[llvm] [AMDGPU] Enable WMMA256bInsts + Wave32 for gfx1200/gfx1201 + SISchedule fix + TargetParser gfx1200 propagation (PR #202093)

[Alexandra Munkes via llvm-commits]

================
@@ -0,0 +1,44 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1200 -verify-machineinstrs < %s | FileCheck %s
+;
+; Test: WMMA + SWMMAC INT4/INT8 instruction generation for gfx1200
+; Verifies WMMA + SWMMAC instruction generation for gfx1200
+
+; CHECK-LABEL: test_wmma_i32_16x16x16_iu4:
+; CHECK: v_wmma_i32_16x16x16_iu4
+define amdgpu_kernel void @test_wmma_i32_16x16x16_iu4(ptr addrspace(1) %C, ptr addrspace(1) %A, ptr addrspace(1) %B) #0 {
----------------
Malexandra-de wrote:

This test is redundant, it already exists in the [test suite](https://github.com/llvm/llvm-project/blob/9129363adbcc3474639e2a3b2b263905da1f86ca/llvm/test/CodeGen/AMDGPU/wmma-gfx12-w32.ll#L71) since [January 2024](https://github.com/llvm/llvm-project/commit/7fdf608cefa0d9051eb3146ee19c3750e237c799#diff-defc36c74cd762536aae59eeb604f9c035fed406179e8ffb6d5326052c403271).


https://github.com/llvm/llvm-project/pull/202093