| Message ID | 20181218063911.2112-16-richard.henderson@linaro.org |
|---|---|
| State | New |
| Headers | show |
| Series | tcg, target/ppc vector improvements | expand |
On Mon, Dec 17, 2018 at 10:38:52PM -0800, Richard Henderson wrote: > From: Mark Cave-Ayland <mark.cave-ayland@ilande.co.uk> > > Since the VSX registers are actually a superset of the VMX registers then they > can be represented by the same type. Merge ppc_avr_t into ppc_vsr_t and change > ppc_avr_t to be a simple typedef alias. > > Note that due to a difference in the naming of the float32 member between > ppc_avr_t and ppc_vsr_t, references to the ppc_avr_t f member must be replaced > with f32 instead. > > Signed-off-by: Mark Cave-Ayland <mark.cave-ayland@ilande.co.uk> Acked-by: David Gibson <david@gibson.dropbear.id.au> > Message-Id: <20181217122405.18732-7-mark.cave-ayland@ilande.co.uk> > --- > target/ppc/cpu.h | 17 +++++++------ > target/ppc/internal.h | 11 -------- > target/ppc/int_helper.c | 56 +++++++++++++++++++++-------------------- > 3 files changed, 39 insertions(+), 45 deletions(-) > > diff --git a/target/ppc/cpu.h b/target/ppc/cpu.h > index ab68abe8a2..5445d4c3c1 100644 > --- a/target/ppc/cpu.h > +++ b/target/ppc/cpu.h > @@ -230,7 +230,6 @@ typedef struct opc_handler_t opc_handler_t; > /* Types used to describe some PowerPC registers etc. */ > typedef struct DisasContext DisasContext; > typedef struct ppc_spr_t ppc_spr_t; > -typedef union ppc_avr_t ppc_avr_t; > typedef union ppc_tlb_t ppc_tlb_t; > typedef struct ppc_hash_pte64 ppc_hash_pte64_t; > > @@ -254,22 +253,26 @@ struct ppc_spr_t { > #endif > }; > > -/* Altivec registers (128 bits) */ > -union ppc_avr_t { > - float32 f[4]; > +/* VSX/Altivec registers (128 bits) */ > +typedef union _ppc_vsr_t { > uint8_t u8[16]; > uint16_t u16[8]; > uint32_t u32[4]; > + uint64_t u64[2]; > int8_t s8[16]; > int16_t s16[8]; > int32_t s32[4]; > - uint64_t u64[2]; > int64_t s64[2]; > + float32 f32[4]; > + float64 f64[2]; > + float128 f128; > #ifdef CONFIG_INT128 > __uint128_t u128; > #endif > - Int128 s128; > -}; > + Int128 s128; > +} ppc_vsr_t; > + > +typedef ppc_vsr_t ppc_avr_t; > > #if !defined(CONFIG_USER_ONLY) > /* Software TLB cache */ > diff --git a/target/ppc/internal.h b/target/ppc/internal.h > index a9bcadff42..b4b1f7b3db 100644 > --- a/target/ppc/internal.h > +++ b/target/ppc/internal.h > @@ -204,17 +204,6 @@ EXTRACT_HELPER(IMM8, 11, 8); > EXTRACT_HELPER(DCMX, 16, 7); > EXTRACT_HELPER_SPLIT_3(DCMX_XV, 5, 16, 0, 1, 2, 5, 1, 6, 6); > > -typedef union _ppc_vsr_t { > - uint8_t u8[16]; > - uint16_t u16[8]; > - uint32_t u32[4]; > - uint64_t u64[2]; > - float32 f32[4]; > - float64 f64[2]; > - float128 f128; > - Int128 s128; > -} ppc_vsr_t; > - > #if defined(HOST_WORDS_BIGENDIAN) > #define VsrB(i) u8[i] > #define VsrH(i) u16[i] > diff --git