diff options
Diffstat (limited to 'include/clang/Basic/arm_neon.td')
| -rw-r--r-- | include/clang/Basic/arm_neon.td | 109 |
1 files changed, 83 insertions, 26 deletions
diff --git a/include/clang/Basic/arm_neon.td b/include/clang/Basic/arm_neon.td index c35336166c39..af049be7e295 100644 --- a/include/clang/Basic/arm_neon.td +++ b/include/clang/Basic/arm_neon.td @@ -206,6 +206,15 @@ def OP_DOT_LNQ : Op<(call "vdot", $p0, $p1, (bitcast $p1, (splat(bitcast "uint32x4_t", $p2), $p3)))>; +def OP_FMLAL_LN : Op<(call "vfmlal_low", $p0, $p1, + (dup_typed $p1, (call "vget_lane", $p2, $p3)))>; +def OP_FMLSL_LN : Op<(call "vfmlsl_low", $p0, $p1, + (dup_typed $p1, (call "vget_lane", $p2, $p3)))>; +def OP_FMLAL_LN_Hi : Op<(call "vfmlal_high", $p0, $p1, + (dup_typed $p1, (call "vget_lane", $p2, $p3)))>; +def OP_FMLSL_LN_Hi : Op<(call "vfmlsl_high", $p0, $p1, + (dup_typed $p1, (call "vget_lane", $p2, $p3)))>; + //===----------------------------------------------------------------------===// // Instructions //===----------------------------------------------------------------------===// @@ -337,48 +346,78 @@ def VSLI_N : WInst<"vsli_n", "dddi", //////////////////////////////////////////////////////////////////////////////// // E.3.14 Loads and stores of a single vector def VLD1 : WInst<"vld1", "dc", - "QUcQUsQUiQUlQcQsQiQlQhQfQPcQPsUcUsUiUlcsilhfPcPs">; + "QUcQUsQUiQUlQcQsQiQlQfQPcQPsUcUsUiUlcsilfPcPs">; def VLD1_X2 : WInst<"vld1_x2", "2c", - "cfhilsUcUiUlUsQcQfQhQiQlQsQUcQUiQUlQUsPcPsQPcQPs">; + "cfilsUcUiUlUsQcQfQiQlQsQUcQUiQUlQUsPcPsQPcQPs">; def VLD1_X3 : WInst<"vld1_x3", "3c", - "cfhilsUcUiUlUsQcQfQhQiQlQsQUcQUiQUlQUsPcPsQPcQPs">; + "cfilsUcUiUlUsQcQfQiQlQsQUcQUiQUlQUsPcPsQPcQPs">; def VLD1_X4 : WInst<"vld1_x4", "4c", - "cfhilsUcUiUlUsQcQfQhQiQlQsQUcQUiQUlQUsPcPsQPcQPs">; + "cfilsUcUiUlUsQcQfQiQlQsQUcQUiQUlQUsPcPsQPcQPs">; def VLD1_LANE : WInst<"vld1_lane", "dcdi", - "QUcQUsQUiQUlQcQsQiQlQhQfQPcQPsUcUsUiUlcsilhfPcPs">; + "QUcQUsQUiQUlQcQsQiQlQfQPcQPsUcUsUiUlcsilfPcPs">; def VLD1_DUP : WInst<"vld1_dup", "dc", - "QUcQUsQUiQUlQcQsQiQlQhQfQPcQPsUcUsUiUlcsilhfPcPs">; + "QUcQUsQUiQUlQcQsQiQlQfQPcQPsUcUsUiUlcsilfPcPs">; def VST1 : WInst<"vst1", "vpd", - "QUcQUsQUiQUlQcQsQiQlQhQfQPcQPsUcUsUiUlcsilhfPcPs">; + "QUcQUsQUiQUlQcQsQiQlQfQPcQPsUcUsUiUlcsilfPcPs">; def VST1_X2 : WInst<"vst1_x2", "vp2", - "cfhilsUcUiUlUsQcQfQhQiQlQsQUcQUiQUlQUsPcPsQPcQPs">; + "cfilsUcUiUlUsQcQfQiQlQsQUcQUiQUlQUsPcPsQPcQPs">; def VST1_X3 : WInst<"vst1_x3", "vp3", - "cfhilsUcUiUlUsQcQfQhQiQlQsQUcQUiQUlQUsPcPsQPcQPs">; + "cfilsUcUiUlUsQcQfQiQlQsQUcQUiQUlQUsPcPsQPcQPs">; def VST1_X4 : WInst<"vst1_x4", "vp4", - "cfhilsUcUiUlUsQcQfQhQiQlQsQUcQUiQUlQUsPcPsQPcQPs">; + "cfilsUcUiUlUsQcQfQiQlQsQUcQUiQUlQUsPcPsQPcQPs">; def