From patchwork Mon Jun 6 18:40:58 2011 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Peter Maydell X-Patchwork-Id: 1760 Return-Path: Delivered-To: unknown Received: from imap.gmail.com (74.125.159.109) by localhost6.localdomain6 with IMAP4-SSL; 08 Jun 2011 14:55:35 -0000 Delivered-To: patches@linaro.org Received: by 10.52.181.10 with SMTP id ds10cs53942vdc; Mon, 6 Jun 2011 11:41:05 -0700 (PDT) Received: by 10.216.59.83 with SMTP id r61mr3904026wec.5.1307385662496; Mon, 06 Jun 2011 11:41:02 -0700 (PDT) Received: from mnementh.archaic.org.uk (mnementh.archaic.org.uk [81.2.115.146]) by mx.google.com with ESMTPS id o20si6618238weq.26.2011.06.06.11.41.01 (version=TLSv1/SSLv3 cipher=OTHER); Mon, 06 Jun 2011 11:41:02 -0700 (PDT) Received-SPF: pass (google.com: best guess record for domain of pm215@archaic.org.uk designates 81.2.115.146 as permitted sender) client-ip=81.2.115.146; Authentication-Results: mx.google.com; spf=pass (google.com: best guess record for domain of pm215@archaic.org.uk designates 81.2.115.146 as permitted sender) smtp.mail=pm215@archaic.org.uk Received: from pm215 by mnementh.archaic.org.uk with local (Exim 4.72) (envelope-from ) id 1QTejU-0006Ec-Hk; Mon, 06 Jun 2011 19:41:00 +0100 From: Peter Maydell To: qemu-devel@nongnu.org Cc: patches@linaro.org Subject: [PATCH v2 4/6] target-arm: Pass fp status pointer explicitly to neon fp helpers Date: Mon, 6 Jun 2011 19:40:58 +0100 Message-Id: <1307385660-23935-5-git-send-email-peter.maydell@linaro.org> X-Mailer: git-send-email 1.7.2.5 In-Reply-To: <1307385660-23935-1-git-send-email-peter.maydell@linaro.org> References: <1307385660-23935-1-git-send-email-peter.maydell@linaro.org> Make the Neon helpers for various floating point operations take an explicit pointer to the float_status they use, so they don't rely on the global environment pointer any more. This also allows us to drop the mul/sub/add helpers completely and just use the vfp versions. Signed-off-by: Peter Maydell --- target-arm/helper.h | 19 +++----- target-arm/neon_helper.c | 57 ++++++++++-------------- target-arm/translate.c | 111 +++++++++++++++++++++++++++++++++------------ 3 files changed, 113 insertions(+), 74 deletions(-) diff --git a/target-arm/helper.h b/target-arm/helper.h index 40b4677..c29efd5 100644 --- a/target-arm/helper.h +++ b/target-arm/helper.h @@ -350,17 +350,14 @@ DEF_HELPER_1(neon_qneg_s8, i32, i32) DEF_HELPER_1(neon_qneg_s16, i32, i32) DEF_HELPER_1(neon_qneg_s32, i32, i32) -DEF_HELPER_2(neon_min_f32, i32, i32, i32) -DEF_HELPER_2(neon_max_f32, i32, i32, i32) -DEF_HELPER_2(neon_abd_f32, i32, i32, i32) -DEF_HELPER_2(neon_add_f32, i32, i32, i32) -DEF_HELPER_2(neon_sub_f32, i32, i32, i32) -DEF_HELPER_2(neon_mul_f32, i32, i32, i32) -DEF_HELPER_2(neon_ceq_f32, i32, i32, i32) -DEF_HELPER_2(neon_cge_f32, i32, i32, i32) -DEF_HELPER_2(neon_cgt_f32, i32, i32, i32) -DEF_HELPER_2(neon_acge_f32, i32, i32, i32) -DEF_HELPER_2(neon_acgt_f32, i32, i32, i32) +DEF_HELPER_3(neon_min_f32, i32, i32, i32, ptr) +DEF_HELPER_3(neon_max_f32, i32, i32, i32, ptr) +DEF_HELPER_3(neon_abd_f32, i32, i32, i32, ptr) +DEF_HELPER_3(neon_ceq_f32, i32, i32, i32, ptr) +DEF_HELPER_3(neon_cge_f32, i32, i32, i32, ptr) +DEF_HELPER_3(neon_cgt_f32, i32, i32, i32, ptr) +DEF_HELPER_3(neon_acge_f32, i32, i32, i32, ptr) +DEF_HELPER_3(neon_acgt_f32, i32, i32, i32, ptr) /* iwmmxt_helper.c */ DEF_HELPER_2(iwmmxt_maddsq, i64, i64, i64) diff --git a/target-arm/neon_helper.c b/target-arm/neon_helper.c index 9165519..fda4021 100644 --- a/target-arm/neon_helper.c +++ b/target-arm/neon_helper.c @@ -18,8 +18,6 @@ #define SET_QC() env->vfp.xregs[ARM_VFP_FPSCR] = CPSR_Q -#define NFS (&env->vfp.standard_fp_status) - #define NEON_TYPE1(name, type) \ typedef struct \ { \ @@ -1770,69 +1768,62 @@ uint32_t HELPER(neon_qneg_s32)(uint32_t x) } /* NEON Float helpers. */ -uint32_t HELPER(neon_min_f32)(uint32_t a, uint32_t b) +uint32_t HELPER(neon_min_f32)(uint32_t a, uint32_t b, void *fpstp) { - return float32_val(float32_min(make_float32(a), make_float32(b), NFS)); + float_status *fpst = fpstp; + return float32_val(float32_min(make_float32(a), make_float32(b), fpst)); } -uint32_t HELPER(neon_max_f32)(uint32_t a, uint32_t b) +uint32_t HELPER(neon_max_f32)(uint32_t a, uint32_t b, void *fpstp) { - return float32_val(float32_max(make_float32(a), make_float32(b), NFS)); + float_status *fpst = fpstp; + return float32_val(float32_max(make_float32(a), make_float32(b), fpst)); } -uint32_t HELPER(neon_abd_f32)(uint32_t a, uint32_t b) +uint32_t HELPER(neon_abd_f32)(uint32_t a, uint32_t b, void *fpstp) { + float_status *fpst = fpstp; float32 f0 = make_float32(a); float32 f1 = make_float32(b); - return float32_val(float32_abs(float32_sub(f0, f1, NFS))); -} - -uint32_t HELPER(neon_add_f32)(uint32_t a, uint32_t b) -{ - return float32_val(float32_add(make_float32(a), make_float32(b), NFS)); -} - -uint32_t HELPER(neon_sub_f32)(uint32_t a, uint32_t b) -{ - return float32_val(float32_sub(make_float32(a), make_float32(b), NFS)); -} - -uint32_t HELPER(neon_mul_f32)(uint32_t a, uint32_t b) -{ - return float32_val(float32_mul(make_float32(a), make_float32(b), NFS)); + return float32_val(float32_abs(float32_sub(f0, f1, fpst))); } /* Floating point comparisons produce an integer result. * Note that EQ doesn't signal InvalidOp for QNaNs but GE and GT do. * Softfloat routines return 0/1, which we convert to the 0/-1 Neon requires. */ -uint32_t HELPER(neon_ceq_f32)(uint32_t a, uint32_t b) +uint32_t HELPER(neon_ceq_f32)(uint32_t a, uint32_t b, void *fpstp) { - return -float32_eq_quiet(make_float32(a), make_float32(b), NFS); + float_status *fpst = fpstp; + return -float32_eq_quiet(make_float32(a), make_float32(b), fpst); } -uint32_t HELPER(neon_cge_f32)(uint32_t a, uint32_t b) +uint32_t HELPER(neon_cge_f32)(uint32_t a, uint32_t b, void *fpstp) { - return -float32_le(make_float32(b), make_float32(a), NFS); + float_status *fpst = fpstp; + return -float32_le(make_float32(b), make_float32(a), fpst); } -uint32_t HELPER(neon_cgt_f32)(uint32_t a, uint32_t b) +uint32_t HELPER(neon_cgt_f32)(uint32_t