Patchwork [5/7] target-arm: Add separate Neon float-int conversion helpers

login
register
mail settings
Submitter Peter Maydell
Date May 6, 2011, 12:48 p.m.
Message ID <1304686095-30265-6-git-send-email-peter.maydell@linaro.org>
Download mbox | patch
Permalink /patch/94383/
State New
Headers show

Comments

Peter Maydell - May 6, 2011, 12:48 p.m.
Add the Neon-specific float-int conversion helper functions which
use the standard FPSCR value rather than the VFP FPSCR.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target-arm/helper.h    |   10 ++++++++++
 target-arm/op_helper.c |   12 ++++++++++++
 target-arm/translate.c |   29 +++++++++++++++++------------
 3 files changed, 39 insertions(+), 12 deletions(-)

Patch

diff --git a/target-arm/helper.h b/target-arm/helper.h
index 2c54d5e..1b4005a 100644
--- a/target-arm/helper.h
+++ b/target-arm/helper.h
@@ -127,6 +127,16 @@  DEF_HELPER_2(vfp_sltod, f64, i64, i32)
 DEF_HELPER_2(vfp_uhtod, f64, i64, i32)
 DEF_HELPER_2(vfp_ultod, f64, i64, i32)
 
+DEF_HELPER_1(neon_sitos, f32, i32)
+DEF_HELPER_1(neon_uitos, f32, i32)
+DEF_HELPER_1(neon_tosizs, i32, f32)
+DEF_HELPER_1(neon_touizs, i32, f32)
+
+DEF_HELPER_2(neon_ultos, f32, i32, i32);
+DEF_HELPER_2(neon_sltos, f32, i32, i32);
+DEF_HELPER_2(neon_touls, i32, f32, i32);
+DEF_HELPER_2(neon_tosls, i32, f32, i32);
+
 DEF_HELPER_2(vfp_fcvt_f16_to_f32, f32, i32, env)
 DEF_HELPER_2(vfp_fcvt_f32_to_f16, i32, f32, env)
 DEF_HELPER_2(neon_fcvt_f16_to_f32, f32, i32, env)
diff --git a/target-arm/op_helper.c b/target-arm/op_helper.c
index 1afea43..3998d9c 100644
--- a/target-arm/op_helper.c
+++ b/target-arm/op_helper.c
@@ -448,14 +448,23 @@  CONV_ITOF(vfp_##name##to##p, fsz, sign, &env->vfp.fp_status) \
 CONV_FTOI(vfp_##to##name##p, fsz, sign, &env->vfp.fp_status, ) \
 CONV_FTOI(vfp_##to##name##z##p, fsz, sign, &env->vfp.fp_status, _round_to_zero)
 
+#define NEON_CONVS(name, p, fsz, sign) \
+CONV_ITOF(neon_##name##to##p, fsz, sign, &env->vfp.standard_fp_status) \
+CONV_FTOI(neon_##to##name##z##p, fsz, sign, &env->vfp.standard_fp_status, \
+          _round_to_zero)
+
 VFP_CONVS(si, s, 32, )
 VFP_CONVS(si, d, 64, )
 VFP_CONVS(ui, s, 32, u)
 VFP_CONVS(ui, d, 64, u)
 
+NEON_CONVS(si, s, 32, )
+NEON_CONVS(ui, s, 32, u)
+
 #undef CONV_ITOF
 #undef CONV_FTOI
 #undef VFP_CONVS
+#undef NEON_CONVS
 
 /* VFP3 fixed point conversion.  */
 #define VFP_CONV_FIX(pfx, name, p, fsz, itype, sign, status) \
@@ -485,4 +494,7 @@  VFP_CONV_FIX(vfp_, sl, s, 32, int32, , &env->vfp.fp_status)
 VFP_CONV_FIX(vfp_, uh, s, 32, uint16, u, &env->vfp.fp_status)
 VFP_CONV_FIX(vfp_, ul, s, 32, uint32, u, &env->vfp.fp_status)
 
+VFP_CONV_FIX(neon_, sl, s, 32, int32, , &env->vfp.standard_fp_status)
+VFP_CONV_FIX(neon_, ul, s, 32, uint32, u, &env->vfp.standard_fp_status)
+
 #undef VFP_CONV_FIX
diff --git a/target-arm/translate.c b/target-arm/translate.c
index 195cf30..10592a5 100644
--- a/target-arm/translate.c
+++ b/target-arm/translate.c
@@ -5220,6 +5220,7 @@  static int disas_neon_data_insn(CPUState * env, DisasContext *s, uint32_t insn)
                 }
             } else if (op >= 14) {
                 /* VCVT fixed-point.  */
+                TCGv tmp_shift;
                 if (!(insn & (1 << 21)) || (q && ((rd | rm) & 1))) {
                     return 1;
                 }
@@ -5227,21 +5228,25 @@  static int disas_neon_data_insn(CPUState * env, DisasContext *s, uint32_t insn)
                  * hence this 32-shift where the ARM ARM has 64-imm6.
                  */
                 shift = 32 - shift;
+                tmp_shift = tcg_const_i32(shift);
                 for (pass = 0; pass < (q ? 4 : 2); pass++) {
                     tcg_gen_ld_f32(cpu_F0s, cpu_env, neon_reg_offset(rm, pass));
                     if (!(op & 1)) {
-                        if (u)
-                            gen_vfp_ulto(0, shift);
-                        else
-                            gen_vfp_slto(0, shift);
+                        if (u) {
+                            gen_helper_neon_ultos(cpu_F0s, cpu_F0s, tmp_shift);
+                        } else {
+                            gen_helper_neon_sltos(cpu_F0s, cpu_F0s, tmp_shift);
+                        }
                     } else {
-                        if (u)
-                            gen_vfp_toul(0, shift);
-                        else
-                            gen_vfp_tosl(0, shift);
+                        if (u) {
+                            gen_helper_neon_touls(cpu_F0s, cpu_F0s, tmp_shift);
+                        } else {
+                            gen_helper_neon_tosls(cpu_F0s, cpu_F0s, tmp_shift);
+                        }
                     }
                     tcg_gen_st_f32(cpu_F0s, cpu_env, neon_reg_offset(rd, pass));
                 }
+                tcg_temp_free_i32(tmp_shift);
             } else {
                 return 1;
             }
@@ -6051,16 +6056,16 @@  static int disas_neon_data_insn(CPUState * env, DisasContext *s, uint32_t insn)
                             gen_helper_rsqrte_f32(cpu_F0s, cpu_F0s, cpu_env);
                             break;
                         case NEON_2RM_VCVT_FS: /* VCVT.F32.S32 */
-                            gen_vfp_sito(0);
+                            gen_helper_neon_sitos(cpu_F0s, cpu_F0s);
                             break;
                         case NEON_2RM_VCVT_FU: /* VCVT.F32.U32 */
-                            gen_vfp_uito(0);
+                            gen_helper_neon_uitos(cpu_F0s, cpu_F0s);
                             break;
                         case NEON_2RM_VCVT_SF: /* VCVT.S32.F32 */
-                            gen_vfp_tosiz(0);
+                            gen_helper_neon_tosizs(cpu_F0s, cpu_F0s);
                             break;
                         case NEON_2RM_VCVT_UF: /* VCVT.U32.F32 */
-                            gen_vfp_touiz(0);
+                            gen_helper_neon_touizs(cpu_F0s, cpu_F0s);
                             break;
                         default:
                             /* Reserved op values were caught by the