[llvm] r308179 - [AMDGPU] CodeGen: check dst operand type to determine if omod is supported for VOP3 instructions
Chandler Carruth via llvm-commits
llvm-commits at lists.llvm.org
Tue Jul 18 00:35:22 PDT 2017
This has been in tree for 12 hours spamming. Reverting now.
Sam, please be more careful when committing to watch for followup on the
list.
On Mon, Jul 17, 2017 at 1:57 PM Eric Christopher via llvm-commits <
llvm-commits at lists.llvm.org> wrote:
> This is causing a lot of warnings/errors in tablegen. Can you please fix
> or revert?
>
> Too few operands in record V_DIV_SCALE_F64_vi (no match for variable omod):
> V_DIV_SCALE_F64_vi { // Instruction AMDGPUInst PredicateControl InstSI
> SIMCInstr VOP3_Real Enc64 VOP3be VOP3be_vi _vi
> field bit isRegisterLoad = 0;
> field bit isRegisterStore = 0;
> field bits<64> SoftFail = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
>
> Thanks!
>
> -eric
>
> On Mon, Jul 17, 2017 at 7:24 AM Sam Kolton via llvm-commits <
> llvm-commits at lists.llvm.org> wrote:
>
>> Author: skolton
>> Date: Mon Jul 17 07:23:38 2017
>> New Revision: 308179
>>
>> URL: http://llvm.org/viewvc/llvm-project?rev=308179&view=rev
>> Log:
>> [AMDGPU] CodeGen: check dst operand type to determine if omod is
>> supported for VOP3 instructions
>>
>> Summary:
>> Previously, CodeGen checked first src operand type to determine if omod
>> is supported by instruction. This isn't correct for some instructions: e.g.
>> V_CMP_EQ_F32 has floating-point src operands but desn't support omod.
>> Changed .td files to check if dst operand instead of src operand.
>>
>> Reviewers: arsenm, vpykhtin
>>
>> Subscribers: kzhuravl, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye
>>
>> Differential Revision: https://reviews.llvm.org/D35350
>>
>> Modified:
>> llvm/trunk/lib/Target/AMDGPU/SIInstrInfo.td
>> llvm/trunk/lib/Target/AMDGPU/SIInstructions.td
>> llvm/trunk/lib/Target/AMDGPU/VOP2Instructions.td
>> llvm/trunk/lib/Target/AMDGPU/VOP3Instructions.td
>> llvm/trunk/lib/Target/AMDGPU/VOPCInstructions.td
>> llvm/trunk/lib/Target/AMDGPU/VOPInstructions.td
>>
>> llvm/trunk/test/CodeGen/AMDGPU/rename-independent-subregs-mac-operands.mir
>> llvm/trunk/test/CodeGen/AMDGPU/sdwa-peephole-instr.mir
>> llvm/trunk/test/CodeGen/AMDGPU/sdwa-vop2-64bit.mir
>> llvm/trunk/test/CodeGen/AMDGPU/vccz-corrupt-bug-workaround.mir
>> llvm/trunk/test/MC/AMDGPU/vop3-errs.s
>>
>> Modified: llvm/trunk/lib/Target/AMDGPU/SIInstrInfo.td
>> URL:
>> http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/AMDGPU/SIInstrInfo.td?rev=308179&r1=308178&r2=308179&view=diff
>>
>> ==============================================================================
>> --- llvm/trunk/lib/Target/AMDGPU/SIInstrInfo.td (original)
>> +++ llvm/trunk/lib/Target/AMDGPU/SIInstrInfo.td Mon Jul 17 07:23:38 2017
>> @@ -1436,7 +1436,7 @@ class VOPProfile <list<ValueType> _ArgVT
>>
>> field bit IsPacked = isPackedType<Src0VT>.ret;
