Skip to content

Rename vmmlaq_f16_f16 to vmmlaq_f16 #443

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
acoplan-arm merged 1 commit into from
Jul 14, 2026
+9 −7
Merged

Rename vmmlaq_f16_f16 to vmmlaq_f16 #443

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
9 changes: 5 additions & 4 deletions neon_intrinsics/advsimd.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -170,10 +170,11 @@ for more information about Arm’s trademarks.
floating point conversion intrinsics from "Half Precision to 32-bit"
and "Half Precision to 64-bit".

### Changes for next release
### Changes since 2026Q1

* Added support for FEAT_F16F32DOT
* Added support for FEAT_F16F32MM and FEAT_F16MM
* Renamed vmmlaq_f16_f16 to vmmlaq_f16

<!---
**** Do not remove! ****
Expand Down Expand Up @@ -6251,6 +6252,6 @@ The intrinsics in this section are guarded by the macro ``__ARM_NEON``.

#### Matrix multiply

| Intrinsic | Argument preparation | AArch64 Instruction | Result | Supported architectures |
|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|----------------------------------------------|-----------------------------|-------------------|---------------------------|
| <code>float16x8_t <a href="https://developer.arm.com/architectures/instruction-sets/intrinsics/vmmlaq_f16_f16" target="_blank">vmmlaq_f16_f16</a>(<br>&nbsp;&nbsp;&nbsp;&nbsp; float16x8_t r,<br>&nbsp;&nbsp;&nbsp;&nbsp; float16x8_t a,<br>&nbsp;&nbsp;&nbsp;&nbsp; float16x8_t b)</code> | `r -> Vd.8H`<br>`a -> Vn.8H`<br>`b -> Vm.8H` | `FMMLA Vd.8H, Vn.8H, Vm.8H` | `Vd.8H -> result` | `A64` |
| Intrinsic | Argument preparation | AArch64 Instruction | Result | Supported architectures |
|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|----------------------------------------------|-----------------------------|-------------------|---------------------------|
| <code>float16x8_t <a href="https://developer.arm.com/architectures/instruction-sets/intrinsics/vmmlaq_f16" target="_blank">vmmlaq_f16</a>(<br>&nbsp;&nbsp;&nbsp;&nbsp; float16x8_t r,<br>&nbsp;&nbsp;&nbsp;&nbsp; float16x8_t a,<br>&nbsp;&nbsp;&nbsp;&nbsp; float16x8_t b)</code> | `r -> Vd.8H`<br>`a -> Vn.8H`<br>`b -> Vm.8H` | `FMMLA Vd.8H, Vn.8H, Vm.8H` | `Vd.8H -> result` | `A64` |
3 changes: 2 additions & 1 deletion neon_intrinsics/advsimd.template.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -170,10 +170,11 @@ for more information about Arm’s trademarks.
floating point conversion intrinsics from "Half Precision to 32-bit"
and "Half Precision to 64-bit".

### Changes for next release
### Changes since 2026Q1

* Added support for FEAT_F16F32DOT
* Added support for FEAT_F16F32MM and FEAT_F16MM
* Renamed vmmlaq_f16_f16 to vmmlaq_f16

<!---
**** Do not remove! ****
Expand Down
2 changes: 1 addition & 1 deletion tools/intrinsic_db/advsimd.csv
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4848,4 +4848,4 @@ float32x4_t vdotq_lane_f32_f16(float32x4_t r, float16x8_t a, float16x4_t b, __bu
float32x4_t vmmlaq_f32_f16(float32x4_t r, float16x8_t a, float16x8_t b) r -> Vd.4S;a -> Vn.8H;b -> Vm.8H FMMLA Vd.4S, Vn.8H, Vm.8H Vd.4S -> result A64

<SECTION> Non-widening half-precision matrix multiply instruction. Requires the +f16mm architecture extension.
float16x8_t vmmlaq_f16_f16(float16x8_t r, float16x8_t a, float16x8_t b) r -> Vd.8H;a -> Vn.8H;b -> Vm.8H FMMLA Vd.8H, Vn.8H, Vm.8H Vd.8H -> result A64
float16x8_t vmmlaq_f16(float16x8_t r, float16x8_t a, float16x8_t b) r -> Vd.8H;a -> Vn.8H;b -> Vm.8H FMMLA Vd.8H, Vn.8H, Vm.8H Vd.8H -> result A64
2 changes: 1 addition & 1 deletion tools/intrinsic_db/advsimd_classification.csv
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4726,4 +4726,4 @@ vdotq_laneq_f32_f16 Vector arithmetic|Dot product
vdot_laneq_f32_f16 Vector arithmetic|Dot product
vdotq_lane_f32_f16 Vector arithmetic|Dot product
vmmlaq_f32_f16 Vector arithmetic|Matrix multiply
vmmlaq_f16_f16 Vector arithmetic|Matrix multiply
vmmlaq_f16 Vector arithmetic|Matrix multiply
Loading