LowerTypeTests: Shrink check size by 1 instruction on x86.

llvm/lib/Transforms/IPO/LowerTypeTests.cpp

@@ -143,7 +143,7 @@ bool BitSetInfo::containsGlobalOffset(uint64_t Offset) const {
   if (BitOffset >= BitSize)
     return false;
 
-  return Bits.count(BitOffset);
+  return Bits.count(BitSize - 1 - BitOffset);
 }
 
 void BitSetInfo::print(raw_ostream &OS) const {
@@ -188,7 +188,11 @@ BitSetInfo BitSetBuilder::build() {
   BSI.BitSize = ((Max - Min) >> BSI.AlignLog2) + 1;
   for (uint64_t Offset : Offsets) {
     Offset >>= BSI.AlignLog2;
-    BSI.Bits.insert(Offset);
+    // We invert the order of bits when adding them to the bitset. This is
+    // because the offset that we test against is computed by subtracting the
+    // address that we are testing from the global's address, which means that
+    // the offset increases as the tested address decreases.
+    BSI.Bits.insert(BSI.BitSize - 1 - Offset);
   }
 
   return BSI;
@@ -465,7 +469,8 @@ class LowerTypeTestsModule {
   struct TypeIdLowering {
     TypeTestResolution::Kind TheKind = TypeTestResolution::Unsat;
 
-    /// All except Unsat: the start address within the combined global.
+    /// All except Unsat: the address of the last element within the combined
+    /// global.
     Constant *OffsetedGlobal;
 
     /// ByteArray, Inline, AllOnes: log2 of the required global alignment
@@ -772,7 +777,11 @@ Value *LowerTypeTestsModule::lowerTypeTestCall(Metadata *TypeId, CallInst *CI,
   if (TIL.TheKind == TypeTestResolution::Single)
     return B.CreateICmpEQ(PtrAsInt, OffsetedGlobalAsInt);
 
-  Value *PtrOffset = B.CreateSub(PtrAsInt, OffsetedGlobalAsInt);
+  // Here we compute `last element - address`. The reason why we do this instead
+  // of computing `address - first element` is that it leads to a slightly
+  // shorter instruction sequence on x86. Because it doesn't matter how we do
+  // the subtraction on other architectures, we do so unconditionally.
+  Value *PtrOffset = B.CreateSub(OffsetedGlobalAsInt, PtrAsInt);
 
   // We need to check that the offset both falls within our range and is
   // suitably aligned. We can check both properties at the same time by
@@ -1154,8 +1163,11 @@ void LowerTypeTestsModule::lowerTypeTestCalls(
 
     ByteArrayInfo *BAI = nullptr;
     TypeIdLowering TIL;
+
+    uint64_t GlobalOffset =
+        BSI.ByteOffset + ((BSI.BitSize - 1) << BSI.AlignLog2);
     TIL.OffsetedGlobal = ConstantExpr::getGetElementPtr(
-        Int8Ty, CombinedGlobalAddr, ConstantInt::get(IntPtrTy, BSI.ByteOffset)),
+        Int8Ty, CombinedGlobalAddr, ConstantInt::get(IntPtrTy, GlobalOffset)),
     TIL.AlignLog2 = ConstantInt::get(IntPtrTy, BSI.AlignLog2);
     TIL.SizeM1 = ConstantInt::get(IntPtrTy, BSI.BitSize - 1);
     if (BSI.isAllOnes()) {
@@ -2533,9 +2545,9 @@ PreservedAnalyses SimplifyTypeTestsPass::run(Module &M,
         continue;
       for (Use &U : make_early_inc_range(CE->uses())) {
         auto *CE = dyn_cast<ConstantExpr>(U.getUser());
-        if (U.getOperandNo() == 1 && CE &&
+        if (U.getOperandNo() == 0 && CE &&
             CE->getOpcode() == Instruction::Sub &&
-            MaySimplifyInt(CE->getOperand(0))) {
+            MaySimplifyInt(CE->getOperand(1))) {
           // This is a computation of PtrOffset as generated by
           // LowerTypeTestsModule::lowerTypeTestCall above. If
           // isKnownTypeIdMember passes we just pretend it evaluated to 0. This

