[llvm] [AMDGPU] Merge consecutive wait_alu instruction (PR #128916)

[Ana Mihajlovic via llvm-commits]

https://github.com/mihajlovicana created https://github.com/llvm/llvm-project/pull/128916

None

>From 2c77fd3998321dde8b0a221fc4ff544b014916dc Mon Sep 17 00:00:00 2001
From: Ana Mihajlovic <Ana.Mihajlovic at amd.com>
Date: Wed, 26 Feb 2025 18:20:55 +0100
Subject: [PATCH] merge consecutive wait_alu instructions

---
 .../Target/AMDGPU/AMDGPUWaitSGPRHazards.cpp   | 22 ++++++++++++++
 .../AMDGPU/merge-consecutive-wait-alus.mir    | 30 +++++++++++++++++++
 2 files changed, 52 insertions(+)
 create mode 100644 llvm/test/CodeGen/AMDGPU/merge-consecutive-wait-alus.mir

diff --git a/llvm/lib/Target/AMDGPU/AMDGPUWaitSGPRHazards.cpp b/llvm/lib/Target/AMDGPU/AMDGPUWaitSGPRHazards.cpp
index 4df55eac5d76b..bb15d12ada650 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPUWaitSGPRHazards.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUWaitSGPRHazards.cpp
@@ -164,6 +164,21 @@ class AMDGPUWaitSGPRHazards {
       BuildMI(MBB, MI, MI->getDebugLoc(), TII->get(AMDGPU::DS_NOP));
   }
 
+  unsigned mergeMasks(unsigned Mask1, unsigned Mask2) {
+    unsigned Mask = Mask1 & Mask2;
+
+    Mask = AMDGPU::DepCtr::encodeFieldVmVsrc(
+        Mask, std::min(AMDGPU::DepCtr::decodeFieldVmVsrc(Mask1),
+                       AMDGPU::DepCtr::decodeFieldVmVsrc(Mask2)));
+    Mask = AMDGPU::DepCtr::encodeFieldVaSdst(
+        Mask, std::min(AMDGPU::DepCtr::decodeFieldVaSdst(Mask1),
+                       AMDGPU::DepCtr::decodeFieldVaSdst(Mask2)));
+    Mask = AMDGPU::DepCtr::encodeFieldVaVdst(
+        Mask, std::min(AMDGPU::DepCtr::decodeFieldVaVdst(Mask1),
+                       AMDGPU::DepCtr::decodeFieldVaVdst(Mask2)));
+    return Mask;
+  }
+
   bool runOnMachineBasicBlock(MachineBasicBlock &MBB, bool Emit) {
     enum { WA_VALU = 0x1, WA_SALU = 0x2, WA_VCC = 0x4 };
 
@@ -362,6 +377,13 @@ class AMDGPUWaitSGPRHazards {
           Mask = AMDGPU::DepCtr::encodeFieldVaSdst(Mask, 0);
         }
         if (Emit) {
+          if (MI != MI->getParent()->begin()) {
+            MachineInstr &PrevMI = *std::prev(MI);
+            if (PrevMI.getOpcode() == AMDGPU::S_WAITCNT_DEPCTR) {
+              Mask = mergeMasks(Mask, PrevMI.getOperand(0).getImm());
+              PrevMI.eraseFromParent();
+            }
+          }
           auto NewMI = BuildMI(MBB, MI, MI->getDebugLoc(),
                                TII->get(AMDGPU::S_WAITCNT_DEPCTR))
                            .addImm(Mask);
diff --git a/llvm/test/CodeGen/AMDGPU/merge-consecutive-wait-alus.mir b/llvm/test/CodeGen/AMDGPU/merge-consecutive-wait-alus.mir
new file mode 100644
index 0000000000000..0cd203e6a9bbb
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/merge-consecutive-wait-alus.mir
@@ -0,0 +1,30 @@
+# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py UTC_ARGS: --version 5
+# RUN: llc -mtriple=amdgcn -mcpu=gfx1200 -verify-machineinstrs -run-pass amdgpu-wait-sgpr-hazards -o -  %s | FileCheck %s
+
+
+---
+name: merge_consecutive_wait_alus
+exposesReturnsTwice: false
+legalized:       false
+regBankSelected: false
+selected:        false
+failedISel:      false
+tracksRegLiveness: true
+body:             |
+  bb.0:
+    liveins: $vgpr0
+
+    ; CHECK-LABEL: name: merge_consecutive_wait_alus
+    ; CHECK: liveins: $vgpr0
+    ; CHECK-NEXT: {{  $}}
+    ; CHECK-NEXT: renamable $sgpr0 = V_CMP_NE_U32_e64 0, $vgpr0, implicit $exec, implicit-def $vcc_lo, implicit-def $vcc_lo
+    ; CHECK-NEXT: S_WAITCNT_DEPCTR 61946
+    ; CHECK-NEXT: renamable $vgpr0 = V_CNDMASK_B32_e64 0, -1, 0, killed $vgpr0, killed $sgpr0, implicit $exec, implicit-def $vcc_lo
+    renamable $sgpr0 = V_CMP_NE_U32_e64 0, $vgpr0, implicit $exec, implicit-def $vcc_lo, implicit-def $vcc
+    S_WAITCNT_DEPCTR 65530
+    renamable $vgpr0 = V_CNDMASK_B32_e64 0, -1, 0, killed $vgpr0, killed $sgpr0, implicit $exec, implicit-def $vcc
+...
+
+
+## NOTE: These prefixes are unused and the list is autogenerated. Do not add tests below this line:
+# CHECK: {{.*}}