Index: lib/CodeGen/SelectionDAG/LegalizeIntegerTypes.cpp =================================================================== --- lib/CodeGen/SelectionDAG/LegalizeIntegerTypes.cpp +++ lib/CodeGen/SelectionDAG/LegalizeIntegerTypes.cpp @@ -1371,6 +1371,11 @@ case ISD::OR: case ISD::XOR: ExpandIntRes_Logical(N, Lo, Hi); break; + case ISD::UMAX: + case ISD::SMAX: + case ISD::UMIN: + case ISD::SMIN: ExpandIntRes_MINMAX(N, Lo, Hi); break; + case ISD::ADD: case ISD::SUB: ExpandIntRes_ADDSUB(N, Lo, Hi); break; @@ -1663,6 +1668,50 @@ } } +static std::pair getExpandedMinMaxOps(int Op) { + + switch (Op) { + default: llvm_unreachable("invalid min/max opcode"); + case ISD::SMAX: return std::make_pair(ISD::SETGT, ISD::UMAX); + case ISD::UMAX: return std::make_pair(ISD::SETUGT, ISD::UMAX); + case ISD::SMIN: return std::make_pair(ISD::SETLT, ISD::UMIN); + case ISD::UMIN: return std::make_pair(ISD::SETULT, ISD::UMIN); + } +} + +void DAGTypeLegalizer::ExpandIntRes_MINMAX(SDNode *N, + SDValue &Lo, SDValue &Hi) { + SDLoc DL(N); + ISD::NodeType LoOpc; + ISD::CondCode CondC; + std::tie(CondC, LoOpc) = getExpandedMinMaxOps(N->getOpcode()); + + // Expand the subcomponents. + SDValue LHSL, LHSH, RHSL, RHSH; + GetExpandedInteger(N->getOperand(0), LHSL, LHSH); + GetExpandedInteger(N->getOperand(1), RHSL, RHSH); + + // Value types + EVT NVT = LHSL.getValueType(); + EVT CCT = getSetCCResultType(NVT); + + // Hi part is always the same op + Hi = DAG.getNode(N->getOpcode(), DL, {NVT, NVT}, {LHSH, RHSH}); + + // We need to know whether to select Lo part that corresponds to 'winning' + // Hi part or if Hi parts are equal. + SDValue IsHiLeft = DAG.getSetCC(DL, CCT, LHSH, RHSH, CondC); + SDValue IsHiEq = DAG.getSetCC(DL, CCT, LHSH, RHSH, ISD::SETEQ); + + // Lo part corresponding to the 'winning' Hi part + SDValue LoCmp = DAG.getSelect(DL, NVT, IsHiLeft, LHSL, RHSL); + + // Recursed Lo part if Hi parts are equal, this uses unsigned version + SDValue LoMinMax = DAG.getNode(LoOpc, DL, {NVT, NVT}, {LHSL, RHSL}); + + Lo = DAG.getSelect(DL, NVT, IsHiEq, LoMinMax, LoCmp); +} + void DAGTypeLegalizer::ExpandIntRes_ADDSUB(SDNode *N, SDValue &Lo, SDValue &Hi) { SDLoc dl(N); Index: lib/CodeGen/SelectionDAG/LegalizeTypes.h =================================================================== --- lib/CodeGen/SelectionDAG/LegalizeTypes.h +++ lib/CodeGen/SelectionDAG/LegalizeTypes.h @@ -361,6 +361,8 @@ void ExpandIntRes_UREM (SDNode *N, SDValue &Lo, SDValue &Hi); void ExpandIntRes_Shift (SDNode *N, SDValue &Lo, SDValue &Hi); + void ExpandIntRes_MINMAX (SDNode *N, SDValue &Lo, SDValue &Hi); + void ExpandIntRes_SADDSUBO (SDNode *N, SDValue &Lo, SDValue &Hi); void ExpandIntRes_UADDSUBO (SDNode *N, SDValue &Lo, SDValue &Hi); void ExpandIntRes_XMULO (SDNode *N, SDValue &Lo, SDValue &Hi); Index: test/CodeGen/AMDGPU/max.ll =================================================================== --- test/CodeGen/AMDGPU/max.ll +++ test/CodeGen/AMDGPU/max.ll @@ -1,19 +1,17 @@ ; RUN: llc -march=amdgcn < %s | FileCheck -check-prefix=SI -check-prefix=FUNC %s +; RUN: llc -march=r600 -mcpu=cypress < %s | FileCheck -check-prefix=EG -check-prefix=FUNC %s -declare i32 @llvm.amdgcn.workitem.id.x() nounwind readnone ; FUNC-LABEL: {{^}}v_test_imax_sge_i32: ; SI: v_max_i32_e32 + +; EG: MAX_INT define void @v_test_imax_sge_i32(i32 addrspace(1)* %out, i32 addrspace(1)* %aptr, i32 addrspace(1)* %bptr) nounwind { - %tid = call i32 @llvm.amdgcn.workitem.id.x() nounwind readnone - %gep0 = getelementptr i32, i32 addrspace(1)* %aptr, i32 %tid - %gep1 = getelementptr i32, i32 addrspace(1)* %bptr, i32 %tid - %outgep = getelementptr i32, i32 addrspace(1)* %out, i32 %tid - %a = load i32, i32 