From f7d5ce97f63149a060841af9e2a2c213b0cba0b3 Mon Sep 17 00:00:00 2001
From: Matt Arsenault <Matthew.Arsenault@amd.com>
Date: Thu, 23 Jul 2020 19:42:37 -0400
Subject: [PATCH] AMDGPU: Optimize copies to exec with other insts after exec
 def

It's possible to have terminator instructions after a write to exec,
so skip over them to find it.
---
 lib/Target/AMDGPU/SIOptimizeExecMasking.cpp   | 17 +++++--
 ...ize-exec-copies-extra-insts-after-copy.mir | 51 +++++++++++++++++++
 2 files changed, 65 insertions(+), 3 deletions(-)
 create mode 100644 test/CodeGen/AMDGPU/optimize-exec-copies-extra-insts-after-copy.mir

diff --git a/lib/Target/AMDGPU/SIOptimizeExecMasking.cpp b/lib/Target/AMDGPU/SIOptimizeExecMasking.cpp
index 2994d1954d7..449b6287a87 100644
--- a/lib/Target/AMDGPU/SIOptimizeExecMasking.cpp
+++ b/lib/Target/AMDGPU/SIOptimizeExecMasking.cpp
@@ -300,9 +300,20 @@ bool SIOptimizeExecMasking::runOnMachineFunction(MachineFunction &MF) {
     if (I == E)
       continue;
 
-    // TODO: It's possible to see other terminator copies after the exec copy.
-    Register CopyToExec = isCopyToExec(*I, ST);
-    if (!CopyToExec.isValid())
+    // It's possible to see other terminator copies after the exec copy. This
+    // can happen if control flow pseudos had their outputs used by phis.
+    Register CopyToExec;
+
+    unsigned SearchCount = 0;
+    const unsigned SearchLimit = 5;
+    while (I != E && SearchCount++ < SearchLimit) {
+      CopyToExec = isCopyToExec(*I, ST);
+      if (CopyToExec)
+        break;
+      ++I;
+    }
+
+    if (!CopyToExec)
       continue;
 
     // Scan backwards to find the def.
diff --git a/test/CodeGen/AMDGPU/optimize-exec-copies-extra-insts-after-copy.mir b/test/CodeGen/AMDGPU/optimize-exec-copies-extra-insts-after-copy.mir
new file mode 100644
index 00000000000..b0e67034a40
--- /dev/null
+++ b/test/CodeGen/AMDGPU/optimize-exec-copies-extra-insts-after-copy.mir
@@ -0,0 +1,51 @@
+# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
+# RUN: llc -march=amdgcn -mcpu=fiji -verify-machineinstrs -run-pass=si-optimize-exec-masking -o - %s | FileCheck %s
+
+# Make sure we can still optimize writes to exec when there are
+# additional terminators after the exec write. This can happen with
+# phi users of control flow intrinsics.
+
+---
+name: instructions_after_copy_to_exec
+tracksRegLiveness: true
+body:             |
+  ; CHECK-LABEL: name: instructions_after_copy_to_exec
+  ; CHECK: bb.0:
+  ; CHECK:   successors: %bb.2(0x40000000), %bb.1(0x40000000)
+  ; CHECK:   liveins: $vgpr0
+  ; CHECK:   renamable $vgpr1 = V_MOV_B32_e32 0, implicit $exec
+  ; CHECK:   renamable $vcc = V_CMP_EQ_U32_e64 0, killed $vgpr0, implicit $exec
+  ; CHECK:   $sgpr0_sgpr1 = S_AND_SAVEEXEC_B64 $vcc, implicit-def $exec, implicit-def $scc, implicit $exec
+  ; CHECK:   renamable $sgpr0_sgpr1 = S_XOR_B64 $exec, killed renamable $sgpr0_sgpr1, implicit-def dead $scc
+  ; CHECK:   renamable $sgpr0_sgpr1 = COPY killed renamable $sgpr0_sgpr1, implicit $exec
+  ; CHECK:   S_CBRANCH_EXECZ %bb.2, implicit $exec
+  ; CHECK: bb.1:
+  ; CHECK:   successors: %bb.2(0x80000000)
+  ; CHECK:   liveins: $sgpr0_sgpr1
+  ; CHECK:   S_NOP 0, implicit $sgpr0_sgpr1
+  ; CHECK: bb.2:
+  ; CHECK:   liveins: $sgpr0_sgpr1
+  ; CHECK:   S_NOP 0, implicit $sgpr0_sgpr1
+  bb.0:
+    liveins: $vgpr0
+
+    renamable $vgpr1 = V_MOV_B32_e32 0, implicit $exec
+    renamable $vcc = V_CMP_EQ_U32_e64 0, killed $vgpr0, implicit $exec
+    renamable $sgpr0_sgpr1 = COPY $exec, implicit-def $exec
+    renamable $sgpr2_sgpr3 = S_AND_B64 renamable $sgpr0_sgpr1, renamable $vcc, implicit-def dead $scc
+    renamable $sgpr0_sgpr1 = S_XOR_B64 renamable $sgpr2_sgpr3, killed renamable $sgpr0_sgpr1, implicit-def dead $scc
+    $exec = S_MOV_B64_term killed renamable $sgpr2_sgpr3
+    renamable $sgpr0_sgpr1 = S_MOV_B64_term killed renamable $sgpr0_sgpr1, implicit $exec
+    S_CBRANCH_EXECZ %bb.2, implicit $exec
+
+  bb.1:
+    liveins: $sgpr0_sgpr1
+
+    S_NOP 0, implicit $sgpr0_sgpr1
+
+  bb.2:
+    liveins: $sgpr0_sgpr1
+
+    S_NOP 0, implicit $sgpr0_sgpr1
+
+...