forked from OSchip/llvm-project
[TargetLowering] Only inspect attributes in the arguments for ArgListEntry
Parameter attributes are considered part of the function [1], and like mismatched calling conventions [2], we can't have the verifier check for mismatched parameter attributes. This is a reland after fixing MSan issues in D102667. [1] https://llvm.org/docs/LangRef.html#parameter-attributes [2] https://llvm.org/docs/FAQ.html#why-does-instcombine-simplifycfg-turn-a-call-to-a-function-with-a-mismatched-calling-convention-into-unreachable-why-not-make-the-verifier-reject-it Reviewed By: rnk Differential Revision: https://reviews.llvm.org/D101806
This commit is contained in:
Arthur Eubanks
parent
b86302e500
commit
1c7f32334d
|
|
@ -64,6 +64,7 @@ Changes to the LLVM IR
|
|||
* The opaque pointer type ``ptr`` has been introduced. It is still in the
|
||||
process of being worked on and should not be used yet.
|
||||
|
||||
=======
|
||||
Changes to building LLVM
|
||||
------------------------
|
||||
|
||||
|
|
@ -74,6 +75,13 @@ Changes to building LLVM
|
|||
Changes to TableGen
|
||||
-------------------
|
||||
|
||||
Changes to Backend Code Generation
|
||||
----------------------------------
|
||||
|
||||
* When lowering calls, only ABI attributes on the call itself are checked, not
|
||||
the caller. Frontends need to make sure to properly set ABI attributes on
|
||||
calls (and always should have).
|
||||
|
||||
Changes to the ARM Backend
|
||||
--------------------------
|
||||
|
||||
|
|
|
|||
|
|
@ -102,29 +102,32 @@ bool TargetLowering::parametersInCSRMatch(const MachineRegisterInfo &MRI,
|
|||
return true;
|
||||
}
|
||||
|
||||
/// Set CallLoweringInfo attribute flags based on a call instruction
|
||||
/// and called function attributes.
|
||||
/// Set CallLoweringInfo attribute flags based on the call instruction's
|
||||
/// argument attributes.
|
||||
void TargetLoweringBase::ArgListEntry::setAttributes(const CallBase *Call,
|
||||
unsigned ArgIdx) {
|
||||
IsSExt = Call->paramHasAttr(ArgIdx, Attribute::SExt);
|
||||
IsZExt = Call->paramHasAttr(ArgIdx, Attribute::ZExt);
|
||||
IsInReg = Call->paramHasAttr(ArgIdx, Attribute::InReg);
|
||||
IsSRet = Call->paramHasAttr(ArgIdx, Attribute::StructRet);
|
||||
IsNest = Call->paramHasAttr(ArgIdx, Attribute::Nest);
|
||||
IsByVal = Call->paramHasAttr(ArgIdx, Attribute::ByVal);
|
||||
IsPreallocated = Call->paramHasAttr(ArgIdx, Attribute::Preallocated);
|
||||
IsInAlloca = Call->paramHasAttr(ArgIdx, Attribute::InAlloca);
|
||||
IsReturned = Call->paramHasAttr(ArgIdx, Attribute::Returned);
|
||||
IsSwiftSelf = Call->paramHasAttr(ArgIdx, Attribute::SwiftSelf);
|
||||
IsSwiftAsync = Call->paramHasAttr(ArgIdx, Attribute::SwiftAsync);
|
||||
IsSwiftError = Call->paramHasAttr(ArgIdx, Attribute::SwiftError);
|
||||
Alignment = Call->getParamStackAlign(ArgIdx);
|
||||
auto Attrs = Call->getAttributes();
|
||||
|
||||
IsSExt = Attrs.hasParamAttribute(ArgIdx, Attribute::SExt);
|
||||
IsZExt = Attrs.hasParamAttribute(ArgIdx, Attribute::ZExt);
|
||||
IsInReg = Attrs.hasParamAttribute(ArgIdx, Attribute::InReg);
|
||||
IsSRet = Attrs.hasParamAttribute(ArgIdx, Attribute::StructRet);
|
||||
IsNest = Attrs.hasParamAttribute(ArgIdx, Attribute::Nest);
|
||||
IsReturned = Attrs.hasParamAttribute(ArgIdx, Attribute::Returned);
|
||||
IsSwiftSelf = Attrs.hasParamAttribute(ArgIdx, Attribute::SwiftSelf);
|
||||
IsSwiftAsync = Attrs.hasParamAttribute(ArgIdx, Attribute::SwiftAsync);
|
||||
IsSwiftError = Attrs.hasParamAttribute(ArgIdx, Attribute::SwiftError);
|
||||
Alignment = Attrs.getParamStackAlignment(ArgIdx);
|
||||
|
||||
IsByVal = Attrs.hasParamAttribute(ArgIdx, Attribute::ByVal);
|
||||
ByValType = nullptr;
|
||||
if (IsByVal) {
|
||||
ByValType = Call->getParamByValType(ArgIdx);
|
||||
if (!Alignment)
|
||||
Alignment = Call->getParamAlign(ArgIdx);
|
||||
}
|
||||
IsInAlloca = Attrs.hasParamAttribute(ArgIdx, Attribute::InAlloca);
|
||||
IsPreallocated = Attrs.hasParamAttribute(ArgIdx, Attribute::Preallocated);
|
||||
PreallocatedType = nullptr;
|
||||
if (IsPreallocated)
|
||||
PreallocatedType = Call->getParamPreallocatedType(ArgIdx);
|
||||
|
|
|
|||
|
|
@ -38,9 +38,9 @@ entry:
|
|||
; CHECK-NOT: mov x0, {{x[0-9]+}}
|
||||
; CHECK: b {{_?B_ctor_base}}
|
||||
%0 = bitcast %struct.C* %this to %struct.A*
|
||||
%call = tail call %struct.A* @A_ctor_base(%struct.A* %0)
|
||||
%call = tail call %struct.A* @A_ctor_base(%struct.A* returned %0)
|
||||
%1 = getelementptr inbounds %struct.C, %struct.C* %this, i32 0, i32 0
|
||||
%call2 = tail call %struct.B* @B_ctor_base(%struct.B* %1, i32 %x)
|
||||
%call2 = tail call %struct.B* @B_ctor_base(%struct.B* returned %1, i32 %x)
|
||||
ret %struct.C* %this
|
||||
}
|
||||
|
||||
|
|
@ -88,7 +88,7 @@ define %struct.C* @C_ctor_complete(%struct.C* %this, i32 %x) {
|
|||
entry:
|
||||
; CHECK-LABEL: C_ctor_complete:
|
||||
; CHECK: b {{_?C_ctor_base}}
|
||||
%call = tail call %struct.C* @C_ctor_base(%struct.C* %this, i32 %x)
|
||||
%call = tail call %struct.C* @C_ctor_base(%struct.C* returned %this, i32 %x)
|
||||
ret %struct.C* %this
|
||||
}
|
||||
|
||||
|
|
@ -135,8 +135,8 @@ entry:
|
|||
; CHECK-NOT: mov x0, {{x[0-9]+}}
|
||||
; CHECK: b {{_?B_ctor_complete}}
|
||||
%b = getelementptr inbounds %struct.D, %struct.D* %this, i32 0, i32 0
|
||||
%call = tail call %struct.B* @B_ctor_complete(%struct.B* %b, i32 %x)
|
||||
%call2 = tail call %struct.B* @B_ctor_complete(%struct.B* %b, i32 %x)
|
||||
%call = tail call %struct.B* @B_ctor_complete(%struct.B* returned %b, i32 %x)
|
||||
%call2 = tail call %struct.B* @B_ctor_complete(%struct.B* returned %b, i32 %x)
|
||||
ret %struct.D* %this
|
||||
}
|
||||
|
||||
|
|
@ -166,8 +166,8 @@ entry:
|
|||
; CHECK-LABEL: E_ctor_base:
|
||||
; CHECK-NOT: b {{_?B_ctor_complete}}
|
||||
%b = getelementptr inbounds %struct.E, %struct.E* %this, i32 0, i32 0
|
||||
%call = tail call %struct.B* @B_ctor_complete(%struct.B* %b, i32 %x)
|
||||
%call = tail call %struct.B* @B_ctor_complete(%struct.B* returned %b, i32 %x)
|
||||
%b2 = getelementptr inbounds %struct.E, %struct.E* %this, i32 0, i32 1
|
||||
%call2 = tail call %struct.B* @B_ctor_complete(%struct.B* %b2, i32 %x)
|
||||
%call2 = tail call %struct.B* @B_ctor_complete(%struct.B* returned %b2, i32 %x)