a/target/ppc/int_helper.c b/target/ppc/int_helper.c > index fcac90a4a9..9d715be25c 100644 > --- a/target/ppc/int_helper.c > +++ b/target/ppc/int_helper.c > @@ -548,8 +548,8 @@ VARITH_DO(muluwm, *, u32) > { \ > int i; \ > \ > - for (i = 0; i < ARRAY_SIZE(r->f); i++) { \ > - r->f[i] = func(a->f[i], b->f[i], &env->vec_status); \ > + for (i = 0; i < ARRAY_SIZE(r->f32); i++) { \ > + r->f32[i] = func(a->f32[i], b->f32[i], &env->vec_status); \ > } \ > } > VARITHFP(addfp, float32_add) > @@ -563,9 +563,9 @@ VARITHFP(maxfp, float32_max) > ppc_avr_t *b, ppc_avr_t *c) \ > { \ > int i; \ > - for (i = 0; i < ARRAY_SIZE(r->f); i++) { \ > - r->f[i] = float32_muladd(a->f[i], c->f[i], b->f[i], \ > - type, &env->vec_status); \ > + for (i = 0; i < ARRAY_SIZE(r->f32); i++) { \ > + r->f32[i] = float32_muladd(a->f32[i], c->f32[i], b->f32[i], \ > + type, &env->vec_status); \ > } \ > } > VARITHFPFMA(maddfp, 0); > @@ -670,9 +670,9 @@ VABSDU(w, u32) > { \ > int i; \ > \ > - for (i = 0; i < ARRAY_SIZE(r->f); i++) { \ > + for (i = 0; i < ARRAY_SIZE(r->f32); i++) { \ > float32 t = cvt(b->element[i], &env->vec_status); \ > - r->f[i] = float32_scalbn(t, -uim, &env->vec_status); \ > + r->f32[i] = float32_scalbn(t, -uim, &env->vec_status); \ > } \ > } > VCF(ux, uint32_to_float32, u32) > @@ -782,9 +782,9 @@ VCMPNE(w, u32, uint32_t, 0) > uint32_t none = 0; \ > int i; \ > \ > - for (i = 0; i < ARRAY_SIZE(r->f); i++) { \ > + for (i = 0; i < ARRAY_SIZE(r->f32); i++) { \ > uint32_t result; \ > - int rel = float32_compare_quiet(a->f[i], b->f[i], \ > + int rel = float32_compare_quiet(a->f32[i], b->f32[i], \ > &env->vec_status); \ > if (rel == float_relation_unordered) { \ > result = 0; \ > @@ -816,14 +816,16 @@ static inline void vcmpbfp_internal(CPUPPCState *env, ppc_avr_t *r, > int i; > int all_in = 0; > > - for (i = 0; i < ARRAY_SIZE(r->f); i++) { > - int le_rel = float32_compare_quiet(a->f[i], b->f[i], &env->vec_status); > + for (i = 0; i < ARRAY_SIZE(r->f32); i++) { > + int le_rel = float32_compare_quiet(a->f32[i], b->f32[i], > + &env->vec_status); > if (le_rel == float_relation_unordered) { > r->u32[i] = 0xc0000000; > all_in = 1; > } else { > - float32 bneg = float32_chs(b->f[i]); > - int ge_rel = float32_compare_quiet(a->f[i], bneg, &env->vec_status); > + float32 bneg = float32_chs(b->f32[i]); > + int ge_rel = float32_compare_quiet(a->f32[i], bneg, > + &env->vec_status); > int le = le_rel != float_relation_greater; > int ge = ge_rel != float_relation_less; > > @@ -856,11 +858,11 @@ void helper_vcmpbfp_dot(CPUPPCState *env, ppc_avr_t *r, ppc_avr_t *a, > float_status s = env->vec_status; \ > \ > set_float_rounding_mode(float_round_to_zero, &s); \ > - for (i = 0; i < ARRAY_SIZE(r->f); i++) { \ > - if (float32_is_any_nan(b->f[i])) { \ > + for (i = 0; i < ARRAY_SIZE(r->f32); i++) { \ > + if (float32_is_any_nan(b->f32[i])) { \ > r->element[i] = 0; \ > } else { \ > - float64 t = float32_to_float64(b->f[i], &s); \ > + float64 t = float32_to_float64(b->f32[i], &s); \ > int64_t j; \ > \ > t = float64_scalbn(t, uim, &s); \ > @@ -1661,8 +1663,8 @@ void helper_vrefp(CPUPPCState *env, ppc_avr_t *r, ppc_avr_t *b) > { > int i; > > - for (i = 0; i < ARRAY_SIZE(r->f); i++) { > - r->f[i] = float32_div(float32_one, b->f[i], &env->vec_status); > + for (i = 0; i < ARRAY_SIZE(r->f32); i++) { > + r->f32[i] = float32_div(float32_one, b->f32[i], &env->vec_status); > } > } > > @@ -1674,8 +1676,8 @@ void helper_vrefp(CPUPPCState *env, ppc_avr_t *r, ppc_avr_t *b) > float_status s = env->vec_status; \ > \ > set_float_rounding_mode(rounding, &s); \ > - for (i = 0; i < ARRAY_SIZE(r->f); i++) { \ > - r->f[i] = float32_round_to_int (b->f[i], &s); \ > + for (i = 0; i < ARRAY_SIZE(r->f32); i++) { \ > + r->f32[i] = float32_round_to_int (b->f32[i], &s); \ > } \ > } > VRFI(n, float_round_nearest_even) > @@ -1705,10 +1707,10 @@ void helper_vrsqrtefp(CPUPPCState *env, ppc_avr_t *r, ppc_avr_t *b) > { > int i; > > - for (i = 0; i < ARRAY_SIZE(r->f); i++) { > - float32 t = float32_sqrt(b->f[i], &env->vec_status); > + for (i = 0; i < ARRAY_SIZE(r->f32); i++) { > + float32 t = float32_sqrt(b->f32[i], &env->vec_status); > > - r->f[i] = float32_div(float32_one, t, &env->vec_status); > + r->f32[i] = float32_div(float32_one, t, &env->vec_status); > } > } > > @@ -1751,8 +1753,8 @@ void helper_vexptefp(CPUPPCState *env, ppc_avr_t *r, ppc_avr_t *b) > { > int i; > > - for (i = 0; i < ARRAY_SIZE(r->f); i++) { > - r->f[i] = float32_exp2(b->f[i], &env->vec_status); > + for (i = 0; i < ARRAY_SIZE(r->f32); i++) { > + r->f32[i] = float32_exp2(b->f32[i], &env->vec_status); > } > } > > @@ -1760,8 +1762,8 @@ void helper_vlogefp(CPUPPCState *env, ppc_avr_t *r, ppc_avr_t *b) > { > int i; > > - for (i = 0; i < ARRAY_SIZE(r->f); i++) { > - r->f[i] = float32_log2(b->f[i], &env->vec_status); > + for (i = 0; i < ARRAY_SIZE(r->f32); i++) { > + r->f32[i] = float32_log2(b->f32[i], &env->vec_status); > } > } > -- David Gibson | I'll have my music baroque, and my code david AT gibson.dropbear.id.au | minimalist, thank you. NOT _the_ _other_ | _way_ _around_! http://www.ozlabs.org/~dgibson
diff --git a/target/ppc/cpu.h b/target/ppc/cpu.h index ab68abe8a2..5445d4c3c1 100644 --- a/target/ppc/cpu.h +++ b/target/ppc/cpu.h @@ -230,7 +230,6 @@ typedef struct opc_handler_t opc_handler_t; /* Types used to describe some PowerPC registers etc. */ typedef struct DisasContext DisasContext; typedef struct ppc_spr_t ppc_spr_t; -typedef union ppc_avr_t ppc_avr_t; typedef union ppc_tlb_t ppc_tlb_t; typedef struct ppc_hash_pte64 ppc_hash_pte64_t; @@ -254,22 +253,26 @@ struct ppc_spr_t { #endif }; -/* Altivec registers (128 bits) */ -union ppc_avr_t { - float32 