diff --git a/llvm/lib/Target/AMDGPU/AMDGPULegalizerInfo.cpp b/llvm/lib/Target/AMDGPU/AMDGPULegalizerInfo.cpp index e65e56dc7e6f..49e8b36b41b4 100644 --- a/llvm/lib/Target/AMDGPU/AMDGPULegalizerInfo.cpp +++ b/llvm/lib/Target/AMDGPU/AMDGPULegalizerInfo.cpp @@ -82,6 +82,21 @@ static LegalityPredicate numElementsNotEven(unsigned TypeIdx) { }; } +// Any combination of 32 or 64-bit elements up to 512 bits, and multiples of +// v2s16. +static LegalityPredicate isRegisterType(unsigned TypeIdx) { + return [=](const LegalityQuery &Query) { + const LLT Ty = Query.Types[TypeIdx]; + if (Ty.isVector()) { + const int EltSize = Ty.getElementType().getSizeInBits(); + return EltSize == 32 || EltSize == 64 || + (EltSize == 16 && Ty.getNumElements() % 2 == 0); + } + + return Ty.getSizeInBits() % 32 == 0 && Ty.getSizeInBits() <= 512; + }; +} + AMDGPULegalizerInfo::AMDGPULegalizerInfo(const GCNSubtarget &ST_, const GCNTargetMachine &TM) : ST(ST_) { @@ -102,7 +117,6 @@ AMDGPULegalizerInfo::AMDGPULegalizerInfo(const GCNSubtarget &ST_, const LLT V2S16 = LLT::vector(2, 16); const LLT V4S16 = LLT::vector(4, 16); - const LLT V8S16 = LLT::vector(8, 16); const LLT V2S32 = LLT::vector(2, 32); const LLT V3S32 = LLT::vector(3, 32); @@ -647,19 +661,8 @@ AMDGPULegalizerInfo::AMDGPULegalizerInfo(const GCNSubtarget &ST_, Query.Types[0].getScalarSizeInBits() == 64; }); - // TODO: Support any combination of s16, s32, s64, pointer vectors. getActionDefinitionsBuilder(G_CONCAT_VECTORS) - .legalFor({{V4S32, V2S32}, - {V8S32, V2S32}, - {V8S32, V4S32}, - {V4S64, V2S64}, - {V4S16, V2S16}, - {V8S16, V2S16}, - {V8S16, V4S16}, - {LLT::vector(4, LocalPtr), LLT::vector(2, LocalPtr)}, - {LLT::vector(4, PrivatePtr), LLT::vector(2, PrivatePtr)}}) - // FIXME: Should restrict maximum size, but there seems to be a missing predicate. - .legalIf(typeInSet(1, {V2S32, V4S32, V8S32,V2S16, V4S16, V8S16, LLT::vector(16, 16), V2S64})); + .legalIf(isRegisterType(0)); // Merge/Unmerge for (unsigned Op : {G_MERGE_VALUES, G_UNMERGE_VALUES}) { diff --git a/llvm/test/CodeGen/AMDGPU/GlobalISel/inst-select-concat-vectors.mir b/llvm/test/CodeGen/AMDGPU/GlobalISel/inst-select-concat-vectors.mir index 4b3b206a3afb..123123a78ab1 100644 --- a/llvm/test/CodeGen/AMDGPU/GlobalISel/inst-select-concat-vectors.mir +++ b/llvm/test/CodeGen/AMDGPU/GlobalISel/inst-select-concat-vectors.mir @@ -639,10 +639,10 @@ body: | liveins: $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7, $sgpr8_sgpr9_sgpr10_sgpr11_sgpr12_sgpr13_sgpr14_sgpr15 ; GCN-LABEL: name: test_concat_vectors_s_v8s64_s_v4s64_s_v4s64 - ; GCN: [[COPY:%[0-9]+]]:sgpr(<4 x s64>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7 - ; GCN: [[COPY1:%[0-9]+]]:sgpr(<4 x s64>) = COPY $sgpr8_sgpr9_sgpr10_sgpr11_sgpr12_sgpr13_sgpr14_sgpr15 - ; GCN: [[CONCAT_VECTORS:%[0-9]+]]:sgpr(<8 x s64>) = G_CONCAT_VECTORS [[COPY]](<4 x s64>), [[COPY1]](<4 x s64>) - ; GCN: $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9_sgpr10_sgpr11_sgpr12_sgpr13_sgpr14_sgpr15 = COPY [[CONCAT_VECTORS]](<8 x s64>) + ; GCN: [[COPY:%[0-9]+]]:sreg_256 = COPY $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7 + ; GCN: [[COPY1:%[0-9]+]]:sreg_256 = COPY $sgpr8_sgpr9_sgpr10_sgpr11_sgpr12_sgpr13_sgpr14_sgpr15 + ; GCN: [[REG_SEQUENCE:%[0-9]+]]:sreg_512 = REG_SEQUENCE [[COPY]], %subreg.sub0_sub1_sub2_sub3_sub4_sub5_sub6_sub7, [[COPY1]], %subreg.sub8_sub9_sub10_sub11_sub12_sub13_sub14_sub15 + ; GCN: $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7_sgpr8_sgpr9_sgpr10_sgpr11_sgpr12_sgpr13_sgpr14_sgpr15 = COPY [[REG_SEQUENCE]] %0:sgpr(<4 x s64>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7, %1:sgpr(<4 x s64>) = COPY $sgpr8_sgpr9_sgpr10_sgpr11_sgpr12_sgpr13_sgpr14_sgpr15 %4:sgpr(<8 x s64>) = G_CONCAT_VECTORS %0, %1 @@ -683,10 +683,10 @@ body: | liveins: $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr4_sgpr5_sgpr6_sgpr7 ; GCN-LABEL: name: test_concat_vectors_s_v4p1_s_v2p1_s_v2p1 - ; GCN: [[COPY:%[0-9]+]]:sgpr(<2 x p1>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3 - ; GCN: [[COPY1:%[0-9]+]]:sgpr(<2 x p1>) = COPY $sgpr4_sgpr5_sgpr6_sgpr7 - ; GCN: [[CONCAT_VECTORS:%[0-9]+]]:sgpr(<4 x p1>) = G_CONCAT_VECTORS [[COPY]](<2 x p1>), [[COPY1]](<2 x p1>) - ; GCN: $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7 = COPY [[CONCAT_VECTORS]](<4 x p1>) + ; GCN: [[COPY:%[0-9]+]]:sreg_128 = COPY $sgpr0_sgpr1_sgpr2_sgpr3 + ; GCN: [[COPY1:%[0-9]+]]:sreg_128 = COPY $sgpr4_sgpr5_sgpr6_sgpr7 + ; GCN: [[REG_SEQUENCE:%[0-9]+]]:sreg_256 = REG_SEQUENCE [[COPY]], %subreg.sub0_sub1_sub2_sub3, [[COPY1]], %subreg.sub4_sub5_sub6_sub7 + ; GCN: $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7 = COPY [[REG_SEQUENCE]] %0:sgpr(<2 x p1>) = COPY $sgpr0_sgpr1_sgpr2_sgpr3 %1:sgpr(<2 x p1>) = COPY $sgpr4_sgpr5_sgpr6_sgpr7 %3:sgpr(<4 x p1>) = G_CONCAT_VECTORS %0, %1 @@ -723,12 +723,12 @@ body: | liveins: $sgpr0_sgpr1, $sgpr2_sgpr3, $sgpr4_sgpr5, $sgpr6_sgpr7 ; GCN-LABEL: name: test_concat_vectors_s_v8p3_s_v2p3_s_v2p3_v2p3_s_v2p3 - ; GCN: [[COPY:%[0-9]+]]:sgpr(<2 x p3>) = COPY $sgpr0_sgpr1 - ; GCN: [[COPY1:%[0-9]+]]:sgpr(<2 x p3>) = COPY $sgpr2_sgpr3 - ; GCN: [[COPY2:%[0-9]+]]:sgpr(<2 x p3>) = COPY $sgpr4_sgpr5 - ; GCN: [[COPY3:%[0-9]+]]:sgpr(<2 x p3>) = COPY $sgpr6_sgpr7 - ; GCN: [[CONCAT_VECTORS:%[0-9]+]]:sgpr(<8 x p3>) = G_CONCAT_VECTORS [[COPY]](<2 x p3>), [[COPY1]](<2 x p3>), [[COPY2]](<2 x p3>), [[COPY3]](<2 x p3>) - ; GCN: $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7 = COPY [[CONCAT_VECTORS]](<8 x p3>) + ; GCN: [[COPY:%[0-9]+]]:sreg_64_xexec = COPY $sgpr0_sgpr1 + ; GCN: [[COPY1:%[0-9]+]]:sreg_64_xexec = COPY $sgpr2_sgpr3 + ; GCN: [[COPY2:%[0-9]+]]:sreg_64_xexec = COPY $sgpr4_sgpr5 + ; GCN: [[COPY3:%[0-9]+]]:sreg_64_xexec = COPY $sgpr6_sgpr7 + ; GCN: [[REG_SEQUENCE:%[0-9]+]]:sreg_256 = REG_SEQUENCE [[COPY]], %subreg.sub0_sub1, [[COPY1]], %subreg.sub2_sub3, [[COPY2]], %subreg.sub4_sub5, [[COPY3]], %subreg.sub6_sub7 + ; GCN: $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7 = COPY [[REG_SEQUENCE]] %0:sgpr(<2 x p3>) = COPY $sgpr0_sgpr1 %1:sgpr(<2 x p3>) = COPY $sgpr2_sgpr3 %2:sgpr(<2 x p3>) = COPY $sgpr4_sgpr5 diff --git a/llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-concat-vectors.mir b/llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-concat-vectors.mir index c3e1bca6003a..f5c924bb6a96 100644 --- a/llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-concat-vectors.mir +++ b/llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-concat-vectors.mir @@ -127,3 +127,88 @@ body: | %2:_(<4 x s64>) = G_CONCAT_VECTORS %0, %1 $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7 = COPY %2 ... + +--- +name: concat_vectors_v2p1_v2p1 + +body: | + bb.0: + liveins: $vgpr0_vgpr1_vgpr2_vgpr3, $vgpr4_vgpr5_vgpr6_vgpr7 + ; CHECK-LABEL: name: concat_vectors_v2p1_v2p1 + ; CHECK: [[COPY:%[0-9]+]]:_(<2 x p1>) = COPY $vgpr0_vgpr1_vgpr2_vgpr3 + ; CHECK: [[COPY1:%[0-9]+]]:_(<2 x p1>) = COPY $vgpr4_vgpr5_vgpr6_vgpr7 + ; CHECK: [[CONCAT_VECTORS:%[0-9]+]]:_(<4 x p1>) = G_CONCAT_VECTORS [[COPY]](<2 x p1>), [[COPY1]](<2 x p1>) + ; CHECK: $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7 = COPY [[CONCAT_VECTORS]](<4 x p1>) + %0:_(<2 x p1>) = COPY $vgpr0_vgpr1_vgpr2_vgpr3 + %1:_(<2 x p1>) = COPY $vgpr4_vgpr5_vgpr6_vgpr7 + %2:_(<4 x p1>) = G_CONCAT_VECTORS %0, %1 + $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7 = COPY %2 +... + +--- +name: concat_vectors_v2p0_v2p0 + +body: | + bb.0: + liveins: $vgpr0_vgpr1_vgpr2_vgpr3, $vgpr4_vgpr5_vgpr6_vgpr7 + ; CHECK-LABEL: name: concat_vectors_v2p0_v2p0 + ; CHECK: [[COPY:%[0-9]+]]:_(<2 x