addrspace(1)* %gep0, align 4 - %b = load i32, i32 addrspace(1)* %gep1, align 4 + %a = load i32, i32 addrspace(1)* %aptr, align 4 + %b = load i32, i32 addrspace(1)* %bptr, align 4 %cmp = icmp sge i32 %a, %b %val = select i1 %cmp, i32 %a, i32 %b - store i32 %val, i32 addrspace(1)* %outgep, align 4 + store i32 %val, i32 addrspace(1)* %out, align 4 ret void } @@ -22,21 +20,25 @@ ; SI: v_max_i32_e32 ; SI: v_max_i32_e32 ; SI: v_max_i32_e32 + +; These could be merged into one +; EG: MAX_INT +; EG: MAX_INT +; EG: MAX_INT +; EG: MAX_INT define void @v_test_imax_sge_v4i32(<4 x i32> addrspace(1)* %out, <4 x i32> addrspace(1)* %aptr, <4 x i32> addrspace(1)* %bptr) nounwind { - %tid = call i32 @llvm.amdgcn.workitem.id.x() nounwind readnone - %gep0 = getelementptr <4 x i32>, <4 x i32> addrspace(1)* %aptr, i32 %tid - %gep1 = getelementptr <4 x i32>, <4 x i32> addrspace(1)* %bptr, i32 %tid - %outgep = getelementptr <4 x i32>, <4 x i32> addrspace(1)* %out, i32 %tid - %a = load <4 x i32>, <4 x i32> addrspace(1)* %gep0, align 4 - %b = load <4 x i32>, <4 x i32> addrspace(1)* %gep1, align 4 + %a = load <4 x i32>, <4 x i32> addrspace(1)* %aptr, align 4 + %b = load <4 x i32>, <4 x i32> addrspace(1)* %bptr, align 4 %cmp = icmp sge <4 x i32> %a, %b %val = select <4 x i1> %cmp, <4 x i32> %a, <4 x i32> %b - store <4 x i32> %val, <4 x i32> addrspace(1)* %outgep, align 4 + store <4 x i32> %val, <4 x i32> addrspace(1)* %out, align 4 ret void } ; FUNC-LABEL: @s_test_imax_sge_i32 ; SI: s_max_i32 + +; EG: MAX_INT define void @s_test_imax_sge_i32(i32 addrspace(1)* %out, i32 %a, i32 %b) nounwind { %cmp = icmp sge i32 %a, %b %val = select i1 %cmp, i32 %a, i32 %b @@ -46,6 +48,8 @@ ; FUNC-LABEL: {{^}}s_test_imax_sge_imm_i32: ; SI: s_max_i32 {{s[0-9]+}}, {{s[0-9]+}}, 9 + +; EG: MAX_INT {{.*}}literal.{{[xyzw]}} define void @s_test_imax_sge_imm_i32(i32 addrspace(1)* %out, i32 %a) nounwind { %cmp = icmp sge i32 %a, 9 %val = select i1 %cmp, i32 %a, i32 9 @@ -57,21 +61,21 @@ ; SI: buffer_load_sbyte ; SI: buffer_load_sbyte ; SI: v_max_i32_e32 + +; EG: MAX_INT define void @v_test_imax_sge_i8(i8 addrspace(1)* %out, i8 addrspace(1)* %aptr, i8 addrspace(1)* %bptr) nounwind { - %tid = call i32 @llvm.amdgcn.workitem.id.x() nounwind readnone - %gep0 = getelementptr i8, i8 addrspace(1)* %aptr, i32 %tid - %gep1 = getelementptr i8, i8 addrspace(1)* %bptr, i32 %tid - %outgep = getelementptr i8, i8 addrspace(1)* %out, i32 %tid - %a = load i8, i8 addrspace(1)* %gep0, align 1 - %b = load i8, i8 addrspace(1)* %gep1, align 1 + %a = load i8, i8 addrspace(1)* %aptr, align 1 + %b = load i8, i8 addrspace(1)* %bptr, align 1 %cmp = icmp sge i8 %a, %b %val = select i1 %cmp, i8 %a, i8 %b - store i8 %val, i8 addrspace(1)* %outgep, align 1 + store i8 %val, i8 addrspace(1)* %out, align 1 ret void } ; FUNC-LABEL: {{^}}s_test_imax_sgt_imm_i32: ; SI: s_max_i32 {{s[0-9]+}}, {{s[0-9]+}}, 9 + +; EG: MAX_INT {{.*}}literal.{{[xyzw]}} define void @s_test_imax_sgt_imm_i32(i32 addrspace(1)* %out, i32 %a) nounwind { %cmp = icmp sgt i32 %a, 9 %val = select i1 %cmp, i32 %a, i32 9 @@ -82,29 +86,33 @@ ; FUNC-LABEL: {{^}}s_test_imax_sgt_imm_v2i32: ; SI: s_max_i32 {{s[0-9]+}}, {{s[0-9]+}}, 9 ; SI: s_max_i32 {{s[0-9]+}}, {{s[0-9]+}}, 9 + +; EG: MAX_INT {{.*}}literal.{{[xyzw]}} +; EG: MAX_INT {{.*}}literal.