>> field bit HasOpSel = IsPacked;
>> - field bit HasOMod = !if(HasOpSel, 0, HasModifiers);
>> + field bit HasOMod = !if(HasOpSel, 0, isFloatType<DstVT>.ret);
>> field bit HasSDWAOMod = isFloatType<DstVT>.ret;
>>
>> field bit HasExt = getHasExt<NumSrcArgs, DstVT, Src0VT, Src1VT>.ret;
>>
>> Modified: llvm/trunk/lib/Target/AMDGPU/SIInstructions.td
>> URL:
>> http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/AMDGPU/SIInstructions.td?rev=308179&r1=308178&r2=308179&view=diff
>>
>> ==============================================================================
>> --- llvm/trunk/lib/Target/AMDGPU/SIInstructions.td (original)
>> +++ llvm/trunk/lib/Target/AMDGPU/SIInstructions.td Mon Jul 17 07:23:38
>> 2017
>> @@ -1060,7 +1060,7 @@ def : Pat <
>>
>> class FPToI1Pat<Instruction Inst, int KOne, ValueType kone_type,
>> ValueType vt, SDPatternOperator fp_to_int> : Pat <
>> (i1 (fp_to_int (vt (VOP3Mods vt:$src0, i32:$src0_modifiers)))),
>> - (i1 (Inst 0, (kone_type KOne), $src0_modifiers, $src0, DSTCLAMP.NONE,
>> DSTOMOD.NONE))
>> + (i1 (Inst 0, (kone_type KOne), $src0_modifiers, $src0, DSTCLAMP.NONE))
>> >;
>>
>> def : FPToI1Pat<V_CMP_EQ_F32_e64, CONST.FP32_ONE, i32, f32, fp_to_uint>;
>>
>> Modified: llvm/trunk/lib/Target/AMDGPU/VOP2Instructions.td
>> URL:
>> http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/AMDGPU/VOP2Instructions.td?rev=308179&r1=308178&r2=308179&view=diff
>>
>> ==============================================================================
>> --- llvm/trunk/lib/Target/AMDGPU/VOP2Instructions.td (original)
>> +++ llvm/trunk/lib/Target/AMDGPU/VOP2Instructions.td Mon Jul 17 07:23:38
>> 2017
>> @@ -117,7 +117,10 @@ class VOP2_SDWA_Pseudo <string OpName, V
>> class getVOP2Pat64 <SDPatternOperator node, VOPProfile P> : LetDummies {
>> list<dag> ret = !if(P.HasModifiers,
>> [(set P.DstVT:$vdst,
>> - (node (P.Src0VT (VOP3Mods0 P.Src0VT:$src0, i32:$src0_modifiers,
>> i1:$clamp, i32:$omod)),
>> + (node (P.Src0VT
>> + !if(P.HasOMod,
>> + (VOP3Mods0 P.Src0VT:$src0, i32:$src0_modifiers,
>> i1:$clamp, i32:$omod),
>> + (VOP3Mods0 P.Src0VT:$src0, i32:$src0_modifiers,
>> i1:$clamp))),
>> (P.Src1VT (VOP3Mods P.Src1VT:$src1, i32:$src1_modifiers))))],
>> [(set P.DstVT:$vdst, (node P.Src0VT:$src0, P.Src1VT:$src1))]);
>> }
>> @@ -813,9 +816,11 @@ let SubtargetPredicate = isVI in {
>>
>> // Aliases to simplify matching of floating-point instructions that
>> // are VOP2 on SI and VOP3 on VI.
>> -class SI2_VI3Alias <string name, Instruction inst> : InstAlias <
>> +class SI2_VI3Alias <string name, VOP3_Real inst> : InstAlias <
>> name#" $dst, $src0, $src1",
>> - (inst VGPR_32:$dst, 0, VCSrc_f32:$src0, 0, VCSrc_f32:$src1, 0, 0)
>> + !if(inst.Pfl.HasOMod,
>> + (inst VGPR_32:$dst, 0, VCSrc_f32:$src0, 0, VCSrc_f32:$src1, 0, 0),
>> + (inst VGPR_32:$dst, 0, VCSrc_f32:$src0, 0, VCSrc_f32:$src1, 0))
>> >, PredicateControl {
>> let UseInstAsmMatchConverter = 0;
>> let AsmVariantName = AMDGPUAsmVariants.VOP3;
>>
