[all-commits] [llvm/llvm-project] 908e30: [AArch64] Implement intrinsics for FP8 SME FMLAL/F...

[SpencerAbson via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 908e30658ddf634f7c929f0c7e78dd40405c795a
      https://github.com/llvm/llvm-project/commit/908e30658ddf634f7c929f0c7e78dd40405c795a
  Author: SpencerAbson <Spencer.Abson at arm.com>
  Date:   2024-12-17 (Tue, 17 Dec 2024)

  Changed paths:
    M clang/include/clang/Basic/arm_sme.td
    M clang/test/CodeGen/AArch64/fp8-intrinsics/acle_sme2_fp8_mla.c
    M clang/test/Sema/aarch64-fp8-intrinsics/acle_sme2_fp8_mla.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-fp8-intrinsics-mla.ll

  Log Message:
  -----------
  [AArch64] Implement intrinsics for FP8 SME FMLAL/FMLALL (multi) (#119546)

This patch implements the following intrinsics:

Multi-vector 8-bit floating-point multiply-add long (multiple vectors).

``` c
// Only if __ARM_FEATURE_SME_F8F16 != 0
void svmla_za16[_mf8]_vg2x2_fpm(uint32_t slice, svmfloat8x2_t zn, svmfloat8x2_t zm,
                                fpm_t fpm) __arm_streaming __arm_inout("za");

void svmla_za16[_mf8]_vg2x4_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 svmla_za32[_mf8]_vg4x2_fpm(uint32_t slice, svmfloat8x2_t zn, svmfloat8x2_t zm,
                                fpm_t fpm) __arm_streaming __arm_inout("za");

void svmla_za32[_mf8]_vg4x4_fpm(uint32_t slice, svmfloat8x4_t zn, svmfloat8x4_t zm,
                                fpm_t fpm) __arm_streaming __arm_inout("za");                              
```

In accordance with https://github.com/ARM-software/acle/pull/323



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