[all-commits] [llvm/llvm-project] 804b81: [AArch64] Add FP8 Neon intrinsics for dot-product ...

[Momchil Velikov via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 804b81d39f2d50743fd2090aed72dad29f5fb388
      https://github.com/llvm/llvm-project/commit/804b81d39f2d50743fd2090aed72dad29f5fb388
  Author: Momchil Velikov <momchil.velikov at arm.com>
  Date:   2025-01-27 (Mon, 27 Jan 2025)

  Changed paths:
    M clang/include/clang/Basic/arm_neon.td
    M clang/include/clang/Basic/arm_neon_incl.td
    M clang/lib/CodeGen/CGBuiltin.cpp
    M clang/lib/CodeGen/CodeGenFunction.h
    A clang/test/CodeGen/AArch64/fp8-intrinsics/acle_neon_fp8_fdot.c
    A clang/test/Sema/aarch64-fp8-intrinsics/acle_neon_fp8_fdot.c
    M llvm/include/llvm/IR/IntrinsicsAArch64.td
    M llvm/lib/Target/AArch64/AArch64InstrFormats.td
    M llvm/lib/Target/AArch64/AArch64InstrInfo.td
    A llvm/test/CodeGen/AArch64/fp8-neon-fdot.ll

  Log Message:
  -----------
  [AArch64] Add FP8 Neon intrinsics for dot-product (#123613)

This patch adds the following intrinsics:

float16x4_t vdot_f16_mf8_fpm(float16x4_t vd, mfloat8x8_t vn, mfloat8x8_t
vm, fpm_t fpm)
float16x8_t vdotq_f16_mf8_fpm(float16x8_t vd, mfloat8x16_t vn,
mfloat8x16_t vm, fpm_t fpm)
    
float16x4_t vdot_lane_f16_mf8_fpm(float16x4_t vd, mfloat8x8_t vn,
mfloat8x8_t vm, __builtin_constant_p(lane), fpm_t fpm)
float16x4_t vdot_laneq_f16_mf8_fpm(float16x4_t vd, mfloat8x8_t vn,
mfloat8x16_t vm, __builtin_constant_p(lane), fpm_t fpm)
float16x8_t vdotq_lane_f16_mf8_fpm(float16x8_t vd, mfloat8x16_t vn,
mfloat8x8_t vm, __builtin_constant_p(lane), fpm_t fpm)
float16x8_t vdotq_laneq_f16_mf8_fpm(float16x8_t vd, mfloat8x16_t vn,
mfloat8x16_t vm, __builtin_constant_p(lane), fpm_t fpm)
    
float32x2_t vdot_f32_mf8_fpm(float32x2_t vd, mfloat8x8_t vn, mfloat8x8_t
vm, fpm_t fpm)
float32x4_t vdotq_f32_mf8_fpm(float32x4_t vd, mfloat8x16_t vn,
mfloat8x16_t vm, fpm_t fpm)

float32x2_t vdot_lane_f32_mf8_fpm(float32x2_t vd, mfloat8x8_t vn,
mfloat8x8_t vm, __builtin_constant_p(lane), fpm_t fpm)
float32x2_t vdot_laneq_f32_mf8_fpm(float32x2_t vd, mfloat8x8_t vn,
mfloat8x16_t vm, __builtin_constant_p(lane), fpm_t fpm)
float32x4_t vdotq_lane_f32_mf8_fpm(float32x4_t vd, mfloat8x16_t vn,
mfloat8x8_t vm, __builtin_constant_p(lane), fpm_t fpm)
float32x4_t vdotq_laneq_f32_mf8_fpm(float32x4_t vd, mfloat8x16_t vn,
mfloat8x16_t vm, __builtin_constant_p(lane), fpm_t fpm)



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