llvm/test/Transforms/LowerTypeTests/aarch64-jumptable.ll

@@ -41,7 +41,7 @@ define i1 @foo(ptr %p) {
 ; AARCH64-LABEL: define i1 @foo
 ; AARCH64-SAME: (ptr [[P:%.*]]) {
 ; AARCH64-NEXT:    [[TMP1:%.*]] = ptrtoint ptr [[P]] to i64
-; AARCH64-NEXT:    [[TMP2:%.*]] = sub i64 [[TMP1]], ptrtoint (ptr @.cfi.jumptable to i64)
+; AARCH64-NEXT:    [[TMP2:%.*]] = sub i64 ptrtoint (ptr getelementptr (i8, ptr @.cfi.jumptable, i64 8) to i64), [[TMP1]]
 ; AARCH64-NEXT:    [[TMP3:%.*]] = call i64 @llvm.fshr.i64(i64 [[TMP2]], i64 [[TMP2]], i64 3)
 ; AARCH64-NEXT:    [[TMP4:%.*]] = icmp ule i64 [[TMP3]], 1
 ; AARCH64-NEXT:    ret i1 [[TMP4]]

llvm/test/Transforms/LowerTypeTests/asm.ll

@@ -3,10 +3,9 @@
 
 define void @call(ptr %p) {
   ; CHECK:      movl $__typeid_allones7_global_addr, %eax
-  ; CHECK-NEXT: movq %rdi, %rcx
-  ; CHECK-NEXT: subq %rax, %rcx
-  ; CHECK-NEXT: rorq $__typeid_allones7_align, %rcx
-  ; CHECK-NEXT: cmpq $__typeid_allones7_size_m1@ABS8, %rcx
+  ; CHECK-NEXT: subq %rdi, %rax
+  ; CHECK-NEXT: rorq $__typeid_allones7_align, %rax
+  ; CHECK-NEXT: cmpq $__typeid_allones7_size_m1@ABS8, %rax
   %x = call i1 @llvm.type.test(ptr %p, metadata !"allones7")
   br i1 %x, label %t, label %f
 

llvm/test/Transforms/LowerTypeTests/export-allones.ll

@@ -141,11 +141,11 @@
 
 ; CHECK: [[G:@[0-9]+]] = private constant { [2048 x i8] } zeroinitializer
 
-; CHECK: @__typeid_typeid1_global_addr = hidden alias i8, ptr [[G]]
+; CHECK: @__typeid_typeid1_global_addr = hidden alias i8, getelementptr (i8, ptr [[G]], i64 2)
 ; X86: @__typeid_typeid1_align = hidden alias i8, inttoptr (i64 1 to ptr)
 ; X86: @__typeid_typeid1_size_m1 = hidden alias i8, inttoptr (i64 1 to ptr)
 
-; CHECK: @__typeid_typeid2_global_addr = hidden alias i8, getelementptr (i8, ptr [[G]], i64 4)
+; CHECK: @__typeid_typeid2_global_addr = hidden alias i8, getelementptr (i8, ptr [[G]], i64 516)
 ; X86: @__typeid_typeid2_align = hidden alias i8, inttoptr (i64 2 to ptr)
 ; X86: @__typeid_typeid2_size_m1 = hidden alias i8, inttoptr (i64 128 to ptr)
 

llvm/test/Transforms/LowerTypeTests/export-bytearray.ll

@@ -14,13 +14,13 @@
 ; CHECK: [[G:@[0-9]+]] = private constant { [2048 x i8] } zeroinitializer
 ; CHECK: [[B:@[0-9]+]] = private constant [258 x i8] c"\03\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\02\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\00\01"
 
