LGTM

commit 2531535984ad989ce88aeee23cb92a827da6686e
Author: Changpeng Fang <changpeng.fang@gmail.com>
Date: Thu Jan 23 16:57:43 2020 -0800

Fix the LIT test failures.
(Yes, I messed up with a release build check, Thanks for catching these).

Where are these failing LIT tests located? I did LIT tests before posting for review and also before integrating.
Maybe my check is incomplete. Thanks.

Updated based on feedback:

Rename a few functions and variables:

update based on comment.

Update based on feedback:

update based on feedback.

Update based on the comments.

Update based on feedback from the reviewer.

Implement rcp optimization for fdiv in AMGGPUCodegenPrepare to insert amdgcn_rcp intrinsic. For f32 type fdiv,
if fpmath metadata is unavailable, we could not do rcp optimization unless fast unsafe math is specified.

Introduce an intrinsic in AMDGPUCodeGenPrepare to generate correctly rounded fdiv32.

In D71293#1778867, @arsenm wrote:

The attribute should not de directly checked (we probably shouldn’t even be putting it on the function). The proper thing to check is the fpmath metadata on the individual instruction. This isn’t propagated into the DAG, so AMDGPUCodeGenPrepare inserts intrinsic calls which isn’t ideal

:
So what's your suggestion here? The current logic in AMDGPUCodeGenPrepare is to find cases that we can insert the intrinsic to generate "Faster 2.5 ULP division that does not support denormals."
Otherwise SIISelLowering will lower FDIV32 UnsafeMath and Demorm support.

Update based on the comments

Add test case.

update the test based on the comment:

1. use a defined comparison
2. remove "unreachable", and make it branch to exit.

Rebase and update the diffs.

1. Remove the use of structs to simplify the test
2. generate llc checks with utils/update_llc_test_checks.py

I am working on a regression caused by this patch. It is a memory access fault actually.
However, if we put back the original consition, my test would pass.

Add comment to the test

update the test with update_test_checks.py

Fix a typo and add a test.

Remove the unused Target Instruction Info argument in a couple functions.

Use MachineInstr::mayAlias to replace areMemAccessesTriviallyDisjoint in LoadStoreOptimizer pass.

Update based on reviewer's suggestions:

1. -check-prefix=GCN
2. addrspace(0) is not needed.

In D56454#1350348, @arsenm wrote:

This problem isn't limited to private address space. This should have tests for every address space, and with cases using unrelated bases

In D56454#1350293, @rampitec wrote:

Can you add a test where low half does not produce a chain? An arithmetic operation and an undef.

Update based on the comments from the reviewers:

update the test based on the following suggestion:

There should be no unnamed variables left.

Cheap check first.

In D55241#1323977, @arsenm wrote:

No, it's not committed. Variable + constant is a common case in general.

It would probably be better to do this fold in the DAG for now though

Fix typos.

In D55241#1317703, @arsenm wrote:

D30466 is the primitive computeKnownBits

In D55241#1317688, @arsenm wrote:

In D55241#1317631, @cfang wrote:

In D55241#1317630, @arsenm wrote:

We should try to use some known bits information to keep this. I have a patch to add a machine version, but there might be a better way

Would you please explain how would your knownbit approach resolve the negative index issue while keep the optimization for gfx9+?
Or just post your patch. Thanks.

If you know the base index isn't negative, you don't need to disable this

In D55241#1317630, @arsenm wrote:

We should try to use some known bits information to keep this. I have a patch to add a machine version, but there might be a better way

Add test for non-uniform case.

Thanks Justin for your comment. I added Daniel as a reviewer.