+2013-09-06 James Greenhalgh <james.greenhalgh@arm.com>
+
+ * config/arm/types.md
+ (type): Split f_cvt as f_cvt, f_cvtf2i, f_cvti2f.
+ * config/aarch64/aarch64.md
+ (l<fcvt_pattern><su_optab><GPF:mode><GPI:mode>2): Update with
+ new attributes.
+ (fix_trunc<GPF:mode><GPI:mode>2): Likewise.
+ (fixuns_trunc<GPF:mode><GPI:mode>2): Likewise.
+ (float<GPI:mode><GPF:mode>2): Likewise.
+ * config/arm/vfp.md
+ (*truncsisf2_vfp): Update with new attributes.
+ (*truncsidf2_vfp): Likewise.
+ (fixuns_truncsfsi2): Likewise.
+ (fixuns_truncdfsi2): Likewise.
+ (*floatsisf2_vfp): Likewise.
+ (*floatsidf2_vfp): Likewise.
+ (floatunssisf2): Likewise.
+ (floatunssidf2): Likewise.
+ (*combine_vcvt_f32_<FCVTI32typename>): Likewise.
+ (*combine_vcvt_f64_<FCVTI32typename>): Likewise.
+ * config/arm/arm1020e.md: Update with new attributes.
+ * config/arm/cortex-a15-neon.md: Update with new attributes.
+ * config/arm/cortex-a5.md: Update with new attributes.
+ * config/arm/cortex-a53.md: Update with new attributes.
+ * config/arm/cortex-a7.md: Update with new attributes.
+ * config/arm/cortex-a8-neon.md: Update with new attributes.
+ * config/arm/cortex-a9.md: Update with new attributes.
+ * config/arm/cortex-m4-fpu.md: Update with new attributes.
+ * config/arm/cortex-r4f.md: Update with new attributes.
+ * config/arm/marvell-pj4.md: Update with new attributes.
+ * config/arm/vfp11.md: Update with new attributes.
+
2013-09-06 James Greenhalgh <james.greenhalgh@arm.com>
* config/aarch64/arm_neon.h
"TARGET_FLOAT"
"fcvt<frint_suffix><su>\\t%<GPI:w>0, %<GPF:s>1"
[(set_attr "v8type" "fcvtf2i")
- (set_attr "type" "f_cvt")
+ (set_attr "type" "f_cvtf2i")
(set_attr "mode" "<GPF:MODE>")
(set_attr "mode2" "<GPI:MODE>")]
)
"TARGET_FLOAT"
"fcvtzs\\t%<GPI:w>0, %<GPF:s>1"
[(set_attr "v8type" "fcvtf2i")
- (set_attr "type" "f_cvt")
+ (set_attr "type" "f_cvtf2i")
(set_attr "mode" "<GPF:MODE>")
(set_attr "mode2" "<GPI:MODE>")]
)
"TARGET_FLOAT"
"fcvtzu\\t%<GPI:w>0, %<GPF:s>1"
[(set_attr "v8type" "fcvtf2i")
- (set_attr "type" "f_cvt")
+ (set_attr "type" "f_cvtf2i")
(set_attr "mode" "<GPF:MODE>")
(set_attr "mode2" "<GPI:MODE>")]
)
"TARGET_FLOAT"
"scvtf\\t%<GPF:s>0, %<GPI:w>1"
[(set_attr "v8type" "fcvti2f")
- (set_attr "type" "f_cvt")
+ (set_attr "type" "f_cvti2f")
(set_attr "mode" "<GPF:MODE>")
(set_attr "mode2" "<GPI:MODE>")]
)
(define_insn_reservation "v10_cvt" 5
(and (eq_attr "vfp10" "yes")
- (eq_attr "type" "f_cvt"))
+ (eq_attr "type" "f_cvt,f_cvti2f,f_cvtf2i"))
"1020a_e+v10_fmac")
(define_insn_reservation "v10_fmul" 6