|
||||
ret %struct.E* %this
|
||||
}
|
||||
|
|
|
|||
|
|
@ -91,7 +91,7 @@ define signext i16 @test10(i64 %a) {
|
|||
define void @test11(i64 %a) {
|
||||
%tmp = lshr i64 %a, 23
|
||||
%res = trunc i64 %tmp to i16
|
||||
call void @use(i16 %res, i64 %tmp)
|
||||
call void @use(i16 signext %res, i64 %tmp)
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
|
|||
|
|
@ -11,7 +11,7 @@ declare void @test_explicit_sret(i1024* sret(i1024)) #0
|
|||
; CHECK-LABEL: _test_tailcall_explicit_sret:
|
||||
; CHECK-NEXT: b _test_explicit_sret
|
||||
define void @test_tailcall_explicit_sret(i1024* sret(i1024) %arg) #0 {
|
||||
tail call void @test_explicit_sret(i1024* %arg)
|
||||
tail call void @test_explicit_sret(i1024* sret(i1024) %arg)
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
@ -20,7 +20,7 @@ define void @test_tailcall_explicit_sret(i1024* sret(i1024) %arg) #0 {
|
|||
; CHECK: bl _test_explicit_sret
|
||||
; CHECK: ret
|
||||
define void @test_call_explicit_sret(i1024* sret(i1024) %arg) #0 {
|
||||
call void @test_explicit_sret(i1024* %arg)
|
||||
call void @test_explicit_sret(i1024* sret(i1024) %arg)
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
@ -30,7 +30,7 @@ define void @test_call_explicit_sret(i1024* sret(i1024) %arg) #0 {
|
|||
; CHECK: ret
|
||||
define void @test_tailcall_explicit_sret_alloca_unused() #0 {
|
||||
%l = alloca i1024, align 8
|
||||
tail call void @test_explicit_sret(i1024* %l)
|
||||
tail call void @test_explicit_sret(i1024* sret(i1024) %l)
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
@ -44,7 +44,7 @@ define void @test_tailcall_explicit_sret_alloca_dummyusers(i1024* %ptr) #0 {
|
|||
%l = alloca i1024, align 8
|
||||
%r = load i1024, i1024* %ptr, align 8
|
||||
store i1024 %r, i1024* %l, align 8
|
||||
tail call void @test_explicit_sret(i1024* %l)
|
||||
tail call void @test_explicit_sret(i1024* sret(i1024) %l)
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
@ -56,7 +56,7 @@ define void @test_tailcall_explicit_sret_alloca_dummyusers(i1024* %ptr) #0 {
|
|||
; CHECK: ret
|
||||
define void @test_tailcall_explicit_sret_gep(i1024* %ptr) #0 {
|
||||
%ptr2 = getelementptr i1024, i1024* %ptr, i32 1
|
||||
tail call void @test_explicit_sret(i1024* %ptr2)
|
||||
tail call void @test_explicit_sret(i1024* sret(i1024) %ptr2)
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
@ -69,7 +69,7 @@ define void @test_tailcall_explicit_sret_gep(i1024* %ptr) #0 {
|
|||
; CHECK: ret
|
||||
define i1024 @test_tailcall_explicit_sret_alloca_returned() #0 {
|
||||
%l = alloca i1024, align 8
|
||||
tail call void @test_explicit_sret(i1024* %l)
|
||||
tail call void @test_explicit_sret(i1024* sret(i1024) %l)
|
||||
%r = load i1024, i1024* %l, align 8
|
||||
ret i1024 %r
|
||||
}
|
||||
|
|
|
|||
|
|
@ -92,7 +92,7 @@ define amdgpu_kernel void @test_call_external_void_func_i1_imm() #0 {
|
|||
; GCN-NEXT: s_endpgm
|
||||
define amdgpu_kernel void @test_call_external_void_func_i1_signext(i32) #0 {
|
||||
%var = load volatile i1, i1 addrspace(1)* undef
|
||||
call void @external_void_func_i1_signext(i1 %var)
|
||||
call void @external_void_func_i1_signext(i1 signext %var)
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
@ -113,7 +113,7 @@ define amdgpu_kernel void @test_call_external_void_func_i1_signext(i32) #0 {
|
|||
; GCN-NEXT: s_endpgm
|
||||
define amdgpu_kernel void @test_call_external_void_func_i1_zeroext(i32) #0 {
|
||||
%var = load volatile i1, i1 addrspace(1)* undef
|
||||
call void @external_void_func_i1_zeroext(i1 %var)
|
||||
call void @external_void_func_i1_zeroext(i1 zeroext %var)
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
@ -148,7 +148,7 @@ define amdgpu_kernel void @test_call_external_void_func_i8_imm(i32) #0 {
|
|||
; GCN-NEXT: s_endpgm
|
||||
define amdgpu_kernel void @test_call_external_void_func_i8_signext(i32) #0 {
|
||||
%var = load volatile i8, i8 addrspace(1)* undef
|
||||
call void @external_void_func_i8_signext(i8 %var)
|
||||
call void @external_void_func_i8_signext(i8 signext %var)
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
@ -166,7 +166,7 @@ define amdgpu_kernel void @test_call_external_void_func_i8_signext(i32) #0 {
|
|||
; GCN-NEXT: s_endpgm
|
||||
define amdgpu_kernel void @test_call_external_void_func_i8_zeroext(i32) #0 {
|
||||
%var = load volatile i8, i8 addrspace(1)* undef
|
||||
call void @external_void_func_i8_zeroext(i8 %var)
|
||||
call void @external_void_func_i8_zeroext(i8 zeroext %var)
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
@ -195,7 +195,7 @@ define amdgpu_kernel void @test_call_external_void_func_i16_imm() #0 {
|
|||
; GCN-NEXT: s_endpgm
|
||||
define amdgpu_kernel void @test_call_external_void_func_i16_signext(i32) #0 {
|
||||
%var = load volatile i16, i16 addrspace(1)* undef
|
||||
call void @external_void_func_i16_signext(i16 %var)
|
||||
call void @external_void_func_i16_signext(i16 signext %var)
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
@ -212,7 +212,7 @@ define amdgpu_kernel void @test_call_external_void_func_i16_signext(i32) #0 {
|
|||
; GCN-NEXT: s_endpgm
|
||||
define amdgpu_kernel void @test_call_external_void_func_i16_zeroext(i32) #0 {
|
||||
%var = load volatile i16, i16 addrspace(1)* undef
|
||||
call void @external_void_func_i16_zeroext(i16 %var)
|
||||
call void @external_void_func_i16_zeroext(i16 zeroext %var)
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
|
|||
|
|
@ -517,7 +517,7 @@ define amdgpu_kernel void @kern_call_too_many_args_use_workitem_id_x_byval() #1
|
|||
i32 210, i32 220, i32 230, i32 240,
|
||||
i32 250, i32 260, i32 270, i32 280,
|
||||
i32 290, i32 300, i32 310, i32 320,
|
||||
i32 addrspace(5)* %alloca)
|
||||
i32 addrspace(5)* byval(i32) %alloca)
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
@ -541,7 +541,7 @@ define void @func_call_too_many_args_use_workitem_id_x_byval() #1 {
|
|||
i32 210, i32 220, i32 230, i32 240,
|
||||
i32 250, i32 260, i32 270, i32 280,
|
||||
i32 290, i32 300, i32 310, i32 320,
|
||||
i32 addrspace(5)* %alloca)
|
||||
i32 addrspace(5)* byval(i32) %alloca)
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
|
|||
|
|
@ -649,7 +649,7 @@ define amdgpu_kernel void @kern_call_too_many_args_use_workitem_id_x_byval() #1
|
|||
i32 210, i32 220, i32 230, i32 240,