f[4]; +/* VSX/Altivec registers (128 bits) */ +typedef union _ppc_vsr_t { uint8_t u8[16]; uint16_t u16[8]; uint32_t u32[4]; + uint64_t u64[2]; int8_t s8[16]; int16_t s16[8]; int32_t s32[4]; - uint64_t u64[2]; int64_t s64[2]; + float32 f32[4]; + float64 f64[2]; + float128 f128; #ifdef CONFIG_INT128 __uint128_t u128; #endif - Int128 s128; -}; + Int128 s128; +} ppc_vsr_t; + +typedef ppc_vsr_t ppc_avr_t; #if !defined(CONFIG_USER_ONLY) /* Software TLB cache */ diff --git a/target/ppc/internal.h b/target/ppc/internal.h index a9bcadff42..b4b1f7b3db 100644 --- a/target/ppc/internal.h +++ b/target/ppc/internal.h @@ -204,17 +204,6 @@ EXTRACT_HELPER(IMM8, 11, 8); EXTRACT_HELPER(DCMX, 16, 7); EXTRACT_HELPER_SPLIT_3(DCMX_XV, 5, 16, 0, 1, 2, 5, 1, 6, 6); -typedef union _ppc_vsr_t { - uint8_t u8[16]; - uint16_t u16[8]; - uint32_t u32[4]; - uint64_t u64[2]; - float32 f32[4]; - float64 f64[2]; - float128 f128; - Int128 s128; -} ppc_vsr_t; - #if defined(HOST_WORDS_BIGENDIAN) #define VsrB(i) u8[i] #define VsrH(i) u16[i] diff --git a/target/ppc/int_helper.c b/target/ppc/int_helper.c index fcac90a4a9..9d715be25c 100644 --- a/target/ppc/int_helper.c +++ b/target/ppc/int_helper.c @@ -548,8 +548,8 @@ VARITH_DO(muluwm, *, u32) { \ int i; \ \ - for (i = 0; i < ARRAY_SIZE(r->f); i++) { \ - r->f[i] = func(a->f[i], b->f[i], &env->vec_status); \ + for (i = 0; i < ARRAY_SIZE(r->f32); i++) { \ + r->f32[i] = func(a->f32[i], b->f32[i], &env->vec_status); \ } \ } VARITHFP(addfp, float32_add) @@ -563,9 +563,9 @@ VARITHFP(maxfp, float32_max) ppc_avr_t *b, ppc_avr_t *c) \ { \ int i; \ - for (i = 0; i < ARRAY_SIZE(r->f); i++) { \ - r->f[i] = float32_muladd(a->f[i], c->f[i], b->f[i], \ - type, &env->vec_status); \ + for (i = 0; i < ARRAY_SIZE(r->f32); i++) { \ + r->f32[i] = float32_muladd(a->f32[i], c->f32[i], b->f32[i], \ + type, &env->vec_status); \ } \ } VARITHFPFMA(maddfp, 0); @@ -670,9 +670,9 @@ VABSDU(w, u32) { \ int i; \ \ - for (i = 0; i < ARRAY_SIZE(r->f); i++) { \ + for (i = 0; i < ARRAY_SIZE(r->f32); i++) { \ float32 t = cvt(b->element[i], &env->vec_status); \ - r->f[i] = float32_scalbn(t, -uim, &env->vec_status); \ + r->f32[i] = float32_scalbn(t, -uim, &env->vec_status); \ } \ } VCF(ux, uint32_to_float32, u32) @@ -782,9 +782,9 @@ VCMPNE(w, u32, uint32_t, 0) uint32_t none = 0; \ int i; \ \ - for (i = 0; i < ARRAY_SIZE(r->f); i++) { \ + for (i = 0; i < ARRAY_SIZE(r->f32); i++) { \ uint32_t result; \ - int rel = float32_compare_quiet(a->f[i], b->f[i], \ + int rel = float32_compare_quiet(a->f32[i], b->f32[i], \ &env->vec_status); \ if (rel == float_relation_unordered) { \ result = 0; \ @@ -816,14 +816,16 @@ static inline void vcmpbfp_internal(CPUPPCState *env, ppc_avr_t *r, int i; int all_in = 0; - for (i = 0; i < ARRAY_SIZE(r->f); i++) { - int le_rel = float32_compare_quiet(a->f[i], b->f[i], &env->vec_status); + for (i = 0; i < ARRAY_SIZE(r->f32); i++) { + int le_rel = float32_compare_quiet(a->f32[i], b->f32[i], + &env->vec_status); if (le_rel == float_relation_unordered) { r->u32[i] = 0xc0000000; all_in = 1; } else { - float32 bneg = float32_chs(b->f[i]); - int ge_rel = float32_compare_quiet(a->f[i], bneg, &env->vec_status); + float32 bneg = float32_chs(b->f32[i]); + int ge_rel = float32_compare_quiet(a->f32[i], bneg, + &env->vec_status); int le = le_rel != float_relation_greater; int ge = ge_rel != float_relation_less; @@ -856,11 +858,11 @@ void helper_vcmpbfp_dot(CPUPPCState *env, ppc_avr_t *r, ppc_avr_t *a, float_status s = env->vec_status; \ \ set_float_rounding_mode(float_round_to_zero, &s); \ - for (i = 0; i < ARRAY_SIZE(r->f); i++) { \ - if (float32_is_any_nan(b->f[i])) { \ + for (i = 0; i < ARRAY_SIZE(r->f32); i++) { \ + if (float32_is_any_nan(b->f32[i])) { \ r->element[i] = 0; \ } else { \ - float64 t = float32_to_float64(b->f[i], &s); \ + float64 t = float32_to_float64(b->f32[i], &s); \ int64_t j; \ \ t = float64_scalbn(t, uim, &s); \ @@ -1661,8 +1663,8 @@ void helper_vrefp(CPUPPCState *env, ppc_avr_t *r, ppc_avr_t *b) { int i; - for (i = 0; i < ARRAY_SIZE(r->f); i++) { - r->f[i] = float32_div(float32_one, b->f[i], &env->vec_status); + for (i = 0; i < ARRAY_SIZE(r->f32); i++) { + r->f32[i] = float32_div(float32_one, b->f32[i], &env->vec_status); } } @@ -1674,8 +1676,8 @@ void helper_vrefp(CPUPPCState *env, ppc_avr_t *r, ppc_avr_t *b) float_status s = env->vec_status; \ \ set_float_rounding_mode(rounding, &s); \ - for (i = 0; i < ARRAY_SIZE(r->f); i++) { \ - r->f[i] = float32_round_to_int (b->f[i], &s); \ + for (i = 0; i < ARRAY_SIZE(r->f32); i++) { \ + r->f32[i] = float32_round_to_int (b->f32[i], &s); \ } \ } VRFI(n, float_round_nearest_even) @@ -1705,10 +1707,10 @@ void helper_vrsqrtefp(CPUPPCState *env, ppc_avr_t *r, ppc_avr_t *b) { int i; - for (i = 0; i < ARRAY_SIZE(r->f); i++) { - float32 t = float32_sqrt(b->f[i], &env->vec_status); + for (i = 0; i < ARRAY_SIZE(r->f32); i++) { + float32 t = float32_sqrt(b->f32[i], &env->vec_status); - r->f[i] = float32_div(float32_one, t, &env->vec_status); + r->f32[i] = float32_div(float32_one, t, &env->vec_status); } } @@ -1751,8 +1753,8 @@ void helper_vexptefp(CPUPPCState *env, ppc_avr_t *r, ppc_avr_t *b) { int i; - for (i = 0; i < ARRAY_SIZE(r->f); i++) { - r->f[i] = float32_exp2(b->f[i], &env->vec_status); + for (i = 0; i < ARRAY_SIZE(r->f32); i++) { + r->f32[i] = float32_exp2(b->f32[i], &env->vec_status); } } @@ -1760,8 +1762,8 @@ void helper_vlogefp(CPUPPCState *env, ppc_avr_t *r, ppc_avr_t *b) { int i; - for (i = 0; i < ARRAY_SIZE(r->f); i++) { - r->f[i] = float32_log2(b->f[i], &env->vec_status); + for (i = 0; i < ARRAY_SIZE(r->f32); i++) { + r->f32[i] = float32_log2(b->f32[i], &env->vec_status); } }