Skip to content

Commit

Permalink
Revert @llvm.isnan intrinsic patchset.
Browse files Browse the repository at this point in the history 
Please refer to
https://lists.llvm.org/pipermail/llvm-dev/2021-September/152440.html
(and that whole thread.)

TLDR: the original patch had no prior RFC, yet it had some changes that
really need a proper RFC discussion. It won't be productive to discuss
such an RFC, once it's actually posted, while said patch is already
committed, because that introduces bias towards already-committed stuff,
and the tree is potentially in broken state meanwhile.

While the end result of discussion may lead back to the current design,
it may also not lead to the current design.

Therefore i take it upon myself
to revert the tree back to last known good state.

This reverts commit 4c4093e.
This reverts commit 0a2b1ba.
This reverts commit d987371.
This reverts commit 791006f.
This reverts commit c22b64e.
This reverts commit 72ebcd3.
This reverts commit 5fa6039.
This reverts commit 9efda54.
This reverts commit 94d3ff0.
  • Loading branch information
@LebedevRI
LebedevRI committed Sep 2, 2021
1 parent 9722e8f commit 3f1f08f
Show file tree
Hide file tree
Showing 39 changed files with 158 additions and 2,997 deletions.
28 changes: 24 additions & 4 deletions clang/lib/CodeGen/CGBuiltin.cpp
View file
Expand Up @@ -3068,17 +3068,37 @@ RValue CodeGenFunction::EmitBuiltinExpr(const GlobalDecl GD, unsigned BuiltinID,
// ZExt bool to int type.
return RValue::get(Builder.CreateZExt(LHS, ConvertType(E->getType())));
}

case Builtin::BI__builtin_isnan: {
CodeGenFunction::CGFPOptionsRAII FPOptsRAII(*this, E);
Value *V = EmitScalarExpr(E->getArg(0));
llvm::Type *Ty = V->getType();
const llvm::fltSemantics &Semantics = Ty->getFltSemantics();
if (!Builder.getIsFPConstrained() ||
Builder.getDefaultConstrainedExcept() == fp::ebIgnore ||
!Ty->isIEEE()) {
V = Builder.CreateFCmpUNO(V, V, "cmp");
return RValue::get(Builder.CreateZExt(V, ConvertType(E->getType())));
}

if (Value *Result = getTargetHooks().testFPKind(V, BuiltinID, Builder, CGM))
return RValue::get(Result);

Function *F = CGM.getIntrinsic(Intrinsic::isnan, V->getType());
Value *Call = Builder.CreateCall(F, V);
return RValue::get(Builder.CreateZExt(Call, ConvertType(E->getType())));
// NaN has all exp bits set and a non zero significand. Therefore:
// isnan(V) == ((exp mask - (abs(V) & exp mask)) < 0)
unsigned bitsize = Ty->getScalarSizeInBits();
llvm::IntegerType *IntTy = Builder.getIntNTy(bitsize);
Value *IntV = Builder.CreateBitCast(V, IntTy);
APInt AndMask = APInt::getSignedMaxValue(bitsize);
Value *AbsV =
Builder.CreateAnd(IntV, llvm::ConstantInt::get(IntTy, AndMask));
APInt ExpMask = APFloat::getInf(Semantics).bitcastToAPInt();
Value *Sub =
Builder.CreateSub(llvm::ConstantInt::get(IntTy, ExpMask), AbsV);
// V = sign bit (Sub) <=> V = (Sub < 0)
V = Builder.CreateLShr(Sub, llvm::ConstantInt::get(IntTy, bitsize - 1));
if (bitsize > 32)
V = Builder.CreateTrunc(V, ConvertType(E->getType()));
return RValue::get(V);
}