|
||||
i32 250, i32 260, i32 270, i32 280,
|
||||
i32 290, i32 300, i32 310, i32 320,
|
||||
i32 addrspace(5)* %alloca)
|
||||
i32 addrspace(5)* byval(i32) %alloca)
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
@ -686,7 +686,7 @@ define void @func_call_too_many_args_use_workitem_id_x_byval() #1 {
|
|||
i32 210, i32 220, i32 230, i32 240,
|
||||
i32 250, i32 260, i32 270, i32 280,
|
||||
i32 290, i32 300, i32 310, i32 320,
|
||||
i32 addrspace(5)* %alloca)
|
||||
i32 addrspace(5)* byval(i32) %alloca)
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
|
|||
|
|
@ -214,7 +214,7 @@ define amdgpu_gfx void @test_call_external_void_func_i1_signext(i32) #0 {
|
|||
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
||||
; GFX10-NEXT: s_setpc_b64 s[4:5]
|
||||
%var = load volatile i1, i1 addrspace(1)* undef
|
||||
call amdgpu_gfx void @external_void_func_i1_signext(i1 %var)
|
||||
call amdgpu_gfx void @external_void_func_i1_signext(i1 signext%var)
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
@ -280,7 +280,7 @@ define amdgpu_gfx void @test_call_external_void_func_i1_zeroext(i32) #0 {
|
|||
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
||||
; GFX10-NEXT: s_setpc_b64 s[4:5]
|
||||
%var = load volatile i1, i1 addrspace(1)* undef
|
||||
call amdgpu_gfx void @external_void_func_i1_zeroext(i1 %var)
|
||||
call amdgpu_gfx void @external_void_func_i1_zeroext(i1 zeroext %var)
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
@ -401,7 +401,7 @@ define amdgpu_gfx void @test_call_external_void_func_i8_signext(i32) #0 {
|
|||
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
||||
; GFX10-NEXT: s_setpc_b64 s[4:5]
|
||||
%var = load volatile i8, i8 addrspace(1)* undef
|
||||
call amdgpu_gfx void @external_void_func_i8_signext(i8 %var)
|
||||
call amdgpu_gfx void @external_void_func_i8_signext(i8 signext %var)
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
@ -463,7 +463,7 @@ define amdgpu_gfx void @test_call_external_void_func_i8_zeroext(i32) #0 {
|
|||
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
||||
; GFX10-NEXT: s_setpc_b64 s[4:5]
|
||||
%var = load volatile i8, i8 addrspace(1)* undef
|
||||
call amdgpu_gfx void @external_void_func_i8_zeroext(i8 %var)
|
||||
call amdgpu_gfx void @external_void_func_i8_zeroext(i8 zeroext %var)
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
@ -584,7 +584,7 @@ define amdgpu_gfx void @test_call_external_void_func_i16_signext(i32) #0 {
|
|||
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
||||
; GFX10-NEXT: s_setpc_b64 s[4:5]
|
||||
%var = load volatile i16, i16 addrspace(1)* undef
|
||||
call amdgpu_gfx void @external_void_func_i16_signext(i16 %var)
|
||||
call amdgpu_gfx void @external_void_func_i16_signext(i16 signext %var)
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
@ -646,7 +646,7 @@ define amdgpu_gfx void @test_call_external_void_func_i16_zeroext(i32) #0 {
|
|||
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
||||
; GFX10-NEXT: s_setpc_b64 s[4:5]
|
||||
%var = load volatile i16, i16 addrspace(1)* undef
|
||||
call amdgpu_gfx void @external_void_func_i16_zeroext(i16 %var)
|
||||
call amdgpu_gfx void @external_void_func_i16_zeroext(i16 zeroext %var)
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
@ -3081,7 +3081,7 @@ define amdgpu_gfx void @test_call_external_void_func_byval_struct_i8_i32() #0 {
|
|||
%gep1 = getelementptr inbounds { i8, i32 }, { i8, i32 } addrspace(5)* %val, i32 0, i32 1
|
||||
store i8 3, i8 addrspace(5)* %gep0
|
||||
store i32 8, i32 addrspace(5)* %gep1
|
||||
call amdgpu_gfx void @external_void_func_byval_struct_i8_i32({ i8, i32 } addrspace(5)* %val)
|
||||
call amdgpu_gfx void @external_void_func_byval_struct_i8_i32({ i8, i32 } addrspace(5)* byval({ i8, i32 }) %val)
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
@ -3173,7 +3173,7 @@ define amdgpu_gfx void @test_call_external_void_func_sret_struct_i8_i32_byval_st
|
|||
%in.gep1 = getelementptr inbounds { i8, i32 }, { i8, i32 } addrspace(5)* %in.val, i32 0, i32 1
|
||||
store i8 3, i8 addrspace(5)* %in.gep0
|
||||
store i32 8, i32 addrspace(5)* %in.gep1
|
||||
call amdgpu_gfx void @external_void_func_sret_struct_i8_i32_byval_struct_i8_i32({ i8, i32 } addrspace(5)* %out.val, { i8, i32 } addrspace(5)* %in.val)
|
||||
call amdgpu_gfx void @external_void_func_sret_struct_i8_i32_byval_struct_i8_i32({ i8, i32 } addrspace(5)* sret({ i8, i32 }) %out.val, { i8, i32 } addrspace(5)* byval({ i8, i32 }) %in.val)
|
||||
%out.gep0 = getelementptr inbounds { i8, i32 }, { i8, i32 } addrspace(5)* %out.val, i32 0, i32 0
|
||||
%out.gep1 = getelementptr inbounds { i8, i32 }, { i8, i32 } addrspace(5)* %out.val, i32 0, i32 1
|
||||
%out.val0 = load i8, i8 addrspace(5)* %out.gep0
|
||||
|
|
@ -3384,7 +3384,7 @@ define amdgpu_gfx void @test_call_external_void_func_i1_imm_inreg() #0 {
|
|||
; GFX10-NEXT: s_mov_b32 exec_lo, s6
|
||||
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
||||
; GFX10-NEXT: s_setpc_b64 s[4:5]
|
||||
call amdgpu_gfx void @external_void_func_i1_inreg(i1 true)
|
||||
call amdgpu_gfx void @external_void_func_i1_inreg(i1 inreg true)
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
@ -3443,7 +3443,7 @@ define amdgpu_gfx void @test_call_external_void_func_i8_imm_inreg(i32) #0 {
|
|||
; GFX10-NEXT: s_mov_b32 exec_lo, s6
|
||||
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
||||
; GFX10-NEXT: s_setpc_b64 s[4:5]
|
||||
call amdgpu_gfx void @external_void_func_i8_inreg(i8 123)
|
||||
call amdgpu_gfx void @external_void_func_i8_inreg(i8 inreg 123)
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
@ -3502,7 +3502,7 @@ define amdgpu_gfx void @test_call_external_void_func_i16_imm_inreg() #0 {
|
|||
; GFX10-NEXT: s_mov_b32 exec_lo, s6
|
||||
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
||||
; GFX10-NEXT: s_setpc_b64 s[4:5]
|
||||
call amdgpu_gfx void @external_void_func_i16_inreg(i16 123)
|
||||
call amdgpu_gfx void @external_void_func_i16_inreg(i16 inreg 123)
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
@ -3561,7 +3561,7 @@ define amdgpu_gfx void @test_call_external_void_func_i32_imm_inreg(i32) #0 {
|
|||
; GFX10-NEXT: s_mov_b32 exec_lo, s6
|
||||
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
||||
; GFX10-NEXT: s_setpc_b64 s[4:5]
|
||||
