qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: "Alex Bennée" <alex.bennee@linaro.org>
To: qemu-arm@nongnu.org
Cc: qemu-devel@nongnu.org, richard.henderson@linaro.org,
	"Alex Bennée" <alex.bennee@linaro.org>,
	"Peter Maydell" <peter.maydell@linaro.org>
Subject: [Qemu-devel] [PATCH v4 13/31] arm/translate-a64: add FP16 pairwise ops simd_three_reg_same_fp16
Date: Tue, 27 Feb 2018 14:38:34 +0000	[thread overview]
Message-ID: <20180227143852.11175-14-alex.bennee@linaro.org> (raw)
In-Reply-To: <20180227143852.11175-1-alex.bennee@linaro.org>

This includes FMAXNMP, FADDP, FMAXP, FMINNMP, FMINP.

Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
---
v2
  - checkpatch fixes
---
 target/arm/translate-a64.c | 208 +++++++++++++++++++++++++++++----------------
 1 file changed, 133 insertions(+), 75 deletions(-)

diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c
index 217e73ef58..e96e6cdd15 100644
--- a/target/arm/translate-a64.c
+++ b/target/arm/translate-a64.c
@@ -10247,6 +10247,7 @@ static void disas_simd_three_reg_same_fp16(DisasContext *s, uint32_t insn)
     int datasize, elements;
     int pass;
     TCGv_ptr fpst;
+    bool pairwise = false;
 
     if (!arm_dc_feature(s, ARM_FEATURE_V8_FP16)) {
         unallocated_encoding(s);
@@ -10272,91 +10273,148 @@ static void disas_simd_three_reg_same_fp16(DisasContext *s, uint32_t insn)
     datasize = is_q ? 128 : 64;
     elements = datasize / 16;
 
+    switch (fpopcode) {
+    case 0x10: /* FMAXNMP */
+    case 0x12: /* FADDP */
+    case 0x16: /* FMAXP */
+    case 0x18: /* FMINNMP */
+    case 0x1e: /* FMINP */
+        pairwise = true;
+        break;
+    }
+
     fpst = get_fpstatus_ptr(true);
 
-    for (pass = 0; pass < elements; pass++) {
+    if (pairwise) {
+        int maxpass = is_q ? 8 : 4;
         TCGv_i32 tcg_op1 = tcg_temp_new_i32();
         TCGv_i32 tcg_op2 = tcg_temp_new_i32();
-        TCGv_i32 tcg_res = tcg_temp_new_i32();
+        TCGv_i32 tcg_res[8];
 
-        read_vec_element_i32(s, tcg_op1, rn, pass, MO_16);
-        read_vec_element_i32(s, tcg_op2, rm, pass, MO_16);
+        for (pass = 0; pass < maxpass; pass++) {
+            int passreg = pass < (maxpass / 2) ? rn : rm;
+            int passelt = (pass << 1) & (maxpass - 1);
 
