mirror of
https://github.com/yuzu-emu/unicorn.git
synced 2024-12-23 01:05:36 +00:00
target/arm: Fix VUDOT/VSDOT (scalar) on big-endian hosts
The helper functions for performing the udot/sdot operations against a scalar were not using an address-swizzling macro when converting the index of the scalar element into a pointer into the vm array. This had no effect on little-endian hosts but meant we generated incorrect results on big-endian hosts. For these insns, the index is indexing over group of 4 8-bit values, so 32 bits per indexed entity, and H4() is therefore what we want. (For Neon the only possible input indexes are 0 and 1.) Backports d1a9254be5cc93afb15be19f7543da6ff4806256
This commit is contained in:
parent
5c6730a432
commit
6b8096d9fc
|
@ -294,7 +294,7 @@ void HELPER(gvec_sdot_idx_b)(void *vd, void *vn, void *vm, uint32_t desc)
|
|||
intptr_t index = simd_data(desc);
|
||||
uint32_t *d = vd;
|
||||
int8_t *n = vn;
|
||||
int8_t *m_indexed = (int8_t *)vm + index * 4;
|
||||
int8_t *m_indexed = (int8_t *)vm + H4(index) * 4;
|
||||
|
||||
/* Notice the special case of opr_sz == 8, from aa64/aa32 advsimd.
|
||||
* Otherwise opr_sz is a multiple of 16.
|
||||
|
@ -325,7 +325,7 @@ void HELPER(gvec_udot_idx_b)(void *vd, void *vn, void *vm, uint32_t desc)
|
|||
intptr_t index = simd_data(desc);
|
||||
uint32_t *d = vd;
|
||||
uint8_t *n = vn;
|
||||
uint8_t *m_indexed = (uint8_t *)vm + index * 4;
|
||||
uint8_t *m_indexed = (uint8_t *)vm + H4(index) * 4;
|
||||
|
||||
/* Notice the special case of opr_sz == 8, from aa64/aa32 advsimd.
|
||||
* Otherwise opr_sz is a multiple of 16.
|
||||
|
|
Loading…
Reference in a new issue