call amdgpu_gfx void @external_void_func_i32_inreg(i32 42)
|
||||
call amdgpu_gfx void @external_void_func_i32_inreg(i32 inreg 42)
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
@ -3622,7 +3622,7 @@ define amdgpu_gfx void @test_call_external_void_func_i64_imm_inreg() #0 {
|
|||
; GFX10-NEXT: s_mov_b32 exec_lo, s6
|
||||
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
||||
; GFX10-NEXT: s_setpc_b64 s[4:5]
|
||||
call amdgpu_gfx void @external_void_func_i64_inreg(i64 123)
|
||||
call amdgpu_gfx void @external_void_func_i64_inreg(i64 inreg 123)
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
@ -3684,7 +3684,7 @@ define amdgpu_gfx void @test_call_external_void_func_v2i64_inreg() #0 {
|
|||
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
||||
; GFX10-NEXT: s_setpc_b64 s[4:5]
|
||||
%val = load <2 x i64>, <2 x i64> addrspace(4)* null
|
||||
call amdgpu_gfx void @external_void_func_v2i64_inreg(<2 x i64> %val)
|
||||
call amdgpu_gfx void @external_void_func_v2i64_inreg(<2 x i64> inreg %val)
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
@ -3749,7 +3749,7 @@ define amdgpu_gfx void @test_call_external_void_func_v2i64_imm_inreg() #0 {
|
|||
; GFX10-NEXT: s_mov_b32 exec_lo, s6
|
||||
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
||||
; GFX10-NEXT: s_setpc_b64 s[4:5]
|
||||
call amdgpu_gfx void @external_void_func_v2i64_inreg(<2 x i64> <i64 8589934593, i64 17179869187>)
|
||||
call amdgpu_gfx void @external_void_func_v2i64_inreg(<2 x i64> inreg <i64 8589934593, i64 17179869187>)
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
@ -3817,7 +3817,7 @@ define amdgpu_gfx void @test_call_external_void_func_v3i64_inreg() #0 {
|
|||
%load = load <2 x i64>, <2 x i64> addrspace(4)* null
|
||||
%val = shufflevector <2 x i64> %load, <2 x i64> <i64 8589934593, i64 undef>, <3 x i32> <i32 0, i32 1, i32 2>
|
||||
|
||||
call amdgpu_gfx void @external_void_func_v3i64_inreg(<3 x i64> %val)
|
||||
call amdgpu_gfx void @external_void_func_v3i64_inreg(<3 x i64> inreg %val)
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
@ -3888,7 +3888,7 @@ define amdgpu_gfx void @test_call_external_void_func_v4i64_inreg() #0 {
|
|||
; GFX10-NEXT: s_setpc_b64 s[4:5]
|
||||
%load = load <2 x i64>, <2 x i64> addrspace(4)* null
|
||||
%val = shufflevector <2 x i64> %load, <2 x i64> <i64 8589934593, i64 17179869187>, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
|
||||
call amdgpu_gfx void @external_void_func_v4i64_inreg(<4 x i64> %val)
|
||||
call amdgpu_gfx void @external_void_func_v4i64_inreg(<4 x i64> inreg %val)
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
@ -3947,7 +3947,7 @@ define amdgpu_gfx void @test_call_external_void_func_f16_imm_inreg() #0 {
|
|||
; GFX10-NEXT: s_mov_b32 exec_lo, s6
|
||||
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
||||
; GFX10-NEXT: s_setpc_b64 s[4:5]
|
||||
call amdgpu_gfx void @external_void_func_f16_inreg(half 4.0)
|
||||
call amdgpu_gfx void @external_void_func_f16_inreg(half inreg 4.0)
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
@ -4006,7 +4006,7 @@ define amdgpu_gfx void @test_call_external_void_func_f32_imm_inreg() #0 {
|
|||
; GFX10-NEXT: s_mov_b32 exec_lo, s6
|
||||
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
||||
; GFX10-NEXT: s_setpc_b64 s[4:5]
|
||||
call amdgpu_gfx void @external_void_func_f32_inreg(float 4.0)
|
||||
call amdgpu_gfx void @external_void_func_f32_inreg(float inreg 4.0)
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
@ -4067,7 +4067,7 @@ define amdgpu_gfx void @test_call_external_void_func_v2f32_imm_inreg() #0 {
|
|||
; GFX10-NEXT: s_mov_b32 exec_lo, s6
|
||||
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
||||
; GFX10-NEXT: s_setpc_b64 s[4:5]
|
||||
call amdgpu_gfx void @external_void_func_v2f32_inreg(<2 x float> <float 1.0, float 2.0>)
|
||||
call amdgpu_gfx void @external_void_func_v2f32_inreg(<2 x float> inreg <float 1.0, float 2.0>)
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
@ -4130,7 +4130,7 @@ define amdgpu_gfx void @test_call_external_void_func_v3f32_imm_inreg() #0 {
|
|||
; GFX10-NEXT: s_mov_b32 exec_lo, s6
|
||||
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
||||
; GFX10-NEXT: s_setpc_b64 s[4:5]
|
||||
call amdgpu_gfx void @external_void_func_v3f32_inreg(<3 x float> <float 1.0, float 2.0, float 4.0>)
|
||||
call amdgpu_gfx void @external_void_func_v3f32_inreg(<3 x float> inreg <float 1.0, float 2.0, float 4.0>)
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
@ -4197,7 +4197,7 @@ define amdgpu_gfx void @test_call_external_void_func_v5f32_imm_inreg() #0 {
|
|||
; GFX10-NEXT: s_mov_b32 exec_lo, s6
|
||||
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
||||
; GFX10-NEXT: s_setpc_b64 s[4:5]
|
||||
call amdgpu_gfx void @external_void_func_v5f32_inreg(<5 x float> <float 1.0, float 2.0, float 4.0, float -1.0, float 0.5>)
|
||||
call amdgpu_gfx void @external_void_func_v5f32_inreg(<5 x float> inreg <float 1.0, float 2.0, float 4.0, float -1.0, float 0.5>)
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
@ -4258,7 +4258,7 @@ define amdgpu_gfx void @test_call_external_void_func_f64_imm_inreg() #0 {
|
|||
; GFX10-NEXT: s_mov_b32 exec_lo, s6
|
||||
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
||||
; GFX10-NEXT: s_setpc_b64 s[4:5]
|
||||
call amdgpu_gfx void @external_void_func_f64_inreg(double 4.0)
|
||||
call amdgpu_gfx void @external_void_func_f64_inreg(double inreg 4.0)
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
@ -4323,7 +4323,7 @@ define amdgpu_gfx void @test_call_external_void_func_v2f64_imm_inreg() #0 {
|
|||
; GFX10-NEXT: s_mov_b32 exec_lo, s6
|
||||
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
||||
; GFX10-NEXT: s_setpc_b64 s[4:5]
|
||||
call amdgpu_gfx void @external_void_func_v2f64_inreg(<2 x double> <double 2.0, double 4.0>)
|
||||
call amdgpu_gfx void @external_void_func_v2f64_inreg(<2 x double> inreg <double 2.0, double 4.0>)
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
@ -4392,7 +4392,7 @@ define amdgpu_gfx void @test_call_external_void_func_v3f64_imm_inreg() #0 {
|
|||
; GFX10-NEXT: s_mov_b32 exec_lo, s6
|
||||
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
||||
; GFX10-NEXT: s_setpc_b64 s[4:5]
|
||||