VST1_LANE : WInst<"vst1_lane", "vpdi", - "QUcQUsQUiQUlQcQsQiQlQhQfQPcQPsUcUsUiUlcsilhfPcPs">; + "QUcQUsQUiQUlQcQsQiQlQfQPcQPsUcUsUiUlcsilfPcPs">; +let ArchGuard = "(__ARM_FP & 2)" in { +def VLD1_F16 : WInst<"vld1", "dc", "hQh">; +def VLD1_X2_F16 : WInst<"vld1_x2", "2c", "hQh">; +def VLD1_X3_F16 : WInst<"vld1_x3", "3c", "hQh">; +def VLD1_X4_F16 : WInst<"vld1_x4", "4c", "hQh">; +def VLD1_LANE_F16 : WInst<"vld1_lane", "dcdi", "hQh">; +def VLD1_DUP_F16 : WInst<"vld1_dup", "dc", "hQh">; +def VST1_F16 : WInst<"vst1", "vpd", "hQh">; +def VST1_X2_F16 : WInst<"vst1_x2", "vp2", "hQh">; +def VST1_X3_F16 : WInst<"vst1_x3", "vp3", "hQh">; +def VST1_X4_F16 : WInst<"vst1_x4", "vp4", "hQh">; +def VST1_LANE_F16 : WInst<"vst1_lane", "vpdi", "hQh">; +} //////////////////////////////////////////////////////////////////////////////// // E.3.15 Loads and stores of an N-element structure -def VLD2 : WInst<"vld2", "2c", "QUcQUsQUiQcQsQiQhQfQPcQPsUcUsUiUlcsilhfPcPs">; -def VLD3 : WInst<"vld3", "3c", "QUcQUsQUiQcQsQiQhQfQPcQPsUcUsUiUlcsilhfPcPs">; -def VLD4 : WInst<"vld4", "4c", "QUcQUsQUiQcQsQiQhQfQPcQPsUcUsUiUlcsilhfPcPs">; +def VLD2 : WInst<"vld2", "2c", "QUcQUsQUiQcQsQiQfQPcQPsUcUsUiUlcsilfPcPs">; +def VLD3 : WInst<"vld3", "3c", "QUcQUsQUiQcQsQiQfQPcQPsUcUsUiUlcsilfPcPs">; +def VLD4 : WInst<"vld4", "4c", "QUcQUsQUiQcQsQiQfQPcQPsUcUsUiUlcsilfPcPs">; def VLD2_DUP : WInst<"vld2_dup", "2c", - "UcUsUiUlcsilhfPcPsQcQfQhQiQlQsQPcQPsQUcQUiQUlQUs">; + "UcUsUiUlcsilfPcPsQcQfQiQlQsQPcQPsQUcQUiQUlQUs">; def VLD3_DUP : WInst<"vld3_dup", "3c", - "UcUsUiUlcsilhfPcPsQcQfQhQiQlQsQPcQPsQUcQUiQUlQUs">; + "UcUsUiUlcsilfPcPsQcQfQiQlQsQPcQPsQUcQUiQUlQUs">; def VLD4_DUP : WInst<"vld4_dup", "4c", - "UcUsUiUlcsilhfPcPsQcQfQhQiQlQsQPcQPsQUcQUiQUlQUs">; -def VLD2_LANE : WInst<"vld2_lane", "2c2i", "QUsQUiQsQiQhQfQPsUcUsUicsihfPcPs">; -def VLD3_LANE : WInst<"vld3_lane", "3c3i", "QUsQUiQsQiQhQfQPsUcUsUicsihfPcPs">; -def VLD4_LANE : WInst<"vld4_lane", "4c4i", "QUsQUiQsQiQhQfQPsUcUsUicsihfPcPs">; -def VST2 : WInst<"vst2", "vp2", "QUcQUsQUiQcQsQiQhQfQPcQPsUcUsUiUlcsilhfPcPs">; -def VST3 : WInst<"vst3", "vp3", "QUcQUsQUiQcQsQiQhQfQPcQPsUcUsUiUlcsilhfPcPs">; -def VST4 : WInst<"vst4", "vp4", "QUcQUsQUiQcQsQiQhQfQPcQPsUcUsUiUlcsilhfPcPs">; -def VST2_LANE : WInst<"vst2_lane", "vp2i", "QUsQUiQsQiQhQfQPsUcUsUicsihfPcPs">; -def VST3_LANE : WInst<"vst3_lane", "vp3i", "QUsQUiQsQiQhQfQPsUcUsUicsihfPcPs">; -def VST4_LANE : WInst<"vst4_lane", "vp4i", "QUsQUiQsQiQhQfQPsUcUsUicsihfPcPs">; + "UcUsUiUlcsilfPcPsQcQfQiQlQsQPcQPsQUcQUiQUlQUs">; +def VLD2_LANE : WInst<"vld2_lane", "2c2i", "QUsQUiQsQiQfQPsUcUsUicsifPcPs">; +def VLD3_LANE : WInst<"vld3_lane", "3c3i", "QUsQUiQsQiQfQPsUcUsUicsifPcPs">; +def VLD4_LANE : WInst<"vld4_lane", "4c4i", "QUsQUiQsQiQfQPsUcUsUicsifPcPs">; +def VST2 : WInst<"vst2", "vp2", "QUcQUsQUiQcQsQiQfQPcQPsUcUsUiUlcsilfPcPs">; +def VST3 : WInst<"vst3", "vp3", "QUcQUsQUiQcQsQiQfQPcQPsUcUsUiUlcsilfPcPs">; +def VST4 : WInst<"vst4", "vp4", "QUcQUsQUiQcQsQiQfQPcQPsUcUsUiUlcsilfPcPs">; +def VST2_LANE : WInst<"vst2_lane", "vp2i", "QUsQUiQsQiQfQPsUcUsUicsifPcPs">; +def VST3_LANE : WInst<"vst3_lane", "vp3i", "QUsQUiQsQiQfQPsUcUsUicsifPcPs">; +def VST4_LANE : WInst<"vst4_lane", "vp4i", "QUsQUiQsQiQfQPsUcUsUicsifPcPs">; +let ArchGuard = "(__ARM_FP & 2)" in { +def VLD2_F16 : WInst<"vld2", "2c", "hQh">; +def VLD3_F16 : WInst<"vld3", "3c", "hQh">; +def VLD4_F16 : WInst<"vld4", "4c", "hQh">; +def VLD2_DUP_F16 : WInst<"vld2_dup", "2c", "hQh">; +def VLD3_DUP_F16 : WInst<"vld3_dup", "3c", "hQh">; +def VLD4_DUP_F16 : WInst<"vld4_dup", "4c", "hQh">; +def VLD2_LANE_F16 : WInst<"vld2_lane", "2c2i", "hQh">; +def VLD3_LANE_F16 : WInst<"vld3_lane", "3c3i", "hQh">; +def VLD4_LANE_F16 : WInst<"vld4_lane", "4c4i", "hQh">; +def VST2_F16 : WInst<"vst2", "vp2", "hQh">; +def VST3_F16 : WInst<"vst3", "vp3", "hQh">; +def VST4_F16 : WInst<"vst4", "vp4", "hQh">; +def VST2_LANE_F16 : WInst<"vst2_lane", "vp2i", "hQh">; +def VST3_LANE_F16 : WInst<"vst3_lane", "vp3i", "hQh">; +def VST4_LANE_F16 : WInst<"vst4_lane", "vp4i", "hQh">; +} //////////////////////////////////////////////////////////////////////////////// // E.3.16 Extract lanes from a vector @@ -1610,3 +1649,21 @@ let ArchGuard = "defined(__ARM_FEATURE_DOTPROD) && defined(__aarch64__)" in { // Variants indexing into a 128-bit vector are A64 only. def UDOT_LANEQ : SOpInst<"vdot_laneq", "dd89i", "iUiQiQUi", OP_DOT_LNQ>; } + +// v8.2-A FP16 fused multiply-add long instructions. +let ArchGuard = "defined(__ARM_FEATURE_FP16FML) && defined(__aarch64__)" in { + def VFMLAL_LOW : SInst<"vfmlal_low", "ffHH", "UiQUi">; + def VFMLSL_LOW : SInst<"vfmlsl_low", "ffHH", "UiQUi">; + def VFMLAL_HIGH : SInst<"vfmlal_high", "ffHH", "UiQUi">; + def VFMLSL_HIGH : SInst<"vfmlsl_high", "ffHH", "UiQUi">; + + def VFMLAL_LANE_LOW : SOpInst<"vfmlal_lane_low", "ffH0i", "UiQUi", OP_FMLAL_LN>; + def VFMLSL_LANE_LOW : SOpInst<"vfmlsl_lane_low", "ffH0i", "UiQUi", OP_FMLSL_LN>; + def VFMLAL_LANE_HIGH : SOpInst<"vfmlal_lane_high", "ffH0i", "UiQUi", OP_FMLAL_LN_Hi>; + def VFMLSL_LANE_HIGH : SOpInst<"vfmlsl_lane_high", "ffH0i", "UiQUi", OP_FMLSL_LN_Hi>; + + def VFMLAL_LANEQ_LOW : SOpInst<"vfmlal_laneq_low", "ffH1i", "UiQUi", OP_FMLAL_LN>; + def VFMLSL_LANEQ_LOW : SOpInst<"vfmlsl_laneq_low", "ffH1i", "UiQUi", OP_FMLSL_LN>; + def VFMLAL_LANEQ_HIGH : SOpInst<"vfmlal_laneq_high", "ffH1i", "UiQUi", OP_FMLAL_LN_Hi>; + def VFMLSL_LANEQ_HIGH : SOpInst<"vfmlsl_laneq_high", "ffH1i", "UiQUi", OP_FMLSL_LN_Hi>; +} |
