Skip to content

Commit

Permalink
Merge pull request llvm#101 from alexcrichton/more-wasm-updates
Browse files Browse the repository at this point in the history 
Penultimate wasm SIMD update (hopefully)
  • Loading branch information
@cuviper
cuviper authored Apr 27, 2021
2 parents 0ed6038 + 05751c8 commit 06c2b9d
Show file tree
Hide file tree
Showing 21 changed files with 623 additions and 1,048 deletions.
7 changes: 0 additions & 7 deletions clang/include/clang/Basic/BuiltinsWebAssembly.def
View file
Original file line number Diff line number Diff line change
Expand Up @@ -191,13 +191,6 @@ TARGET_BUILTIN(__builtin_wasm_narrow_u_i8x16_i16x8, "V16UcV8UsV8Us", "nc", "simd
TARGET_BUILTIN(__builtin_wasm_narrow_s_i16x8_i32x4, "V8sV4iV4i", "nc", "simd128")
TARGET_BUILTIN(__builtin_wasm_narrow_u_i16x8_i32x4, "V8UsV4UiV4Ui", "nc", "simd128")

TARGET_BUILTIN(__builtin_wasm_extend_low_s_i32x4_i64x2, "V2LLiV4i", "nc", "simd128")
TARGET_BUILTIN(__builtin_wasm_extend_high_s_i32x4_i64x2, "V2LLiV4i", "nc", "simd128")
TARGET_BUILTIN(__builtin_wasm_extend_low_u_i32x4_i64x2, "V2LLUiV4Ui", "nc", "simd128")
TARGET_BUILTIN(__builtin_wasm_extend_high_u_i32x4_i64x2, "V2LLUiV4Ui", "nc", "simd128")