{{[xyzw]}} define void @s_test_imax_sgt_imm_v2i32(<2 x i32> addrspace(1)* %out, <2 x i32> %a) nounwind { %cmp = icmp sgt <2 x i32> %a, %val = select <2 x i1> %cmp, <2 x i32> %a, <2 x i32> store <2 x i32> %val, <2 x i32> addrspace(1)* %out, align 4 ret void } + ; FUNC-LABEL: @v_test_imax_sgt_i32 ; SI: v_max_i32_e32 + +; EG: MAX_INT define void @v_test_imax_sgt_i32(i32 addrspace(1)* %out, i32 addrspace(1)* %aptr, i32 addrspace(1)* %bptr) nounwind { - %tid = call i32 @llvm.amdgcn.workitem.id.x() nounwind readnone - %gep0 = getelementptr i32, i32 addrspace(1)* %aptr, i32 %tid - %gep1 = getelementptr i32, i32 addrspace(1)* %bptr, i32 %tid - %outgep = getelementptr i32, i32 addrspace(1)* %out, i32 %tid - %a = load i32, i32 addrspace(1)* %gep0, align 4 - %b = load i32, i32 addrspace(1)* %gep1, align 4 + %a = load i32, i32 addrspace(1)* %aptr, align 4 + %b = load i32, i32 addrspace(1)* %bptr, align 4 %cmp = icmp sgt i32 %a, %b %val = select i1 %cmp, i32 %a, i32 %b - store i32 %val, i32 addrspace(1)* %outgep, align 4 + store i32 %val, i32 addrspace(1)* %out, align 4 ret void } ; FUNC-LABEL: @s_test_imax_sgt_i32 ; SI: s_max_i32 + +; EG: MAX_INT define void @s_test_imax_sgt_i32(i32 addrspace(1)* %out, i32 %a, i32 %b) nounwind { %cmp = icmp sgt i32 %a, %b %val = select i1 %cmp, i32 %a, i32 %b @@ -114,21 +122,21 @@ ; FUNC-LABEL: @v_test_umax_uge_i32 ; SI: v_max_u32_e32 + +; EG: MAX_UINT define void @v_test_umax_uge_i32(i32 addrspace(1)* %out, i32 addrspace(1)* %aptr, i32 addrspace(1)* %bptr) nounwind { - %tid = call i32 @llvm.amdgcn.workitem.id.x() nounwind readnone - %gep0 = getelementptr i32, i32 addrspace(1)* %aptr, i32 %tid - %gep1 = getelementptr i32, i32 addrspace(1)* %bptr, i32 %tid - %outgep = getelementptr i32, i32 addrspace(1)* %out, i32 %tid - %a = load i32, i32 addrspace(1)* %gep0, align 4 - %b = load i32, i32 addrspace(1)* %gep1, align 4 + %a = load i32, i32 addrspace(1)* %aptr, align 4 + %b = load i32, i32 addrspace(1)* %bptr, align 4 %cmp = icmp uge i32 %a, %b %val = select i1 %cmp, i32 %a, i32 %b - store i32 %val, i32 addrspace(1)* %outgep, align 4 + store i32 %val, i32 addrspace(1)* %out, align 4 ret void } ; FUNC-LABEL: @s_test_umax_uge_i32 ; SI: s_max_u32 + +; EG: MAX_UINT define void @s_test_umax_uge_i32(i32 addrspace(1)* %out, i32 %a, i32 %b) nounwind { %cmp = icmp uge i32 %a, %b %val = select i1 %cmp, i32 %a, i32 %b @@ -142,6 +150,11 @@ ; SI: s_max_u32 ; SI-NOT: s_max_u32 ; SI: s_endpgm + +; EG: MAX_UINT +; EG: MAX_UINT +; EG: MAX_UINT +; EG-NOT: MAX_UINT define void @s_test_umax_uge_v3i32(<3 x i32> addrspace(1)* %out, <3 x i32> %a, <3 x i32> %b) nounwind { %cmp = icmp uge <3 x i32> %a, %b %val = select <3 x i1> %cmp, <3 x i32> %a, <3 x i32> %b @@ -153,36 +166,34 @@ ; SI: buffer_load_ubyte ; SI: buffer_load_ubyte ; SI: v_max_u32_e32 + +; EG: MAX_UINT define void @v_test_umax_uge_i8(i8 addrspace(1)* %out, i8 addrspace(1)* %aptr, i8 addrspace(1)* %bptr) nounwind { - %tid = call i32 @llvm.amdgcn.workitem.id.x() nounwind readnone - %gep0 = getelementptr i8, i8 addrspace(1)* %aptr, i32 %tid - %gep1 = getelementptr i8, i8 addrspace(1)* %bptr, i32 %tid - %outgep = getelementptr i8, i8 addrspace(1)* %out, i32 %tid - %a = load i8, i8 addrspace(1)* %gep0, align 1 - %b = load i8, i8 addrspace(1)* %gep1, align 1 + %a = load i8, i8 addrspace(1)* %aptr, align 1 + %b = load i8, i8 addrspace(1)* %bptr, align 1 %cmp = icmp uge i8 %a, %b %val = select i1 %cmp, i8 %a, i8 %b - store i8 %val, i8 addrspace(1)* %outgep, align 1 + store i8 %val, i8 addrspace(1)* %out, align 1 ret void } ; FUNC-LABEL: @v_test_umax_ugt_i32 ; SI: v_max_u32_e32 + +; EG: MAX_UINT define void @v_test_umax_ugt_i32(i32 addrspace(1)* %out, i32 addrspace(1)* %aptr, i32 addrspace(1)* %bptr) nounwind { - %tid = call i32 @llvm.amdgcn.workitem.id.x() nounwind readnone - %gep0 = getelementptr i32, i32 addrspace(1)* %aptr, i32 %tid - %gep1 = getelementptr i32, i32 addrspace(1)* %bptr, i32 %tid - %outgep = getelementptr i32, i32 addrspace(1)* %out, i32 %tid - %a = load i32, i32 addrspace(1)* %gep0, align 4 - %b = load i32, i32 