>> Modified: llvm/trunk/lib/Target/AMDGPU/VOP3Instructions.td
>> URL:
>> http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/AMDGPU/VOP3Instructions.td?rev=308179&r1=308178&r2=308179&view=diff
>>
>> ==============================================================================
>> --- llvm/trunk/lib/Target/AMDGPU/VOP3Instructions.td (original)
>> +++ llvm/trunk/lib/Target/AMDGPU/VOP3Instructions.td Mon Jul 17 07:23:38
>> 2017
>> @@ -12,17 +12,21 @@
>>
>> //===----------------------------------------------------------------------===//
>>
>> class getVOP3ModPat<VOPProfile P, SDPatternOperator node> {
>> + dag src0 = !if(P.HasOMod,
>> + (VOP3Mods0 P.Src0VT:$src0, i32:$src0_modifiers, i1:$clamp,
>> i32:$omod),
>> + (VOP3Mods0 P.Src0VT:$src0, i32:$src0_modifiers, i1:$clamp));
>> +
>> list<dag> ret3 = [(set P.DstVT:$vdst,
>> - (node (P.Src0VT (VOP3Mods0 P.Src0VT:$src0, i32:$src0_modifiers,
>> i1:$clamp, i32:$omod)),
>> + (node (P.Src0VT src0),
>> (P.Src1VT (VOP3Mods P.Src1VT:$src1, i32:$src1_modifiers)),
>> (P.Src2VT (VOP3Mods P.Src2VT:$src2, i32:$src2_modifiers))))];
>>
>> list<dag> ret2 = [(set P.DstVT:$vdst,
>> - (node (P.Src0VT (VOP3Mods0 P.Src0VT:$src0, i32:$src0_modifiers,
>> i1:$clamp, i32:$omod)),
>> + (node (P.Src0VT src0),
>> (P.Src1VT (VOP3Mods P.Src1VT:$src1, i32:$src1_modifiers))))];
>>
>> list<dag> ret1 = [(set P.DstVT:$vdst,
>> - (node (P.Src0VT (VOP3Mods0 P.Src0VT:$src0, i32:$src0_modifiers,
>> i1:$clamp, i32:$omod))))];
>> + (node (P.Src0VT src0)))];
>>
>> list<dag> ret = !if(!eq(P.NumSrcArgs, 3), ret3,
>> !if(!eq(P.NumSrcArgs, 2), ret2,
>>
>> Modified: llvm/trunk/lib/Target/AMDGPU/VOPCInstructions.td
>> URL:
>> http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/AMDGPU/VOPCInstructions.td?rev=308179&r1=308178&r2=308179&view=diff
>>
>> ==============================================================================
>> --- llvm/trunk/lib/Target/AMDGPU/VOPCInstructions.td (original)
>> +++ llvm/trunk/lib/Target/AMDGPU/VOPCInstructions.td Mon Jul 17 07:23:38
>> 2017
>> @@ -148,6 +148,19 @@ class VOPCInstAlias <VOP3_Pseudo ps, Ins
>> let SubtargetPredicate = AssemblerPredicate;
>> }
>>
>> +class getVOPCPat64 <PatLeaf cond, VOPProfile P> : LetDummies {
>> + list<dag> ret = !if(P.HasModifiers,
>> + [(set i1:$sdst,
>> + (setcc (P.Src0VT
>> + !if(P.HasOMod,
>> + (VOP3Mods0 P.Src0VT:$src0, i32:$src0_modifiers,
>> i1:$clamp, i32:$omod),
>> + (VOP3Mods0 P.Src0VT:$src0, i32:$src0_modifiers,
>> i1:$clamp))),
>> + (P.Src1VT (VOP3Mods P.Src1VT:$src1, i32:$src1_modifiers)),
>> + cond))],
>> + [(set i1:$sdst, (setcc P.Src0VT:$src0, P.Src1VT:$src1, cond))]);
>> +}
>> +
>> +
>> multiclass VOPC_Pseudos <string opName,
>> VOPC_Profile P,
>> PatLeaf cond = COND_NULL,
>> @@ -163,14 +176,7 @@ multiclass VOPC_Pseudos <string opName,
>> let isCommutable = 1;
>> }
>>
>> - def _e64 : VOP3_Pseudo<opName, P,
>> - !if(P.HasModifiers,
>> - [(set i1:$sdst,
>> - (setcc (P.Src0VT (VOP3Mods0 P.Src0VT:$src0,