TARGET_BUILTIN(__builtin_wasm_convert_low_s_i32x4_f64x2, "V2dV4i", "nc", "simd128")
TARGET_BUILTIN(__builtin_wasm_convert_low_u_i32x4_f64x2, "V2dV4Ui", "nc", "simd128")
TARGET_BUILTIN(__builtin_wasm_trunc_sat_zero_s_f64x2_i32x4, "V4iV2d", "nc", "simd128")
TARGET_BUILTIN(__builtin_wasm_trunc_sat_zero_u_f64x2_i32x4, "V4UiV2d", "nc", "simd128")
TARGET_BUILTIN(__builtin_wasm_demote_zero_f64x2_f32x4, "V4fV2d", "nc", "simd128")
Expand Down
70 changes: 20 additions & 50 deletions clang/lib/CodeGen/CGBuiltin.cpp
View file
Original file line number Diff line number Diff line change
Expand Up @@ -16756,8 +16756,8 @@ Value *CodeGenFunction::EmitWebAssemblyBuiltinExpr(unsigned BuiltinID,
case WebAssembly::BI__builtin_wasm_trunc_saturate_s_i32x4_f32x4: {
Value *Src = EmitScalarExpr(E->getArg(0));
llvm::Type *ResT = ConvertType(E->getType());
Function *Callee = CGM.getIntrinsic(Intrinsic::wasm_trunc_saturate_signed,
{ResT, Src->getType()});
Function *Callee =
CGM.getIntrinsic(Intrinsic::fptosi_sat, {ResT, Src->getType()});
return Builder.CreateCall(Callee, {Src});
}
case WebAssembly::BI__builtin_wasm_trunc_saturate_u_i32_f32:
Expand All @@ -16767,8 +16767,8 @@ Value *CodeGenFunction::EmitWebAssemblyBuiltinExpr(unsigned BuiltinID,
case WebAssembly::BI__builtin_wasm_trunc_saturate_u_i32x4_f32x4: {
Value *Src = EmitScalarExpr(E->getArg(0));
llvm::Type *ResT = ConvertType(E->getType());
Function *Callee = CGM.getIntrinsic(Intrinsic::wasm_trunc_saturate_unsigned,
{ResT, Src->getType()});
Function *Callee =
CGM.getIntrinsic(Intrinsic::fptoui_sat, {ResT, Src->getType()});
return Builder.CreateCall(Callee, {Src});
}
case WebAssembly::BI__builtin_wasm_min_f32:
Expand Down Expand Up @@ -16819,19 +16819,19 @@ Value *CodeGenFunction::EmitWebAssemblyBuiltinExpr(unsigned BuiltinID,
switch (BuiltinID) {
case WebAssembly::BI__builtin_wasm_ceil_f32x4:
case WebAssembly::BI__builtin_wasm_ceil_f64x2:
IntNo = Intrinsic::wasm_ceil;
IntNo = Intrinsic::ceil;
break;
case WebAssembly::BI__builtin_wasm_floor_f32x4:
case WebAssembly::BI__builtin_wasm_floor_f64x2:
IntNo = Intrinsic::wasm_floor;
IntNo = Intrinsic::floor;
break;
case WebAssembly::BI__builtin_wasm_trunc_f32x4:
case WebAssembly::BI__builtin_wasm_trunc_f64x2:
IntNo = Intrinsic::wasm_trunc;
IntNo = Intrinsic::trunc;
break;
case WebAssembly::BI__builtin_wasm_nearest_f32x4:
case WebAssembly::BI__builtin_wasm_nearest_f64x2:
IntNo = Intrinsic::wasm_nearest;
IntNo = Intrinsic::nearbyint;
break;
default:
llvm_unreachable("unexpected builtin ID");
Expand Down Expand Up @@ -17158,58 +17158,28 @@ Value *CodeGenFunction::EmitWebAssemblyBuiltinExpr(unsigned BuiltinID,
CGM.getIntrinsic(IntNo, {ConvertType(E->getType()), Low->getType()});
return Builder.CreateCall(Callee, {Low, High});
}
case WebAssembly::BI__builtin_wasm_extend_low_s_i32x4_i64x2:
case WebAssembly::BI__builtin_wasm_extend_high_s_i32x4_i64x2:
case WebAssembly::BI__builtin_wasm_extend_low_u_i32x4_i64x2:
case WebAssembly::BI__builtin_wasm_extend_high_u_i32x4_i64x2: {
Value *Vec = EmitScalarExpr(E->getArg(0));
unsigned IntNo;
switch (BuiltinID) {
case WebAssembly::BI__builtin_wasm_extend_low_s_i32x4_i64x2:
IntNo = Intrinsic::wasm_extend_low_signed;
break;
case WebAssembly::BI__builtin_wasm_extend_high_s_i32x4_i64x2:
IntNo = Intrinsic::wasm_extend_high_signed;
break;
case WebAssembly::BI__builtin_wasm_extend_low_u_i32x4_i64x2:
IntNo = Intrinsic::wasm_extend_low_unsigned;
break;
case WebAssembly::BI__builtin_wasm_extend_high_u_i32x4_i64x2:
IntNo = Intrinsic::wasm_extend_high_unsigned;
break;
}
Function *Callee = CGM.getIntrinsic(IntNo);
return Builder.CreateCall(Callee, Vec);
}
case WebAssembly::BI__builtin_wasm_convert_low_s_i32x4_f64x2:
case WebAssembly::BI__builtin_wasm_convert_low_u_i32x4_f64x2: {
Value *Vec = EmitScalarExpr(E->getArg(0));
unsigned IntNo;
switch (BuiltinID) {
case WebAssembly::BI__builtin_wasm_convert_low_s_i32x4_f64x2:
IntNo = Intrinsic::wasm_convert_low_signed;
break;
case WebAssembly::BI__builtin_wasm_convert_low_u_i32x4_f64x2:
IntNo = Intrinsic::wasm_convert_low_unsigned;
break;
}
Function *Callee = CGM.getIntrinsic(IntNo);
return Builder.CreateCall(Callee, Vec);
}
case WebAssembly::BI__builtin_wasm_trunc_sat_zero_s_f64x2_i32x4:
case WebAssembly::BI__builtin_wasm_trunc_sat_zero_u_f64x2_i32x4: {
Value *Vec = EmitScalarExpr(E->getArg(0));
unsigned IntNo;
switch (BuiltinID) {
case WebAssembly::BI__builtin_wasm_trunc_sat_zero_s_f64x2_i32x4:
IntNo = Intrinsic::wasm_trunc_sat_zero_signed;
IntNo = Intrinsic::fptosi_sat;
break;
case WebAssembly::BI__builtin_wasm_trunc_sat_zero_u_f64x2_i32x4:
IntNo = Intrinsic::wasm_trunc_sat_zero_unsigned;
IntNo = Intrinsic::fptoui_sat;
break;
}
Function *Callee = CGM.getIntrinsic(IntNo);
return Builder.CreateCall(Callee, Vec);
llvm::Type *SrcT = Vec->getType();
llvm::Type *TruncT =
SrcT->getWithNewType(llvm::IntegerType::get(getLLVMContext(), 32));
Function *Callee = CGM.getIntrinsic(IntNo, {TruncT, SrcT});
Value *Trunc = Builder.CreateCall(Callee, Vec);
Value *Splat = Builder.CreateVectorSplat(2, Builder.getInt32(0));
Value *ConcatMask =
llvm::ConstantVector::get({Builder.getInt32(0), Builder.getInt32(1),
Builder.getInt32(2), Builder.getInt32(3)});
return Builder.CreateShuffleVector(Trunc, Splat, ConcatMask);
}
case WebAssembly::BI__builtin_wasm_demote_zero_f64x2_f32x4: {
Value *Vec = EmitScalarExpr(E->getArg(0));
Expand Down
82 changes: 24 additions & 58 deletions clang/test/CodeGen/builtins-wasm.c
View file
Original file line number Diff line number Diff line change
Expand Up @@ -123,49 +123,49 @@ long long trunc_u_i64_f64(double f) {