-        switch (fpopcode) {
-        case 0x0: /* FMAXNM */
-            gen_helper_advsimd_maxnumh(tcg_res, tcg_op1, tcg_op2, fpst);
-            break;
-        case 0x1: /* FMLA */
-            read_vec_element_i32(s, tcg_res, rd, pass, MO_16);
-            gen_helper_advsimd_muladdh(tcg_res, tcg_op1, tcg_op2, tcg_res,
-                                       fpst);
-            break;
-        case 0x2: /* FADD */
-            gen_helper_advsimd_addh(tcg_res, tcg_op1, tcg_op2, fpst);
-            break;
-        case 0x3: /* FMULX */
-            gen_helper_advsimd_mulxh(tcg_res, tcg_op1, tcg_op2, fpst);
-            break;
-        case 0x4: /* FCMEQ */
-            gen_helper_advsimd_ceq_f16(tcg_res, tcg_op1, tcg_op2, fpst);
-            break;
-        case 0x6: /* FMAX */
-            gen_helper_advsimd_maxh(tcg_res, tcg_op1, tcg_op2, fpst);
-            break;
-        case 0x7: /* FRECPS */
-            gen_helper_recpsf_f16(tcg_res, tcg_op1, tcg_op2, fpst);
-            break;
-        case 0x8: /* FMINNM */
-            gen_helper_advsimd_minnumh(tcg_res, tcg_op1, tcg_op2, fpst);
-            break;
-        case 0x9: /* FMLS */
-             /* As usual for ARM, separate negation for fused multiply-add */
-            tcg_gen_xori_i32(tcg_op1, tcg_op1, 0x8000);
-            read_vec_element_i32(s, tcg_res, rd, pass, MO_16);
-            gen_helper_advsimd_muladdh(tcg_res, tcg_op1, tcg_op2, tcg_res,
-                                       fpst);
-            break;
-        case 0xa: /* FSUB */
-            gen_helper_advsimd_subh(tcg_res, tcg_op1, tcg_op2, fpst);
-            break;
-        case 0xe: /* FMIN */
-            gen_helper_advsimd_minh(tcg_res, tcg_op1, tcg_op2, fpst);
-            break;
-        case 0xf: /* FRSQRTS */
-            gen_helper_rsqrtsf_f16(tcg_res, tcg_op1, tcg_op2, fpst);
-            break;
-        case 0x13: /* FMUL */
-            gen_helper_advsimd_mulh(tcg_res, tcg_op1, tcg_op2, fpst);
-            break;
-        case 0x14: /* FCMGE */
-            gen_helper_advsimd_cge_f16(tcg_res, tcg_op1, tcg_op2, fpst);
-            break;
-        case 0x15: /* FACGE */
-            gen_helper_advsimd_acge_f16(tcg_res, tcg_op1, tcg_op2, fpst);
-            break;
-        case 0x17: /* FDIV */
-            gen_helper_advsimd_divh(tcg_res, tcg_op1, tcg_op2, fpst);
-            break;
-        case 0x1a: /* FABD */
-            gen_helper_advsimd_subh(tcg_res, tcg_op1, tcg_op2, fpst);
-            tcg_gen_andi_i32(tcg_res, tcg_res, 0x7fff);
-            break;
-        case 0x1c: /* FCMGT */
-            gen_helper_advsimd_cgt_f16(tcg_res, tcg_op1, tcg_op2, fpst);
-            break;
-        case 0x1d: /* FACGT */
-            gen_helper_advsimd_acgt_f16(tcg_res, tcg_op1, tcg_op2, fpst);
-            break;
-        default:
-            fprintf(stderr, "%s: insn %#04x, fpop %#2x @ %#" PRIx64 "\n",
-                    __func__, insn, fpopcode, s->pc);
-            g_assert_not_reached();
+            read_vec_element_i32(s, tcg_op1, passreg, passelt, MO_16);
+            read_vec_element_i32(s, tcg_op2, passreg, passelt + 1, MO_16);
+            tcg_res[pass] = tcg_temp_new_i32();
+
+            switch (fpopcode) {
+            case 0x10: /* FMAXNMP */
+                gen_helper_advsimd_maxnumh(tcg_res[pass], tcg_op1, tcg_op2,
+                                           fpst);
+                break;
+            case 0x12: /* FADDP */
+                gen_helper_advsimd_addh(tcg_res[pass], tcg_op1, tcg_op2, fpst);
+                break;
+            case 0x16: /* FMAXP */
+                gen_helper_advsimd_maxh(tcg_res[pass], tcg_op1, tcg_op2, fpst);
+                break;
+            case 0x18: /* FMINNMP */
+                gen_helper_advsimd_minnumh(tcg_res[pass], tcg_op1, tcg_op2,
+                                           fpst);
+                break;
+            case 0x1e: /* FMINP */
+                gen_helper_advsimd_minh(tcg_res[pass], tcg_op1, tcg_op2, fpst);
+                break;
+            default:
+                g_assert_not_reached();
+            }
+        }
+
+        for (pass = 0; pass < maxpass; pass++) {
+            write_vec_element_i32(s, tcg_res[pass], rd, pass, MO_16);
+            tcg_temp_free_i32(tcg_res[pass]);
         }
 
