1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-25 04:02:41 +01:00
llvm-mirror/test/CodeGen/AMDGPU/i1-copy-phi.ll
Nicolai Haehnle 734b898f0d AMDGPU: Rewrite SILowerI1Copies to always stay on SALU
Summary:
Instead of writing boolean values temporarily into 32-bit VGPRs
if they are involved in PHIs or are observed from outside a loop,
we use bitwise masking operations to combine lane masks in a way
that is consistent with wave control flow.

Move SIFixSGPRCopies to before this pass, since that pass
incorrectly attempts to move SGPR phis to VGPRs.

This should recover most of the code quality that was lost with
the bug fix in "AMDGPU: Remove PHI loop condition optimization".

There are still some relevant cases where code quality could be
improved, in particular:

- We often introduce redundant masks with EXEC. Ideally, we'd
  have a generic computeKnownBits-like analysis to determine
  whether masks are already masked by EXEC, so we can avoid this
  masking both here and when lowering uniform control flow.

- The criterion we use to determine whether a def is observed
  from outside a loop is conservative: it doesn't check whether
  (loop) branch conditions are uniform.

Change-Id: Ibabdb373a7510e426b90deef00f5e16c5d56e64b

Reviewers: arsenm, rampitec, tpr

Subscribers: kzhuravl, jvesely, wdng, mgorny, yaxunl, dstuttard, t-tye, eraman, llvm-commits

Differential Revision: https://reviews.llvm.org/D53496

llvm-svn: 345719
2018-10-31 13:27:08 +00:00

40 lines
1.1 KiB
LLVM

; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefix=SI %s
; RUN: llc -march=amdgcn -mcpu=tonga -verify-machineinstrs < %s | FileCheck -check-prefix=SI %s
; SI-LABEL: {{^}}br_i1_phi:
; SI: ; %bb
; SI: s_mov_b64 [[TMP:s\[[0-9]+:[0-9]+\]]], 0
; SI: ; %bb2
; SI: s_mov_b64 [[TMP]], exec
; SI: ; %bb3
; SI: s_and_saveexec_b64 {{s\[[0-9]+:[0-9]+\]}}, [[TMP]]
define amdgpu_kernel void @br_i1_phi(i32 %arg) {
bb:
%tidig = call i32 @llvm.amdgcn.workitem.id.x()
%cmp = trunc i32 %tidig to i1
br i1 %cmp, label %bb2, label %bb3
bb2: ; preds = %bb
br label %bb3
bb3: ; preds = %bb2, %bb
%tmp = phi i1 [ true, %bb2 ], [ false, %bb ]
br i1 %tmp, label %bb4, label %bb6
bb4: ; preds = %bb3
%val = load volatile i32, i32 addrspace(1)* undef
%tmp5 = mul i32 %val, %arg
br label %bb6
bb6: ; preds = %bb4, %bb3
ret void
}
declare i32 @llvm.amdgcn.workitem.id.x() #0
attributes #0 = { nounwind readnone }