[libunwind] [lld] [lldb] [clang] [clang-tools-extra] [compiler-rt] [llvm] [flang] [libcxx] [AMDGPU] - Add constant folding for s_quadmask (PR #72381)

[Jessica Del via cfe-commits]

https://github.com/OutOfCache updated https://github.com/llvm/llvm-project/pull/72381

>From 00d0f99207242befc8022031ccd8faf573cbf014 Mon Sep 17 00:00:00 2001
From: Jessica Del <Jessica.Del at amd.com>
Date: Tue, 14 Nov 2023 22:17:26 +0100
Subject: [PATCH 1/2] [AMDGPU] - Add constant folding for s_quadmask

If the input is a constant we can constant fold the `s_quadmask`
intrinsic.
---
 llvm/lib/Analysis/ConstantFolding.cpp            | 14 ++++++++++++++
 llvm/test/CodeGen/AMDGPU/llvm.amdgcn.quadmask.ll | 12 ++++--------
 2 files changed, 18 insertions(+), 8 deletions(-)

diff --git a/llvm/lib/Analysis/ConstantFolding.cpp b/llvm/lib/Analysis/ConstantFolding.cpp
index 966a65ac26b8017..40b5938fcda0c2a 100644
--- a/llvm/lib/Analysis/ConstantFolding.cpp
+++ b/llvm/lib/Analysis/ConstantFolding.cpp
@@ -1533,6 +1533,7 @@ bool llvm::canConstantFoldCallTo(const CallBase *Call, const Function *F) {
   case Intrinsic::amdgcn_perm:
   case Intrinsic::amdgcn_wave_reduce_umin:
   case Intrinsic::amdgcn_wave_reduce_umax:
+  case Intrinsic::amdgcn_s_quadmask:
   case Intrinsic::arm_mve_vctp8:
   case Intrinsic::arm_mve_vctp16:
   case Intrinsic::arm_mve_vctp32:
@@ -2422,6 +2423,19 @@ static Constant *ConstantFoldScalarCall1(StringRef Name,
 
       return ConstantFP::get(Ty->getContext(), Val);
     }
+
+    case Intrinsic::amdgcn_s_quadmask: {
+      uint64_t Val = Op->getZExtValue();
+      uint64_t QuadMask = 0;
+      for (unsigned i = 0; i < Op->getBitWidth() / 4; ++i, Val >>= 4) {
+        if (!(Val & 0xF))
+          continue;
+
+        QuadMask |= (1 << i);
+      }
+      return ConstantInt::get(Ty, QuadMask);
+    }
+
     default:
       return nullptr;
     }
diff --git a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.quadmask.ll b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.quadmask.ll
index 65443a6efa789d9..0f500c0999ad9a8 100644
--- a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.quadmask.ll
+++ b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.quadmask.ll
@@ -9,11 +9,10 @@ define i32 @test_quadmask_constant_i32() {
 ; GFX11-LABEL: test_quadmask_constant_i32:
 ; GFX11:       ; %bb.0: ; %entry
 ; GFX11-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GFX11-NEXT:    s_quadmask_b32 s0, 0x85fe3a92
-; GFX11-NEXT:    v_mov_b32_e32 v0, s0
+; GFX11-NEXT:    v_mov_b32_e32 v0, 0xcb
 ; GFX11-NEXT:    s_setpc_b64 s[30:31]
 entry:
-  %qm = call i32 @llvm.amdgcn.s.quadmask.i32(i32 u0x85FE3A92)
+  %qm = call i32 @llvm.amdgcn.s.quadmask.i32(i32 u0x85003092)
   ret i32 %qm
 }
 
@@ -50,13 +49,10 @@ define i64 @test_quadmask_constant_i64() {
 ; GFX11-LABEL: test_quadmask_constant_i64:
 ; GFX11:       ; %bb.0: ; %entry
 ; GFX11-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GFX11-NEXT:    s_mov_b32 s0, 0x85fe3a92
-; GFX11-NEXT:    s_mov_b32 s1, 0x67de48fc
-; GFX11-NEXT:    s_quadmask_b64 s[0:1], s[0:1]
-; GFX11-NEXT:    v_dual_mov_b32 v0, s0 :: v_dual_mov_b32 v1, s1
+; GFX11-NEXT:    v_dual_mov_b32 v0, 0xe3e6 :: v_dual_mov_b32 v1, 0
 ; GFX11-NEXT:    s_setpc_b64 s[30:31]
 entry:
-  %qm = call i64 @llvm.amdgcn.s.quadmask.i64(i64 u0x67DE48FC85FE3A92)
+  %qm = call i64 @llvm.amdgcn.s.quadmask.i64(i64 u0x67D000FC85F00A90)
   ret i64 %qm
 }
 

>From 144c4dc164ec137e518cfd647c116373e7a61b8f Mon Sep 17 00:00:00 2001
From: Jessica Del <Jessica.Del at amd.com>
Date: Wed, 15 Nov 2023 15:59:56 +0100
Subject: [PATCH 2/2] fixup! [AMDGPU] - Add constant folding for s_quadmask

---
 llvm/lib/Analysis/ConstantFolding.cpp | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/llvm/lib/Analysis/ConstantFolding.cpp b/llvm/lib/Analysis/ConstantFolding.cpp
index 40b5938fcda0c2a..39bbb04fbcf26cc 100644
--- a/llvm/lib/Analysis/ConstantFolding.cpp
+++ b/llvm/lib/Analysis/ConstantFolding.cpp
@@ -2427,11 +2427,11 @@ static Constant *ConstantFoldScalarCall1(StringRef Name,
     case Intrinsic::amdgcn_s_quadmask: {
       uint64_t Val = Op->getZExtValue();
       uint64_t QuadMask = 0;
-      for (unsigned i = 0; i < Op->getBitWidth() / 4; ++i, Val >>= 4) {
+      for (unsigned I = 0; I < Op->getBitWidth() / 4; ++I, Val >>= 4) {
         if (!(Val & 0xF))
           continue;
 
-        QuadMask |= (1 << i);
+        QuadMask |= (1 << I);
       }
       return ConstantInt::get(Ty, QuadMask);
     }