case Builtin::BI__builtin_matrix_transpose: {
Expand Down
37 changes: 20 additions & 17 deletions clang/test/CodeGen/X86/strictfp_builtins.c
View file
Expand Up @@ -17,7 +17,7 @@ int printf(const char *, ...);
// CHECK-NEXT: store i32 [[X:%.*]], i32* [[X_ADDR]], align 4
// CHECK-NEXT: [[TMP0:%.*]] = load i8*, i8** [[STR_ADDR]], align 8
// CHECK-NEXT: [[TMP1:%.*]] = load i32, i32* [[X_ADDR]], align 4
// CHECK-NEXT: [[CALL:%.*]] = call i32 (i8*, ...) @printf(i8* getelementptr inbounds ([8 x i8], [8 x i8]* @.str, i64 0, i64 0), i8* [[TMP0]], i32 [[TMP1]]) #[[ATTR3:[0-9]+]]
// CHECK-NEXT: [[CALL:%.*]] = call i32 (i8*, ...) @printf(i8* getelementptr inbounds ([8 x i8], [8 x i8]* @.str, i64 0, i64 0), i8* [[TMP0]], i32 [[TMP1]]) [[ATTR4:#.*]]
// CHECK-NEXT: ret void
//
void p(char *str, int x) {
Expand All @@ -29,13 +29,13 @@ void p(char *str, int x) {
// CHECK-LABEL: @test_long_double_isinf(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[LD_ADDR:%.*]] = alloca x86_fp80, align 16
// CHECK-NEXT: store x86_fp80 [[LD:%.*]], x86_fp80* [[LD_ADDR]], align 16
// CHECK-NEXT: store x86_fp80 [[D:%.*]], x86_fp80* [[LD_ADDR]], align 16
// CHECK-NEXT: [[TMP0:%.*]] = load x86_fp80, x86_fp80* [[LD_ADDR]], align 16
// CHECK-NEXT: [[TMP1:%.*]] = bitcast x86_fp80 [[TMP0]] to i80
// CHECK-NEXT: [[TMP2:%.*]] = shl i80 [[TMP1]], 1
// CHECK-NEXT: [[TMP3:%.*]] = icmp eq i80 [[TMP2]], -18446744073709551616
// CHECK-NEXT: [[TMP4:%.*]] = zext i1 [[TMP3]] to i32
// CHECK-NEXT: call void @p(i8* getelementptr inbounds ([10 x i8], [10 x i8]* @.str.1, i64 0, i64 0), i32 [[TMP4]]) #[[ATTR3]]
// CHECK-NEXT: [[BITCAST:%.*]] = bitcast x86_fp80 [[TMP0]] to i80
// CHECK-NEXT: [[SHL1:%.*]] = shl i80 [[BITCAST]], 1
// CHECK-NEXT: [[CMP:%.*]] = icmp eq i80 [[SHL1]], -18446744073709551616
// CHECK-NEXT: [[RES:%.*]] = zext i1 [[CMP]] to i32
// CHECK-NEXT: call void @p(i8* getelementptr inbounds ([10 x i8], [10 x i8]* @.str.[[#STRID:1]], i64 0, i64 0), i32 [[RES]]) [[ATTR4]]
// CHECK-NEXT: ret void
//
void test_long_double_isinf(long double ld) {
Expand All @@ -47,13 +47,13 @@ void test_long_double_isinf(long double ld) {
// CHECK-LABEL: @test_long_double_isfinite(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[LD_ADDR:%.*]] = alloca x86_fp80, align 16
// CHECK-NEXT: store x86_fp80 [[LD:%.*]], x86_fp80* [[LD_ADDR]], align 16
// CHECK-NEXT: store x86_fp80 [[D:%.*]], x86_fp80* [[LD_ADDR]], align 16
// CHECK-NEXT: [[TMP0:%.*]] = load x86_fp80, x86_fp80* [[LD_ADDR]], align 16