>> i32:$src0_modifiers,
>> - i1:$clamp, i32:$omod)),
>> - (P.Src1VT (VOP3Mods P.Src1VT:$src1,
>> i32:$src1_modifiers)),
>> - cond))],
>> - [(set i1:$sdst, (setcc P.Src0VT:$src0, P.Src1VT:$src1, cond))])>,
>> + def _e64 : VOP3_Pseudo<opName, P, getVOPCPat64<cond, P>.ret>,
>> Commutable_REV<revOp#"_e64", !eq(revOp, opName)> {
>> let Defs = !if(DefExec, [EXEC], []);
>> let SchedRW = P.Schedule;
>> @@ -634,7 +640,7 @@ class FCMP_Pattern <PatLeaf cond, Instru
>> (i64 (AMDGPUsetcc (vt (VOP3Mods vt:$src0, i32:$src0_modifiers)),
>> (vt (VOP3Mods vt:$src1, i32:$src1_modifiers)), cond)),
>> (inst $src0_modifiers, $src0, $src1_modifiers, $src1,
>> - DSTCLAMP.NONE, DSTOMOD.NONE)
>> + DSTCLAMP.NONE)
>> >;
>>
>> def : FCMP_Pattern <COND_OEQ, V_CMP_EQ_F32_e64, f32>;
>>
>> Modified: llvm/trunk/lib/Target/AMDGPU/VOPInstructions.td
>> URL:
>> http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Target/AMDGPU/VOPInstructions.td?rev=308179&r1=308178&r2=308179&view=diff
>>
>> ==============================================================================
>> --- llvm/trunk/lib/Target/AMDGPU/VOPInstructions.td (original)
>> +++ llvm/trunk/lib/Target/AMDGPU/VOPInstructions.td Mon Jul 17 07:23:38
>> 2017
>> @@ -136,6 +136,8 @@ class VOP3_Real <VOP3_Pseudo ps, int Enc
>> let TSFlags = ps.TSFlags;
>> let UseNamedOperandTable = ps.UseNamedOperandTable;
>> let Uses = ps.Uses;
>> +
>> + VOPProfile Pfl = ps.Pfl;
>> }
>>
>> // XXX - Is there any reason to distingusih this from regular VOP3
>>
>> Modified:
>> llvm/trunk/test/CodeGen/AMDGPU/rename-independent-subregs-mac-operands.mir
>> URL:
>> http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/AMDGPU/rename-independent-subregs-mac-operands.mir?rev=308179&r1=308178&r2=308179&view=diff
>>
>> ==============================================================================
>> ---
>> llvm/trunk/test/CodeGen/AMDGPU/rename-independent-subregs-mac-operands.mir
>> (original)
>> +++
>> llvm/trunk/test/CodeGen/AMDGPU/rename-independent-subregs-mac-operands.mir
>> Mon Jul 17 07:23:38 2017
>> @@ -34,7 +34,7 @@ body: |
>> bb.0:
>> successors: %bb.2, %bb.1
>>
>> - %7 = V_CMP_NEQ_F32_e64 0, 0, 0, undef %3, 0, 0, implicit %exec
>> + %7 = V_CMP_NEQ_F32_e64 0, 0, 0, undef %3, 0, implicit %exec
>> %vcc = COPY killed %7
>> S_CBRANCH_VCCZ %bb.2, implicit killed %vcc
>>
>>
>> Modified: llvm/trunk/test/CodeGen/AMDGPU/sdwa-peephole-instr.mir
>> URL:
>> http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/AMDGPU/sdwa-peephole-instr.mir?rev=308179&r1=308178&r2=308179&view=diff
>>
>> ==============================================================================
>> --- llvm/trunk/test/CodeGen/AMDGPU/sdwa-peephole-instr.mir (original)
>> +++ llvm/trunk/test/CodeGen/AMDGPU/sdwa-peephole-instr.mir Mon Jul 17
>> 07:23:38 2017
>> @@ -332,7 +332,7 @@ body: |
>>
>>
>> # VI: %vcc = V_CMP_EQ_F32_sdwa 0, %{{[0-9]+}}, 0, %{{[0-9]+}}, 0, 6, 4,
>> implicit-def %vcc, implicit %exec
