llvm-project

c2172431 - [AArch64] Implements FP8 SVE intrinsics for dot-product (#118125)

[AArch64] Implements FP8 SVE intrinsics for dot-product (#118125) This patch adds the following intrinsics: * 8-bit floating-point dot product to single-precision. // Only if (__ARM_FEATURE_SVE2 && __ARM_FEATURE_FP8DOT4) || __ARM_FEATURE_SSVE_FP8DOT4 svfloat32_t svdot[_f32_mf8]_fpm(svfloat32_t zda, svmfloat8_t zn, svmfloat8_t zm, fpm_t fpm); svfloat32_t svdot[_n_f32_mf8]_fpm(svfloat32_t zda, svmfloat8_t zn, mfloat8_t zm, fpm_t fpm); * 8-bit floating-point indexed dot product to single-precision. // Only if (__ARM_FEATURE_SVE2 && __ARM_FEATURE_FP8DOT4) || __ARM_FEATURE_SSVE_FP8DOT4 svfloat32_t svdot_lane[_f32_mf8]_fpm(svfloat32_t zda, svmfloat8_t zn, svmfloat8_t zm, uint64_t imm0_3, fpm_t fpm); * 8-bit floating-point dot product to half-precision. // Only if (__ARM_FEATURE_SVE2 && __ARM_FEATURE_FP8DOT2) || __ARM_FEATURE_SSVE_FP8DOT2 svfloat16_t svdot[_f16_mf8]_fpm(svfloat16_t zda, svmfloat8_t zn, svmfloat8_t zm, fpm_t fpm); svfloat16_t svdot[_n_f16_mf8]_fpm(svfloat16_t zda, svmfloat8_t zn, mfloat8_t zm, fpm_t fpm); * 8-bit floating-point indexed dot product to half-precision. // Only if (__ARM_FEATURE_SVE2 && __ARM_FEATURE_FP8DOT2) || __ARM_FEATURE_SSVE_FP8DOT2 svfloat16_t svdot_lane[_f16_mf8]_fpm(svfloat16_t zda, svmfloat8_t zn, svmfloat8_t zm, uint64_t imm0_7, fpm_t fpm);