motorhead/qemu
1
0
Fork 0
mirror of https://github.com/Motorhead1991/qemu.git synced 2025-08-22 17:42:10 -06:00
Code Issues Projects Releases Packages Wiki Activity Actions

target/arm: Handle FPCR.AH in negation in FMLS (vector)

Browse source 
Handle the FPCR.AH "don't negate the sign of a NaN" semantics
in FMLS (vector), by implementing a new set of helpers for
the AH=1 case.

The float_muladd_negate_product flag produces the same result
as negating either of the multiplication operands, assuming
neither of the operands are NaNs.  But since FEAT_AFP does not
negate NaNs, this behaviour is exactly what we need.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
This commit is contained in:
Peter Maydell 2025-02-01 16:39:45 +00:00
parent b85d8684c5
commit 1fae4f5e9f
3 changed files with 32 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

4
target/arm/helper.h
View file

@ -782,6 +782,10 @@ DEF_HELPER_FLAGS_5(gvec_vfms_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32)
DEF_HELPER_FLAGS_5(gvec_vfms_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(gvec_vfms_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32)
DEF_HELPER_FLAGS_5(gvec_vfms_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(gvec_vfms_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32)
DEF_HELPER_FLAGS_5(gvec_ah_vfms_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32)
DEF_HELPER_FLAGS_5(gvec_ah_vfms_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32)
DEF_HELPER_FLAGS_5(gvec_ah_vfms_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32)
DEF_HELPER_FLAGS_5(gvec_ftsmul_h, TCG_CALL_NO_RWG, DEF_HELPER_FLAGS_5(gvec_ftsmul_h, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, fpst, i32) void, ptr, ptr, ptr, fpst, i32)
DEF_HELPER_FLAGS_5(gvec_ftsmul_s, TCG_CALL_NO_RWG, DEF_HELPER_FLAGS_5(gvec_ftsmul_s, TCG_CALL_NO_RWG,

7
target/arm/tcg/translate-a64.c
View file

@ -5860,7 +5860,12 @@ static gen_helper_gvec_3_ptr * const f_vector_fmls[3] = {
gen_helper_gvec_vfms_s, gen_helper_gvec_vfms_s,
gen_helper_gvec_vfms_d, gen_helper_gvec_vfms_d,
}; };
TRANS(FMLS_v, do_fp3_vector, a, 0, f_vector_fmls) static gen_helper_gvec_3_ptr * const f_vector_fmls_ah[3] = {
gen_helper_gvec_ah_vfms_h,
gen_helper_gvec_ah_vfms_s,
gen_helper_gvec_ah_vfms_d,
};
TRANS(FMLS_v, do_fp3_vector_2fn, a, 0, f_vector_fmls, f_vector_fmls_ah)
static gen_helper_gvec_3_ptr * const f_vector_fcmeq[3] = { static gen_helper_gvec_3_ptr * const f_vector_fcmeq[3] = {
gen_helper_gvec_fceq_h, gen_helper_gvec_fceq_h,

22
target/arm/tcg/vec_helper.c
View file

@ -1558,6 +1558,24 @@ static float64 float64_mulsub_f(float64 dest, float64 op1, float64 op2,
return float64_muladd(float64_chs(op1), op2, dest, 0, stat); return float64_muladd(float64_chs(op1), op2, dest, 0, stat);
} }
static float16 float16_ah_mulsub_f(float16 dest, float16 op1, float16 op2,
float_status *stat)
{
return float16_muladd(op1, op2, dest, float_muladd_negate_product, stat);
}
static float32 float32_ah_mulsub_f(float32 dest, float32 op1, float32 op2,
float_status *stat)
{
return float32_muladd(op1, op2, dest, float_muladd_negate_product, stat);
}
static float64 float64_ah_mulsub_f(float64 dest, float64 op1, float64 op2,
float_status *stat)
{
return float64_muladd(op1, op2, dest, float_muladd_negate_product, stat);
}
#define DO_MULADD(NAME, FUNC, TYPE) \ #define DO_MULADD(NAME, FUNC, TYPE) \
void HELPER(NAME)(void *vd, void *vn, void *vm, \ void HELPER(NAME)(void *vd, void *vn, void *vm, \
float_status *stat, uint32_t desc) \ float_status *stat, uint32_t desc) \
@ -1584,6 +1602,10 @@ DO_MULADD(gvec_vfms_h, float16_mulsub_f, float16)
DO_MULADD(gvec_vfms_s, float32_mulsub_f, float32) DO_MULADD(gvec_vfms_s, float32_mulsub_f, float32)
DO_MULADD(gvec_vfms_d, float64_mulsub_f, float64) DO_MULADD(gvec_vfms_d, float64_mulsub_f, float64)
DO_MULADD(gvec_ah_vfms_h, float16_ah_mulsub_f, float16)
DO_MULADD(gvec_ah_vfms_s, float32_ah_mulsub_f, float32)
DO_MULADD(gvec_ah_vfms_d, float64_ah_mulsub_f, float64)
/* For the indexed ops, SVE applies the index per 128-bit vector segment. /* For the indexed ops, SVE applies the index per 128-bit vector segment.
* For AdvSIMD, there is of course only one such vector segment. * For AdvSIMD, there is of course only one such vector segment.
*/ */