>> -# VI: %{{[0-9]+}} = V_CMPX_GT_F32_e64 0, 23, 0, killed %{{[0-9]+}}, 0,
>> 0, implicit-def %exec, implicit %exec
>> +# VI: %{{[0-9]+}} = V_CMPX_GT_F32_e64 0, 23, 0, killed %{{[0-9]+}}, 0,
>> implicit-def %exec, implicit %exec
>> # VI: %vcc = V_CMP_LT_I32_sdwa 0, %{{[0-9]+}}, 0, %3, 0, 6, 4,
>> implicit-def %vcc, implicit %exec
>> # VI: %{{[0-9]+}} = V_CMPX_EQ_I32_e64 23, killed %{{[0-9]+}},
>> implicit-def %exec, implicit %exec
>>
>> @@ -345,20 +345,21 @@ body: |
>>
>>
>> # VI: %vcc = V_CMP_EQ_F32_sdwa 0, %{{[0-9]+}}, 0, %{{[0-9]+}}, 1, 6, 4,
>> implicit-def %vcc, implicit %exec
>> -# VI: %vcc = V_CMPX_GT_F32_e64 0, 23, 0, killed %{{[0-9]+}}, 0, 2,
>> implicit-def %exec, implicit %exec
>> -# VI: %vcc = V_CMP_EQ_F32_e64 0, %{{[0-9]+}}, 0, killed %{{[0-9]+}}, 1,
>> 2, implicit %exec
>> +# VI: %vcc = V_CMPX_GT_F32_sdwa 0, %{{[0-9]+}}, 0, %{{[0-9]+}}, 0, 6, 4,
>> implicit-def %vcc, implicit-def %exec, implicit %exec
>> +# VI: %vcc = V_CMP_EQ_F32_sdwa 0, %{{[0-9]+}}, 0, %{{[0-9]+}}, 1, 6, 4,
>> implicit-def %vcc, implicit %exec
>> # VI: %vcc = V_CMPX_GT_F32_sdwa 1, %{{[0-9]+}}, 0, %{{[0-9]+}}, 0, 6, 4,
>> implicit-def %vcc, implicit-def %exec, implicit %exec
>> # VI: %vcc = V_CMPX_GT_F32_sdwa 0, %{{[0-9]+}}, 1, %{{[0-9]+}}, 0, 6, 4,
>> implicit-def %vcc, implicit-def %exec, implicit %exec
>> # VI: %vcc = V_CMPX_GT_F32_sdwa 1, %{{[0-9]+}}, 1, %{{[0-9]+}}, 0, 6, 4,
>> implicit-def %vcc, implicit-def %exec, implicit %exec
>> -# VI: %vcc = V_CMPX_GT_F32_e64 1, 23, 1, killed %{{[0-9]+}}, 1, 2,
>> implicit-def %exec, implicit %exec
>> +# VI: %vcc = V_CMPX_GT_F32_sdwa 1, %{{[0-9]+}}, 1, %{{[0-9]+}}, 1, 6, 4,
>> implicit-def %vcc, implicit-def %exec, implicit %exec
>>
>> -# GFX9: %vcc = V_CMP_EQ_F32_e64 0, %{{[0-9]+}}, 0, killed %{{[0-9]+}},
>> 1, 0, implicit %exec
>> -# GFX9: %vcc = V_CMPX_GT_F32_e64 0, 23, 0, killed %{{[0-9]+}}, 0, 2,
>> implicit-def %exec, implicit %exec
>> -# GFX9: %vcc = V_CMP_EQ_F32_e64 0, %{{[0-9]+}}, 0, killed %{{[0-9]+}},
>> 1, 2, implicit %exec
>> +# GFX9: %vcc = V_CMP_EQ_F32_e64 0, %{{[0-9]+}}, 0, killed %{{[0-9]+}},
>> 1, implicit %exec
>> +# GFX9: %vcc = V_CMPX_GT_F32_sdwa 0, %{{[0-9]+}}, 0, %{{[0-9]+}}, 0, 6,
>> 4, implicit-def %vcc, implicit-def %exec, implicit %exec
>> +# GFX9: %vcc = V_CMP_EQ_F32_e64 0, %{{[0-9]+}}, 0, killed %{{[0-9]+}},
>> 1, implicit %exec
>> # GFX9: %vcc = V_CMPX_GT_F32_sdwa 1, %{{[0-9]+}}, 0, %{{[0-9]+}}, 0, 6,
>> 4, implicit-def %vcc, implicit-def %exec, implicit %exec
>> # GFX9: %vcc = V_CMPX_GT_F32_sdwa 0, %{{[0-9]+}}, 1, %{{[0-9]+}}, 0, 6,
>> 4, implicit-def %vcc, implicit-def %exec, implicit %exec
>> # GFX9: %vcc = V_CMPX_GT_F32_sdwa 1, %{{[0-9]+}}, 1, %{{[0-9]+}}, 0, 6,
>> 4, implicit-def %vcc, implicit-def %exec, implicit %exec
>> -# GFX9: %vcc = V_CMPX_GT_F32_e64 1, 23, 1, killed %{{[0-9]+}}, 1, 2,
>> implicit-def %exec, implicit %exec
>> +# GFX9: %vcc = V_CMPX_GT_F32_e64 1, 23, 1, killed %{{[0-9]+}}, 1,
>> implicit-def %exec, implicit %exec