a, uint32_t b, void *fpstp) { - return -float32_lt(make_float32(b), make_float32(a), NFS); + float_status *fpst = fpstp; + return -float32_lt(make_float32(b), make_float32(a), fpst); } -uint32_t HELPER(neon_acge_f32)(uint32_t a, uint32_t b) +uint32_t HELPER(neon_acge_f32)(uint32_t a, uint32_t b, void *fpstp) { + float_status *fpst = fpstp; float32 f0 = float32_abs(make_float32(a)); float32 f1 = float32_abs(make_float32(b)); - return -float32_le(f1, f0, NFS); + return -float32_le(f1, f0, fpst); } -uint32_t HELPER(neon_acgt_f32)(uint32_t a, uint32_t b) +uint32_t HELPER(neon_acgt_f32)(uint32_t a, uint32_t b, void *fpstp) { + float_status *fpst = fpstp; float32 f0 = float32_abs(make_float32(a)); float32 f1 = float32_abs(make_float32(b)); - return -float32_lt(f1, f0, NFS); + return -float32_lt(f1, f0, fpst); } #define ELEM(V, N, SIZE) (((V) >> ((N) * (SIZE))) & ((1ull << (SIZE)) - 1)) diff --git a/target-arm/translate.c b/target-arm/translate.c index 9ed747f..27d9887 100644 --- a/target-arm/translate.c +++ b/target-arm/translate.c @@ -4857,57 +4857,78 @@ static int disas_neon_data_insn(CPUState * env, DisasContext *s, uint32_t insn) } break; case NEON_3R_FLOAT_ARITH: /* Floating point arithmetic. */ + { + TCGv_ptr fpstatus = get_fpstatus_ptr(1); switch ((u << 2) | size) { case 0: /* VADD */ - gen_helper_neon_add_f32(tmp, tmp, tmp2); + case 4: /* VPADD */ + gen_helper_vfp_adds(tmp, tmp, tmp2, fpstatus); break; case 2: /* VSUB */ - gen_helper_neon_sub_f32(tmp, tmp, tmp2); - break; - case 4: /* VPADD */ - gen_helper_neon_add_f32(tmp, tmp, tmp2); + gen_helper_vfp_subs(tmp, tmp, tmp2, fpstatus); break; case 6: /* VABD */ - gen_helper_neon_abd_f32(tmp, tmp, tmp2); + gen_helper_neon_abd_f32(tmp, tmp, tmp2, fpstatus); break; default: abort(); } + tcg_temp_free_ptr(fpstatus); break; + } case NEON_3R_FLOAT_MULTIPLY: - gen_helper_neon_mul_f32(tmp, tmp, tmp2); + { + TCGv_ptr fpstatus = get_fpstatus_ptr(1); + gen_helper_vfp_muls(tmp, tmp, tmp2, fpstatus); if (!u) { tcg_temp_free_i32(tmp2); tmp2 = neon_load_reg(rd, pass); if (size == 0) { - gen_helper_neon_add_f32(tmp, tmp, tmp2); + gen_helper_vfp_adds(tmp, tmp, tmp2, fpstatus); } else { - gen_helper_neon_sub_f32(tmp, tmp2, tmp); + gen_helper_vfp_subs(tmp, tmp2, tmp, fpstatus); } } + tcg_temp_free_ptr(fpstatus); break; + } case NEON_3R_FLOAT_CMP: + { + TCGv_ptr fpstatus = get_fpstatus_ptr(1); if (!u) { - gen_helper_neon_ceq_f32(tmp, tmp, tmp2); + gen_helper_neon_ceq_f32(tmp, tmp, tmp2, fpstatus); } else { - if (size == 0) - gen_helper_neon_cge_f32(tmp, tmp, tmp2); - else - gen_helper_neon_cgt_f32(tmp, tmp, tmp2); + if (size == 0) { + gen_helper_neon_cge_f32(tmp, tmp, tmp2, fpstatus); + } else { + gen_helper_neon_cgt_f32(tmp, tmp, tmp2, fpstatus); + } } + tcg_temp_free_ptr(fpstatus); break; + } case NEON_3R_FLOAT_ACMP: - if (size == 0) - gen_helper_neon_acge_f32(tmp, tmp, tmp2); - else - gen_helper_neon_acgt_f32(tmp, tmp, tmp2); + { + TCGv_ptr fpstatus = get_fpstatus_ptr(1); + if (size == 0) { + gen_helper_neon_acge_f32(tmp, tmp, tmp2, fpstatus); + } else { + gen_helper_neon_acgt_f32(tmp, tmp, tmp2, fpstatus); + } + tcg_temp_free_ptr(fpstatus); break; + } case NEON_3R_FLOAT_MINMAX: - if (size == 0) - gen_helper_neon_max_f32(tmp, tmp, tmp2); - else - gen_helper_neon_min_f32(tmp, tmp, tmp2); + { + TCGv_ptr fpstatus = get_fpstatus_ptr(1); + if (size == 0) { + gen_helper_neon_max_f32(tmp, tmp, tmp2, fpstatus); + } else { + gen_helper_neon_min_f32(tmp, tmp, tmp2, fpstatus); + } + tcg_temp_free_ptr(fpstatus); break; + } case NEON_3R_VRECPS_VRSQRTS: if (size == 0) gen_helper_recps_f32(tmp, tmp, tmp2, cpu_env); @@ -5606,7 +5627,9 @@ static int disas_neon_data_insn(CPUState * env, DisasContext *s, uint32_t insn) gen_helper_neon_qrdmulh_s32(tmp, tmp, tmp2); } } else if (op & 1) { - gen_helper_neon_mul_f32(tmp, tmp, tmp2); + TCGv_ptr fpstatus = get_fpstatus_ptr(1); + gen_helper_vfp_muls(tmp, tmp, tmp2, fpstatus); + tcg_temp_free_ptr(fpstatus); } else { switch (size) { case 0: gen_helper_neon_mul_u8(tmp, tmp, tmp2); break; @@ -5624,14 +5647,22 @@ static int disas_neon_data_insn(CPUState * env, DisasContext *s, uint32_t insn) gen_neon_add(size, tmp, tmp2); break; case 1: - gen_helper_neon_add_f32(tmp, tmp, tmp2); + { + TCGv_ptr fpstatus = get_fpstatus_ptr(1); + gen_helper_vfp_adds(tmp, tmp, tmp2, fpstatus); + tcg_temp_free_ptr(fpstatus); break; + } case 4: gen_neon_rsb(size, tmp, tmp2); break; case 5: - gen_helper_neon_sub_f32(tmp, tmp2, tmp); + { + TCGv_ptr fpstatus = get_fpstatus_ptr(1); + gen_helper_vfp_subs(tmp, tmp2, tmp, fpstatus); + tcg_temp_free_ptr(fpstatus); break; + } default: abort(); } @@ -6029,30 +6060,50 @@ static int disas_neon_data_insn(CPUState * env, DisasContext *s, uint32_t insn) tcg_temp_free(tmp2); break; case NEON_2RM_VCGT0_F: + { + TCGv_ptr fpstatus = get_fpstatus_ptr(1); tmp2 = tcg_const_i32(0); - gen_helper_neon_cgt_f32(tmp, tmp, tmp2); + gen_helper_neon_cgt_f32(tmp, tmp, tmp2, fpstatus); tcg_temp_free(tmp2); + tcg_temp_free_ptr(fpstatus); break; + } case NEON_2RM_VCGE0_F: + { + TCGv_ptr fpstatus = get_fpstatus_ptr(1); tmp2 = tcg_const_i32(0); - gen_helper_neon_cge_f32(tmp, tmp, tmp2); + gen_helper_neon_cge_f32(tmp, tmp, tmp2, fpstatus); tcg_temp_free(tmp2); + tcg_temp_free_ptr(fpstatus); break; + } case NEON_2RM_VCEQ0_F: + { + TCGv_ptr fpstatus = get_fpstatus_ptr(1); tmp2 = tcg_const_i32(0); - gen_helper_neon_ceq_f32(tmp, tmp, tmp2); + gen_helper_neon_ceq_f32(tmp, tmp, tmp2, fpstatus); tcg_temp_free(tmp2); + tcg_temp_free_ptr(fpstatus); break; + } case NEON_2RM_VCLE0_F: + { + TCGv_ptr fpstatus = get_fpstatus_ptr(1); tmp2 = tcg_const_i32(0); - gen_helper_neon_cge_f32(tmp, tmp2, tmp); + gen_helper_neon_cge_f32(tmp, tmp2, tmp, fpstatus); tcg_temp_free(tmp2); + tcg_temp_free_ptr(fpstatus); break; + } case NEON_2RM_VCLT0_F: + { + TCGv_ptr fpstatus = get_fpstatus_ptr(1); tmp2 = tcg_const_i32(0); - gen_helper_neon_cgt_f32(tmp, tmp2, tmp); + gen_helper_neon_cgt_f32(tmp, tmp2, tmp, fpstatus); tcg_temp_free(tmp2); + tcg_temp_free_ptr(fpstatus); break; + } case NEON_2RM_VABS_F: gen_vfp_abs(0); break;