[PATCH] D147683: AMDGPU: mark SET_INACTIVE_* as convergent operation

Ruiling, Song via Phabricator via llvm-commits llvm-commits at lists.llvm.org
Wed Apr 5 23:45:13 PDT 2023


ruiling created this revision.
ruiling added reviewers: arsenm, foad, critson, nhaehnle.
Herald added subscribers: kosarev, StephenFan, kerbowa, hiraditya, 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.

set_inactive is actually a kind of operation that is passing certain
value from active threads to inactive threads. In later WWM operation,
the activated threads which were disabled before would read such
values passed to them by set_inactive operation. So I think the
set_inactive is a convergent operation.


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D147683

Files:
  llvm/lib/Target/AMDGPU/SIInstructions.td
  llvm/test/CodeGen/AMDGPU/should-not-hoist-set-inactive.ll


Index: llvm/test/CodeGen/AMDGPU/should-not-hoist-set-inactive.ll
===================================================================
--- llvm/test/CodeGen/AMDGPU/should-not-hoist-set-inactive.ll
+++ llvm/test/CodeGen/AMDGPU/should-not-hoist-set-inactive.ll
@@ -5,34 +5,34 @@
 ; 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:    v_cmp_eq_u32_e64 s5, 0, v0
+; GCN-NEXT:    v_cmp_ne_u32_e64 s6, 0, v2
+; GCN-NEXT:    s_mov_b32 s7, 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_or_b32 exec_lo, exec_lo, s8
+; GCN-NEXT:    s_andn2_b32 exec_lo, exec_lo, s7
 ; 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_and_b32 s8, exec_lo, s6
+; GCN-NEXT:    s_or_b32 s7, s8, s7
+; GCN-NEXT:    s_and_saveexec_b32 s8, 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 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_or_saveexec_b32 s9, -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:    s_mov_b32 exec_lo, s9
 ; GCN-NEXT:    v_mov_b32_e32 v0, v4
-; GCN-NEXT:    s_and_b32 exec_lo, exec_lo, s6
+; GCN-NEXT:    s_and_b32 exec_lo, exec_lo, s5
 ; GCN-NEXT:    s_cbranch_execz .LBB0_1
 ; GCN-NEXT:  ; %bb.4: ; %bb2
 ; GCN-NEXT:    ; in Loop: Header=BB0_2 Depth=1
Index: llvm/lib/Target/AMDGPU/SIInstructions.td
===================================================================
--- llvm/lib/Target/AMDGPU/SIInstructions.td
+++ llvm/lib/Target/AMDGPU/SIInstructions.td
@@ -222,7 +222,7 @@
 
 // Invert the exec mask and overwrite the inactive lanes of dst with inactive,
 // restoring it after we're done.
-let Defs = [SCC] in {
+let Defs = [SCC], isConvergent = 1 in {
 def V_SET_INACTIVE_B32 : VPseudoInstSI <(outs VGPR_32:$vdst),
   (ins VSrc_b32: $src, VSrc_b32:$inactive),
   [(set i32:$vdst, (int_amdgcn_set_inactive i32:$src, i32:$inactive))]> {


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D147683.511291.patch
Type: text/x-patch
Size: 2891 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20230406/67975a83/attachment.bin>


More information about the llvm-commits mailing list