>> +
>>
>>
>> name: vopc_instructions
>> @@ -415,28 +416,28 @@ body: |
>> V_CMPX_EQ_I32_e32 123, killed %13, implicit-def %vcc, implicit-def
>> %exec, implicit %exec
>>
>> %14 = V_AND_B32_e64 %5, %3, implicit %exec
>> - %vcc = V_CMP_EQ_F32_e64 0, %6, 0, killed %14, 0, 0, implicit %exec
>> + %vcc = V_CMP_EQ_F32_e64 0, %6, 0, killed %14, 0, implicit %exec
>> %15 = V_AND_B32_e64 %5, %3, implicit %exec
>> - %18 = V_CMPX_GT_F32_e64 0, 23, 0, killed %15, 0, 0, implicit-def
>> %exec, implicit %exec
>> + %18 = V_CMPX_GT_F32_e64 0, 23, 0, killed %15, 0, implicit-def %exec,
>> implicit %exec
>> %16 = V_AND_B32_e64 %5, %3, implicit %exec
>> %vcc = V_CMP_LT_I32_e64 %6, killed %16, implicit %exec
>> %17 = V_AND_B32_e64 %5, %3, implicit %exec
>> %19 = V_CMPX_EQ_I32_e64 23, killed %17, implicit-def %exec, implicit
>> %exec
>>
>> %20 = V_AND_B32_e64 %5, %3, implicit %exec
>> - %vcc = V_CMP_EQ_F32_e64 0, %6, 0, killed %20, 1, 0, implicit %exec
>> + %vcc = V_CMP_EQ_F32_e64 0, %6, 0, killed %20, 1, implicit %exec
>> %21 = V_AND_B32_e64 %5, %3, implicit %exec
>> - %vcc = V_CMPX_GT_F32_e64 0, 23, 0, killed %21, 0, 2, implicit-def
>> %exec, implicit %exec
>> + %vcc = V_CMPX_GT_F32_e64 0, 23, 0, killed %21, 0, implicit-def
>> %exec, implicit %exec
>> %23 = V_AND_B32_e64 %5, %3, implicit %exec
>> - %vcc = V_CMP_EQ_F32_e64 0, %6, 0, killed %23, 1, 2, implicit %exec
>> + %vcc = V_CMP_EQ_F32_e64 0, %6, 0, killed %23, 1, implicit %exec
>> %24 = V_AND_B32_e64 %5, %3, implicit %exec
>> - %vcc = V_CMPX_GT_F32_e64 1, 23, 0, killed %24, 0, 0, implicit-def
>> %exec, implicit %exec
>> + %vcc = V_CMPX_GT_F32_e64 1, 23, 0, killed %24, 0, implicit-def
>> %exec, implicit %exec
>> %25 = V_AND_B32_e64 %5, %3, implicit %exec
>> - %vcc = V_CMPX_GT_F32_e64 0, 23, 1, killed %25, 0, 0, implicit-def
>> %exec, implicit %exec
>> + %vcc = V_CMPX_GT_F32_e64 0, 23, 1, killed %25, 0, implicit-def
>> %exec, implicit %exec
>> %26 = V_AND_B32_e64 %5, %3, implicit %exec
>> - %vcc = V_CMPX_GT_F32_e64 1, 23, 1, killed %26, 0, 0, implicit-def
>> %exec, implicit %exec
>> + %vcc = V_CMPX_GT_F32_e64 1, 23, 1, killed %26, 0, implicit-def
>> %exec, implicit %exec
>> %27 = V_AND_B32_e64 %5, %3, implicit %exec
>> - %vcc = V_CMPX_GT_F32_e64 1, 23, 1, killed %27, 1, 2, implicit-def
>> %exec, implicit %exec
>> + %vcc = V_CMPX_GT_F32_e64 1, 23, 1, killed %27, 1, implicit-def
>> %exec, implicit %exec
>>
>>
>> %100 = V_MOV_B32_e32 %vcc_lo, implicit %exec
>>
>> Modified: llvm/trunk/test/CodeGen/AMDGPU/sdwa-vop2-64bit.mir
>> URL:
>> http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/AMDGPU/sdwa-vop2-64bit.mir?rev=308179&r1=308178&r2=308179&view=diff
>>
>> ==============================================================================
>> --- llvm/trunk/test/CodeGen/AMDGPU/sdwa-vop2-64bit.mir (original)
>> +++ llvm/trunk/test/CodeGen/AMDGPU/sdwa-vop2-64bit.mir Mon Jul 17
>> 07:23:38 2017
>> @@ -8,7 +8,7 @@
>>
>> # GCN: %{{[0-9]+}} = V_BCNT_U32_B32_e64 %{{[0-9]+}}, killed %{{[0-9]+}},