-; CHECK: @__typeid_typeid1_global_addr = hidden alias i8, ptr [[G]]
+; CHECK: @__typeid_typeid1_global_addr = hidden alias i8, getelementptr (i8, ptr [[G]], i64 130)
 ; X86: @__typeid_typeid1_align = hidden alias i8, inttoptr (i64 1 to ptr)
 ; X86: @__typeid_typeid1_size_m1 = hidden alias i8, inttoptr (i64 65 to ptr)
 ; CHECK: @__typeid_typeid1_byte_array = hidden alias i8, ptr @bits.1
 ; X86: @__typeid_typeid1_bit_mask = hidden alias i8, inttoptr (i8 2 to ptr)
 
-; CHECK: @__typeid_typeid2_global_addr = hidden alias i8, getelementptr (i8, ptr [[G]], i64 4)
+; CHECK: @__typeid_typeid2_global_addr = hidden alias i8, getelementptr (i8, ptr [[G]], i64 1032)
 ; X86: @__typeid_typeid2_align = hidden alias i8, inttoptr (i64 2 to ptr)
 ; X86: @__typeid_typeid2_size_m1 = hidden alias i8, inttoptr (i64 257 to ptr)
 ; CHECK: @__typeid_typeid2_byte_array = hidden alias i8, ptr @bits

llvm/test/Transforms/LowerTypeTests/export-icall.ll

@@ -36,7 +36,7 @@ define void @f3(i32 %x) !type !8 {
 !8 = !{i64 0, !"typeid3"}
 
 
-; CHECK-DAG: @__typeid_typeid1_global_addr = hidden alias i8, ptr [[JT1:.*]]
+; CHECK-DAG: @__typeid_typeid1_global_addr = hidden alias i8, getelementptr (i8, ptr [[JT1:.*]], i64 32)
 ; CHECK-DAG: @__typeid_typeid1_align = hidden alias i8, inttoptr (i64 3 to ptr)
 ; CHECK-DAG: @__typeid_typeid1_size_m1 = hidden alias i8, inttoptr (i64 4 to ptr)
 

llvm/test/Transforms/LowerTypeTests/export-inline.ll

@@ -13,12 +13,12 @@
 
 ; CHECK: [[G:@[0-9]+]] = private constant { [2048 x i8] } zeroinitializer
 
-; CHECK: @__typeid_typeid1_global_addr = hidden alias i8, ptr [[G]]
+; CHECK: @__typeid_typeid1_global_addr = hidden alias i8, getelementptr (i8, ptr [[G]], i64 6)
 ; CHECK-X86: @__typeid_typeid1_align = hidden alias i8, inttoptr (i8 1 to ptr)
 ; CHECK-X86: @__typeid_typeid1_size_m1 = hidden alias i8, inttoptr (i64 3 to ptr)
 ; CHECK-X86: @__typeid_typeid1_inline_bits = hidden alias i8, inttoptr (i32 9 to ptr)
 
-; CHECK: @__typeid_typeid2_global_addr = hidden alias i8, getelementptr (i8, ptr [[G]], i64 4)
+; CHECK: @__typeid_typeid2_global_addr = hidden alias i8, getelementptr (i8, ptr [[G]], i64 136)
 ; CHECK-X86: @__typeid_typeid2_align = hidden alias i8, inttoptr (i8 2 to ptr)
 ; CHECK-X86: @__typeid_typeid2_size_m1 = hidden alias i8, inttoptr (i64 33 to ptr)
 ; CHECK-X86: @__typeid_typeid2_inline_bits = hidden alias i8, inttoptr (i64 8589934593 to ptr)

