[llvm] fold mov dec/inc to lea +- 1 (PR #185194)

[Simon Pilgrim via llvm-commits]

================
@@ -0,0 +1,101 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 6
+; RUN: llc < %s -mtriple=x86_64-unknown-linux-gnu -mattr=+avx2,+slow-3ops-lea | FileCheck %s
+; RUN: llc < %s -mtriple=x86_64-unknown-linux-gnu -mattr=+avx2,-slow-3ops-lea | FileCheck %s
+
+define i64 @mov_dec(<32 x i8> %x) local_unnamed_addr {
+; CHECK-LABEL: mov_dec:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    vpmovmskb %ymm0, %ecx
+; CHECK-NEXT:    leal -1(%rcx), %eax
+; CHECK-NEXT:    shlq $32, %rcx
+; CHECK-NEXT:    orq %rcx, %rax
+; CHECK-NEXT:    vzeroupper
+; CHECK-NEXT:    retq
+  %cmp = icmp slt <32 x i8> %x, zeroinitializer
+  %mvmsk = bitcast <32 x i1> %cmp to i32
----------------
RKSimon wrote:

do we need this vector/pmovmskb pattern to test the fold? it feels like this should be a more general test and not require avx2

https://github.com/llvm/llvm-project/pull/185194