call amdgpu_gfx void @external_void_func_v3f64_inreg(<3 x double> <double 2.0, double 4.0, double 8.0>)
|
||||
call amdgpu_gfx void @external_void_func_v3f64_inreg(<3 x double> inreg <double 2.0, double 4.0, double 8.0>)
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
@ -4452,7 +4452,7 @@ define amdgpu_gfx void @test_call_external_void_func_v2i16_inreg() #0 {
|
|||
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
||||
; GFX10-NEXT: s_setpc_b64 s[4:5]
|
||||
%val = load <2 x i16>, <2 x i16> addrspace(4)* undef
|
||||
call amdgpu_gfx void @external_void_func_v2i16_inreg(<2 x i16> %val)
|
||||
call amdgpu_gfx void @external_void_func_v2i16_inreg(<2 x i16> inreg %val)
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
@ -4512,7 +4512,7 @@ define amdgpu_gfx void @test_call_external_void_func_v3i16_inreg() #0 {
|
|||
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
||||
; GFX10-NEXT: s_setpc_b64 s[4:5]
|
||||
%val = load <3 x i16>, <3 x i16> addrspace(4)* undef
|
||||
call amdgpu_gfx void @external_void_func_v3i16_inreg(<3 x i16> %val)
|
||||
call amdgpu_gfx void @external_void_func_v3i16_inreg(<3 x i16> inreg %val)
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
@ -4572,7 +4572,7 @@ define amdgpu_gfx void @test_call_external_void_func_v3f16_inreg() #0 {
|
|||
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
||||
; GFX10-NEXT: s_setpc_b64 s[4:5]
|
||||
%val = load <3 x half>, <3 x half> addrspace(4)* undef
|
||||
call amdgpu_gfx void @external_void_func_v3f16_inreg(<3 x half> %val)
|
||||
call amdgpu_gfx void @external_void_func_v3f16_inreg(<3 x half> inreg %val)
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
@ -4633,7 +4633,7 @@ define amdgpu_gfx void @test_call_external_void_func_v3i16_imm_inreg() #0 {
|
|||
; GFX10-NEXT: s_mov_b32 exec_lo, s6
|
||||
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
||||
; GFX10-NEXT: s_setpc_b64 s[4:5]
|
||||
call amdgpu_gfx void @external_void_func_v3i16_inreg(<3 x i16> <i16 1, i16 2, i16 3>)
|
||||
call amdgpu_gfx void @external_void_func_v3i16_inreg(<3 x i16> inreg <i16 1, i16 2, i16 3>)
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
@ -4694,7 +4694,7 @@ define amdgpu_gfx void @test_call_external_void_func_v3f16_imm_inreg() #0 {
|
|||
; GFX10-NEXT: s_mov_b32 exec_lo, s6
|
||||
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
||||
; GFX10-NEXT: s_setpc_b64 s[4:5]
|
||||
call amdgpu_gfx void @external_void_func_v3f16_inreg(<3 x half> <half 1.0, half 2.0, half 4.0>)
|
||||
call amdgpu_gfx void @external_void_func_v3f16_inreg(<3 x half> inreg <half 1.0, half 2.0, half 4.0>)
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
@ -4754,7 +4754,7 @@ define amdgpu_gfx void @test_call_external_void_func_v4i16_inreg() #0 {
|
|||
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
||||
; GFX10-NEXT: s_setpc_b64 s[4:5]
|
||||
%val = load <4 x i16>, <4 x i16> addrspace(4)* undef
|
||||
call amdgpu_gfx void @external_void_func_v4i16_inreg(<4 x i16> %val)
|
||||
call amdgpu_gfx void @external_void_func_v4i16_inreg(<4 x i16> inreg %val)
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
@ -4815,7 +4815,7 @@ define amdgpu_gfx void @test_call_external_void_func_v4i16_imm_inreg() #0 {
|
|||
; GFX10-NEXT: s_mov_b32 exec_lo, s6
|
||||
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
||||
; GFX10-NEXT: s_setpc_b64 s[4:5]
|
||||
call amdgpu_gfx void @external_void_func_v4i16_inreg(<4 x i16> <i16 1, i16 2, i16 3, i16 4>)
|
||||
call amdgpu_gfx void @external_void_func_v4i16_inreg(<4 x i16> inreg <i16 1, i16 2, i16 3, i16 4>)
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
@ -4875,7 +4875,7 @@ define amdgpu_gfx void @test_call_external_void_func_v2f16_inreg() #0 {
|
|||
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
||||
; GFX10-NEXT: s_setpc_b64 s[4:5]
|
||||
%val = load <2 x half>, <2 x half> addrspace(4)* undef
|
||||
call amdgpu_gfx void @external_void_func_v2f16_inreg(<2 x half> %val)
|
||||
call amdgpu_gfx void @external_void_func_v2f16_inreg(<2 x half> inreg %val)
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
@ -4935,7 +4935,7 @@ define amdgpu_gfx void @test_call_external_void_func_v2i32_inreg() #0 {
|
|||
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
||||
; GFX10-NEXT: s_setpc_b64 s[4:5]
|
||||
%val = load <2 x i32>, <2 x i32> addrspace(4)* undef
|
||||
call amdgpu_gfx void @external_void_func_v2i32_inreg(<2 x i32> %val)
|
||||
call amdgpu_gfx void @external_void_func_v2i32_inreg(<2 x i32> inreg %val)
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
@ -4996,7 +4996,7 @@ define amdgpu_gfx void @test_call_external_void_func_v2i32_imm_inreg() #0 {
|
|||
; GFX10-NEXT: s_mov_b32 exec_lo, s6
|
||||
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
||||
; GFX10-NEXT: s_setpc_b64 s[4:5]
|
||||
call amdgpu_gfx void @external_void_func_v2i32_inreg(<2 x i32> <i32 1, i32 2>)
|
||||
call amdgpu_gfx void @external_void_func_v2i32_inreg(<2 x i32> inreg <i32 1, i32 2>)
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
@ -5059,7 +5059,7 @@ define amdgpu_gfx void @test_call_external_void_func_v3i32_imm_inreg(i32) #0 {
|
|||
; GFX10-NEXT: s_mov_b32 exec_lo, s6
|
||||
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
||||
; GFX10-NEXT: s_setpc_b64 s[4:5]
|
||||
call amdgpu_gfx void @external_void_func_v3i32_inreg(<3 x i32> <i32 3, i32 4, i32 5>)
|
||||
call amdgpu_gfx void @external_void_func_v3i32_inreg(<3 x i32> inreg <i32 3, i32 4, i32 5>)
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
@ -5124,7 +5124,7 @@ define amdgpu_gfx void @test_call_external_void_func_v3i32_i32_inreg(i32) #0 {
|
|||
; GFX10-NEXT: s_mov_b32 exec_lo, s6
|
||||
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
||||
; GFX10-NEXT: s_setpc_b64 s[4:5]
|
||||
call amdgpu_gfx void @external_void_func_v3i32_i32_inreg(<3 x i32> <i32 3, i32 4, i32 5>, i32 6)
|
||||
call amdgpu_gfx void @external_void_func_v3i32_i32_inreg(<3 x i32> inreg <i32 3, i32 4, i32 5>, i32 inreg 6)
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
@ -5184,7 +5184,7 @@ define amdgpu_gfx void @test_call_external_void_func_v4i32_inreg() #0 {
|
|||
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
||||
; GFX10-NEXT: s_setpc_b64 s[4:5]
|
||||
%val = load <4 x i32>, <4 x i32> addrspace(4)* undef
|
||||
call amdgpu_gfx void @external_void_func_v4i32_inreg(<4 x i32> %val)
