Re: [PATCH v2 3/3] aarch64: Add support for fp8fma instructions

2024-12-09 Thread Richard Sandiford
writes: > The AArch64 FEAT_FP8FMA extension introduces instructions for > multiply-add of vectors. > > This patch introduces the following instructions: > 1. {vmlalbq|vmlaltq}_f16_mf8_fpm. > 2. {vmlalbq|vmlaltq}_lane{q}_f16_mf8_fpm. > 3. {vmlallbbq|vmlallbtq|vmlalltbq|vmlallttq}_f32_mf8_fpm. > 4.

[PATCH v2 3/3] aarch64: Add support for fp8fma instructions

2024-11-14 Thread saurabh.jha
The AArch64 FEAT_FP8FMA extension introduces instructions for multiply-add of vectors. This patch introduces the following instructions: 1. {vmlalbq|vmlaltq}_f16_mf8_fpm. 2. {vmlalbq|vmlaltq}_lane{q}_f16_mf8_fpm. 3. {vmlallbbq|vmlallbtq|vmlalltbq|vmlallttq}_f32_mf8_fpm. 4. {vmlallbbq|vmlallbtq|vm