[PATCH] D147682: AMDGPU: Add a test to show bad compilation to set_inactive

[Ruiling, Song via Phabricator via llvm-commits]

ruiling created this revision.
ruiling added reviewers: arsenm, foad.
Herald added subscribers: kosarev, StephenFan, kerbowa, tpr, dstuttard, yaxunl, jvesely, kzhuravl.
Herald added a project: All.
ruiling requested review of this revision.
Herald added subscribers: llvm-commits, wdng.
Herald added a project: LLVM.

The set_inactive was originally inside a if branch, but was incorrectly
hoisted out of the loop. So the lanes that were disabled later after the
if() branch inside the loop were not set correctly. It should stay in
the if branch.


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D147682

Files:
  llvm/test/CodeGen/AMDGPU/should-not-hoist-set-inactive.ll


Index: llvm/test/CodeGen/AMDGPU/should-not-hoist-set-inactive.ll
===================================================================
--- /dev/null
+++ llvm/test/CodeGen/AMDGPU/should-not-hoist-set-inactive.ll
@@ -0,0 +1,75 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 2
+; RUN: llc -march=amdgcn -mcpu=gfx1010 -verify-machineinstrs < %s | FileCheck %s -check-prefix=GCN
+
+define amdgpu_cs void @should_not_hoist_set_inactive(<4 x i32> inreg %i14, i32 inreg %v, i32 %lane, i32 %f, i32 %f2) #0 {
+; GCN-LABEL: should_not_hoist_set_inactive:
+; GCN:       ; %bb.0: ; %.entry
+; GCN-NEXT:    v_cmp_gt_i32_e32 vcc_lo, 3, v1
+; GCN-NEXT:    v_cmp_eq_u32_e64 s6, 0, v0
+; GCN-NEXT:    v_cmp_ne_u32_e64 s5, 0, v2
+; GCN-NEXT:    v_mov_b32_e32 v3, s4
+; GCN-NEXT:    s_not_b32 exec_lo, exec_lo
+; GCN-NEXT:    v_mov_b32_e32 v3, 0
+; GCN-NEXT:    s_not_b32 exec_lo, exec_lo
+; GCN-NEXT:    s_mov_b32 s4, 0
+; GCN-NEXT:    s_branch .LBB0_2
+; GCN-NEXT:  .LBB0_1: ; %bb4
+; GCN-NEXT:    ; in Loop: Header=BB0_2 Depth=1
+; GCN-NEXT:    s_waitcnt_depctr 0xffe3
+; GCN-NEXT:    s_or_b32 exec_lo, exec_lo, s7
+; GCN-NEXT:    s_andn2_b32 exec_lo, exec_lo, s4
+; GCN-NEXT:    s_cbranch_execz .LBB0_5
+; GCN-NEXT:  .LBB0_2: ; %bb
+; GCN-NEXT:    ; =>This Inner Loop Header: Depth=1
+; GCN-NEXT:    s_and_b32 s7, exec_lo, s5
+; GCN-NEXT:    s_or_b32 s4, s7, s4
+; GCN-NEXT:    s_and_saveexec_b32 s7, vcc_lo
+; GCN-NEXT:    s_cbranch_execz .LBB0_1
+; GCN-NEXT:  ; %bb.3: ; %bb1
+; GCN-NEXT:    ; in Loop: Header=BB0_2 Depth=1
+; GCN-NEXT:    s_or_saveexec_b32 s8, -1
+; GCN-NEXT:    v_mov_b32_e32 v4, 0
+; GCN-NEXT:    v_mov_b32_dpp v4, v3 row_xmask:1 row_mask:0xf bank_mask:0xf
+; GCN-NEXT:    s_mov_b32 exec_lo, s8
+; GCN-NEXT:    v_mov_b32_e32 v0, v4
+; GCN-NEXT:    s_and_b32 exec_lo, exec_lo, s6
+; GCN-NEXT:    s_cbranch_execz .LBB0_1
+; GCN-NEXT:  ; %bb.4: ; %bb2
+; GCN-NEXT:    ; in Loop: Header=BB0_2 Depth=1
+; GCN-NEXT:    buffer_atomic_add v0, off, s[0:3], 0
+; GCN-NEXT:    s_branch .LBB0_1
+; GCN-NEXT:  .LBB0_5: ; %bb5
+; GCN-NEXT:    s_endpgm
+.entry:
+  br label %bb
+
+bb:
+  %i17 = icmp slt i32 %f, 3
+  br i1 %i17, label %bb1, label %bb4
+
+bb1:
+  %i25 = call i32 @llvm.amdgcn.set.inactive.i32(i32 %v, i32 0)
+  %i26 = call i32 @llvm.amdgcn.update.dpp.i32(i32 0, i32 %i25, i32 353, i32 15, i32 15, i1 false)
+  %i38 = call i32 @llvm.amdgcn.strict.wwm.i32(i32 %i26)
+  %i39 = icmp eq i32 %lane, 0
+  br i1 %i39, label %bb2, label %bb3
+
+bb2:
+  %i41 = call i32 @llvm.amdgcn.raw.buffer.atomic.add.i32(i32 %i38, <4 x i32> %i14, i32 0, i32 0, i32 0)
+  br label %bb3
+
+bb3:
+  br label %bb4
+
+bb4:
+  %exit = icmp eq i32 %f2, 0
+  br i1 %exit, label %bb, label %bb5
+
+bb5:
+  ret void
+}
+
+declare i32 @llvm.amdgcn.set.inactive.i32(i32, i32)
+declare i32 @llvm.amdgcn.update.dpp.i32(i32, i32, i32 immarg, i32 immarg, i32 immarg, i1 immarg)
+declare i32 @llvm.amdgcn.strict.wwm.i32(i32)
+declare i32 @llvm.amdgcn.raw.buffer.atomic.add.i32(i32, <4 x i32>, i32, i32, i32 immarg)


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D147682.511290.patch
Type: text/x-patch
Size: 3036 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20230406/54ad1d29/attachment.bin>