|
||||
call amdgpu_gfx void @external_void_func_v4i32_inreg(<4 x i32> inreg %val)
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
@ -5249,7 +5249,7 @@ define amdgpu_gfx void @test_call_external_void_func_v4i32_imm_inreg() #0 {
|
|||
; GFX10-NEXT: s_mov_b32 exec_lo, s6
|
||||
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
||||
; GFX10-NEXT: s_setpc_b64 s[4:5]
|
||||
call amdgpu_gfx void @external_void_func_v4i32_inreg(<4 x i32> <i32 1, i32 2, i32 3, i32 4>)
|
||||
call amdgpu_gfx void @external_void_func_v4i32_inreg(<4 x i32> inreg <i32 1, i32 2, i32 3, i32 4>)
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
@ -5316,7 +5316,7 @@ define amdgpu_gfx void @test_call_external_void_func_v5i32_imm_inreg() #0 {
|
|||
; GFX10-NEXT: s_mov_b32 exec_lo, s6
|
||||
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
||||
; GFX10-NEXT: s_setpc_b64 s[4:5]
|
||||
call amdgpu_gfx void @external_void_func_v5i32_inreg(<5 x i32> <i32 1, i32 2, i32 3, i32 4, i32 5>)
|
||||
call amdgpu_gfx void @external_void_func_v5i32_inreg(<5 x i32> inreg <i32 1, i32 2, i32 3, i32 4, i32 5>)
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
@ -5381,7 +5381,7 @@ define amdgpu_gfx void @test_call_external_void_func_v8i32_inreg() #0 {
|
|||
; GFX10-NEXT: s_setpc_b64 s[4:5]
|
||||
%ptr = load <8 x i32> addrspace(4)*, <8 x i32> addrspace(4)* addrspace(4)* undef
|
||||
%val = load <8 x i32>, <8 x i32> addrspace(4)* %ptr
|
||||
call amdgpu_gfx void @external_void_func_v8i32_inreg(<8 x i32> %val)
|
||||
call amdgpu_gfx void @external_void_func_v8i32_inreg(<8 x i32> inreg %val)
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
@ -5454,7 +5454,7 @@ define amdgpu_gfx void @test_call_external_void_func_v8i32_imm_inreg() #0 {
|
|||
; GFX10-NEXT: s_mov_b32 exec_lo, s6
|
||||
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
||||
; GFX10-NEXT: s_setpc_b64 s[4:5]
|
||||
call amdgpu_gfx void @external_void_func_v8i32_inreg(<8 x i32> <i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8>)
|
||||
call amdgpu_gfx void @external_void_func_v8i32_inreg(<8 x i32> inreg <i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8>)
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
@ -5519,7 +5519,7 @@ define amdgpu_gfx void @test_call_external_void_func_v16i32_inreg() #0 {
|
|||
; GFX10-NEXT: s_setpc_b64 s[4:5]
|
||||
%ptr = load <16 x i32> addrspace(4)*, <16 x i32> addrspace(4)* addrspace(4)* undef
|
||||
%val = load <16 x i32>, <16 x i32> addrspace(4)* %ptr
|
||||
call amdgpu_gfx void @external_void_func_v16i32_inreg(<16 x i32> %val)
|
||||
call amdgpu_gfx void @external_void_func_v16i32_inreg(<16 x i32> inreg %val)
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
@ -5697,7 +5697,7 @@ define amdgpu_gfx void @test_call_external_void_func_v32i32_inreg() #0 {
|
|||
; GFX10-NEXT: s_setpc_b64 s[4:5]
|
||||
%ptr = load <32 x i32> addrspace(4)*, <32 x i32> addrspace(4)* addrspace(4)* undef
|
||||
%val = load <32 x i32>, <32 x i32> addrspace(4)* %ptr
|
||||
call amdgpu_gfx void @external_void_func_v32i32_inreg(<32 x i32> %val)
|
||||
call amdgpu_gfx void @external_void_func_v32i32_inreg(<32 x i32> inreg %val)
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
@ -5883,7 +5883,7 @@ define amdgpu_gfx void @test_call_external_void_func_v32i32_i32_inreg(i32) #0 {
|
|||
%ptr0 = load <32 x i32> addrspace(4)*, <32 x i32> addrspace(4)* addrspace(4)* undef
|
||||
%val0 = load <32 x i32>, <32 x i32> addrspace(4)* %ptr0
|
||||
%val1 = load i32, i32 addrspace(4)* undef
|
||||
call amdgpu_gfx void @external_void_func_v32i32_i32_inreg(<32 x i32> %val0, i32 %val1)
|
||||
call amdgpu_gfx void @external_void_func_v32i32_i32_inreg(<32 x i32> inreg %val0, i32 inreg %val1)
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
|
|||
|
|
@ -24,6 +24,6 @@ define amdgpu_gfx float @caller(float %arg0) {
|
|||
; GCN-NEXT: s_addc_u32 s7, s7, callee@rel32@hi+12
|
||||
; GCN-NEXT: s_setpc_b64 s[6:7]
|
||||
%add = fadd float %arg0, 1.0
|
||||
%call = tail call amdgpu_gfx float @callee(float %add, float 2.0)
|
||||
%call = tail call amdgpu_gfx float @callee(float %add, float inreg 2.0)
|
||||
ret float %call
|
||||
}
|
||||
|
|
|
|||
|
|
@ -13,6 +13,6 @@ entry:
|
|||
; CHECK-NOT: r0
|
||||
; CHECK: bl returns_r0
|
||||
; CHECK-NOT: r0
|
||||
%b = call i32 @returns_r0(i32 %a)
|
||||
%b = call i32 @returns_r0(i32 returned %a)
|
||||
ret i32 %a
|
||||
}
|
||||
|
|
|
|||
|
|
@ -22,9 +22,9 @@ entry:
|
|||
; CHECKT2D: uxth r0, r0
|
||||
; CHECKT2D: bl _identity32
|
||||
; CHECKT2D: mov r0, [[SAVEX]]
|
||||
%call = tail call i16 @identity16(i16 %x)
|
||||
%call = tail call i16 @identity16(i16 returned %x)
|
||||
%b = zext i16 %call to i32
|
||||
%call2 = tail call i32 @identity32(i32 %b)
|
||||
%call2 = tail call i32 @identity32(i32 returned %b)
|
||||
ret i16 %x
|
||||
}
|
||||
|
||||
|
|
@ -56,9 +56,9 @@ entry:
|
|||
; This shouldn't be required
|
||||
; CHECKT2D: mov r0, [[SAVEX]]
|
||||
|
||||
%call = tail call i16 @retzext16(i16 %x)
|
||||
%call = tail call i16 @retzext16(i16 returned %x)
|
||||
%b = zext i16 %call to i32
|
||||
%call2 = tail call i32 @identity32(i32 %b)
|
||||
%call2 = tail call i32 @identity32(i32 returned %b)
|
||||
ret i16 %x
|
||||
}
|
||||
|
||||
|
|
@ -76,9 +76,9 @@ entry:
|
|||
; CHECKT2D: sxth r0, {{r[0-9]+}}
|
||||
; CHECKT2D: bl _identity32
|
||||
; CHECKT2D: mov r0, [[SAVEX]]
|
||||
%call = tail call i16 @retzext16(i16 %x)
|
||||
%call = tail call i16 @retzext16(i16 returned %x)
|
||||
%b = sext i16 %call to i32
|
||||
%call2 = tail call i32 @identity32(i32 %b)
|
||||
%call2 = tail call i32 @identity32(i32 returned %b)
|
||||
ret i16 %x
|
||||
}
|
||||
|
||||
|
|
@ -96,10 +96,10 @@ entry:
|
|||
; CHECKT2D: uxth r0, r0
|
||||
; CHECKT2D: bl _identity32
|
||||
; CHECKT2D: b.w _paramzext16
|
||||
%call = tail call i16 @paramzext16(i16 %x)
|
||||
%call = tail call i16 @paramzext16(i16 zeroext returned %x)
|
||||
%b = zext i16 %call to i32
|
||||
%call2 = tail call i32 @identity32(i32 %b)
|
||||
%call3 = tail call i16 @paramzext16(i16 %call)
|
||||
%call2 = tail call i32 @identity32(i32 returned %b)
|
||||
%call3 = tail call i16 @paramzext16(i16 zeroext returned %call)
|
||||
ret i16 %call3
|
||||
}
|
||||
|
||||
|
|
@ -121,13 +121,13 @@ entry:
|
|||
