Index: llvm/lib/Target/AMDGPU/AMDGPULegalizerInfo.cpp =================================================================== --- llvm/lib/Target/AMDGPU/AMDGPULegalizerInfo.cpp +++ llvm/lib/Target/AMDGPU/AMDGPULegalizerInfo.cpp @@ -598,8 +598,7 @@ .lower(); getActionDefinitionsBuilder(G_FPEXT) - .legalFor({{S64, S32}, {S32, S16}}) - .lowerFor({{S64, S16}}) // FIXME: Implement + .legalFor({{S64, S32}, {S32, S16}, {S64, S16}}) .scalarize(0); getActionDefinitionsBuilder(G_FSUB) Index: llvm/lib/Target/AMDGPU/SIInstructions.td =================================================================== --- llvm/lib/Target/AMDGPU/SIInstructions.td +++ llvm/lib/Target/AMDGPU/SIInstructions.td @@ -856,7 +856,7 @@ def : GCNPat < (f64 (fpextend f16:$src)), - (V_CVT_F64_F32_e32 (V_CVT_F32_F16_e32 $src)) + (V_CVT_F64_F32_e32 (V_CVT_F32_F16_e32 VSrc_b32:$src)) >; // fp_to_fp16 patterns Index: llvm/test/CodeGen/AMDGPU/GlobalISel/inst-select-fpext.mir =================================================================== --- /dev/null +++ llvm/test/CodeGen/AMDGPU/GlobalISel/inst-select-fpext.mir @@ -0,0 +1,24 @@ +# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py +# RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=fiji -run-pass=instruction-select %s -o - | FileCheck %s + +--- +name: test_fpext_f16_to_f64 +alignment: 1 +legalized: true +regBankSelected: true + +body: | + bb.0: + liveins: $vgpr0 + + ; CHECK-LABEL: name: test_fpext_f16_to_f64 + ; CHECK: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0 + ; CHECK: %3:vgpr_32 = nofpexcept V_CVT_F32_F16_e32 [[COPY]], implicit $mode, implicit $exec + ; CHECK: %2:vreg_64 = nofpexcept V_CVT_F64_F32_e32 %3, implicit $mode, implicit $exec + ; CHECK: $vgpr0_vgpr1 = COPY %2 + %0:vgpr(s32) = COPY $vgpr0 + %1:vgpr(s16) = G_TRUNC %0(s32) + %2:vgpr(s64) = G_FPEXT %1(s16) + $vgpr0_vgpr1 = COPY %2(s64) + +... Index: llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-fpext.mir =================================================================== --- llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-fpext.mir +++ llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-fpext.mir @@ -192,3 +192,42 @@ %1:_(<4 x s64>) = G_FPEXT %0 $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7 = COPY %1 ... + +--- +name: test_fpext_f16_to_f64 +body: | + bb.0: + liveins: $vgpr0 + + ; CHECK-LABEL: name: test_fpext_f16_to_f64 + ; CHECK: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0 + ; CHECK: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[COPY]](s32) + ; CHECK: [[FPEXT:%[0-9]+]]:_(s64) = G_FPEXT [[TRUNC]](s16) + ; CHECK: $vgpr0_vgpr1 = COPY [[FPEXT]](s64) + %0:_(s32) = COPY $vgpr0 + %1:_(s16) = G_TRUNC %0 + %2:_(s64) = G_FPEXT %1 + $vgpr0_vgpr1 = COPY %2 +... + +--- +name: test_fpext_v2f16_to_v2f64 +body: | + bb.0: + liveins: $vgpr0 + + ; CHECK-LABEL: name: test_fpext_v2f16_to_v2f64 + ; CHECK: [[COPY:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr0 + ; CHECK: [[BITCAST:%[0-9]+]]:_(s32) = G_BITCAST [[COPY]](<2 x s16>) + ; CHECK: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[BITCAST]](s32) + ; CHECK: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 16 + ; CHECK: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST]], [[C]](s32) + ; CHECK: [[TRUNC1:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR]](s32) + ; CHECK: [[FPEXT:%[0-9]+]]:_(s64) = nnan G_FPEXT [[TRUNC]](s16) + ; CHECK: [[FPEXT1:%[0-9]+]]:_(s64) = nnan G_FPEXT [[TRUNC1]](s16) + ; CHECK: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s64>) = G_BUILD_VECTOR [[FPEXT]](s64), [[FPEXT1]](s64) + ; CHECK: $vgpr0_vgpr1_vgpr2_vgpr3 = COPY [[BUILD_VECTOR]](<2 x s64>) + %0:_(<2 x s16>) = COPY $vgpr0 + %1:_(<2 x s64>) = nnan G_FPEXT %0 + $vgpr0_vgpr1_vgpr2_vgpr3 = COPY %1 +...