addrspace(1)* %gep1, align 4 + %a = load i32, i32 addrspace(1)* %aptr, align 4 + %b = load i32, i32 addrspace(1)* %bptr, align 4 %cmp = icmp ugt i32 %a, %b %val = select i1 %cmp, i32 %a, i32 %b - store i32 %val, i32 addrspace(1)* %outgep, align 4 + store i32 %val, i32 addrspace(1)* %out, align 4 ret void } ; FUNC-LABEL: {{^}}s_test_umax_ugt_i32: ; SI: s_max_u32 + +; EG: MAX_UINT define void @s_test_umax_ugt_i32(i32 addrspace(1)* %out, i32 %a, i32 %b) nounwind { %cmp = icmp ugt i32 %a, %b %val = select i1 %cmp, i32 %a, i32 %b @@ -193,6 +204,9 @@ ; FUNC-LABEL: {{^}}s_test_umax_ugt_imm_v2i32: ; SI-DAG: s_max_u32 {{s[0-9]+}}, {{s[0-9]+}}, 15 ; SI-DAG: s_max_u32 {{s[0-9]+}}, {{s[0-9]+}}, 23 + +; EG: MAX_UINT {{.*}}literal.{{[xyzw]}} +; EG: MAX_UINT {{.*}}literal.{{[xyzw]}} define void @s_test_umax_ugt_imm_v2i32(<2 x i32> addrspace(1)* %out, <2 x i32> %a) nounwind { %cmp = icmp ugt <2 x i32> %a, %val = select <2 x i1> %cmp, <2 x i32> %a, <2 x i32> @@ -207,6 +221,8 @@ ; SI: s_max_u32 [[MAX:s[0-9]+]], [[A]], [[B]] ; SI: v_mov_b32_e32 [[VMAX:v[0-9]+]], [[MAX]] ; SI: buffer_store_dword [[VMAX]] + +; EG: MAX_UINT define void @simplify_demanded_bits_test_umax_ugt_i16(i32 addrspace(1)* %out, i16 zeroext %a, i16 zeroext %b) nounwind { %a.ext = zext i16 %a to i32 %b.ext = zext i16 %b to i32 @@ -225,6 +241,8 @@ ; SI: s_max_i32 [[MAX:s[0-9]+]], [[A]], [[B]] ; SI: v_mov_b32_e32 [[VMAX:v[0-9]+]], [[MAX]] ; SI: buffer_store_dword [[VMAX]] + +; EG: MAX_INT define void @simplify_demanded_bits_test_max_slt_i16(i32 addrspace(1)* %out, i16 signext %a, i16 signext %b) nounwind { %a.ext = sext i16 %a to i32 %b.ext = sext i16 %b to i32 @@ -242,9 +260,60 @@ ; SI: s_sext_i32_i16 ; SI: s_sext_i32_i16 ; SI: s_max_i32 + +; EG: MAX_INT define void @s_test_imax_sge_i16(i16 addrspace(1)* %out, i16 %a, i16 %b) nounwind { %cmp = icmp sge i16 %a, %b %val = select i1 %cmp, i16 %a, i16 %b store i16 %val, i16 addrspace(1)* %out ret void } + +; 64 bit +; FUNC-LABEL: {{^}}test_umax_ugt_i64 +; SI: s_endpgm + +; EG: MAX_UINT +; EG: MAX_UINT +define void @test_umax_ugt_i64(i64 addrspace(1)* %out, i64 %a, i64 %b) nounwind { + %tmp = icmp ugt i64 %a, %b + %val = select i1 %tmp, i64 %a, i64 %b + store i64 %val, i64 addrspace(1)* %out, align 8 + ret void +} + +; FUNC-LABEL: {{^}}test_umax_uge_i64 +; SI: s_endpgm + +; EG: MAX_UINT +; EG: MAX_UINT +define void @test_umax_uge_i64(i64 addrspace(1)* %out, i64 %a, i64 %b) nounwind { + %tmp = icmp uge i64 %a, %b + %val = select i1 %tmp, i64 %a, i64 %b + store i64 %val, i64 addrspace(1)* %out, align 8 + ret void +} + +; FUNC-LABEL: {{^}}test_imax_sgt_i64 +; SI: s_endpgm + +; EG-DAG: MAX_UINT +; EG-DAG: MAX_INT +define void @test_imax_sgt_i64(i64 addrspace(1)* %out, i64 %a, i64 %b) nounwind { + %tmp = icmp sgt i64 %a, %b + %val = select i1 %tmp, i64 %a, i64 %b + store i64 %val, i64 addrspace(1)* %out, align 8 + ret void +} + +; FUNC-LABEL: {{^}}test_imax_sge_i64 +; SI: s_endpgm + +; EG-DAG: MAX_UINT +; EG-DAG: MAX_INT +define void @test_imax_sge_i64(i64 addrspace(1)* %out, i64 %a, i64 %b) nounwind { + %tmp = icmp sge i64 %a, %b + %val = select i1 %tmp, i64 %a, i64 %b + store i64 %val, i64 addrspace(1)* %out, align 8 + ret void +} Index: test/CodeGen/AMDGPU/min.ll =================================================================== --- test/CodeGen/AMDGPU/min.ll +++ test/CodeGen/AMDGPU/min.ll @@ -1,24 +1,25 @@ ; RUN: llc -march=amdgcn < %s | FileCheck -check-prefix=SI -check-prefix=FUNC %s +; RUN: llc -march=r600 -mcpu=cypress < %s | FileCheck -check-prefix=EG -check-prefix=FUNC %s declare i32 @llvm.amdgcn.workitem.id.x() nounwind readnone ; FUNC-LABEL: {{^}}v_test_imin_sle_i32: ; SI: v_min_i32_e32 + +; EG: MIN_INT define void @v_test_imin_sle_i32(i32 addrspace(1)* %out, i32 addrspace(1)* %aptr, i32 addrspace(1)* %bptr) nounwind { - %tid = call i32 @llvm.amdgcn.workitem.id.x() nounwind readnone - %gep0 = getelementptr i32, i32 addrspace(1)* %aptr, i32 %tid - %gep1 = getelementptr i32, i32 addrspace(1)* %bptr, i32 %tid - %outgep = getelementptr i32, i32 addrspace(1)* %out, i32 %tid - %a = load i32, i32 addrspace(1)* %gep0, align 4 - %b = load i32, i32 addrspace(1)* %gep1, align 4 + %a = load i32, i32 addrspace(1)* %aptr, align 4 + %b = load i32, i32 addrspace(1)* %bptr, align 4 %cmp = icmp sle i32 %a, %b %val = select i1 %cmp, i32 %a, i32 %b - store i32 %val, i32 addrspace(1)* %outgep, align 4 + store i32 %val, i32 addrspace(1)* %out, align 4 ret void } ; FUNC-LABEL: {{^}}s_test_imin_sle_i32: ; SI: s_min_i32 + +; EG: MIN_INT define void @s_test_imin_sle_i32(i32 addrspace(1)* %out, i32 %a, i32 %b) nounwind { %cmp = icmp sle i32 %a, %b %val = select i1 %cmp, i32 %a, i32 %b @@ -28,6 +29,8 @@ ; FUNC-LABEL: {{^}}s_test_imin_sle_v1i32: ; SI: s_min_i32 + +; EG: MIN_INT define void @s_test_imin_sle_v1i32(<1 x i32> addrspace(1)* %out, <1 x i32> %a, <1 x i32> %b) nounwind { %cmp = icmp sle <1 x i32> %a, %b %val = select <1 x i1> %cmp, <1 x i32> %a, <1 x i32> %b @@ -40,6 +43,11 @@ ; SI: s_min_i32 ; SI: s_min_i32 ; SI: s_min_i32 + +; EG: MIN_INT +; EG: MIN_INT +; EG: MIN_INT +; EG: MIN_INT define void @s_test_imin_sle_v4i32(<4 x i32> addrspace(1)* %out, <4 x i32> %a, <4 x i32> %b) nounwind { %cmp = icmp sle <4 x i32> %a, %b %val = select <4 x i1> %cmp, <4 x i32> %a, <4 x i32> %b @@ -79,6 +87,11 @@ ; SI: v_min_i32 ; SI: s_endpgm + +; EG: MIN_INT +; EG: MIN_INT +; EG: MIN_INT +; EG: MIN_INT define void @s_test_imin_sle_v4i8(<4 x i8> addrspace(1)* %out, <4 x i8> %a, <4 x i8> %b) nounwind { %cmp = icmp sle <4 x i8> %a, %b %val = select <4 x i1> %cmp, <4 x i8> %a, <4 x i8> %b @@ -91,6 +104,11 @@ ; SI: v_min_i32 ; SI: v_min_i32 ; SI: v_min_i32 + +; EG: MIN_INT +; EG: MIN_INT +; EG: MIN_INT +; EG: MIN_INT define void @s_test_imin_sle_v4i16(<4 x i16> addrspace(1)* %out, <4 x i16> %a, <4 x i16> %b) nounwind { %cmp = icmp sle <4 x i16> %a, %b %val = select <4 x i1> %cmp, <4 x i16> %a, <4 x i16> %b @@ -100,21 +118,21 @@ ; FUNC-LABEL: @v_test_imin_slt_i32 ; SI: v_min_i32_e32 + +; EG: MIN_INT define void @v_test_imin_slt_i32(i32 addrspace(1)* %out, i32 addrspace(1)* %aptr, i32 addrspace(1)* %bptr) nounwind { - %tid = call i32 @llvm.amdgcn.workitem.id.x() nounwind readnone - %gep0 = getelementptr i32, i32 addrspace(1)* %aptr, i32 %tid - %gep1 = getelementptr i32, i32 addrspace(1)* %bptr, i32 %tid - %outgep = getelementptr i32, i32 addrspace(1)* %out, i32 %tid - %a = load i32, i32 addrspace(1)* %gep0, align 4 - %b = load i32, i32 addrspace(1)* %gep1, align 4 + %a = load i32, i32 addrspace(1)* %aptr, align 4 + %b = load i32, i32 addrspace(1)* %bptr, align 4 %cmp = icmp slt i32 %a, %b %val = select i1 %cmp, i32 %a, i32 %b - store i32 %val, i32 addrspace(1)* %outgep, align 4 + store i32 %val, i32 addrspace(1)* %out, align 4 ret void } ; FUNC-LABEL: @s_test_imin_slt_i32 ; SI: s_min_i32 + +; EG: MIN_INT define void @s_test_imin_slt_i32(i32 addrspace(1)* %out, i32 %a, i32 %b) nounwind { %cmp = icmp slt i32 %a, %b %val = select i1 %cmp, i32 %a, i32 %b @@ -125,6 +143,9 @@ ; FUNC-LABEL: {{^}}s_test_imin_slt_v2i32: ; SI: s_min_i32 ; SI: s_min_i32 + +; EG: MIN_INT +; EG: MIN_INT define void @s_test_imin_slt_v2i32(<2 x i32> addrspace(1)* %out, <2 x i32> %a, <2 x i32> %b) nounwind { %cmp = icmp slt <2 x i32> %a, %b %val = select <2 x i1> %cmp, <2 x i32> %a, <2 x i32> %b @@ -134,6 +155,8 @@ ; FUNC-LABEL: {{^}}s_test_imin_slt_imm_i32: ; SI: s_min_i32 {{s[0-9]+}}, {{s[0-9]+}}, 8 + +; EG: MIN_INT {{.