[llvm] True16 Add OpSel when optimizing exec mask (PR #128928)

[Brox Chen via llvm-commits]

https://github.com/broxigarchen updated https://github.com/llvm/llvm-project/pull/128928

>From 0ec718f6dd351d79a7a72e32c187c264d7627dff Mon Sep 17 00:00:00 2001
From: guochen2 <guochen2 at amd.com>
Date: Wed, 26 Feb 2025 13:13:05 -0500
Subject: [PATCH]  True16 Add OpSel when optimizing exec mask

True16 VOPCX have the opsel argument. Add it when we create these
instructions in SIOptimizeExecMasking.
---
 .../Target/AMDGPU/SIOptimizeExecMasking.cpp   |  2 +
 llvm/test/CodeGen/AMDGPU/true16-saveexec.mir  | 64 +++++++++++++++++++
 2 files changed, 66 insertions(+)
 create mode 100644 llvm/test/CodeGen/AMDGPU/true16-saveexec.mir

diff --git a/llvm/lib/Target/AMDGPU/SIOptimizeExecMasking.cpp b/llvm/lib/Target/AMDGPU/SIOptimizeExecMasking.cpp
index 920c3e11e4718..745e4086bc7fe 100644
--- a/llvm/lib/Target/AMDGPU/SIOptimizeExecMasking.cpp
+++ b/llvm/lib/Target/AMDGPU/SIOptimizeExecMasking.cpp
@@ -632,6 +632,8 @@ bool SIOptimizeExecMasking::optimizeVCMPSaveExecSequence(
 
   TryAddImmediateValueFromNamedOperand(AMDGPU::OpName::clamp);
 
+  TryAddImmediateValueFromNamedOperand(AMDGPU::OpName::op_sel);
+
   // The kill flags may no longer be correct.
   if (Src0->isReg())
     MRI->clearKillFlags(Src0->getReg());
diff --git a/llvm/test/CodeGen/AMDGPU/true16-saveexec.mir b/llvm/test/CodeGen/AMDGPU/true16-saveexec.mir
new file mode 100644
index 0000000000000..07259a1d031f3
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/true16-saveexec.mir
@@ -0,0 +1,64 @@
+# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py UTC_ARGS: --version 2
+# RUN: llc -march=amdgcn -mcpu=gfx1100 -mattr=+wavefrontsize64 -run-pass=si-optimize-exec-masking -verify-machineinstrs -o - %s | FileCheck %s
+
+---
+name:            int
+tracksRegLiveness: true
+body:             |
+  ; CHECK-LABEL: name: int
+  ; CHECK: bb.0:
+  ; CHECK-NEXT:   successors: %bb.1(0x80000000)
+  ; CHECK-NEXT:   liveins: $vgpr20
+  ; CHECK-NEXT: {{  $}}
+  ; CHECK-NEXT:   $sgpr0_sgpr1 = S_MOV_B64 $exec
+  ; CHECK-NEXT:   V_CMPX_LT_I16_t16_nosdst_e64 0, 15, 0, $vgpr20_lo16, 0, implicit-def $exec, implicit $exec
+  ; CHECK-NEXT:   renamable $sgpr0_sgpr1 = S_XOR_B64 $exec, killed renamable $sgpr0_sgpr1, implicit-def dead $scc
+  ; CHECK-NEXT:   S_CBRANCH_EXECZ %bb.1, implicit $exec
+  ; CHECK-NEXT:   S_BRANCH %bb.1
+  ; CHECK-NEXT: {{  $}}
+  ; CHECK-NEXT: bb.1:
+  ; CHECK-NEXT:   S_ENDPGM 0
+  bb.1:
+    liveins: $vgpr20
+    $vcc = V_CMP_LT_I16_t16_e64 0, 15, 0, $vgpr20_lo16, 0, implicit $exec
+    renamable $sgpr0_sgpr1 = COPY $exec, implicit-def $exec
+    renamable $sgpr2_sgpr3 = S_AND_B64 renamable $sgpr0_sgpr1, killed $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
+    S_CBRANCH_EXECZ %bb.2, implicit $exec
+    S_BRANCH %bb.2
+
+  bb.2:
+    S_ENDPGM 0
+...
+
+---
+name:            float
+tracksRegLiveness: true
+body:             |
+  ; CHECK-LABEL: name: float
+  ; CHECK: bb.0:
+  ; CHECK-NEXT:   successors: %bb.1(0x80000000)
+  ; CHECK-NEXT:   liveins: $vgpr20
+  ; CHECK-NEXT: {{  $}}
+  ; CHECK-NEXT:   $sgpr0_sgpr1 = S_MOV_B64 $exec
+  ; CHECK-NEXT:   V_CMPX_LT_F16_t16_nosdst_e64 0, 15, 0, $vgpr20_lo16, 1, 0, implicit-def $exec, implicit $mode, implicit $exec
+  ; CHECK-NEXT:   renamable $sgpr0_sgpr1 = S_XOR_B64 $exec, killed renamable $sgpr0_sgpr1, implicit-def dead $scc
+  ; CHECK-NEXT:   S_CBRANCH_EXECZ %bb.1, implicit $exec
+  ; CHECK-NEXT:   S_BRANCH %bb.1
+  ; CHECK-NEXT: {{  $}}
+  ; CHECK-NEXT: bb.1:
+  ; CHECK-NEXT:   S_ENDPGM 0
+  bb.1:
+    liveins: $vgpr20
+    $vcc = V_CMP_LT_F16_t16_e64 0, 15, 0, $vgpr20_lo16, 1, 0, implicit $exec, implicit $mode
+    renamable $sgpr0_sgpr1 = COPY $exec, implicit-def $exec
+    renamable $sgpr2_sgpr3 = S_AND_B64 renamable $sgpr0_sgpr1, killed $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
+    S_CBRANCH_EXECZ %bb.2, implicit $exec
+    S_BRANCH %bb.2
+
+  bb.2:
+    S_ENDPGM 0
+...