0
 ; CHECK-NEXT:    mov.b v0[2], w1
@@ -94,6 +123,42 @@ define <16 x i8> @test_insert_v16i8_insert_2_undef_base_different_valeus(i8 %a,
   %v.6 = insertelement <16 x i8> %v.4, i8 %a, i32 6
   %v.7 = insertelement <16 x i8> %v.6, i8 %b, i32 7
   %v.8 = insertelement <16 x i8> %v.7, i8 %a, i32 8
+  %v.10 = insertelement <16 x i8> %v.8, i8 %a, i32 10
+  %v.11 = insertelement <16 x i8> %v.10, i8 %a, i32 11
+  %v.12 = insertelement <16 x i8> %v.11, i8 %b, i32 12
+  %v.13 = insertelement <16 x i8> %v.12, i8 %a, i32 13
+  %v.14 = insertelement <16 x i8> %v.13, i8 %a, i32 14
+  %v.15 = insertelement <16 x i8> %v.14, i8 %b, i32 15
+  ret <16 x i8> %v.15
+}
+
+; Similar to above, but we leave element 8 as undef. One interesting part with
+; this test case is that %a and %b may be poison, so simply inserting %a or %b
+; at index 8 would make the result vector more poisonous.
+define <16 x i8> @test_insert_v16i8_insert_2_undef_base_different_values_skip8(i32 %a0, i32 %b0) {
+; CHECK-LABEL: test_insert_v16i8_insert_2_undef_base_different_values_skip8:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    lsr w8, w0, #5
+; CHECK-NEXT:    dup.16b v0, w8
+; CHECK-NEXT:    lsr w8, w1, #5
+; CHECK-NEXT:    mov.b v0[2], w8
+; CHECK-NEXT:    mov.b v0[5], wzr
+; CHECK-NEXT:    mov.b v0[7], w8
+; CHECK-NEXT:    mov.b v0[9], wzr
+; CHECK-NEXT:    mov.b v0[12], w8
+; CHECK-NEXT:    mov.b v0[15], w8
+; CHECK-NEXT:    ret
+  %a1 = lshr exact i32 %a0, 5
+  %a = trunc i32 %a1 to i8
+  %b1 = lshr exact i32 %b0, 5
+  %b = trunc i32 %b1 to i8
+  %v.0 = insertelement <16 x i8> <i8 undef, i8 undef, i8 undef, i8 undef, i8 undef, i8 0, i8 undef, i8 undef, i8 undef, i8 0, i8 undef, i8 undef, i8 undef, i8 undef, i8 undef, i8 undef>  , i8 %a, i32 0
+  %v.1 = insertelement <16 x i8> %v.0, i8 %a, i32 1
+  %v.2 = insertelement <16 x i8> %v.1, i8 %b, i32 2
+  %v.3 = insertelement <16 x i8> %v.2, i8 %a, i32 3
+  %v.4 = insertelement <16 x i8> %v.3, i8 %a, i32 4
+  %v.6 = insertelement <16 x i8> %v.4, i8 %a, i32 6
+  %v.7 = insertelement <16 x i8> %v.6, i8 %b, i32 7
   %v.10 = insertelement <16 x i8> %v.7, i8 %a, i32 10
   %v.11 = insertelement <16 x i8> %v.10, i8 %a, i32 11
   %v.12 = insertelement <16 x i8> %v.11, i8 %b, i32 12