*}}literal.{{[xyzw]}} define void @s_test_imin_slt_imm_i32(i32 addrspace(1)* %out, i32 %a) nounwind { %cmp = icmp slt i32 %a, 8 %val = select i1 %cmp, i32 %a, i32 8 @@ -143,6 +166,8 @@ ; FUNC-LABEL: {{^}}s_test_imin_sle_imm_i32: ; SI: s_min_i32 {{s[0-9]+}}, {{s[0-9]+}}, 8 + +; EG: MIN_INT {{.*}}literal.{{[xyzw]}} define void @s_test_imin_sle_imm_i32(i32 addrspace(1)* %out, i32 %a) nounwind { %cmp = icmp sle i32 %a, 8 %val = select i1 %cmp, i32 %a, i32 8 @@ -152,16 +177,14 @@ ; FUNC-LABEL: @v_test_umin_ule_i32 ; SI: v_min_u32_e32 + +; EG: MIN_UINT define void @v_test_umin_ule_i32(i32 addrspace(1)* %out, i32 addrspace(1)* %aptr, i32 addrspace(1)* %bptr) nounwind { - %tid = call i32 @llvm.amdgcn.workitem.id.x() nounwind readnone - %gep0 = getelementptr i32, i32 addrspace(1)* %aptr, i32 %tid - %gep1 = getelementptr i32, i32 addrspace(1)* %bptr, i32 %tid - %outgep = getelementptr i32, i32 addrspace(1)* %out, i32 %tid - %a = load i32, i32 addrspace(1)* %gep0, align 4 - %b = load i32, i32 addrspace(1)* %gep1, align 4 + %a = load i32, i32 addrspace(1)* %aptr, align 4 + %b = load i32, i32 addrspace(1)* %bptr, align 4 %cmp = icmp ule i32 %a, %b %val = select i1 %cmp, i32 %a, i32 %b - store i32 %val, i32 addrspace(1)* %outgep, align 4 + store i32 %val, i32 addrspace(1)* %out, align 4 ret void } @@ -171,20 +194,22 @@ ; SI: v_min_u32_e32 ; SI-NOT: v_min_u32_e32 ; SI: s_endpgm + +; EG: MIN_UINT +; EG: MIN_UINT +; EG: MIN_UINT define void @v_test_umin_ule_v3i32(<3 x i32> addrspace(1)* %out, <3 x i32> addrspace(1)* %aptr, <3 x i32> addrspace(1)* %bptr) nounwind { - %tid = call i32 @llvm.amdgcn.workitem.id.x() nounwind readnone - %gep0 = getelementptr <3 x i32>, <3 x i32> addrspace(1)* %aptr, i32 %tid - %gep1 = getelementptr <3 x i32>, <3 x i32> addrspace(1)* %bptr, i32 %tid - %outgep = getelementptr <3 x i32>, <3 x i32> addrspace(1)* %out, i32 %tid - %a = load <3 x i32>, <3 x i32> addrspace(1)* %gep0 - %b = load <3 x i32>, <3 x i32> addrspace(1)* %gep1 + %a = load <3 x i32>, <3 x i32> addrspace(1)* %aptr + %b = load <3 x i32>, <3 x i32> addrspace(1)* %bptr %cmp = icmp ule <3 x i32> %a, %b %val = select <3 x i1> %cmp, <3 x i32> %a, <3 x i32> %b - store <3 x i32> %val, <3 x i32> addrspace(1)* %outgep + store <3 x i32> %val, <3 x i32> addrspace(1)* %out ret void } ; FUNC-LABEL: @s_test_umin_ule_i32 ; SI: s_min_u32 + +; EG: MIN_UINT define void @s_test_umin_ule_i32(i32 addrspace(1)* %out, i32 %a, i32 %b) nounwind { %cmp = icmp ule i32 %a, %b %val = select i1 %cmp, i32 %a, i32 %b @@ -194,16 +219,14 @@ ; FUNC-LABEL: @v_test_umin_ult_i32 ; SI: v_min_u32_e32 + +; EG: MIN_UINT define void @v_test_umin_ult_i32(i32 addrspace(1)* %out, i32 addrspace(1)* %aptr, i32 addrspace(1)* %bptr) nounwind { - %tid = call i32 @llvm.amdgcn.workitem.id.x() nounwind readnone - %gep0 = getelementptr i32, i32 addrspace(1)* %aptr, i32 %tid - %gep1 = getelementptr i32, i32 addrspace(1)* %bptr, i32 %tid - %outgep = getelementptr i32, i32 addrspace(1)* %out, i32 %tid - %a = load i32, i32 addrspace(1)* %gep0, align 4 - %b = load i32, i32 addrspace(1)* %gep1, align 4 + %a = load i32, i32 addrspace(1)* %aptr, align 4 + %b = load i32, i32 addrspace(1)* %aptr, align 4 %cmp = icmp ult i32 %a, %b %val = select i1 %cmp, i32 %a, i32 %b - store i32 %val, i32 addrspace(1)* %outgep, align 4 + store i32 %val, i32 addrspace(1)* %out, align 4 ret void } @@ -211,21 +234,21 @@ ; SI: buffer_load_ubyte ; SI: buffer_load_ubyte ; SI: v_min_u32_e32 + +; EG: MIN_UINT define void @v_test_umin_ult_i8(i8 addrspace(1)* %out, i8 addrspace(1)* %aptr, i8 addrspace(1)* %bptr) nounwind { - %tid = call i32 @llvm.amdgcn.workitem.id.x() nounwind