>> implicit-def %vcc, implicit %exec
>> # GCN: %{{[0-9]+}} = V_BFM_B32_e64 %{{[0-9]+}}, killed %{{[0-9]+}},
>> implicit-def %vcc, implicit %exec
>> -# GCN: %{{[0-9]+}} = V_CVT_PKNORM_I16_F32_e64 0, %{{[0-9]+}}, 0, killed
>> %{{[0-9]+}}, 0, 0, implicit-def %vcc, implicit %exec
>> +# GCN: %{{[0-9]+}} = V_CVT_PKNORM_I16_F32_e64 0, %{{[0-9]+}}, 0, killed
>> %{{[0-9]+}}, 0, implicit-def %vcc, implicit %exec
>> # GCN: %{{[0-9]+}} = V_READLANE_B32 killed %{{[0-9]+}}, 0, implicit-def
>> %vcc, implicit %exec
>>
>> ---
>> @@ -50,7 +50,7 @@ body: |
>> %15 = V_BFM_B32_e64 %13, killed %14, implicit-def %vcc, implicit
>> %exec
>>
>> %16 = V_LSHRREV_B32_e64 16, %15, implicit %exec
>> - %17 = V_CVT_PKNORM_I16_F32_e64 0, %15, 0, killed %16, 0, 0,
>> implicit-def %vcc, implicit %exec
>> + %17 = V_CVT_PKNORM_I16_F32_e64 0, %15, 0, killed %16, 0,
>> implicit-def %vcc, implicit %exec
>>
>> %18 = V_LSHRREV_B32_e64 16, %17, implicit %exec
>> %19 = V_READLANE_B32 killed %18, 0, implicit-def %vcc, implicit %exec
>>
>> Modified: llvm/trunk/test/CodeGen/AMDGPU/vccz-corrupt-bug-workaround.mir
>> URL:
>> http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/AMDGPU/vccz-corrupt-bug-workaround.mir?rev=308179&r1=308178&r2=308179&view=diff
>>
>> ==============================================================================
>> --- llvm/trunk/test/CodeGen/AMDGPU/vccz-corrupt-bug-workaround.mir
>> (original)
>> +++ llvm/trunk/test/CodeGen/AMDGPU/vccz-corrupt-bug-workaround.mir Mon
>> Jul 17 07:23:38 2017
>> @@ -81,7 +81,7 @@ body: |
>> %sgpr0_sgpr1 = S_LOAD_DWORDX2_IMM killed %sgpr0_sgpr1, 11, 0 ::
>> (non-temporal dereferenceable invariant load 8 from `i64 addrspace(2)*
>> undef`)
>> %sgpr7 = S_MOV_B32 61440
>> %sgpr6 = S_MOV_B32 -1
>> - %vcc = V_CMP_EQ_F32_e64 0, 0, 0, %sgpr2, 0, 0, implicit %exec
>> + %vcc = V_CMP_EQ_F32_e64 0, 0, 0, %sgpr2, 0, implicit %exec
>> S_CBRANCH_VCCZ %bb.1.else, implicit killed %vcc
>>
>> bb.2.if:
>>
>> Modified: llvm/trunk/test/MC/AMDGPU/vop3-errs.s
>> URL:
>> http://llvm.org/viewvc/llvm-project/llvm/trunk/test/MC/AMDGPU/vop3-errs.s?rev=308179&r1=308178&r2=308179&view=diff
>>
>> ==============================================================================
>> --- llvm/trunk/test/MC/AMDGPU/vop3-errs.s (original)
>> +++ llvm/trunk/test/MC/AMDGPU/vop3-errs.s Mon Jul 17 07:23:38 2017
>> @@ -1,35 +1,47 @@
>> -// RUN: not llvm-mc -arch=amdgcn -show-encoding %s 2>&1 | FileCheck %s
>> -// RUN: not llvm-mc -arch=amdgcn -mcpu=SI -show-encoding %s 2>&1 |
>> FileCheck %s
>> +// RUN: not llvm-mc -arch=amdgcn -show-encoding %s 2>&1 | FileCheck %s
>> --check-prefix=GFX67 --check-prefix=GCN
>> +// RUN: not llvm-mc -arch=amdgcn -mcpu=SI -show-encoding %s 2>&1 |
>> FileCheck %s --check-prefix=GFX67 --check-prefix=GCN
>> +// RUN: not llvm-mc -arch=amdgcn -mcpu=fiji -show-encoding %s 2>&1 |
>> FileCheck %s --check-prefix=GFX89 --check-prefix=GCN
