gemm_f16: Build fails in debug mode for AArch64

[brunocaballero]

Hi,

I created a small Rust example:

use gemm_f16::f16;

fn main() {
    println!("Hello, fp16!");

    let a = f16::from_f32(3.1f32);
    let b = f16::from_f32(2.2f32);
    
    let c = a * b;
    if c.is_normal() {
        println!("Is normal!");
    }
    println!("Result {c}")

}

Building in release mode for target AArch64/Linux works, but it fails when building in debug mode.

error: instruction requires: fullfp16

But I am not sure in which context fillfp16 is not supported, maybe the llvm toolchain?

microdoc@microdoc-tools-builder:~/proj/f16tests$ cargo build --release --target aarch64-unknown-linux-gnu
    Finished `release` profile [optimized] target(s) in 0.02s
microdoc@microdoc-tools-builder:~/proj/f16tests$ cargo build --target aarch64-unknown-linux-gnu
   Compiling reborrow v0.5.5
   Compiling cfg-if v1.0.0
   Compiling libm v0.2.8
   Compiling crossbeam-utils v0.8.20
   Compiling rayon-core v1.12.1
   Compiling either v1.12.0
   Compiling bitflags v1.3.2
   Compiling once_cell v1.19.0
   Compiling num-traits v0.2.19
   Compiling bytemuck v1.16.1
   Compiling raw-cpuid v10.7.0
   Compiling dyn-stack v0.10.0
   Compiling crossbeam-epoch v0.9.18
   Compiling crossbeam-deque v0.8.5
   Compiling rayon v1.10.0
   Compiling num-complex v0.4.6
   Compiling half v2.4.1
   Compiling pulp v0.18.21
   Compiling gemm-common v0.18.0
   Compiling gemm-f32 v0.18.0
   Compiling gemm-f16 v0.18.0
error: instruction requires: fullfp16
    --> /home/microdoc/.cargo/registry/src/index.crates.io-6f17d22bba15001f/gemm-common-0.18.0/src/simd.rs:2000:18
     |
2000 |                 "fmla {0:v}.8h, {1:v}.8h, {2:v}.h[3]",
     |                  ^
     |
note: instantiated into assembly here
    --> <inline asm>:1:2
     |
1    |     fmla v0.8h, v1.8h, v2.h[3]
     |     ^

error: instruction requires: fullfp16
    --> /home/microdoc/.cargo/registry/src/index.crates.io-6f17d22bba15001f/gemm-common-0.18.0/src/simd.rs:2018:18
     |
2018 |                 "fmla {0:v}.8h, {1:v}.8h, {2:v}.h[6]",
     |                  ^
     |
note: instantiated into assembly here
    --> <inline asm>:1:2
     |
1    |     fmla v0.8h, v1.8h, v2.h[6]
     |     ^

error: instruction requires: fullfp16
    --> /home/microdoc/.cargo/registry/src/index.crates.io-6f17d22bba15001f/gemm-common-0.18.0/src/simd.rs:2006:18
     |
2006 |                 "fmla {0:v}.8h, {1:v}.8h, {2:v}.h[4]",
     |                  ^
     |
note: instantiated into assembly here
    --> <inline asm>:1:2
     |
1    |     fmla v0.8h, v1.8h, v2.h[4]
     |     ^

error: instruction requires: fullfp16
    --> /home/microdoc/.cargo/registry/src/index.crates.io-6f17d22bba15001f/gemm-common-0.18.0/src/simd.rs:1988:18
     |
1988 |                 "fmla {0:v}.8h, {1:v}.8h, {2:v}.h[1]",
     |                  ^
     |
note: instantiated into assembly here
    --> <inline asm>:1:2
     |
1    |     fmla v0.8h, v1.8h, v2.h[1]
     |     ^

error: instruction requires: fullfp16
    --> /home/microdoc/.cargo/registry/src/index.crates.io-6f17d22bba15001f/gemm-common-0.18.0/src/simd.rs:2024:18
     |
2024 |                 "fmla {0:v}.8h, {1:v}.8h, {2:v}.h[7]",
     |                  ^
     |
note: instantiated into assembly here
    --> <inline asm>:1:2
     |
1    |     fmla v0.8h, v1.8h, v2.h[7]
     |     ^

error: instruction requires: fullfp16
    --> /home/microdoc/.cargo/registry/src/index.crates.io-6f17d22bba15001f/gemm-common-0.18.0/src/simd.rs:2012:18
     |
2012 |                 "fmla {0:v}.8h, {1:v}.8h, {2:v}.h[5]",
     |                  ^
     |
note: instantiated into assembly here
    --> <inline asm>:1:2
     |
1    |     fmla v0.8h, v1.8h, v2.h[5]
     |     ^

error: instruction requires: fullfp16
    --> /home/microdoc/.cargo/registry/src/index.crates.io-6f17d22bba15001f/gemm-common-0.18.0/src/simd.rs:1982:18
     |
1982 |                 "fmla {0:v}.8h, {1:v}.8h, {2:v}.h[0]",
     |                  ^
     |
note: instantiated into assembly here
    --> <inline asm>:1:2
     |
1    |     fmla v0.8h, v1.8h, v2.h[0]
     |     ^

error: instruction requires: fullfp16
    --> /home/microdoc/.cargo/registry/src/index.crates.io-6f17d22bba15001f/gemm-common-0.18.0/src/simd.rs:1994:18
     |
1994 |                 "fmla {0:v}.8h, {1:v}.8h, {2:v}.h[2]",
     |                  ^
     |
note: instantiated into assembly here
    --> <inline asm>:1:2
     |
1    |     fmla v0.8h, v1.8h, v2.h[2]
     |     ^

error: instruction requires: fullfp16
    --> /home/microdoc/.cargo/registry/src/index.crates.io-6f17d22bba15001f/gemm-common-0.18.0/src/simd.rs:1954:18
     |
1954 |                 "fadd {0:v}.8h, {1:v}.8h, {2:v}.8h",
     |                  ^
     |
note: instantiated into assembly here
    --> <inline asm>:1:2
     |
1    |     fadd v0.8h, v1.8h, v2.8h
     |     ^

error: instruction requires: fullfp16
    --> /home/microdoc/.cargo/registry/src/index.crates.io-6f17d22bba15001f/gemm-common-0.18.0/src/simd.rs:1966:18
     |
1966 |                 "fmla {0:v}.8h, {1:v}.8h, {2:v}.8h",
     |                  ^
     |
note: instantiated into assembly here
    --> <inline asm>:1:2
     |
1    |     fmla v0.8h, v1.8h, v2.8h
     |     ^

error: instruction requires: fullfp16
    --> /home/microdoc/.cargo/registry/src/index.crates.io-6f17d22bba15001f/gemm-common-0.18.0/src/simd.rs:1940:18
     |
1940 |                 "fmul {0:v}.8h, {1:v}.8h, {2:v}.8h",
     |                  ^
     |
note: instantiated into assembly here
    --> <inline asm>:1:2
     |
1    |     fmul v0.8h, v1.8h, v2.8h
     |     ^

error: could not compile `gemm-f16` (lib) due to 11 previous errors