mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-22 18:54:02 +01:00
74a8dfdced
Summary: This patch introduces command-line support for the Armv8.6-a architecture and assembly support for BFloat16. Details can be found https://community.arm.com/developer/ip-products/processors/b/processors-ip-blog/posts/arm-architecture-developments-armv8-6-a in addition to the GCC patch for the 8..6-a CLI: https://gcc.gnu.org/legacy-ml/gcc-patches/2019-11/msg02647.html In detail this patch - march options for armv8.6-a - BFloat16 assembly This is part of a patch series, starting with command-line and Bfloat16 assembly support. The subsequent patches will upstream intrinsics support for BFloat16, followed by Matrix Multiplication and the remaining Virtualization features of the armv8.6-a architecture. Based on work by: - labrinea - MarkMurrayARM - Luke Cheeseman - Javed Asbar - Mikhail Maltsev - Luke Geeson Reviewers: SjoerdMeijer, craig.topper, rjmccall, jfb, LukeGeeson Reviewed By: SjoerdMeijer Subscribers: stuij, kristof.beyls, hiraditya, dexonsmith, danielkiss, cfe-commits, llvm-commits Tags: #clang, #llvm Differential Revision: https://reviews.llvm.org/D76062
58 lines
2.3 KiB
ArmAsm
58 lines
2.3 KiB
ArmAsm
// RUN: not llvm-mc -triple arm -mattr=+bf16,-neon %s -o /dev/null 2>&1 | FileCheck %s --check-prefixes=NONEON,ALL
|
|
// RUN: not llvm-mc -triple arm -mattr=-bf16 %s -o /dev/null 2>&1 | FileCheck %s --check-prefixes=NOBF16,ALL
|
|
// RUN: not llvm-mc -triple arm %s -o /dev/null 2>&1 | FileCheck %s --check-prefixes=NONEON,ALL
|
|
//
|
|
vdot.bf16 d3, d4, d5
|
|
vdot.bf16 q0, q1, q2
|
|
vdot.bf16 d3, d4, d5[1]
|
|
vdot.bf16 q0, q1, d5[1]
|
|
vmmla.bf16 q0, q1, q2
|
|
vcvt.bf16.f32 d1, q3
|
|
vcvtbeq.bf16.f32 s1, s3
|
|
vcvttne.bf16.f32 s1, s3
|
|
// NOBF16: error: instruction requires: BFloat16 floating point extension
|
|
// NOBF16-NEXT: vdot.bf16 d3, d4, d5
|
|
// NOBF16-NEXT: ^
|
|
// NOBF16-NEXT: error: instruction requires: BFloat16 floating point extension
|
|
// NOBF16-NEXT: vdot.bf16 q0, q1, q2
|
|
// NOBF16-NEXT: ^
|
|
// NOBF16-NEXT: error: instruction requires: BFloat16 floating point extension
|
|
// NOBF16-NEXT: vdot.bf16 d3, d4, d5[1]
|
|
// NOBF16-NEXT: ^
|
|
// NOBF16-NEXT: error: instruction requires: BFloat16 floating point extension
|
|
// NOBF16-NEXT: vdot.bf16 q0, q1, d5[1]
|
|
// NOBF16-NEXT: ^
|
|
// NOBF16-NEXT: error: instruction requires: BFloat16 floating point extension
|
|
// NOBF16-NEXT: vmmla.bf16 q0, q1, q2
|
|
// NOBF16-NEXT: ^
|
|
// NOBF16-NEXT: error: instruction requires: BFloat16 floating point extension
|
|
// NOBF16-NEXT: vcvt.bf16.f32 d1, q3
|
|
// NOBF16-NEXT: ^
|
|
|
|
// NONEON: error: instruction requires: BFloat16 floating point extension NEON
|
|
// NONEON-NEXT: vdot.bf16 d3, d4, d5
|
|
// NONEON-NEXT: ^
|
|
// NONEON-NEXT: error: instruction requires: BFloat16 floating point extension NEON
|
|
// NONEON-NEXT: vdot.bf16 q0, q1, q2
|
|
// NONEON-NEXT: ^
|
|
// NONEON-NEXT: error: instruction requires: BFloat16 floating point extension NEON
|
|
// NONEON-NEXT: vdot.bf16 d3, d4, d5[1]
|
|
// NONEON-NEXT: ^
|
|
// NONEON-NEXT: error: instruction requires: BFloat16 floating point extension NEON
|
|
// NONEON-NEXT: vdot.bf16 q0, q1, d5[1]
|
|
// NONEON-NEXT: ^
|
|
// NONEON-NEXT: error: instruction requires: BFloat16 floating point extension NEON
|
|
// NONEON-NEXT: vmmla.bf16 q0, q1, q2
|
|
// NONEON-NEXT: ^
|
|
// NONEON-NEXT: error: instruction requires: BFloat16 floating point extension NEON
|
|
// NONEON-NEXT: vcvt.bf16.f32 d1, q3
|
|
// NONEON-NEXT: ^
|
|
|
|
|
|
// ALL-NEXT: error: instruction requires: BFloat16 floating point extension
|
|
// ALL-NEXT: vcvtbeq.bf16.f32 s1, s3
|
|
// ALL-NEXT: ^
|
|
// ALL-NEXT: error: instruction requires: BFloat16 floating point extension
|
|
// ALL-NEXT: vcvttne.bf16.f32 s1, s3
|
|
// ALL-NEXT: ^
|