int trunc_saturate_s_i32_f32(float f) {
return __builtin_wasm_trunc_saturate_s_i32_f32(f);
// WEBASSEMBLY: call i32 @llvm.wasm.trunc.saturate.signed.i32.f32(float %f)
// WEBASSEMBLY: call i32 @llvm.fptosi.sat.i32.f32(float %f)
// WEBASSEMBLY-NEXT: ret
}

int trunc_saturate_u_i32_f32(float f) {
return __builtin_wasm_trunc_saturate_u_i32_f32(f);
// WEBASSEMBLY: call i32 @llvm.wasm.trunc.saturate.unsigned.i32.f32(float %f)
// WEBASSEMBLY: call i32 @llvm.fptoui.sat.i32.f32(float %f)
// WEBASSEMBLY-NEXT: ret
}

int trunc_saturate_s_i32_f64(double f) {
return __builtin_wasm_trunc_saturate_s_i32_f64(f);
// WEBASSEMBLY: call i32 @llvm.wasm.trunc.saturate.signed.i32.f64(double %f)
// WEBASSEMBLY: call i32 @llvm.fptosi.sat.i32.f64(double %f)
// WEBASSEMBLY-NEXT: ret
}

int trunc_saturate_u_i32_f64(double f) {
return __builtin_wasm_trunc_saturate_u_i32_f64(f);
// WEBASSEMBLY: call i32 @llvm.wasm.trunc.saturate.unsigned.i32.f64(double %f)
// WEBASSEMBLY: call i32 @llvm.fptoui.sat.i32.f64(double %f)
// WEBASSEMBLY-NEXT: ret
}

long long trunc_saturate_s_i64_f32(float f) {
return __builtin_wasm_trunc_saturate_s_i64_f32(f);
// WEBASSEMBLY: call i64 @llvm.wasm.trunc.saturate.signed.i64.f32(float %f)
// WEBASSEMBLY: call i64 @llvm.fptosi.sat.i64.f32(float %f)
// WEBASSEMBLY-NEXT: ret
}

long long trunc_saturate_u_i64_f32(float f) {
return __builtin_wasm_trunc_saturate_u_i64_f32(f);
// WEBASSEMBLY: call i64 @llvm.wasm.trunc.saturate.unsigned.i64.f32(float %f)
// WEBASSEMBLY: call i64 @llvm.fptoui.sat.i64.f32(float %f)
// WEBASSEMBLY-NEXT: ret
}