llvm/test/Transforms/LowerTypeTests/function.ll

@@ -1,21 +1,21 @@
-; RUN: opt -S -passes=lowertypetests -mtriple=i686-unknown-linux-gnu %s | FileCheck --check-prefixes=X86,X86-LINUX,NATIVE %s
-; RUN: opt -S -passes=lowertypetests -mtriple=x86_64-unknown-linux-gnu %s | FileCheck --check-prefixes=X86,X86-LINUX,NATIVE %s
-; RUN: opt -S -passes=lowertypetests -mtriple=i686-pc-win32 %s | FileCheck --check-prefixes=X86,X86-WIN32,NATIVE %s
-; RUN: opt -S -passes=lowertypetests -mtriple=x86_64-pc-win32 %s | FileCheck --check-prefixes=X86,X86-WIN32,NATIVE %s
-; RUN: opt -S -passes=lowertypetests -mtriple=riscv32-unknown-linux-gnu %s | FileCheck --check-prefixes=RISCV,NATIVE %s
-; RUN: opt -S -passes=lowertypetests -mtriple=riscv64-unknown-linux-gnu %s | FileCheck --check-prefixes=RISCV,NATIVE %s
+; RUN: opt -S -passes=lowertypetests -mtriple=i686-unknown-linux-gnu %s | FileCheck --check-prefixes=X86,X86-LINUX,NATIVE,JT8 %s
+; RUN: opt -S -passes=lowertypetests -mtriple=x86_64-unknown-linux-gnu %s | FileCheck --check-prefixes=X86,X86-LINUX,NATIVE,JT8 %s
+; RUN: opt -S -passes=lowertypetests -mtriple=i686-pc-win32 %s | FileCheck --check-prefixes=X86,X86-WIN32,NATIVE,JT8 %s
+; RUN: opt -S -passes=lowertypetests -mtriple=x86_64-pc-win32 %s | FileCheck --check-prefixes=X86,X86-WIN32,NATIVE,JT8 %s
+; RUN: opt -S -passes=lowertypetests -mtriple=riscv32-unknown-linux-gnu %s | FileCheck --check-prefixes=RISCV,NATIVE,JT8 %s
+; RUN: opt -S -passes=lowertypetests -mtriple=riscv64-unknown-linux-gnu %s | FileCheck --check-prefixes=RISCV,NATIVE,JT8 %s
 ; RUN: opt -S -passes=lowertypetests -mtriple=wasm32-unknown-unknown %s | FileCheck --check-prefix=WASM32 %s
-; RUN: opt -S -passes=lowertypetests -mtriple=loongarch64-unknown-linux-gnu %s | FileCheck --check-prefixes=LOONGARCH64,NATIVE %s
+; RUN: opt -S -passes=lowertypetests -mtriple=loongarch64-unknown-linux-gnu %s | FileCheck --check-prefixes=LOONGARCH64,NATIVE,JT8 %s
 