>> +// RUN: not llvm-mc -arch=amdgcn -mcpu=gfx900 -show-encoding %s 2>&1 |
>> FileCheck %s --check-prefix=GFX89 --check-prefix=GCN
>>
>> v_add_f32_e64 v0, v1
>> -// CHECK: error: too few operands for instruction
>> +// GCN: error: too few operands for instruction
>>
>> v_div_scale_f32 v24, vcc, v22, 1.1, v22
>> -// CHECK: error: invalid operand for instruction
>> +// GCN: error: invalid operand for instruction
>>
>> v_mqsad_u32_u8 v[0:3], s[2:3], v4, v[0:3]
>> -// CHECK: error: instruction not supported on this GPU
>> +// GFX67: error: instruction not supported on this GPU
>> +// GFX89: error: destination must be different than all sources
>>
>> v_mqsad_pk_u16_u8 v[0:1], v[1:2], v9, v[4:5]
>> -// CHECK: error: destination must be different than all sources
>> +// GCN: error: destination must be different than all sources
>>
>> v_mqsad_pk_u16_u8 v[1:2], v[1:2], v9, v[4:5]
>> -// CHECK: error: destination must be different than all sources
>> +// GCN: error: destination must be different than all sources
>>
>> v_mqsad_pk_u16_u8 v[2:3], v[1:2], v9, v[4:5]
>> -// CHECK: error: destination must be different than all sources
>> +// GCN: error: destination must be different than all sources
>>
>> v_mqsad_pk_u16_u8 v[3:4], v[0:1], v9, v[4:5]
>> -// CHECK: error: destination must be different than all sources
>> +// GCN: error: destination must be different than all sources
>>
>> v_mqsad_pk_u16_u8 v[4:5], v[1:2], v9, v[4:5]
>> -// CHECK: error: destination must be different than all sources
>> +// GCN: error: destination must be different than all sources
>>
>> v_mqsad_pk_u16_u8 v[5:6], v[1:2], v9, v[4:5]
>> -// CHECK: error: destination must be different than all sources
>> +// GCN: error: destination must be different than all sources
>>
>> v_mqsad_pk_u16_u8 v[8:9], v[1:2], v9, v[4:5]
>> -// CHECK: error: destination must be different than all sources
>> +// GCN: error: destination must be different than all sources
>>
>> v_mqsad_pk_u16_u8 v[9:10], v[1:2], v9, v[4:5]
>> -// CHECK: error: destination must be different than all sources
>> +// GCN: error: destination must be different than all sources
>> +
>> +v_cmp_eq_f32_e64 vcc, v0, v1 mul:2
>> +// GCN: error: invalid operand for instruction
>> +
>> +v_cmp_le_f64_e64 vcc, v0, v1 mul:4
>> +// GCN: error: invalid operand for instruction
>> +
>> +v_cvt_u32_f32_e64 v0, v1 div:2
>> +// GCN: error: invalid operand for instruction
>> \ No newline at end of file
>>
>>
>> _______________________________________________
>> llvm-commits mailing list
>> llvm-commits at lists.llvm.org
>> http://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-commits
>>
> _______________________________________________
> llvm-commits mailing list
> llvm-commits at lists.llvm.org
> http://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-commits
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20170718/4ed82919/attachment.html>
More information about the llvm-commits
mailing list