long long trunc_saturate_s_i64_f64(double f) {
return __builtin_wasm_trunc_saturate_s_i64_f64(f);
// WEBASSEMBLY: call i64 @llvm.wasm.trunc.saturate.signed.i64.f64(double %f)
// WEBASSEMBLY: call i64 @llvm.fptosi.sat.i64.f64(double %f)
// WEBASSEMBLY-NEXT: ret
}

long long trunc_saturate_u_i64_f64(double f) {
return __builtin_wasm_trunc_saturate_u_i64_f64(f);
// WEBASSEMBLY: call i64 @llvm.wasm.trunc.saturate.unsigned.i64.f64(double %f)
// WEBASSEMBLY: call i64 @llvm.fptoui.sat.i64.f64(double %f)
// WEBASSEMBLY-NEXT: ret
}

Expand Down Expand Up @@ -792,49 +792,49 @@ f64x2 pmax_f64x2(f64x2 x, f64x2 y) {

f32x4 ceil_f32x4(f32x4 x) {
return __builtin_wasm_ceil_f32x4(x);
// WEBASSEMBLY: call <4 x float> @llvm.wasm.ceil.v4f32(<4 x float> %x)
// WEBASSEMBLY: call <4 x float> @llvm.ceil.v4f32(<4 x float> %x)
// WEBASSEMBLY: ret
}

f32x4 floor_f32x4(f32x4 x) {
return __builtin_wasm_floor_f32x4(x);
// WEBASSEMBLY: call <4 x float> @llvm.wasm.floor.v4f32(<4 x float> %x)
// WEBASSEMBLY: call <4 x float> @llvm.floor.v4f32(<4 x float> %x)
// WEBASSEMBLY: ret
}

f32x4 trunc_f32x4(f32x4 x) {
return __builtin_wasm_trunc_f32x4(x);
// WEBASSEMBLY: call <4 x float> @llvm.wasm.trunc.v4f32(<4 x float> %x)
// WEBASSEMBLY: call <4 x float> @llvm.trunc.v4f32(<4 x float> %x)
// WEBASSEMBLY: ret
}

f32x4 nearest_f32x4(f32x4 x) {
return __builtin_wasm_nearest_f32x4(x);
// WEBASSEMBLY: call <4 x float> @llvm.wasm.nearest.v4f32(<4 x float> %x)
// WEBASSEMBLY: call <4 x float> @llvm.nearbyint.v4f32(<4 x float> %x)
// WEBASSEMBLY: ret
}

f64x2 ceil_f64x2(f64x2 x) {
return __builtin_wasm_ceil_f64x2(x);
// WEBASSEMBLY: call <2 x double> @llvm.wasm.ceil.v2f64(<2 x double> %x)
// WEBASSEMBLY: call <2 x double> @llvm.ceil.v2f64(<2 x double> %x)
// WEBASSEMBLY: ret
}

f64x2 floor_f64x2(f64x2 x) {
return __builtin_wasm_floor_f64x2(x);
// WEBASSEMBLY: call <2 x double> @llvm.wasm.floor.v2f64(<2 x double> %x)
// WEBASSEMBLY: call <2 x double> @llvm.floor.v2f64(<2 x double> %x)
// WEBASSEMBLY: ret
}

f64x2 trunc_f64x2(f64x2 x) {
return __builtin_wasm_trunc_f64x2(x);
// WEBASSEMBLY: call <2 x double> @llvm.wasm.trunc.v2f64(<2 x double> %x)
// WEBASSEMBLY: call <2 x double> @llvm.trunc.v2f64(<2 x double> %x)
// WEBASSEMBLY: ret
}

f64x2 nearest_f64x2(f64x2 x) {
return __builtin_wasm_nearest_f64x2(x);
// WEBASSEMBLY: call <2 x double> @llvm.wasm.nearest.v2f64(<2 x double> %x)
// WEBASSEMBLY: call <2 x double> @llvm.nearbyint.v2f64(<2 x double> %x)
// WEBASSEMBLY: ret
}