// CHECK-NEXT: [[TMP1:%.*]] = bitcast x86_fp80 [[TMP0]] to i80
// CHECK-NEXT: [[TMP2:%.*]] = shl i80 [[TMP1]], 1
// CHECK-NEXT: [[TMP3:%.*]] = icmp ult i80 [[TMP2]], -18446744073709551616
// CHECK-NEXT: [[TMP4:%.*]] = zext i1 [[TMP3]] to i32
// CHECK-NEXT: call void @p(i8* getelementptr inbounds ([13 x i8], [13 x i8]* @.str.2, i64 0, i64 0), i32 [[TMP4]]) #[[ATTR3]]
// CHECK-NEXT: [[BITCAST:%.*]] = bitcast x86_fp80 [[TMP0]] to i80
// CHECK-NEXT: [[SHL1:%.*]] = shl i80 [[BITCAST]], 1
// CHECK-NEXT: [[CMP:%.*]] = icmp ult i80 [[SHL1]], -18446744073709551616
// CHECK-NEXT: [[RES:%.*]] = zext i1 [[CMP]] to i32
// CHECK-NEXT: call void @p(i8* getelementptr inbounds ([13 x i8], [13 x i8]* @.str.[[#STRID:STRID+1]], i64 0, i64 0), i32 [[RES]]) [[ATTR4]]
// CHECK-NEXT: ret void
//
void test_long_double_isfinite(long double ld) {
Expand All @@ -65,11 +65,14 @@ void test_long_double_isfinite(long double ld) {
// CHECK-LABEL: @test_long_double_isnan(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[LD_ADDR:%.*]] = alloca x86_fp80, align 16
// CHECK-NEXT: store x86_fp80 [[LD:%.*]], x86_fp80* [[LD_ADDR]], align 16
// CHECK-NEXT: store x86_fp80 [[D:%.*]], x86_fp80* [[LD_ADDR]], align 16
// CHECK-NEXT: [[TMP0:%.*]] = load x86_fp80, x86_fp80* [[LD_ADDR]], align 16
// CHECK-NEXT: [[TMP1:%.*]] = call i1 @llvm.isnan.f80(x86_fp80 [[TMP0]]) #[[ATTR3]]
// CHECK-NEXT: [[TMP2:%.*]] = zext i1 [[TMP1]] to i32
// CHECK-NEXT: call void @p(i8* getelementptr inbounds ([10 x i8], [10 x i8]* @.str.3, i64 0, i64 0), i32 [[TMP2]]) #[[ATTR3]]
// CHECK-NEXT: [[BITCAST:%.*]] = bitcast x86_fp80 [[TMP0]] to i80
// CHECK-NEXT: [[ABS:%.*]] = and i80 [[BITCAST]], 604462909807314587353087
// CHECK-NEXT: [[TMP1:%.*]] = sub i80 604453686435277732577280, [[ABS]]
// CHECK-NEXT: [[ISNAN:%.*]] = lshr i80 [[TMP1]], 79
// CHECK-NEXT: [[RES:%.*]] = trunc i80 [[ISNAN]] to i32
// CHECK-NEXT: call void @p(i8* getelementptr inbounds ([10 x i8], [10 x i8]* @.str.[[#STRID:STRID+1]], i64 0, i64 0), i32 [[RES]]) [[ATTR4]]
// CHECK-NEXT: ret void
//
void test_long_double_isnan(long double ld) {
Expand Down
38 changes: 20 additions & 18 deletions clang/test/CodeGen/aarch64-strictfp-builtins.c
View file
@@ -1,4 +1,3 @@
// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py
// RUN: %clang_cc1 %s -emit-llvm -ffp-exception-behavior=maytrap -fexperimental-strict-floating-point -o - -triple arm64-none-linux-gnu | FileCheck %s

