[llvm] [AMDGPU] Add getCmpSelInstrCost override to re-enable SimplifyCFG speculation for vector types (PR #208043)

[Matt Arsenault via llvm-commits]

================
@@ -0,0 +1,185 @@
+; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --version 6
+; RUN: opt -passes="print<cost-model>" 2>&1 -disable-output -mtriple=amdgcn-unknown-amdhsa < %s | FileCheck -check-prefixes=ALL %s
+; RUN: opt -passes="print<cost-model>" -cost-kind=code-size 2>&1 -disable-output -mtriple=amdgcn-unknown-amdhsa < %s | FileCheck -check-prefixes=ALL-SIZE %s
+
+define void @select_i32(i1 %cond, i32 %a, i32 %b) {
----------------
arsenm wrote:

Isn't this cost specifically for compare and select? This just has the select parts?

https://github.com/llvm/llvm-project/pull/208043