[llvm] [X86] Generate `kmov` for masking integers (PR #120593)

[Abhishek Kaushik via llvm-commits]

================
@@ -0,0 +1,150 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
+; RUN: llc < %s -mtriple=x86_64-- -mcpu=x86-64-v4 | FileCheck %s
+
+define <16 x i1> @mask_16(i32 %mask) {
----------------
abhishek-kaushik22 wrote:

I've added more tests, but this pattern didn't work for 256-bit vectors such as (`v16i16`, `v8i32`, `v4i64`) because a `X86ISD::PCMPEQ` node is generated before we can combine the `setcc`.
I can try and fix this after this gets merged.

https://github.com/llvm/llvm-project/pull/120593