Skip to content

[AArch64] Add intrinsics for 16-bit non-widening FMLA/FMLS #88553

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 3 commits into from
May 10, 2024
Merged

[AArch64] Add intrinsics for 16-bit non-widening FMLA/FMLS #88553

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
2f96bd7
[AArch64] Add intrinsics for 16-bit non-widening FMLA/FMLS
momchil-velikov Apr 12, 2024
6ee3f45
[fixup] Fix incorrect dependency on sme2p1
momchil-velikov May 1, 2024
42f10b3
[fixup] Fix test RUN lines
momchil-velikov May 9, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
34 changes: 34 additions & 0 deletions clang/include/clang/Basic/arm_sme.td
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -458,6 +458,40 @@ let TargetGuard = "sme2,sme-f64f64" in {
def SVMLS_LANE_VG1x4_F64 : Inst<"svmls_lane_za64[_{d}]_vg1x4", "vm4di", "d", MergeNone, "aarch64_sme_fmls_lane_vg1x4", [IsStreaming, IsInOutZA], [ImmCheck<3, ImmCheck0_1>]>;
}

let TargetGuard = "sme-f16f16" in {
def SVMLA_MULTI_VG1x2_F16 : Inst<"svmla_za16[_f16]_vg1x2", "vm22", "h", MergeNone, "aarch64_sme_fmla_vg1x2", [IsStreaming, IsInOutZA], []>;
def SVMLA_MULTI_VG1x4_F16 : Inst<"svmla_za16[_f16]_vg1x4", "vm44", "h", MergeNone, "aarch64_sme_fmla_vg1x4", [IsStreaming, IsInOutZA], []>;
def SVMLS_MULTI_VG1x2_F16 : Inst<"svmls_za16[_f16]_vg1x2", "vm22", "h", MergeNone, "aarch64_sme_fmls_vg1x2", [IsStreaming, IsInOutZA], []>;
def SVMLS_MULTI_VG1x4_F16 : Inst<"svmls_za16[_f16]_vg1x4", "vm44", "h", MergeNone, "aarch64_sme_fmls_vg1x4", [IsStreaming, IsInOutZA], []>;

def SVMLA_SINGLE_VG1x2_F16 : Inst<"svmla[_single]_za16[_f16]_vg1x2", "vm2d", "h", MergeNone, "aarch64_sme_fmla_single_vg1x2", [IsStreaming, IsInOutZA], []>;
def SVMLA_SINGLE_VG1x4_F16 : Inst<"svmla[_single]_za16[_f16]_vg1x4", "vm4d", "h", MergeNone, "aarch64_sme_fmla_single_vg1x4", [IsStreaming, IsInOutZA], []>;
def SVMLS_SINGLE_VG1x2_F16 : Inst<"svmls[_single]_za16[_f16]_vg1x2", "vm2d", "h", MergeNone, "aarch64_sme_fmls_single_vg1x2", [IsStreaming, IsInOutZA], []>;
def SVMLS_SINGLE_VG1x4_F16 : Inst<"svmls[_single]_za16[_f16]_vg1x4", "vm4d", "h", MergeNone, "aarch64_sme_fmls_single_vg1x4", [IsStreaming, IsInOutZA], []>;

def SVMLA_LANE_VG1x2_F16 : Inst<"svmla_lane_za16[_f16]_vg1x2", "vm2di", "h", MergeNone, "aarch64_sme_fmla_lane_vg1x2", [IsStreaming, IsInOutZA], [ImmCheck<3, ImmCheck0_7>]>;
def SVMLA_LANE_VG1x4_F16 : Inst<"svmla_lane_za16[_f16]_vg1x4", "vm4di", "h", MergeNone, "aarch64_sme_fmla_lane_vg1x4", [IsStreaming, IsInOutZA], [ImmCheck<3, ImmCheck0_7>]>;
def SVMLS_LANE_VG1x2_F16 : Inst<"svmls_lane_za16[_f16]_vg1x2", "vm2di", "h", MergeNone, "aarch64_sme_fmls_lane_vg1x2", [IsStreaming, IsInOutZA], [ImmCheck<3, ImmCheck0_7>]>;
def SVMLS_LANE_VG1x4_F16 : Inst<"svmls_lane_za16[_f16]_vg1x4", "vm4di", "h", MergeNone, "aarch64_sme_fmls_lane_vg1x4", [IsStreaming, IsInOutZA], [ImmCheck<3, ImmCheck0_7>]>;
}