; CHECKT2D: bl _paramzext16
|
||||
; CHECKT2D: bl _identity32
|
||||
; CHECKT2D: b.w _paramzext16
|
||||
%call = tail call i16 @paramzext16(i16 %x)
|
||||
%call = tail call i16 @paramzext16(i16 zeroext returned %x)
|
||||
|
||||
; Should make no difference if %x is used below rather than %call, but it does
|
||||
%b = zext i16 %x to i32
|
||||
|
||||
%call2 = tail call i32 @identity32(i32 %b)
|
||||
%call3 = tail call i16 @paramzext16(i16 %call)
|
||||
%call3 = tail call i16 @paramzext16(i16 zeroext returned %call)
|
||||
ret i16 %call3
|
||||
}
|
||||
|
||||
|
|
@ -149,9 +149,9 @@ entry:
|
|||
; FIXME: Tail call should be OK here
|
||||
; CHECKT2D: bl _identity32
|
||||
|
||||
%call = tail call i16 @bothzext16(i16 %x)
|
||||
%call = tail call i16 @bothzext16(i16 zeroext returned %x)
|
||||
%b = zext i16 %x to i32
|
||||
%call2 = tail call i32 @identity32(i32 %b)
|
||||
%call2 = tail call i32 @identity32(i32 returned %b)
|
||||
ret i16 %call
|
||||
}
|
||||
|
||||
|
|
@ -171,8 +171,8 @@ entry:
|
|||
; CHECKT2D: sxth r0, [[SAVEX]]
|
||||
; CHECKT2D: bl _identity32
|
||||
; CHECKT2D: mov r0, [[SAVEX]]
|
||||
%call = tail call i16 @bothzext16(i16 %x)
|
||||
%call = tail call i16 @bothzext16(i16 zeroext returned %x)
|
||||
%b = sext i16 %x to i32
|
||||
%call2 = tail call i32 @identity32(i32 %b)
|
||||
%call2 = tail call i32 @identity32(i32 returned %b)
|
||||
ret i16 %x
|
||||
}
|
||||
|
|
|
|||
|
|
@ -28,9 +28,9 @@ entry:
|
|||
; CHECKT2D-NOT: mov r0, {{r[0-9]+}}
|
||||
; CHECKT2D: b.w _B_ctor_base
|
||||
%0 = bitcast %struct.C* %this to %struct.A*
|
||||
%call = tail call %struct.A* @A_ctor_base(%struct.A* %0)
|
||||
%call = tail call %struct.A* @A_ctor_base(%struct.A* returned %0)
|
||||
%1 = getelementptr inbounds %struct.C, %struct.C* %this, i32 0, i32 0
|
||||
%call2 = tail call %struct.B* @B_ctor_base(%struct.B* %1, i32 %x)
|
||||
%call2 = tail call %struct.B* @B_ctor_base(%struct.B* returned %1, i32 %x)
|
||||
ret %struct.C* %this
|
||||
}
|
||||
|
||||
|
|
@ -59,7 +59,7 @@ entry:
|
|||
; CHECKELF: b C_ctor_base
|
||||
; CHECKT2D-LABEL: C_ctor_complete:
|
||||
; CHECKT2D: b.w _C_ctor_base
|
||||
%call = tail call %struct.C* @C_ctor_base(%struct.C* %this, i32 %x)
|
||||
%call = tail call %struct.C* @C_ctor_base(%struct.C* returned %this, i32 %x)
|
||||
ret %struct.C* %this
|
||||
}
|
||||
|
||||
|
|
@ -86,8 +86,8 @@ entry:
|
|||
; CHECKT2D-NOT: mov r0, {{r[0-9]+}}
|
||||
; CHECKT2D: b.w _B_ctor_complete
|
||||
%b = getelementptr inbounds %struct.D, %struct.D* %this, i32 0, i32 0
|
||||
%call = tail call %struct.B* @B_ctor_complete(%struct.B* %b, i32 %x)
|
||||
%call2 = tail call %struct.B* @B_ctor_complete(%struct.B* %b, i32 %x)
|
||||
%call = tail call %struct.B* @B_ctor_complete(%struct.B* returned %b, i32 %x)
|
||||
%call2 = tail call %struct.B* @B_ctor_complete(%struct.B* returned %b, i32 %x)
|
||||
ret %struct.D* %this
|
||||
}
|
||||
|
||||
|
|
@ -98,8 +98,8 @@ entry:
|
|||
; CHECKT2D-LABEL: E_ctor_base:
|
||||
; CHECKT2D-NOT: b.w _B_ctor_complete
|
||||
%b = getelementptr inbounds %struct.E, %struct.E* %this, i32 0, i32 0
|
||||
%call = tail call %struct.B* @B_ctor_complete(%struct.B* %b, i32 %x)
|
||||
%call = tail call %struct.B* @B_ctor_complete(%struct.B* returned %b, i32 %x)
|
||||
%b2 = getelementptr inbounds %struct.E, %struct.E* %this, i32 0, i32 1
|
||||
%call2 = tail call %struct.B* @B_ctor_complete(%struct.B* %b2, i32 %x)
|
||||
%call2 = tail call %struct.B* @B_ctor_complete(%struct.B* returned %b2, i32 %x)
|
||||
ret %struct.E* %this
|
||||
}
|
||||
|
|
|
|||
|
|
@ -50,7 +50,7 @@ define void @intarg(i8 %a0, ; %i0
|
|||
; CHECK-NOT: add %sp
|
||||
; CHECK: restore
|
||||
define void @call_intarg(i32 %i0, i8* %i1) {
|
||||
call void @intarg(i8 0, i8 1, i16 2, i32 3, i8* undef, i32 5, i32 %i0, i8* %i1)
|
||||
call void @intarg(i8 0, i8 1, i16 2, i32 3, i8* undef, i32 5, i32 signext %i0, i8* %i1)
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
@ -222,7 +222,7 @@ define i32 @inreg_fi(i32 inreg %a0, ; high bits of %i0
|
|||
; SOFT: or %i1, %i0, %o0
|
||||
; CHECK: call inreg_fi
|
||||
define void @call_inreg_fi(i32* %p, i32 %i1, float %f5) {
|
||||
%x = call i32 @inreg_fi(i32 %i1, float %f5)
|
||||
%x = call i32 @inreg_fi(i32 inreg %i1, float inreg %f5)
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
@ -245,7 +245,7 @@ define float @inreg_ff(float inreg %a0, ; %f0
|
|||
; SOFT: or %i1, %i0, %o0
|
||||
; CHECK: call inreg_ff
|
||||
define void @call_inreg_ff(i32* %p, float %f3, float %f5) {
|
||||
%x = call float @inreg_ff(float %f3, float %f5)
|
||||
%x = call float @inreg_ff(float inreg %f3, float inreg %f5)
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
@ -269,7 +269,7 @@ define i32 @inreg_if(float inreg %a0, ; %f0
|
|||
; SOFT: or %i1, %i0, %o0
|
||||
; CHECK: call inreg_if
|
||||
define void @call_inreg_if(i32* %p, float %f3, i32 %i2) {
|
||||
%x = call i32 @inreg_if(float %f3, i32 %i2)
|
||||
%x = call i32 @inreg_if(float inreg %f3, i32 inreg %i2)
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
@ -289,7 +289,7 @@ define i32 @inreg_ii(i32 inreg %a0, ; high bits of %i0
|
|||
; CHECK: or [[R1]], [[R2]], %o0
|
||||
; CHECK: call inreg_ii
|
||||
define void @call_inreg_ii(i32* %p, i32 %i1, i32 %i2) {
|
||||
%x = call i32 @inreg_ii(i32 %i1, i32 %i2)
|
||||
%x = call i32 @inreg_ii(i32 inreg %i1, i32 inreg %i2)
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
|
|||
|
|
@ -66,9 +66,9 @@ define void @foo() {
|
|||
; CHECK-STACK: mvghi 160(%r15), -5
|
||||
; CHECK-STACK: brasl %r14, bar@PLT
|
||||
|
||||
call void @bar (i8 -1, i16 -2, i32 -3, i64 -4, float 0.0, double 0.0,
|
||||
call void @bar (i8 signext -1, i16 signext -2, i32 signext -3, i64 -4, float 0.0, double 0.0,
|
||||
fp128 0xL00000000000000000000000000000000, i64 -5,
|
||||
float -0.0, double -0.0, i8 -6, i16 -7, i32 -8, i64 -9,
|
||||
float -0.0, double -0.0, i8 signext -6, i16 signext -7, i32 signext -8, i64 -9,
|
||||
float 0.0, double 0.0,
|
||||
fp128 0xL00000000000000000000000000000000)
|
||||
ret void
|
||||
|
|
|
|||
|
|
@ -68,9 +68,9 @@ define void @foo() {
|
|||
; CHECK-STACK: mvghi 160(%r15), -5
|
||||
; CHECK-STACK: brasl %r14, bar@PLT
|
||||
|
||||
call void @bar (i8 -1, i16 -2, i32 -3, i64 -4, float 0.0, double 0.0,
|
||||