Expand All @@ -852,13 +852,13 @@ f64x2 sqrt_f64x2(f64x2 x) {

i32x4 trunc_saturate_s_i32x4_f32x4(f32x4 f) {
return __builtin_wasm_trunc_saturate_s_i32x4_f32x4(f);
// WEBASSEMBLY: call <4 x i32> @llvm.wasm.trunc.saturate.signed.v4i32.v4f32(<4 x float> %f)
// WEBASSEMBLY: call <4 x i32> @llvm.fptosi.sat.v4i32.v4f32(<4 x float> %f)
// WEBASSEMBLY-NEXT: ret
}

i32x4 trunc_saturate_u_i32x4_f32x4(f32x4 f) {
return __builtin_wasm_trunc_saturate_u_i32x4_f32x4(f);
// WEBASSEMBLY: call <4 x i32> @llvm.wasm.trunc.saturate.unsigned.v4i32.v4f32(<4 x float> %f)
// WEBASSEMBLY: call <4 x i32> @llvm.fptoui.sat.v4i32.v4f32(<4 x float> %f)
// WEBASSEMBLY-NEXT: ret
}

Expand Down Expand Up @@ -890,52 +890,18 @@ u16x8 narrow_u_i16x8_i32x4(u32x4 low, u32x4 high) {
// WEBASSEMBLY: ret
}

i64x2 extend_low_s_i32x4_i64x2(i32x4 x) {
return __builtin_wasm_extend_low_s_i32x4_i64x2(x);
// WEBASSEMBLY: call <2 x i64> @llvm.wasm.extend.low.signed(<4 x i32> %x)
// WEBASSEMBLY: ret
}

i64x2 extend_high_s_i32x4_i64x2(i32x4 x) {
return __builtin_wasm_extend_high_s_i32x4_i64x2(x);
// WEBASSEMBLY: call <2 x i64> @llvm.wasm.extend.high.signed(<4 x i32> %x)
// WEBASSEMBLY: ret
}

u64x2 extend_low_u_i32x4_i64x2(u32x4 x) {
return __builtin_wasm_extend_low_u_i32x4_i64x2(x);
// WEBASSEMBLY: call <2 x i64> @llvm.wasm.extend.low.unsigned(<4 x i32> %x)
// WEBASSEMBLY: ret
}

u64x2 extend_high_u_i32x4_i64x2(u32x4 x) {
return __builtin_wasm_extend_high_u_i32x4_i64x2(x);
// WEBASSEMBLY: call <2 x i64> @llvm.wasm.extend.high.unsigned(<4 x i32> %x)
// WEBASSEMBLY: ret
}

f64x2 convert_low_s_i32x4_f64x2(i32x4 x) {
return __builtin_wasm_convert_low_s_i32x4_f64x2(x);
// WEBASSEMBLY: call <2 x double> @llvm.wasm.convert.low.signed(<4 x i32> %x)
// WEBASSEMBLY: ret
}

f64x2 convert_low_u_i32x4_f64x2(u32x4 x) {
return __builtin_wasm_convert_low_u_i32x4_f64x2(x);
// WEBASSEMBLY: call <2 x double> @llvm.wasm.convert.low.unsigned(<4 x i32> %x)
// WEBASSEMBLY: ret
}

i32x4 trunc_sat_zero_s_f64x2_i32x4(f64x2 x) {
return __builtin_wasm_trunc_sat_zero_s_f64x2_i32x4(x);
// WEBASSEMBLY: call <4 x i32> @llvm.wasm.trunc.sat.zero.signed(<2 x double> %x)
// WEBASSEMBLY: ret
// WEBASSEMBLY: %0 = tail call <2 x i32> @llvm.fptosi.sat.v2i32.v2f64(<2 x double> %x)
// WEBASSEMBLY: %1 = shufflevector <2 x i32> %0, <2 x i32> zeroinitializer, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
// WEBASSEMBLY: ret <4 x i32> %1
}

u32x4 trunc_sat_zero_u_f64x2_i32x4(f64x2 x) {
return __builtin_wasm_trunc_sat_zero_u_f64x2_i32x4(x);
// WEBASSEMBLY: call <4 x i32> @llvm.wasm.trunc.sat.zero.unsigned(<2 x double> %x)
// WEBASSEMBLY: ret
// WEBASSEMBLY: %0 = tail call <2 x i32> @llvm.fptoui.sat.v2i32.v2f64(<2 x double> %x)
// WEBASSEMBLY: %1 = shufflevector <2 x i32> %0, <2 x i32> zeroinitializer, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
// WEBASSEMBLY: ret <4 x i32> %1
}