p0>) = COPY $vgpr0_vgpr1_vgpr2_vgpr3 + ; CHECK: [[COPY1:%[0-9]+]]:_(<2 x p0>) = COPY $vgpr4_vgpr5_vgpr6_vgpr7 + ; CHECK: [[CONCAT_VECTORS:%[0-9]+]]:_(<4 x p0>) = G_CONCAT_VECTORS [[COPY]](<2 x p0>), [[COPY1]](<2 x p0>) + ; CHECK: $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7 = COPY [[CONCAT_VECTORS]](<4 x p0>) + %0:_(<2 x p0>) = COPY $vgpr0_vgpr1_vgpr2_vgpr3 + %1:_(<2 x p0>) = COPY $vgpr4_vgpr5_vgpr6_vgpr7 + %2:_(<4 x p0>) = G_CONCAT_VECTORS %0, %1 + $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7 = COPY %2 +... + +--- +name: concat_vectors_v2p3_v2p3 + +body: | + bb.0: + liveins: $vgpr0_vgpr1, $vgpr2_vgpr3 + ; CHECK-LABEL: name: concat_vectors_v2p3_v2p3 + ; CHECK: [[COPY:%[0-9]+]]:_(<2 x p3>) = COPY $vgpr0_vgpr1 + ; CHECK: [[COPY1:%[0-9]+]]:_(<2 x p3>) = COPY $vgpr2_vgpr3 + ; CHECK: [[CONCAT_VECTORS:%[0-9]+]]:_(<4 x p3>) = G_CONCAT_VECTORS [[COPY]](<2 x p3>), [[COPY1]](<2 x p3>) + ; CHECK: $vgpr0_vgpr1_vgpr2_vgpr3 = COPY [[CONCAT_VECTORS]](<4 x p3>) + %0:_(<2 x p3>) = COPY $vgpr0_vgpr1 + %1:_(<2 x p3>) = COPY $vgpr2_vgpr3 + %2:_(<4 x p3>) = G_CONCAT_VECTORS %0, %1 + $vgpr0_vgpr1_vgpr2_vgpr3 = COPY %2 +... + +--- +name: concat_vectors_v2p5_v2p5 + +body: | + bb.0: + liveins: $vgpr0_vgpr1, $vgpr2_vgpr3 + ; CHECK-LABEL: name: concat_vectors_v2p5_v2p5 + ; CHECK: [[COPY:%[0-9]+]]:_(<2 x p5>) = COPY $vgpr0_vgpr1 + ; CHECK: [[COPY1:%[0-9]+]]:_(<2 x p5>) = COPY $vgpr2_vgpr3 + ; CHECK: [[CONCAT_VECTORS:%[0-9]+]]:_(<4 x p5>) = G_CONCAT_VECTORS [[COPY]](<2 x p5>), [[COPY1]](<2 x p5>) + ; CHECK: $vgpr0_vgpr1_vgpr2_vgpr3 = COPY [[CONCAT_VECTORS]](<4 x p5>) + %0:_(<2 x p5>) = COPY $vgpr0_vgpr1 + %1:_(<2 x p5>) = COPY $vgpr2_vgpr3 + %2:_(<4 x p5>) = G_CONCAT_VECTORS %0, %1 + $vgpr0_vgpr1_vgpr2_vgpr3 = COPY %2 +... + +--- +name: concat_vectors_v2p999_v2p999 + +body: | + bb.0: + liveins: $vgpr0_vgpr1_vgpr2_vgpr3, $vgpr4_vgpr5_vgpr6_vgpr7 + ; CHECK-LABEL: name: concat_vectors_v2p999_v2p999 + ; CHECK: [[COPY:%[0-9]+]]:_(<2 x p999>) = COPY $vgpr0_vgpr1_vgpr2_vgpr3 + ; CHECK: [[COPY1:%[0-9]+]]:_(<2 x p999>) = COPY $vgpr4_vgpr5_vgpr6_vgpr7 + ; CHECK: [[CONCAT_VECTORS:%[0-9]+]]:_(<4 x p999>) = G_CONCAT_VECTORS [[COPY]](<2 x p999>), [[COPY1]](<2 x p999>) + ; CHECK: $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7 = COPY [[CONCAT_VECTORS]](<4 x p999>) + %0:_(<2 x p999>) = COPY $vgpr0_vgpr1_vgpr2_vgpr3 + %1:_(<2 x p999>) = COPY $vgpr4_vgpr5_vgpr6_vgpr7 + %2:_(<4 x p999>) = G_CONCAT_VECTORS %0, %1 + $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7 = COPY %2 +...