 ; The right format for Arm jump tables depends on the selected
 ; subtarget, so we can't get these tests right without the Arm target
 ; compiled in.
-; RUN: %if arm-registered-target %{ opt -S -passes=lowertypetests -mtriple=arm-unknown-linux-gnu %s | FileCheck --check-prefixes=ARM,NATIVE %s %}
-; RUN: %if arm-registered-target %{ opt -S -passes=lowertypetests -mtriple=thumbv7m-unknown-linux-gnu %s | FileCheck --check-prefixes=THUMB,NATIVE %s %}
-; RUN: %if arm-registered-target %{ opt -S -passes=lowertypetests -mtriple=thumbv8m.base-unknown-linux-gnu %s | FileCheck --check-prefixes=THUMB,NATIVE %s %}
-; RUN: %if arm-registered-target %{ opt -S -passes=lowertypetests -mtriple=thumbv6m-unknown-linux-gnu %s | FileCheck --check-prefixes=THUMBV6M,NATIVE %s %}
-; RUN: %if arm-registered-target %{ opt -S -passes=lowertypetests -mtriple=thumbv5-unknown-linux-gnu %s | FileCheck --check-prefixes=ARM,NATIVE %s %}
-; RUN: %if arm-registered-target %{ opt -S -passes=lowertypetests -mtriple=aarch64-unknown-linux-gnu %s | FileCheck --check-prefixes=ARM,NATIVE %s %}
+; RUN: %if arm-registered-target %{ opt -S -passes=lowertypetests -mtriple=arm-unknown-linux-gnu %s | FileCheck --check-prefixes=ARM,NATIVE,JT4 %s %}
+; RUN: %if arm-registered-target %{ opt -S -passes=lowertypetests -mtriple=thumbv7m-unknown-linux-gnu %s | FileCheck --check-prefixes=THUMB,NATIVE,JT4 %s %}
+; RUN: %if arm-registered-target %{ opt -S -passes=lowertypetests -mtriple=thumbv8m.base-unknown-linux-gnu %s | FileCheck --check-prefixes=THUMB,NATIVE,JT4 %s %}
+; RUN: %if arm-registered-target %{ opt -S -passes=lowertypetests -mtriple=thumbv6m-unknown-linux-gnu %s | FileCheck --check-prefixes=THUMBV6M,NATIVE,JT16 %s %}
+; RUN: %if arm-registered-target %{ opt -S -passes=lowertypetests -mtriple=thumbv5-unknown-linux-gnu %s | FileCheck --check-prefixes=ARM,NATIVE,JT4 %s %}
+; RUN: %if arm-registered-target %{ opt -S -passes=lowertypetests -mtriple=aarch64-unknown-linux-gnu %s | FileCheck --check-prefixes=ARM,NATIVE,JT4 %s %}
 
 ; Tests that we correctly handle bitsets containing 2 or more functions.
 
@@ -54,20 +54,18 @@ define internal void @g() !type !0 {
 declare i1 @llvm.type.test(ptr %ptr, metadata %bitset) noinline readnone
 
 define i1 @foo(ptr %p) {
-  ; NATIVE: sub i64 {{.*}}, ptrtoint (ptr @[[JT]] to i64)
-  ; WASM32: sub i64 {{.*}}, ptrtoint (ptr getelementptr (i8, ptr null, i64 1) to i64)
+  ; JT4: sub i64 ptrtoint (ptr getelementptr (i8, ptr @[[JT]], i64 4) to i64), {{.*}}
+  ; JT8: sub i64 ptrtoint (ptr getelementptr (i8, ptr @[[JT]], i64 8) to i64), {{.*}}
+  ; JT16: sub i64 ptrtoint (ptr getelementptr (i8, ptr @[[JT]], i64 16) to i64), {{.*}}
+  ; WASM32: sub i64 ptrtoint (ptr getelementptr (i8, ptr null, i64 2) to i64), {{.*}}
   ; WASM32: icmp ule i64 {{.*}}, 1
   %x = call i1 @llvm.type.test(ptr %p, metadata !"typeid1")
   ret i1 %x
 }
 
-; X86-LINUX:   define private void @[[JT]]() #[[ATTR:.*]] align 8 {
-; X86-WIN32:   define private void @[[JT]]() #[[ATTR:.*]] align 8 {
-; ARM:         define private void @[[JT]]() #[[ATTR:.*]] align 4 {
-; THUMB:       define private void @[[JT]]() #[[ATTR:.*]] align 4 {
-; THUMBV6M:    define private void @[[JT]]() #[[ATTR:.*]] align 16 {
-; RISCV:       define private void @[[JT]]() #[[ATTR:.*]] align 8 {
-; LOONGARCH64: define private void @[[JT]]() #[[ATTR:.*]] align 8 {
+; JT4:  define private void @[[JT]]() #[[ATTR:.*]] align 4 {
+; JT8:  define private void @[[JT]]() #[[ATTR:.*]] align 8 {
+; JT16: define private void @[[JT]]() #[[ATTR:.*]] align 16 {
 
 ; X86:      jmp ${0:c}@plt
 ; X86-SAME: int3