-        write_vec_element_i32(s, tcg_res, rd, pass, MO_16);
-        tcg_temp_free_i32(tcg_res);
         tcg_temp_free_i32(tcg_op1);
         tcg_temp_free_i32(tcg_op2);
+
+    } else {
+        for (pass = 0; pass < elements; pass++) {
+            TCGv_i32 tcg_op1 = tcg_temp_new_i32();
+            TCGv_i32 tcg_op2 = tcg_temp_new_i32();
+            TCGv_i32 tcg_res = tcg_temp_new_i32();
+
+            read_vec_element_i32(s, tcg_op1, rn, pass, MO_16);
+            read_vec_element_i32(s, tcg_op2, rm, pass, MO_16);
+
+            switch (fpopcode) {
+            case 0x0: /* FMAXNM */
+                gen_helper_advsimd_maxnumh(tcg_res, tcg_op1, tcg_op2, fpst);
+                break;
+            case 0x1: /* FMLA */
+                read_vec_element_i32(s, tcg_res, rd, pass, MO_16);
+                gen_helper_advsimd_muladdh(tcg_res, tcg_op1, tcg_op2, tcg_res,
+                                           fpst);
+                break;
+            case 0x2: /* FADD */
+                gen_helper_advsimd_addh(tcg_res, tcg_op1, tcg_op2, fpst);
+                break;
+            case 0x3: /* FMULX */
+                gen_helper_advsimd_mulxh(tcg_res, tcg_op1, tcg_op2, fpst);
+                break;
+            case 0x4: /* FCMEQ */
+                gen_helper_advsimd_ceq_f16(tcg_res, tcg_op1, tcg_op2, fpst);
+                break;
+            case 0x6: /* FMAX */
+                gen_helper_advsimd_maxh(tcg_res, tcg_op1, tcg_op2, fpst);
+                break;
+            case 0x7: /* FRECPS */
+                gen_helper_recpsf_f16(tcg_res, tcg_op1, tcg_op2, fpst);
+                break;
+            case 0x8: /* FMINNM */
+                gen_helper_advsimd_minnumh(tcg_res, tcg_op1, tcg_op2, fpst);
+                break;
+            case 0x9: /* FMLS */
+                /* As usual for ARM, separate negation for fused multiply-add */
+                tcg_gen_xori_i32(tcg_op1, tcg_op1, 0x8000);
+                read_vec_element_i32(s, tcg_res, rd, pass, MO_16);
+                gen_helper_advsimd_muladdh(tcg_res, tcg_op1, tcg_op2, tcg_res,
+                                           fpst);
+                break;
+            case 0xa: /* FSUB */
+                gen_helper_advsimd_subh(tcg_res, tcg_op1, tcg_op2, fpst);
+                break;
+            case 0xe: /* FMIN */
+                gen_helper_advsimd_minh(tcg_res, tcg_op1, tcg_op2, fpst);
+                break;
+            case 0xf: /* FRSQRTS */
+                gen_helper_rsqrtsf_f16(tcg_res, tcg_op1, tcg_op2, fpst);
+                break;
+            case 0x13: /* FMUL */
+                gen_helper_advsimd_mulh(tcg_res, tcg_op1, tcg_op2, fpst);
+                break;
+            case 0x14: /* FCMGE */
+                gen_helper_advsimd_cge_f16(tcg_res, tcg_op1, tcg_op2, fpst);
+                break;
+            case 0x15: /* FACGE */
+                gen_helper_advsimd_acge_f16(tcg_res, tcg_op1, tcg_op2, fpst);
+                break;
+            case 0x17: /* FDIV */
+                gen_helper_advsimd_divh(tcg_res, tcg_op1, tcg_op2, fpst);
+                break;
+            case 0x1a: /* FABD */
+                gen_helper_advsimd_subh(tcg_res, tcg_op1, tcg_op2, fpst);
+                tcg_gen_andi_i32(tcg_res, tcg_res, 0x7fff);
+                break;
+            case 0x1c: /* FCMGT */
+                gen_helper_advsimd_cgt_f16(tcg_res, tcg_op1, tcg_op2, fpst);
+                break;
+            case 0x1d: /* FACGT */
+                gen_helper_advsimd_acgt_f16(tcg_res, tcg_op1, tcg_op2, fpst);
+                break;
+            default:
+                fprintf(stderr, "%s: insn %#04x, fpop %#2x @ %#" PRIx64 "\n",
+                        __func__, insn, fpopcode, s->pc);
+                g_assert_not_reached();
+            }
+
+            write_vec_element_i32(s, tcg_res, rd, pass, MO_16);
+            tcg_temp_free_i32(tcg_res);
+            tcg_temp_free_i32(tcg_op1);
+            tcg_temp_free_i32(tcg_op2);
+        }
     }
 
