[llvm] [AMDGPU] Include missing FeatureMADIntraFwdBug in gfx11-generic (PR #89936)

[Emma Pilkington via llvm-commits]

https://github.com/epilk created https://github.com/llvm/llvm-project/pull/89936

It seems like this happened because #79460 moved this from `FeatureISAVersion11_Common` to `FeatureISAVersion11_0_Common` while #76955 was being reviewed.

>From e206119721e377f8405d434a0a15effe3500fbf0 Mon Sep 17 00:00:00 2001
From: Emma Pilkington <emma.pilkington95 at gmail.com>
Date: Wed, 24 Apr 2024 09:31:19 -0400
Subject: [PATCH] [AMDGPU] Include missing FeatureMADIntraFwdBug in
 gfx11-generic

---
 llvm/lib/Target/AMDGPU/AMDGPU.td      | 1 +
 llvm/test/CodeGen/AMDGPU/mad_64_32.ll | 1 +
 2 files changed, 2 insertions(+)

diff --git a/llvm/lib/Target/AMDGPU/AMDGPU.td b/llvm/lib/Target/AMDGPU/AMDGPU.td
index 2b81f5d51032dd..8abe9920c02c2d 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPU.td
+++ b/llvm/lib/Target/AMDGPU/AMDGPU.td
@@ -1493,6 +1493,7 @@ def FeatureISAVersion11_Generic: FeatureSet<
     [FeatureMSAALoadDstSelBug,
      FeatureVALUTransUseHazard,
      FeatureUserSGPRInit16Bug,
+     FeatureMADIntraFwdBug,
      FeaturePrivEnabledTrap2NopBug,
      FeatureRequiresCOV6])>;
 
diff --git a/llvm/test/CodeGen/AMDGPU/mad_64_32.ll b/llvm/test/CodeGen/AMDGPU/mad_64_32.ll
index 14bcc4f994f890..400298bcff4f97 100644
--- a/llvm/test/CodeGen/AMDGPU/mad_64_32.ll
+++ b/llvm/test/CodeGen/AMDGPU/mad_64_32.ll
@@ -5,6 +5,7 @@
 ; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -verify-machineinstrs < %s | FileCheck -check-prefixes=GFX11,GFX1100 %s
 ; RUN: llc -mtriple=amdgcn -mcpu=gfx1150 -verify-machineinstrs < %s | FileCheck -check-prefixes=GFX11,GFX1150 %s
 ; RUN: llc -mtriple=amdgcn -mcpu=gfx1200 -verify-machineinstrs < %s | FileCheck -check-prefixes=GFX12 %s
+; RUN: llc -mtriple=amdgcn -mcpu=gfx11-generic --amdhsa-code-object-version=6 -verify-machineinstrs < %s | FileCheck -check-prefixes=GFX11,GFX1100 %s
 
 ; On GFX11, ensure vdst and src2 do not partially overlap. Full overlap is ok.