readnone - %gep0 = getelementptr i8, i8 addrspace(1)* %aptr, i32 %tid - %gep1 = getelementptr i8, i8 addrspace(1)* %bptr, i32 %tid - %outgep = getelementptr i8, i8 addrspace(1)* %out, i32 %tid - %a = load i8, i8 addrspace(1)* %gep0, align 1 - %b = load i8, i8 addrspace(1)* %gep1, align 1 + %a = load i8, i8 addrspace(1)* %aptr, align 1 + %b = load i8, i8 addrspace(1)* %bptr, align 1 %cmp = icmp ult i8 %a, %b %val = select i1 %cmp, i8 %a, i8 %b - store i8 %val, i8 addrspace(1)* %outgep, align 1 + store i8 %val, i8 addrspace(1)* %out, align 1 ret void } ; FUNC-LABEL: @s_test_umin_ult_i32 ; SI: s_min_u32 + +; EG: MIN_UINT define void @s_test_umin_ult_i32(i32 addrspace(1)* %out, i32 %a, i32 %b) nounwind { %cmp = icmp ult i32 %a, %b %val = select i1 %cmp, i32 %a, i32 %b @@ -239,24 +262,23 @@ ; SI-NEXT: v_cndmask_b32 ; SI-NOT: v_min ; SI: s_endpgm + +; EG-NOT: MIN_UINT define void @v_test_umin_ult_i32_multi_use(i32 addrspace(1)* %out0, i1 addrspace(1)* %out1, i32 addrspace(1)* %aptr, i32 addrspace(1)* %bptr) nounwind { - %tid = call i32 @llvm.amdgcn.workitem.id.x() nounwind readnone - %gep0 = getelementptr i32, i32 addrspace(1)* %aptr, i32 %tid - %gep1 = getelementptr i32, i32 addrspace(1)* %bptr, i32 %tid - %outgep0 = getelementptr i32, i32 addrspace(1)* %out0, i32 %tid - %outgep1 = getelementptr i1, i1 addrspace(1)* %out1, i32 %tid - %a = load i32, i32 addrspace(1)* %gep0, align 4 - %b = load i32, i32 addrspace(1)* %gep1, align 4 + %a = load i32, i32 addrspace(1)* %aptr, align 4 + %b = load i32, i32 addrspace(1)* %bptr, align 4 %cmp = icmp ult i32 %a, %b %val = select i1 %cmp, i32 %a, i32 %b - store i32 %val, i32 addrspace(1)* %outgep0, align 4 - store i1 %cmp, i1 addrspace(1)* %outgep1 + store i32 %val, i32 addrspace(1)* %out0, align 4 + store i1 %cmp, i1 addrspace(1)* %out1 ret void } ; FUNC-LABEL: @s_test_umin_ult_v1i32 ; SI: s_min_u32 + +; EG: MIN_UINT define void @s_test_umin_ult_v1i32(<1 x i32> addrspace(1)* %out, <1 x i32> %a, <1 x i32> %b) nounwind { %cmp = icmp ult <1 x i32> %a, %b %val = select <1 x i1> %cmp, <1 x i32> %a, <1 x i32> %b @@ -273,6 +295,15 @@ ; SI: s_min_u32 ; SI: s_min_u32 ; SI: s_min_u32 + +; EG: MIN_UINT +; EG: MIN_UINT +; EG: MIN_UINT +; EG: MIN_UINT +; EG: MIN_UINT +; EG: MIN_UINT +; EG: MIN_UINT +; EG: MIN_UINT define void @s_test_umin_ult_v8i32(<8 x i32> addrspace(1)* %out, <8 x i32> %a, <8 x i32> %b) nounwind { %cmp = icmp ult <8 x i32> %a, %b %val = select <8 x i1> %cmp, <8 x i32> %a, <8 x i32> %b @@ -289,6 +320,15 @@ ; SI: v_min_u32 ; SI: v_min_u32 ; SI: v_min_u32 + +; EG: MIN_UINT +; EG: MIN_UINT +; EG: MIN_UINT +; EG: MIN_UINT +; EG: MIN_UINT +; EG: MIN_UINT +; EG: MIN_UINT +; EG: MIN_UINT define void @s_test_umin_ult_v8i16(<8 x i16> addrspace(1)* %out, <8 x i16> %a, <8 x i16> %b) nounwind { %cmp = icmp ult <8 x i16> %a, %b %val = select <8 x i1> %cmp, <8 x i16> %a, <8 x i16> %b @@ -303,6 +343,8 @@ ; SI: s_min_u32 [[MIN:s[0-9]+]], [[A]], [[B]] ; SI: v_mov_b32_e32 [[VMIN:v[0-9]+]], [[MIN]] ; SI: buffer_store_dword [[VMIN]] + +; EG: MIN_UINT define void @simplify_demanded_bits_test_umin_ult_i16(i32 addrspace(1)* %out, i16 zeroext %a, i16 zeroext %b) nounwind { %a.ext = zext i16 %a to i32 %b.ext = zext i16 %b to i32 @@ -321,6 +363,8 @@ ; SI: s_min_i32 [[MIN:s[0-9]+]], [[A]], [[B]] ; SI: v_mov_b32_e32 [[VMIN:v[0-9]+]], [[MIN]] ; SI: buffer_store_dword [[VMIN]] + +; EG: MIN_INT define void @simplify_demanded_bits_test_min_slt_i16(i32 addrspace(1)* %out, i16 signext %a, i16 signext %b) nounwind { %a.ext = sext i16 %a to i32 %b.ext = sext i16 %b to i32 @@ -334,9 +378,60 @@ ; FUNC-LABEL: {{^}}s_test_imin_sle_i16: ; SI: s_min_i32 + +; EG: MIN_INT define void @s_test_imin_sle_i16(i16 addrspace(1)* %out, i16 %a, i16 %b) nounwind { %cmp = icmp sle i16 %a, %b %val = select i1 %cmp, i16 %a, i16 %b store i16 %val, i16 addrspace(1)* %out ret void } + +; 64 bit +; FUNC-LABEL: {{^}}test_umin_ult_i64 +; SI: s_endpgm + +; EG: MIN_UINT +; EG: MIN_UINT +define void @test_umin_ult_i64(i64 addrspace(1)* %out, i64 %a, i64 %b) nounwind { + %tmp = icmp ult i64 %a, %b + %val = select i1 %tmp, i64 %a, i64 %b + store i64 %val, i64 addrspace(1)* %out, align 8 + ret void +} + +; FUNC-LABEL: {{^}}test_umin_ule_i64 +; SI: s_endpgm + +; EG: MIN_UINT +; EG: MIN_UINT +define void @test_umin_ule_i64(i64 addrspace(1)* %out, i64 %a, i64 %b) nounwind { + %tmp = icmp ule i64 %a, %b + %val = select i1 %tmp, i64 %a, i64 %b + store i64 %val, i64 addrspace(1)* %out, align 8 + ret void +} + +; FUNC-LABEL: {{^}}test_imin_slt_i64 +; SI: s_endpgm + +; EG-DAG: MIN_UINT +; EG-DAG: MIN_INT +define void @test_imin_slt_i64(i64 addrspace(1)* %out, i64 %a, i64 %b) nounwind { + %tmp = icmp slt i64 %a, %b + %val = select i1 %tmp, i64 %a, i64 %b + store i64 %val, i64 addrspace(1)* %out, align 8 + ret void +} + +; FUNC-LABEL: {{^}}test_imin_sle_i64 +; SI: s_endpgm + +; EG-DAG: MIN_UINT +; EG-DAG: MIN_INT +define void @test_imin_sle_i64(i64 addrspace(1)* %out, i64 %a, i64 %b) nounwind { + %tmp = icmp sle i64 %a, %b + %val = select i1 %tmp, i64 %a, i64 %b + store i64 %val, i64 addrspace(1)* %out, align 8 + ret void +} Index: test/CodeGen/AMDGPU/sminmax.ll =================================================================== --- test/CodeGen/AMDGPU/sminmax.ll +++ test/CodeGen/AMDGPU/sminmax.ll @@ -1,9 +1,12 @@ ; RUN: llc -march=amdgcn -mcpu=verde -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=FUNC %s ; RUN: llc -march=amdgcn -mcpu=tonga -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=FUNC %s +; RUN: llc -march=r600 -mcpu=cypress -verify-machineinstrs < %s | FileCheck -check-prefix=EG -check-prefix=FUNC %s ; FUNC-LABEL: {{^}}s_abs_i32: ; GCN: s_abs_i32 ; GCN: s_add_i32 + +; EG: MAX_INT define void @s_abs_i32(i32 addrspace(1)* %out, i32 %val) nounwind { %neg = sub i32 0, %val %cond = icmp sgt i32 %val, %neg @@ -17,6 +20,8 @@ ; GCN: v_sub_i32_e32 [[NEG:v[0-9]+]], vcc, 0, [[SRC:v[0-9]+]] ; GCN: v_max_i32_e32 {{v[0-9]+}}, [[NEG]], [[SRC]] ; GCN: v_add_i32 + +; EG: MAX_INT define void @v_abs_i32(i32 addrspace(1)* %out, i32 addrspace(1)* %src) nounwind { %val = load i32, i32 addrspace(1)* %src, align 4 %neg = sub i32 0, %val @@ -32,6 +37,9 @@ ; GCN: s_abs_i32 ; GCN: s_add_i32 ; GCN: s_add_i32 + +; EG: MAX_INT +; EG: MAX_INT define void @s_abs_v2i32(<2 x i32> addrspace(1)* %out, <2 x i32> %val) nounwind { %z0 = insertelement <2 x i32> undef, i32 0, i32 0 %z1 = insertelement <2 x i32> %z0, i32 0, i32 1 @@ -54,6 +62,9 @@ ; GCN: v_add_i32 ; GCN: v_add_i32 + +; EG: MAX_INT +; EG: MAX_INT define void @v_abs_v2i32(<2 x i32> addrspace(1)* %out, <2 x i32> addrspace(1)* %src) nounwind { %z0 = insertelement <2 x i32> undef, i32 0, i32 0 %z1 = insertelement <2 x i32> %z0, i32 0, i32 1 @@ -79,6 +90,11 @@ ; GCN: s_add_i32 ; GCN: s_add_i32 ; GCN: s_add_i32 + +; EG: MAX_INT +; EG: MAX_INT +; EG: MAX_INT +; EG: MAX_INT define void @s_abs_v4i32(<4 x i32> addrspace(1)* %out, <4 x i32> %val) nounwind { %z0 = insertelement <4 x i32> undef, i32 0, i32 0 %z1 = insertelement <4 x i32> %z0, i32 0, i32 1 @@ -111,6 +127,11 @@ ; GCN: v_add_i32 ; GCN: v_add_i32 ; GCN: v_add_i32 + +; EG: MAX_INT +; EG: MAX_INT +; EG: MAX_INT +; EG: MAX_INT define void @v_abs_v4i32(<4 x i32> addrspace(1)* %out, <4 x i32> addrspace(1)* %src) nounwind { %z0 = insertelement <4 x i32> undef, i32 0, i32 0 %z1 = insertelement <4 x i32> %z0, i32 0, i32 1