let TargetGuard = "sme2,b16b16" in {
def SVMLA_MULTI_VG1x2_BF16 : Inst<"svmla_za16[_bf16]_vg1x2", "vm22", "b", MergeNone, "aarch64_sme_fmla_vg1x2", [IsStreaming, IsInOutZA], []>;
def SVMLA_MULTI_VG1x4_BF16 : Inst<"svmla_za16[_bf16]_vg1x4", "vm44", "b", MergeNone, "aarch64_sme_fmla_vg1x4", [IsStreaming, IsInOutZA], []>;
def SVMLS_MULTI_VG1x2_BF16 : Inst<"svmls_za16[_bf16]_vg1x2", "vm22", "b", MergeNone, "aarch64_sme_fmls_vg1x2", [IsStreaming, IsInOutZA], []>;
def SVMLS_MULTI_VG1x4_BF16 : Inst<"svmls_za16[_bf16]_vg1x4", "vm44", "b", MergeNone, "aarch64_sme_fmls_vg1x4", [IsStreaming, IsInOutZA], []>;

def SVMLA_SINGLE_VG1x2_BF16 : Inst<"svmla[_single]_za16[_bf16]_vg1x2", "vm2d", "b", MergeNone, "aarch64_sme_fmla_single_vg1x2", [IsStreaming, IsInOutZA], []>;
def SVMLA_SINGLE_VG1x4_BF16 : Inst<"svmla[_single]_za16[_bf16]_vg1x4", "vm4d", "b", MergeNone, "aarch64_sme_fmla_single_vg1x4", [IsStreaming, IsInOutZA], []>;
def SVMLS_SINGLE_VG1x2_BF16 : Inst<"svmls[_single]_za16[_bf16]_vg1x2", "vm2d", "b", MergeNone, "aarch64_sme_fmls_single_vg1x2", [IsStreaming, IsInOutZA], []>;
def SVMLS_SINGLE_VG1x4_BF16 : Inst<"svmls[_single]_za16[_bf16]_vg1x4", "vm4d", "b", MergeNone, "aarch64_sme_fmls_single_vg1x4", [IsStreaming, IsInOutZA], []>;

def SVMLA_LANE_VG1x2_BF16 : Inst<"svmla_lane_za16[_bf16]_vg1x2", "vm2di", "b", MergeNone, "aarch64_sme_fmla_lane_vg1x2", [IsStreaming, IsInOutZA], [ImmCheck<3, ImmCheck0_7>]>;
def SVMLA_LANE_VG1x4_BF16 : Inst<"svmla_lane_za16[_bf16]_vg1x4", "vm4di", "b", MergeNone, "aarch64_sme_fmla_lane_vg1x4", [IsStreaming, IsInOutZA], [ImmCheck<3, ImmCheck0_7>]>;
def SVMLS_LANE_VG1x2_BF16 : Inst<"svmls_lane_za16[_bf16]_vg1x2", "vm2di", "b", MergeNone, "aarch64_sme_fmls_lane_vg1x2", [IsStreaming, IsInOutZA], [ImmCheck<3, ImmCheck0_7>]>;
def SVMLS_LANE_VG1x4_BF16 : Inst<"svmls_lane_za16[_bf16]_vg1x4", "vm4di", "b", MergeNone, "aarch64_sme_fmls_lane_vg1x4", [IsStreaming, IsInOutZA], [ImmCheck<3, ImmCheck0_7>]>;
}

// FMLAL/FMLSL/UMLAL/SMLAL
// SMLALL/UMLALL/USMLALL/SUMLALL
let TargetGuard = "sme2" in {
Expand Down
Loading