[llvm] X86: Add pattern for optimized BLSIC IR form (PR #209814)

[via llvm-commits]

================
@@ -909,6 +909,53 @@ define i64 @test_x86_tbm_blsic_u64_sle(i64 %a, i64 %b, i64 %c) nounwind {
   ret i64 %t4
 }
 
+
+define i32 @test_blsic_original(i32 %x) {
----------------
Logans-olo wrote:

Nice, thank you for the clarification

https://github.com/llvm/llvm-project/pull/209814