[llvm] [RegAlloc] Relax the split constrain on MBB prolog (PR #168259)

[Daniil Fukalov via llvm-commits]

================
@@ -1,17 +1,97 @@
-# REQUIRES: asserts
-# RUN: llc -mtriple=amdgcn-- -verify-machineinstrs -debug-only=regalloc -run-pass=greedy -filetype=null %s 2>&1 | FileCheck %s
+# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py UTC_ARGS: --version 6
+# RUN: llc -mtriple=amdgcn-- -verify-machineinstrs -run-pass=greedy -o - %s | FileCheck %s
 
 ---
-# Check that physreg candidate is not used since cannot be spilled in a block,
-# e.g. before exec mask preamble
-# CHECK-NOT: , cannot spill all interferences.
+# Check that spill save/restore should be inserted after $exec mask is defined.
 
 name:            foo
 tracksRegLiveness: true
 machineFunctionInfo:
   scratchRSrcReg: $sgpr0_sgpr1_sgpr2_sgpr3
   stackPtrOffsetReg: $sgpr32
 body:             |
+  ; CHECK-LABEL: name: foo
+  ; CHECK: bb.0:
+  ; CHECK-NEXT:   successors: %bb.1(0x80000000)
+  ; CHECK-NEXT:   liveins: $sgpr96_sgpr97, $sgpr98_sgpr99, $sgpr100_sgpr101, $sgpr102_sgpr103
+  ; CHECK-NEXT: {{  $}}
+  ; CHECK-NEXT:   dead [[COPY:%[0-9]+]]:sreg_64 = COPY $sgpr102_sgpr103
+  ; CHECK-NEXT:   [[COPY1:%[0-9]+]]:sgpr_128 = COPY $sgpr100_sgpr101_sgpr102_sgpr103
+  ; CHECK-NEXT:   SI_SPILL_S128_SAVE [[COPY1]], %stack.0, implicit $exec, implicit $sgpr32 :: (store (s128) into %stack.0, align 4, addrspace 5)
+  ; CHECK-NEXT:   SI_SPILL_S128_SAVE [[COPY1]], %stack.1, implicit $exec, implicit $sgpr32 :: (store (s128) into %stack.1, align 4, addrspace 5)
+  ; CHECK-NEXT:   SI_SPILL_S128_SAVE [[COPY1]], %stack.2, implicit $exec, implicit $sgpr32 :: (store (s128) into %stack.2, align 4, addrspace 5)
+  ; CHECK-NEXT:   SI_SPILL_S128_SAVE [[COPY1]], %stack.3, implicit $exec, implicit $sgpr32 :: (store (s128) into %stack.3, align 4, addrspace 5)
+  ; CHECK-NEXT:   SI_SPILL_S128_SAVE [[COPY1]], %stack.4, implicit $exec, implicit $sgpr32 :: (store (s128) into %stack.4, align 4, addrspace 5)
+  ; CHECK-NEXT:   [[COPY2:%[0-9]+]]:sgpr_128 = COPY [[COPY1]]
+  ; CHECK-NEXT:   [[COPY3:%[0-9]+]]:sgpr_128 = COPY [[COPY1]]
+  ; CHECK-NEXT:   [[COPY4:%[0-9]+]]:sgpr_128 = COPY [[COPY1]]
+  ; CHECK-NEXT:   [[COPY5:%[0-9]+]]:sgpr_128 = COPY [[COPY1]]
+  ; CHECK-NEXT:   [[COPY6:%[0-9]+]]:sgpr_128 = COPY [[COPY1]]
+  ; CHECK-NEXT:   [[COPY7:%[0-9]+]]:sgpr_128 = COPY [[COPY1]]
+  ; CHECK-NEXT:   [[COPY8:%[0-9]+]]:sgpr_128 = COPY [[COPY1]]
+  ; CHECK-NEXT:   [[COPY9:%[0-9]+]]:sgpr_128 = COPY [[COPY1]]
+  ; CHECK-NEXT:   [[COPY10:%[0-9]+]]:sgpr_128 = COPY [[COPY1]]
+  ; CHECK-NEXT:   [[COPY11:%[0-9]+]]:sgpr_128 = COPY [[COPY1]]
+  ; CHECK-NEXT:   [[COPY12:%[0-9]+]]:sgpr_128 = COPY [[COPY1]]
+  ; CHECK-NEXT:   [[COPY13:%[0-9]+]]:sgpr_128 = COPY [[COPY1]]
+  ; CHECK-NEXT:   [[COPY14:%[0-9]+]]:sgpr_128 = COPY [[COPY1]]
