[all-commits] [llvm/llvm-project] ef4b59: [AArch64] Add intrinsics for SME FP8 FDOT single a...

[Jonathan Thackray via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: ef4b597015db0e558f3a75f2f75d471a1cabe0b6
      https://github.com/llvm/llvm-project/commit/ef4b597015db0e558f3a75f2f75d471a1cabe0b6
  Author: Jonathan Thackray <jonathan.thackray at arm.com>
  Date:   2024-12-16 (Mon, 16 Dec 2024)

  Changed paths:
    M clang/include/clang/Basic/arm_sme.td
    M clang/test/CodeGen/AArch64/sme2-intrinsics/acle_sme2_fp8_fdot.c
    M clang/test/Sema/aarch64-sme2-intrinsics/acle_sme2_fp8_fdot.c
    M llvm/include/llvm/IR/IntrinsicsAArch64.td
    M llvm/lib/Target/AArch64/AArch64SMEInstrInfo.td
    M llvm/lib/Target/AArch64/SMEInstrFormats.td
    M llvm/test/CodeGen/AArch64/sme2-intrinsics-fp8-fdot.ll

  Log Message:
  -----------
  [AArch64] Add intrinsics for SME FP8 FDOT single and multi instructions (#119845)

Add support for the following SME 8 bit floating-point dot-product intrinsics:

```
// Only if __ARM_FEATURE_SME_F8F16 != 0
void svdot[_single]_za16[_mf8]_vg1x2_fpm(uint32_t slice, svmfloat8x2_t zn,
                                         svmfloat8_t zm,
                                         fpm_t fpm) __arm_streaming __arm_inout("za");

void svdot[_single]_za16[_mf8]_vg1x4_fpm(uint32_t slice, svmfloat8x4_t zn,
                                         svmfloat8_t zm,
                                         fpm_t fpm) __arm_streaming __arm_inout("za");

void svdot_za16[_mf8]_vg1x2_fpm(uint32_t slice, svmfloat8x2_t zn,
                                svmfloat8x2_t zm,
                                fpm_t fpm) __arm_streaming __arm_inout("za");

void svdot_za16[_mf8]_vg1x4_fpm(uint32_t slice, svmfloat8x4_t zn,
                                svmfloat8x4_t zm,
                                fpm_t fpm) __arm_streaming __arm_inout("za");

// Only if __ARM_FEATURE_SME_F8F32 != 0
void svdot[_single]_za32[_mf8]_vg1x2_fpm(uint32_t slice, svmfloat8x2_t zn,
                                         svmfloat8_t zm,
                                         fpm_t fpm) __arm_streaming __arm_inout("za");

void svdot[_single]_za32[_mf8]_vg1x4_fpm(uint32_t slice, svmfloat8x4_t zn,
                                         svmfloat8_t zm,
                                         fpm_t fpm) __arm_streaming __arm_inout("za");

void svdot_za32[_mf8]_vg1x2_fpm(uint32_t slice, svmfloat8x2_t zn,
                                svmfloat8x2_t zm,
                                fpm_t fpm) __arm_streaming __arm_inout("za");

void svdot_za32[_mf8]_vg1x4_fpm(uint32_t slice, svmfloat8x4_t zn,
                                svmfloat8x4_t zm,
                                fpm_t fpm) __arm_streaming __arm_inout("za");
```

These intrinsics are extracted from:
https://github.com/ARM-software/acle/pull/323/

Co-authored-by: Momchil Velikov <momchil.velikov at arm.com>
Co-authored-by: Marian Lukac <marian.lukac at arm.com>



To unsubscribe from these emails, change your notification settings at https://github.com/llvm/llvm-project/settings/notifications