[AMDGPU] Remove integer division in VOPD checks

There is no way any compiler can simplify this division, while the check is done rather often. Differential Revision: https://reviews.llvm.org/D152613
llvm · Jun 12, 2023 · e2903ab · e2903ab
1 parent f09cca4
commit e2903ab
Show file tree

Hide file tree

Showing 2 changed files with 6 additions and 4 deletions.
diff --git a/llvm/lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.cpp b/llvm/lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.cpp
@@ -577,9 +577,10 @@ std::optional<unsigned> InstInfo::getInvalidCompOperandIndex(
 
   unsigned CompOprIdx;
   for (CompOprIdx = 0; CompOprIdx < Component::MAX_OPR_NUM; ++CompOprIdx) {
-    unsigned BanksNum = BANKS_NUM[CompOprIdx];
+    unsigned BanksMasks = VOPD_VGPR_BANK_MASKS[CompOprIdx];
     if (OpXRegs[CompOprIdx] && OpYRegs[CompOprIdx] &&
-        (OpXRegs[CompOprIdx] % BanksNum == OpYRegs[CompOprIdx] % BanksNum))
+        ((OpXRegs[CompOprIdx] & BanksMasks) ==
+         (OpYRegs[CompOprIdx] & BanksMasks)))
       return CompOprIdx;
   }
 

diff --git a/llvm/lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.h b/llvm/lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.h
@@ -560,8 +560,9 @@ enum Component : unsigned {
   MAX_OPR_NUM = DST_NUM + MAX_SRC_NUM
 };
 
-// Number of VGPR banks per VOPD component operand.
-constexpr unsigned BANKS_NUM[] = {2, 4, 4, 2};
+// LSB mask for VGPR banks per VOPD component operand.
+// 4 banks result in a mask 3, setting 2 lower bits.
+constexpr unsigned VOPD_VGPR_BANK_MASKS[] = {1, 3, 3, 1};
 
 enum ComponentIndex : unsigned { X = 0, Y = 1 };
 constexpr unsigned COMPONENTS[] = {ComponentIndex::X, ComponentIndex::Y};