+  ; CHECK-NEXT:   [[COPY15:%[0-9]+]]:sgpr_128 = COPY [[COPY1]]
+  ; CHECK-NEXT:   [[COPY16:%[0-9]+]]:sgpr_128 = COPY [[COPY1]]
+  ; CHECK-NEXT:   [[COPY17:%[0-9]+]]:sgpr_128 = COPY [[COPY1]]
+  ; CHECK-NEXT:   [[COPY18:%[0-9]+]]:sgpr_128 = COPY [[COPY1]]
+  ; CHECK-NEXT:   [[COPY19:%[0-9]+]]:sgpr_128 = COPY [[COPY1]]
+  ; CHECK-NEXT:   [[COPY20:%[0-9]+]]:sgpr_128 = COPY [[COPY1]]
+  ; CHECK-NEXT:   [[COPY21:%[0-9]+]]:sgpr_128 = COPY [[COPY1]]
+  ; CHECK-NEXT:   S_BRANCH %bb.1
+  ; CHECK-NEXT: {{  $}}
+  ; CHECK-NEXT: bb.1:
+  ; CHECK-NEXT:   successors: %bb.3(0x40000000), %bb.2(0x40000000)
+  ; CHECK-NEXT:   liveins: $sgpr96_sgpr97, $sgpr98_sgpr99, $sgpr102_sgpr103
+  ; CHECK-NEXT: {{  $}}
+  ; CHECK-NEXT:   [[S_OR_SAVEEXEC_B64_:%[0-9]+]]:sreg_64 = S_OR_SAVEEXEC_B64 $sgpr96_sgpr97, implicit-def $exec, implicit-def $scc, implicit $exec
+  ; CHECK-NEXT:   $exec = S_XOR_B64_term $exec, [[S_OR_SAVEEXEC_B64_]], implicit-def $scc
+  ; CHECK-NEXT:   S_CBRANCH_EXECZ %bb.3, implicit $exec
+  ; CHECK-NEXT:   S_BRANCH %bb.2
+  ; CHECK-NEXT: {{  $}}
+  ; CHECK-NEXT: bb.2:
+  ; CHECK-NEXT:   successors: %bb.3(0x40000000), %bb.4(0x40000000)
+  ; CHECK-NEXT:   liveins: $sgpr98_sgpr99, $sgpr102_sgpr103
+  ; CHECK-NEXT: {{  $}}
+  ; CHECK-NEXT:   [[S_OR_SAVEEXEC_B64_1:%[0-9]+]]:sreg_64 = S_OR_SAVEEXEC_B64 $sgpr98_sgpr99, implicit-def $exec, implicit-def $scc, implicit $exec
+  ; CHECK-NEXT:   $exec = S_XOR_B64_term $exec, [[S_OR_SAVEEXEC_B64_1]], implicit-def $scc
+  ; CHECK-NEXT:   S_CBRANCH_EXECZ %bb.3, implicit $exec
+  ; CHECK-NEXT:   S_BRANCH %bb.4
+  ; CHECK-NEXT: {{  $}}
+  ; CHECK-NEXT: bb.3:
+  ; CHECK-NEXT:   successors: %bb.4(0x80000000)
+  ; CHECK-NEXT:   liveins: $sgpr102_sgpr103
+  ; CHECK-NEXT: {{  $}}
+  ; CHECK-NEXT:   [[S_OR_SAVEEXEC_B64_1:%[0-9]+]]:sreg_64 = S_OR_SAVEEXEC_B64 $sgpr102_sgpr103, implicit-def $exec, implicit-def $scc, implicit $exec
+  ; CHECK-NEXT:   $exec = S_XOR_B64_term $exec, [[S_OR_SAVEEXEC_B64_1]], implicit-def $scc
+  ; CHECK-NEXT:   S_BRANCH %bb.4
+  ; CHECK-NEXT: {{  $}}
+  ; CHECK-NEXT: bb.4:
+  ; CHECK-NEXT:   $exec = IMPLICIT_DEF
+  ; CHECK-NEXT:   [[SI_SPILL_S128_RESTORE:%[0-9]+]]:sgpr_128 = SI_SPILL_S128_RESTORE %stack.0, implicit $exec, implicit $sgpr32 :: (load (s128) from %stack.0, align 4, addrspace 5)
+  ; CHECK-NEXT:   S_CMP_EQ_U64 [[COPY1]].sub0_sub1, [[SI_SPILL_S128_RESTORE]].sub2_sub3, implicit-def $scc
+  ; CHECK-NEXT:   [[SI_SPILL_S128_RESTORE1:%[0-9]+]]:sgpr_128 = SI_SPILL_S128_RESTORE %stack.1, implicit $exec, implicit $sgpr32 :: (load (s128) from %stack.1, align 4, addrspace 5)
----------------
dfukalov wrote:

Hi, sorry for the delay, I need to double-check the original issue is still fixed. Please give me a couple of days.

https://github.com/llvm/llvm-project/pull/168259