     tcg_temp_free_ptr(fpst);
-- 
2.15.1

  parent reply	other threads:[~2018-02-27 14:48 UTC|newest]

Thread overview: 43+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-02-27 14:38 [Qemu-devel] [PATCH v4 00/31] Add ARMv8.2 half-precision functions Alex Bennée
2018-02-27 14:38 ` [Qemu-devel] [PATCH v4 01/31] include/exec/helper-head.h: support f16 in helper calls Alex Bennée
2018-02-27 14:38 ` [Qemu-devel] [PATCH v4 02/31] target/arm/cpu64: introduce ARM_V8_FP16 feature bit Alex Bennée
2018-02-27 18:09   ` Peter Maydell
2018-02-27 14:38 ` [Qemu-devel] [PATCH v4 03/31] target/arm/cpu.h: update comment for half-precision values Alex Bennée
2018-02-27 14:38 ` [Qemu-devel] [PATCH v4 04/31] target/arm/cpu.h: add additional float_status flags Alex Bennée
2018-02-27 14:38 ` [Qemu-devel] [PATCH v4 05/31] target/arm/helper: pass explicit fpst to set_rmode Alex Bennée
2018-02-27 14:38 ` [Qemu-devel] [PATCH v4 06/31] arm/translate-a64: implement half-precision F(MIN|MAX)(V|NMV) Alex Bennée
2018-02-27 14:38 ` [Qemu-devel] [PATCH v4 07/31] arm/translate-a64: handle_3same_64 comment fix Alex Bennée
2018-02-27 14:38 ` [Qemu-devel] [PATCH v4 08/31] arm/translate-a64: initial decode for simd_three_reg_same_fp16 Alex Bennée
2018-02-27 14:38 ` [Qemu-devel] [PATCH v4 09/31] arm/translate-a64: add FP16 FADD/FABD/FSUB/FMUL/FDIV to simd_three_reg_same_fp16 Alex Bennée
2018-02-27 14:38 ` [Qemu-devel] [PATCH v4 10/31] arm/translate-a64: add FP16 F[A]C[EQ/GE/GT] " Alex Bennée
2018-02-27 14:38 ` [Qemu-devel] [PATCH v4 11/31] arm/translate-a64: add FP16 FMULA/X/S " Alex Bennée
2018-02-27 14:38 ` [Qemu-devel] [PATCH v4 12/31] arm/translate-a64: add FP16 FR[ECP/SQRT]S " Alex Bennée
2018-02-27 14:38 ` Alex Bennée [this message]
2018-02-27 14:38 ` [Qemu-devel] [PATCH v4 14/31] arm/translate-a64: add FP16 FMULX/MLS/FMLA to simd_indexed Alex Bennée
2018-02-27 17:09   ` Richard Henderson
2018-02-27 17:52     ` Alex Bennée
2018-02-27 17:57       ` Peter Maydell
2018-02-27 18:17         ` Alex Bennée
2018-02-27 14:38 ` [Qemu-devel] [PATCH v4 15/31] arm/translate-a64: add FP16 x2 ops for simd_indexed Alex Bennée
2018-02-27 14:38 ` [Qemu-devel] [PATCH v4 16/31] arm/translate-a64: initial decode for simd_two_reg_misc_fp16 Alex Bennée