// Test that the constrained intrinsics are picking up the exception
Expand All @@ -16,7 +15,7 @@ int printf(const char *, ...);
// CHECK-NEXT: store i32 [[X:%.*]], i32* [[X_ADDR]], align 4
// CHECK-NEXT: [[TMP0:%.*]] = load i8*, i8** [[STR_ADDR]], align 8
// CHECK-NEXT: [[TMP1:%.*]] = load i32, i32* [[X_ADDR]], align 4
// CHECK-NEXT: [[CALL:%.*]] = call i32 (i8*, ...) @printf(i8* getelementptr inbounds ([8 x i8], [8 x i8]* @.str, i64 0, i64 0), i8* [[TMP0]], i32 [[TMP1]]) #[[ATTR3:[0-9]+]]
// CHECK-NEXT: [[CALL:%.*]] = call i32 (i8*, ...) @printf(i8* getelementptr inbounds ([8 x i8], [8 x i8]* @.str, i64 0, i64 0), i8* [[TMP0]], i32 [[TMP1]]) [[ATTR4:#.*]]
// CHECK-NEXT: ret void
//
void p(char *str, int x) {
Expand All @@ -28,13 +27,13 @@ void p(char *str, int x) {
// CHECK-LABEL: @test_long_double_isinf(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[LD_ADDR:%.*]] = alloca fp128, align 16
// CHECK-NEXT: store fp128 [[LD:%.*]], fp128* [[LD_ADDR]], align 16
// CHECK-NEXT: store fp128 [[D:%.*]], fp128* [[LD_ADDR]], align 16
// CHECK-NEXT: [[TMP0:%.*]] = load fp128, fp128* [[LD_ADDR]], align 16
// CHECK-NEXT: [[TMP1:%.*]] = bitcast fp128 [[TMP0]] to i128
// CHECK-NEXT: [[TMP2:%.*]] = shl i128 [[TMP1]], 1
// CHECK-NEXT: [[TMP3:%.*]] = icmp eq i128 [[TMP2]], -10384593717069655257060992658440192
// CHECK-NEXT: [[TMP4:%.*]] = zext i1 [[TMP3]] to i32
// CHECK-NEXT: call void @p(i8* getelementptr inbounds ([10 x i8], [10 x i8]* @.str.1, i64 0, i64 0), i32 [[TMP4]]) #[[ATTR3]]
// CHECK-NEXT: [[BITCAST:%.*]] = bitcast fp128 [[TMP0]] to i128
// CHECK-NEXT: [[SHL1:%.*]] = shl i128 [[BITCAST]], 1
// CHECK-NEXT: [[CMP:%.*]] = icmp eq i128 [[SHL1]], -10384593717069655257060992658440192
// CHECK-NEXT: [[RES:%.*]] = zext i1 [[CMP]] to i32
// CHECK-NEXT: call void @p(i8* getelementptr inbounds ([10 x i8], [10 x i8]* @.str.[[#STRID:1]], i64 0, i64 0), i32 [[RES]]) [[ATTR4]]
// CHECK-NEXT: ret void
//
void test_long_double_isinf(long double ld) {
Expand All @@ -46,13 +45,13 @@ void test_long_double_isinf(long double ld) {
// CHECK-LABEL: @test_long_double_isfinite(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[LD_ADDR:%.*]] = alloca fp128, align 16
// CHECK-NEXT: store fp128 [[LD:%.*]], fp128* [[LD_ADDR]], align 16
// CHECK-NEXT: store fp128 [[D:%.*]], fp128* [[LD_ADDR]], align 16
// CHECK-NEXT: [[TMP0:%.*]] = load fp128, fp128* [[LD_ADDR]], align 16
// CHECK-NEXT: [[TMP1:%.*]] = bitcast fp128 [[TMP0]] to i128
// CHECK-NEXT: [[TMP2:%.*]] = shl i128 [[TMP1]], 1
// CHECK-NEXT: [[TMP3:%.*]] = icmp ult i128 [[TMP2]], -10384593717069655257060992658440192
// CHECK-NEXT: [[TMP4:%.*]] = zext i1 [[TMP3]] to i32
// CHECK-NEXT: call void @p(i8* getelementptr inbounds ([13 x i8], [13 x i8]* @.str.2, i64 0, i64 0), i32 [[TMP4]]) #[[ATTR3]]
// CHECK-NEXT: [[BITCAST:%.*]] = bitcast fp128 [[TMP0]] to i128
// CHECK-NEXT: [[SHL1:%.*]] = shl i128 [[BITCAST]], 1
// CHECK-NEXT: [[CMP:%.*]] = icmp ult i128 [[SHL1]], -10384593717069655257060992658440192
// CHECK-NEXT: [[RES:%.*]] = zext i1 [[CMP]] to i32
// CHECK-NEXT: call void @p(i8* getelementptr inbounds ([13 x i8], [13 x i8]* @.str.[[#STRID:STRID+1]], i64 0, i64 0), i32 [[RES]]) [[ATTR4]]
// CHECK-NEXT: ret void
//
void test_long_double_isfinite(long double ld) {
Expand All @@ -64,11 +63,14 @@ void test_long_double_isfinite(long double ld) {
// CHECK-LABEL: @test_long_double_isnan(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[LD_ADDR:%.*]] = alloca fp128, align 16
// CHECK-NEXT: store fp128 [[LD:%.*]], fp128* [[LD_ADDR]], align 16
// CHECK-NEXT: store fp128 [[D:%.*]], fp128* [[LD_ADDR]], align 16
// CHECK-NEXT: [[TMP0:%.*]] = load fp128, fp128* [[LD_ADDR]], align 16
// CHECK-NEXT: [[TMP1:%.*]] = call i1 @llvm.isnan.f128(fp128 [[TMP0]]) #[[ATTR3]]
// CHECK-NEXT: [[TMP2:%.*]] = zext i1 [[TMP1]] to i32
// CHECK-NEXT: call void @p(i8* getelementptr inbounds ([10 x i8], [10 x i8]* @.str.3, i64 0, i64 0), i32 [[TMP2]]) #[[ATTR3]]
// CHECK-NEXT: [[BITCAST:%.*]] = bitcast fp128 [[TMP0]] to i128
// CHECK-NEXT: [[ABS:%.*]] = and i128 [[BITCAST]], 170141183460469231731687303715884105727
// CHECK-NEXT: [[TMP1:%.*]] = sub i128 170135991163610696904058773219554885632, [[ABS]]
// CHECK-NEXT: [[ISNAN:%.*]] = lshr i128 [[TMP1]], 127
// CHECK-NEXT: [[RES:%.*]] = trunc i128 [[ISNAN]] to i32
// CHECK-NEXT: call void @p(i8* getelementptr inbounds ([10 x i8], [10 x i8]* @.str.[[#STRID:STRID+1]], i64 0, i64 0), i32 [[RES]])
// CHECK-NEXT: ret void
//
void test_long_double_isnan(long double ld) {
Expand Down

0 comments on commit 3f1f08f

Please sign in to comment.