(define_insn_reservation "cortex_a15_vfp_cvt" 6
(and (eq_attr "tune" "cortexa15")
- (eq_attr "type" "f_cvt"))
+ (eq_attr "type" "f_cvt,f_cvtf2i,f_cvti2f"))
"ca15_issue1,ca15_cx_vfp")
(define_insn_reservation "cortex_a15_vfp_cmpd" 8
(define_insn_reservation "cortex_a5_fpalu" 4
(and (eq_attr "tune" "cortexa5")
- (eq_attr "type" "ffariths, fadds, ffarithd, faddd, fcpys, fmuls, f_cvt,\
+ (eq_attr "type" "ffariths, fadds, ffarithd, faddd, fcpys, fmuls,\
+ f_cvt,f_cvtf2i,f_cvti2f,\
fcmps, fcmpd"))
"cortex_a5_ex1+cortex_a5_fpadd_pipe")
(define_insn_reservation "cortex_a53_fpalu" 4
(and (eq_attr "tune" "cortexa53")
- (eq_attr "type" "ffariths, fadds, ffarithd, faddd, fcpys, fmuls, f_cvt,\
+ (eq_attr "type" "ffariths, fadds, ffarithd, faddd, fcpys, fmuls,\
+ f_cvt,f_cvtf2i,f_cvti2f,\
fcmps, fcmpd, fcsel"))
"cortex_a53_slot0+cortex_a53_fpadd_pipe")
(define_insn_reservation "cortex_a7_fpalu" 4
(and (eq_attr "tune" "cortexa7")
(eq_attr "type" "ffariths, fadds, ffarithd, faddd, fcpys,\
- f_cvt, fcmps, fcmpd"))
+ f_cvt, f_cvtf2i, f_cvti2f, fcmps, fcmpd"))
"cortex_a7_ex1+cortex_a7_fpadd_pipe")
;; For fconsts and fconstd, 8-bit immediate data is passed directly from
(define_insn_reservation "cortex_a8_vfp_cvt" 7
(and (eq_attr "tune" "cortexa8")
- (eq_attr "type" "f_cvt"))
+ (eq_attr "type" "f_cvt,f_cvtf2i,f_cvti2f"))
"cortex_a8_vfp,cortex_a8_vfplite*6")
;; NEON -> core transfers.
(define_insn_reservation "cortex_a9_fadd" 4
(and (eq_attr "tune" "cortexa9")
- (eq_attr "type" "fadds, faddd, f_cvt"))
+ (eq_attr "type" "fadds, faddd, f_cvt, f_cvtf2i, f_cvti2f"))
"ca9fp_add")
(define_insn_reservation "cortex_a9_fcmp" 1
(define_insn_reservation "cortex_m4_f_cvt" 2
(and (eq_attr "tune" "cortexm4")
- (eq_attr "type" "f_cvt"))
+ (eq_attr "type" "f_cvt,f_cvtf2i,f_cvti2f"))
"cortex_m4_ex_v")
(define_insn_reservation "cortex_m4_f_load" 2
(define_insn_reservation "cortex_r4_f_cvt" 8
(and (eq_attr "tune_cortexr4" "yes")
- (eq_attr "type" "f_cvt"))
+ (eq_attr "type" "f_cvt,f_cvtf2i,f_cvti2f"))
"cortex_r4_single_issue*3")
(define_insn_reservation "cortex_r4_f_memd" 8
(define_insn_reservation "pj4_vfp_cpy" 4
(and (eq_attr "tune" "marvell_pj4")
(eq_attr "type" "fcpys,ffariths,ffarithd,fconsts,fconstd,\
- fcmps,fcmpd,f_cvt")) "pj4_is,nothing*2,vissue,vfast,nothing*2")
+ fcmps,fcmpd,f_cvt,f_cvtf2i,f_cvti2f"))
+"pj4_is,nothing*2,vissue,vfast,nothing*2")
;; Enlarge latency, and wish that more nondependent insns are
;; scheduled immediately after VFP load.
; clz count leading zeros (CLZ).
; csel From ARMv8-A: conditional select.