f32x4 wasm_demote_zero_f64x2_f32x4(f64x2 x) {
Expand Down
43 changes: 0 additions & 43 deletions llvm/include/llvm/IR/IntrinsicsWebAssembly.td
View file
Original file line number Diff line number Diff line change
Expand Up @@ -157,17 +157,6 @@ def int_wasm_narrow_unsigned :
[llvm_anyvector_ty, LLVMMatchType<1>],
[IntrNoMem, IntrSpeculatable]>;

// TODO: Replace these intrinsics with normal ISel patterns once i32x4 to i64x2
// extending is merged to the proposal.
def int_wasm_extend_low_signed :
Intrinsic<[llvm_v2i64_ty], [llvm_v4i32_ty], [IntrNoMem, IntrSpeculatable]>;
def int_wasm_extend_high_signed :
Intrinsic<[llvm_v2i64_ty], [llvm_v4i32_ty], [IntrNoMem, IntrSpeculatable]>;
def int_wasm_extend_low_unsigned :
Intrinsic<[llvm_v2i64_ty], [llvm_v4i32_ty], [IntrNoMem, IntrSpeculatable]>;
def int_wasm_extend_high_unsigned :
Intrinsic<[llvm_v2i64_ty], [llvm_v4i32_ty], [IntrNoMem, IntrSpeculatable]>;

def int_wasm_q15mulr_sat_signed :
Intrinsic<[llvm_v8i16_ty],
[llvm_v8i16_ty, llvm_v8i16_ty],
Expand All @@ -183,26 +172,6 @@ def int_wasm_pmax :
[LLVMMatchType<0>, LLVMMatchType<0>],
[IntrNoMem, IntrSpeculatable]>;

// TODO: Replace these instrinsics with normal ISel patterns once the
// rounding instructions are merged to the proposal
// (https://github.com/WebAssembly/simd/pull/232).
def int_wasm_ceil :
Intrinsic<[llvm_anyvector_ty],
[LLVMMatchType<0>],
[IntrNoMem, IntrSpeculatable]>;
def int_wasm_floor :
Intrinsic<[llvm_anyvector_ty],
[LLVMMatchType<0>],
[IntrNoMem, IntrSpeculatable]>;
def int_wasm_trunc :
Intrinsic<[llvm_anyvector_ty],
[LLVMMatchType<0>],
[IntrNoMem, IntrSpeculatable]>;
def int_wasm_nearest :
Intrinsic<[llvm_anyvector_ty],
[LLVMMatchType<0>],
[IntrNoMem, IntrSpeculatable]>;

// TODO: Replace these intrinsic with normal ISel patterns once the
// load_zero instructions are merged to the proposal.
def int_wasm_load32_zero :
Expand Down Expand Up @@ -295,18 +264,6 @@ def int_wasm_extadd_pairwise_unsigned :
[IntrNoMem, IntrSpeculatable]>;

// TODO: Remove these if possible if they are merged to the spec.
def int_wasm_convert_low_signed :
Intrinsic<[llvm_v2f64_ty], [llvm_v4i32_ty],
[IntrNoMem, IntrSpeculatable]>;
def int_wasm_convert_low_unsigned :
Intrinsic<[llvm_v2f64_ty], [llvm_v4i32_ty],
[IntrNoMem, IntrSpeculatable]>;
def int_wasm_trunc_sat_zero_signed :
Intrinsic<[llvm_v4i32_ty], [llvm_v2f64_ty],
[IntrNoMem, IntrSpeculatable]>;
def int_wasm_trunc_sat_zero_unsigned :
Intrinsic<[llvm_v4i32_ty], [llvm_v2f64_ty],
[IntrNoMem, IntrSpeculatable]>;
def int_wasm_demote_zero :
Intrinsic<[llvm_v4f32_ty], [llvm_v2f64_ty],
[IntrNoMem, IntrSpeculatable]>;
Expand Down
Loading

0 comments on commit 06c2b9d

Please sign in to comment.