2018-02-27 14:38 ` [Qemu-devel] [PATCH v4 17/31] arm/translate-a64: add FP16 FPRINTx to simd_two_reg_misc_fp16 Alex Bennée
2018-02-27 14:38 ` [Qemu-devel] [PATCH v4 18/31] arm/translate-a64: add FCVTxx " Alex Bennée
2018-02-27 14:38 ` [Qemu-devel] [PATCH v4 19/31] arm/translate-a64: add FP16 FCMxx (zero) " Alex Bennée
2018-02-27 14:38 ` [Qemu-devel] [PATCH v4 20/31] arm/translate-a64: add FP16 SCVTF/UCVFT " Alex Bennée
2018-02-27 14:38 ` [Qemu-devel] [PATCH v4 21/31] arm/translate-a64: add FP16 FNEG/FABS " Alex Bennée
2018-02-27 14:38 ` [Qemu-devel] [PATCH v4 22/31] arm/helper.c: re-factor recpe and add recepe_f16 Alex Bennée
2018-02-27 14:38 ` [Qemu-devel] [PATCH v4 23/31] arm/translate-a64: add FP16 FRECPE Alex Bennée
2018-02-27 14:38 ` [Qemu-devel] [PATCH v4 24/31] arm/translate-a64: add FP16 FRCPX to simd_two_reg_misc_fp16 Alex Bennée
2018-02-27 14:38 ` [Qemu-devel] [PATCH v4 25/31] arm/translate-a64: add FP16 FSQRT " Alex Bennée
2018-02-27 14:38 ` [Qemu-devel] [PATCH v4 26/31] arm/helper.c: re-factor rsqrte and add rsqrte_f16 Alex Bennée
2018-02-27 14:38 ` [Qemu-devel] [PATCH v4 27/31] arm/translate-a64: add FP16 FRSQRTE to simd_two_reg_misc_fp16 Alex Bennée
2018-02-27 14:38 ` [Qemu-devel] [PATCH v4 28/31] arm/translate-a64: add FP16 FMOV to simd_mod_imm Alex Bennée
2018-02-27 14:38 ` [Qemu-devel] [PATCH v4 29/31] arm/translate-a64: add all FP16 ops in simd_scalar_pairwise Alex Bennée
2018-02-27 14:38 ` [Qemu-devel] [PATCH v4 30/31] arm/translate-a64: implement simd_scalar_three_reg_same_fp16 Alex Bennée
2018-02-27 14:38 ` [Qemu-devel] [PATCH v4 31/31] arm/translate-a64: add all single op FP16 to handle_fp_1src_half Alex Bennée
2018-02-27 15:14 ` [Qemu-devel] [PATCH v4 00/31] Add ARMv8.2 half-precision functions no-reply
2018-02-27 15:14 ` no-reply
2018-02-27 18:11 ` [Qemu-devel] [Qemu-arm] " Peter Maydell
2018-02-28 13:32   ` Alex Bennée
2018-02-28 15:02     ` Peter Maydell
2018-02-28 16:58       ` Richard Henderson

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20180227143852.11175-14-alex.bennee@linaro.org \
    --to=alex.bennee@linaro.org \
    --cc=peter.maydell@linaro.org \
    --cc=qemu-arm@nongnu.org \
    --cc=qemu-devel@nongnu.org \
    --cc=richard.henderson@linaro.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).