; extend extend instruction (SXTB, SXTH, UXTB, UXTH).
-; f_cvt conversion between float and integral.
+; f_cvt conversion between float representations.
+; f_cvtf2i conversion between float and integral types.
+; f_cvti2f conversion between integral and float types.
; f_flag transfer of co-processor flags to the CPSR.
; f_load[d,s] double/single load from memory. Used for VFP unit.
; f_mcr transfer arm to vfp reg.
csel,\
extend,\
f_cvt,\
+ f_cvtf2i,\
+ f_cvti2f,\
f_flag,\
f_loadd,\
f_loads,\
"ftosizs%?\\t%0, %1"
[(set_attr "predicable" "yes")
(set_attr "predicable_short_it" "no")
- (set_attr "type" "f_cvt")]
+ (set_attr "type" "f_cvtf2i")]
)
(define_insn "*truncsidf2_vfp"
"ftosizd%?\\t%0, %P1"
[(set_attr "predicable" "yes")
(set_attr "predicable_short_it" "no")
- (set_attr "type" "f_cvt")]
+ (set_attr "type" "f_cvtf2i")]
)
"ftouizs%?\\t%0, %1"
[(set_attr "predicable" "yes")
(set_attr "predicable_short_it" "no")
- (set_attr "type" "f_cvt")]
+ (set_attr "type" "f_cvtf2i")]
)
(define_insn "fixuns_truncdfsi2"
"ftouizd%?\\t%0, %P1"
[(set_attr "predicable" "yes")
(set_attr "predicable_short_it" "no")
- (set_attr "type" "f_cvt")]
+ (set_attr "type" "f_cvtf2i")]
)
"fsitos%?\\t%0, %1"
[(set_attr "predicable" "yes")
(set_attr "predicable_short_it" "no")
- (set_attr "type" "f_cvt")]
+ (set_attr "type" "f_cvti2f")]
)
(define_insn "*floatsidf2_vfp"
"fsitod%?\\t%P0, %1"
[(set_attr "predicable" "yes")
(set_attr "predicable_short_it" "no")
- (set_attr "type" "f_cvt")]
+ (set_attr "type" "f_cvti2f")]
)
"fuitos%?\\t%0, %1"
[(set_attr "predicable" "yes")
(set_attr "predicable_short_it" "no")
- (set_attr "type" "f_cvt")]
+ (set_attr "type" "f_cvti2f")]
)
(define_insn "floatunssidf2"
"fuitod%?\\t%P0, %1"
[(set_attr "predicable" "yes")
(set_attr "predicable_short_it" "no")
- (set_attr "type" "f_cvt")]
+ (set_attr "type" "f_cvti2f")]
)
"TARGET_32BIT && TARGET_HARD_FLOAT && TARGET_VFP3 && !flag_rounding_math"
"vcvt.f32.<FCVTI32typename>\\t%0, %1, %v2"
[(set_attr "predicable" "no")
- (set_attr "type" "f_cvt")]
+ (set_attr "type" "f_cvti2f")]
)
;; Not the ideal way of implementing this. Ideally we would be able to split
vmov.f32\\t%0, %1\;vcvt.f64.<FCVTI32typename>\\t%P0, %P0, %v2
vmov.f64\\t%P0, %1, %1\;vcvt.f64.<FCVTI32typename>\\t%P0, %P0, %v2"
[(set_attr "predicable" "no")
- (set_attr "type" "f_cvt")
+ (set_attr "type" "f_cvti2f")
(set_attr "length" "8")]
)
(define_insn_reservation "vfp_farith" 8
(and (eq_attr "generic_vfp" "yes")
- (eq_attr "type" "fadds,faddd,fconsts,fconstd,f_cvt,fmuls,fmacs,ffmas"))
+ (eq_attr "type" "fadds,faddd,fconsts,fconstd,f_cvt,f_cvtf2i,f_cvti2f,\
+ fmuls,fmacs,ffmas"))
"fmac")
(define_insn_reservation "vfp_fmul" 9