call void @bar (i8 zeroext -1, i16 zeroext -2, i32 zeroext -3, i64 -4, float 0.0, double 0.0,
|
||||
fp128 0xL00000000000000000000000000000000, i64 -5,
|
||||
float -0.0, double -0.0, i8 -6, i16 -7, i32 -8, i64 -9,
|
||||
float -0.0, double -0.0, i8 zeroext -6, i16 zeroext -7, i32 zeroext -8, i64 -9,
|
||||
float 0.0, double 0.0,
|
||||
fp128 0xL00000000000000000000000000000000)
|
||||
ret void
|
||||
|
|
|
|||
|
|
@ -7,7 +7,7 @@ declare x86_fastcallcc void @func(i32*, i64 inreg)
|
|||
|
||||
define x86_fastcallcc void @caller(i32, i64) {
|
||||
%X = alloca i32 ; <i32*> [#uses=1]
|
||||
call x86_fastcallcc void @func( i32* %X, i64 0 )
|
||||
call x86_fastcallcc void @func( i32* %X, i64 inreg 0 )
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
|
|||
|
|
@ -4,7 +4,7 @@
|
|||
declare x86_fastcallcc i64 @callee(i64 inreg)
|
||||
|
||||
define i64 @caller() {
|
||||
%X = call x86_fastcallcc i64 @callee( i64 4294967299 ) ; <i64> [#uses=1]
|
||||
%X = call x86_fastcallcc i64 @callee( i64 inreg 4294967299 ) ; <i64> [#uses=1]
|
||||
; CHECK: mov{{.*}}edx, 1
|
||||
ret i64 %X
|
||||
}
|
||||
|
|
|
|||
|
|
@ -0,0 +1,45 @@
|
|||
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
||||
; RUN: llc < %s -mtriple=x86_64-unknown | FileCheck %s
|
||||
|
||||
; This tests that we only look at the call site for ABI attributes, so f and f2 should codegen differently
|
||||
|
||||
define void @b(i8* byval(i8) %p) {
|
||||
; CHECK-LABEL: b:
|
||||
; CHECK: # %bb.0:
|
||||
; CHECK-NEXT: retq
|
||||
ret void
|
||||
}
|
||||
|
||||
define void @f(i8 %p) {
|
||||
; CHECK-LABEL: f:
|
||||
; CHECK: # %bb.0:
|
||||
; CHECK-NEXT: subq $24, %rsp
|
||||
; CHECK-NEXT: .cfi_def_cfa_offset 32
|
||||
; CHECK-NEXT: movb {{[0-9]+}}(%rsp), %al
|
||||
; CHECK-NEXT: movb %al, (%rsp)
|
||||
; CHECK-NEXT: callq b@PLT
|
||||
; CHECK-NEXT: addq $24, %rsp
|
||||
; CHECK-NEXT: .cfi_def_cfa_offset 8
|
||||
; CHECK-NEXT: retq
|
||||
%a = alloca i8
|
||||
;store i8 %p, i8* %a
|
||||
call void @b(i8* byval(i8) %a)
|
||||
ret void
|
||||
}
|
||||
|
||||
define void @f2(i8 %p) {
|
||||
; CHECK-LABEL: f2:
|
||||
; CHECK: # %bb.0:
|
||||
; CHECK-NEXT: pushq %rax
|
||||
; CHECK-NEXT: .cfi_def_cfa_offset 16
|
||||
; CHECK-NEXT: leaq {{[0-9]+}}(%rsp), %rdi
|
||||
; CHECK-NEXT: callq b@PLT
|
||||
; CHECK-NEXT: popq %rax
|
||||
; CHECK-NEXT: .cfi_def_cfa_offset 8
|
||||
; CHECK-NEXT: retq
|
||||
%a = alloca i8
|
||||
;store i8 %p, i8* %a
|
||||
call void @b(i8* %a)
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
@ -107,7 +107,7 @@ entry:
|
|||
; NORMAL-NEXT: addl $12, %esp
|
||||
define void @test4() optsize {
|
||||
entry:
|
||||
call void @inreg(i32 1, i32 2, i32 3, i32 4)
|
||||
call void @inreg(i32 1, i32 inreg 2, i32 3, i32 4)
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
@ -307,9 +307,9 @@ define void @test11() optsize {
|
|||
define void @test12() optsize {
|
||||
entry:
|
||||
%s = alloca %struct.s, align 4
|
||||
call void @struct(%struct.s* %s, i32 2, i32 3, i32 4)
|
||||
call void @struct(%struct.s* byval(%struct.s) %s, i32 2, i32 3, i32 4)
|
||||
call void @good(i32 5, i32 6, i32 7, i32 8)
|
||||
call void @struct(%struct.s* %s, i32 10, i32 11, i32 12)
|
||||
call void @struct(%struct.s* byval(%struct.s) %s, i32 10, i32 11, i32 12)
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
@ -340,7 +340,7 @@ define void @test12b() optsize {
|
|||
entry:
|
||||
%s = alloca %struct.s, align 4
|
||||
call void @good(i32 1, i32 2, i32 3, i32 4)
|
||||
call void @struct(%struct.s* %s, i32 6, i32 7, i32 8)
|
||||
call void @struct(%struct.s* byval(%struct.s) %s, i32 6, i32 7, i32 8)
|
||||
call void @good(i32 9, i32 10, i32 11, i32 12)
|
||||
ret void
|
||||
}
|
||||
|
|
@ -413,7 +413,7 @@ entry:
|
|||
%0 = bitcast %struct.A* %a to i64*
|
||||
%1 = load i64, i64* %0, align 4
|
||||
store i64 %1, i64* %agg.tmp, align 4
|
||||
%call = call x86_thiscallcc %struct.B* @B_ctor(%struct.B* %ref.tmp, %struct.A* byval(%struct.A) %tmpcast)
|
||||
%call = call x86_thiscallcc %struct.B* @B_ctor(%struct.B* returned %ref.tmp, %struct.A* byval(%struct.A) %tmpcast)
|
||||
%2 = getelementptr inbounds %struct.B, %struct.B* %tmp, i32 0, i32 0
|
||||
call void @B_func(%struct.B* sret(%struct.B) %tmp, %struct.B* %ref.tmp, i32 1)
|
||||
ret void
|
||||
|
|
|
|||
|
|
@ -60,7 +60,7 @@ define void @spill(i32 inreg %a, i32 inreg %b, i32 inreg %c) minsize nounwind {
|
|||
; CHECK-DAG: movl {{.*}}, %edx
|
||||
; CHECK: calll _spill
|
||||
%i = call i32 @param2_ret(i32 1, i32 2)
|
||||
call void @spill(i32 %a, i32 %b, i32 %c)
|
||||
call void @spill(i32 inreg %a, i32 inreg %b, i32 inreg %c)
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
|
|||
|
|
@ -129,11 +129,11 @@ define void @nested_with_init() {
|
|||
; CHECK: pushl [[REGISTER2]]
|
||||
; CHECK: calll _init
|
||||
|
||||
call void @foo_ret_p(%Foo* %b1, %Foo* preallocated(%Foo) %b2) ["preallocated"(token %t2)]
|
||||
call void @foo_ret_p(%Foo* sret(%Foo) %b1, %Foo* preallocated(%Foo) %b2) ["preallocated"(token %t2)]
|
||||
; CHECK-NOT: subl {{\$[0-9]+}}, %esp
|
||||
; CHECK-NOT: pushl
|
||||
; CHECK: calll _foo_ret_p
|
||||
call void @foo_ret_p(%Foo* %tmp, %Foo* preallocated(%Foo) %b1) ["preallocated"(token %t1)]
|
||||
call void @foo_ret_p(%Foo* sret(%Foo) %tmp, %Foo* preallocated(%Foo) %b1) ["preallocated"(token %t1)]
|
||||
; CHECK-NOT: subl {{\$[0-9]+}}, %esp
|
||||
; CHECK-NOT: pushl
|
||||
; CHECK: calll _foo_ret_p
|
||||
|
|
@ -150,7 +150,7 @@ define void @inreg() {
|
|||
; CHECK: subl $8, %esp
|
||||
; CHECK: movl $9, %eax
|
||||
; CHECK: calll _foo_inreg_p
|
||||
call void @foo_inreg_p(i32 9, %Foo* preallocated(%Foo) %b) ["preallocated"(token %t)]
|
||||
call void @foo_inreg_p(i32 inreg 9, %Foo* preallocated(%Foo) %b) ["preallocated"(token %t)]
|
||||
ret void
|
||||
}
|
||||
|
||||
|
|
|
|||
|
|
@ -181,7 +181,7 @@ define x86_stdcallcc void @stdcall_thiscall_tail(i32 %a, i32 %b) {
|
|||
|
||||
declare x86_fastcallcc void @fastcall2(i32 inreg %a, i32 inreg %b)
|
||||
define void @cdecl_fastcall_tail(i32 %a, i32 %b) {
|
||||
tail call x86_fastcallcc void @fastcall2(i32 %a, i32 %b)
|
||||
tail call x86_fastcallcc void @fastcall2(i32 inreg %a, i32 inreg %b)
|
||||
ret void
|
||||
}
|
||||
; fastcall2 won't pop anything.
|
||||
|
|
|
|||
Loading…
Reference in New Issue