[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[Qemu-devel] [PULL 25/42] arm/translate-a64: add FP16 FPRINTx to simd_tw
From: |
Peter Maydell |
Subject: |
[Qemu-devel] [PULL 25/42] arm/translate-a64: add FP16 FPRINTx to simd_two_reg_misc_fp16 |
Date: |
Thu, 1 Mar 2018 11:23:46 +0000 |
From: Alex Bennée <address@hidden>
This adds the full range of half-precision floating point to integral
instructions.
Signed-off-by: Alex Bennée <address@hidden>
Reviewed-by: Richard Henderson <address@hidden>
Message-id: address@hidden
Signed-off-by: Peter Maydell <address@hidden>
---
target/arm/helper-a64.h | 2 +
target/arm/helper-a64.c | 22 ++++++++
target/arm/translate-a64.c | 123 +++++++++++++++++++++++++++++++++++++++++++--
3 files changed, 142 insertions(+), 5 deletions(-)
diff --git a/target/arm/helper-a64.h b/target/arm/helper-a64.h
index 003ffa582f..bc8d5b105b 100644
--- a/target/arm/helper-a64.h
+++ b/target/arm/helper-a64.h
@@ -75,3 +75,5 @@ DEF_HELPER_3(advsimd_maxnum2h, i32, i32, i32, ptr)
DEF_HELPER_3(advsimd_minnum2h, i32, i32, i32, ptr)
DEF_HELPER_3(advsimd_mulx2h, i32, i32, i32, ptr)
DEF_HELPER_4(advsimd_muladd2h, i32, i32, i32, i32, ptr)
+DEF_HELPER_2(advsimd_rinth_exact, f16, f16, ptr)
+DEF_HELPER_2(advsimd_rinth, f16, f16, ptr)
diff --git a/target/arm/helper-a64.c b/target/arm/helper-a64.c
index 4d5ae96d8f..4fd28fdf48 100644
--- a/target/arm/helper-a64.c
+++ b/target/arm/helper-a64.c
@@ -745,3 +745,25 @@ uint32_t HELPER(advsimd_acgt_f16)(float16 a, float16 b,
void *fpstp)
int compare = float16_compare(f0, f1, fpst);
return ADVSIMD_CMPRES(compare == float_relation_greater);
}
+
+/* round to integral */
+float16 HELPER(advsimd_rinth_exact)(float16 x, void *fp_status)
+{
+ return float16_round_to_int(x, fp_status);
+}
+
+float16 HELPER(advsimd_rinth)(float16 x, void *fp_status)
+{
+ int old_flags = get_float_exception_flags(fp_status), new_flags;
+ float16 ret;
+
+ ret = float16_round_to_int(x, fp_status);
+
+ /* Suppress any inexact exceptions the conversion produced */
+ if (!(old_flags & float_flag_inexact)) {
+ new_flags = get_float_exception_flags(fp_status);
+ set_float_exception_flags(new_flags & ~float_flag_inexact, fp_status);
+ }
+
+ return ret;
+}
diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c
index 9c1892c49a..3c37eb99ff 100644
--- a/target/arm/translate-a64.c
+++ b/target/arm/translate-a64.c
@@ -11180,27 +11180,140 @@ static void disas_simd_two_reg_misc(DisasContext *s,
uint32_t insn)
*/
static void disas_simd_two_reg_misc_fp16(DisasContext *s, uint32_t insn)
{
- int fpop, opcode, a;
+ int fpop, opcode, a, u;
+ int rn, rd;
+ bool is_q;
+ bool is_scalar;
+ bool only_in_vector = false;
+
+ int pass;
+ TCGv_i32 tcg_rmode = NULL;
+ TCGv_ptr tcg_fpstatus = NULL;
+ bool need_rmode = false;
+ int rmode;
if (!arm_dc_feature(s, ARM_FEATURE_V8_FP16)) {
unallocated_encoding(s);
return;
}
- if (!fp_access_check(s)) {
- return;
- }
+ rd = extract32(insn, 0, 5);
+ rn = extract32(insn, 5, 5);
- opcode = extract32(insn, 12, 4);
a = extract32(insn, 23, 1);
+ u = extract32(insn, 29, 1);
+ is_scalar = extract32(insn, 28, 1);
+ is_q = extract32(insn, 30, 1);
+
+ opcode = extract32(insn, 12, 5);
fpop = deposit32(opcode, 5, 1, a);
+ fpop = deposit32(fpop, 6, 1, u);
switch (fpop) {
+ case 0x18: /* FRINTN */
+ need_rmode = true;
+ only_in_vector = true;
+ rmode = FPROUNDING_TIEEVEN;
+ break;
+ case 0x19: /* FRINTM */
+ need_rmode = true;
+ only_in_vector = true;
+ rmode = FPROUNDING_NEGINF;
+ break;
+ case 0x38: /* FRINTP */
+ need_rmode = true;
+ only_in_vector = true;
+ rmode = FPROUNDING_POSINF;
+ break;
+ case 0x39: /* FRINTZ */
+ need_rmode = true;
+ only_in_vector = true;
+ rmode = FPROUNDING_ZERO;
+ break;
+ case 0x58: /* FRINTA */
+ need_rmode = true;
+ only_in_vector = true;
+ rmode = FPROUNDING_TIEAWAY;
+ break;
+ case 0x59: /* FRINTX */
+ case 0x79: /* FRINTI */
+ only_in_vector = true;
+ /* current rounding mode */
+ break;
default:
fprintf(stderr, "%s: insn %#04x fpop %#2x\n", __func__, insn, fpop);
g_assert_not_reached();
}
+
+ /* Check additional constraints for the scalar encoding */
+ if (is_scalar) {
+ if (!is_q) {
+ unallocated_encoding(s);
+ return;
+ }
+ /* FRINTxx is only in the vector form */
+ if (only_in_vector) {
+ unallocated_encoding(s);
+ return;
+ }
+ }
+
+ if (!fp_access_check(s)) {
+ return;
+ }
+
+ if (need_rmode) {
+ tcg_fpstatus = get_fpstatus_ptr(true);
+ }
+
+ if (need_rmode) {
+ tcg_rmode = tcg_const_i32(arm_rmode_to_sf(rmode));
+ gen_helper_set_rmode(tcg_rmode, tcg_rmode, tcg_fpstatus);
+ }
+
+ if (is_scalar) {
+ /* no operations yet */
+ } else {
+ for (pass = 0; pass < (is_q ? 8 : 4); pass++) {
+ TCGv_i32 tcg_op = tcg_temp_new_i32();
+ TCGv_i32 tcg_res = tcg_temp_new_i32();
+
+ read_vec_element_i32(s, tcg_op, rn, pass, MO_16);
+
+ switch (fpop) {
+ case 0x18: /* FRINTN */
+ case 0x19: /* FRINTM */
+ case 0x38: /* FRINTP */
+ case 0x39: /* FRINTZ */
+ case 0x58: /* FRINTA */
+ case 0x79: /* FRINTI */
+ gen_helper_advsimd_rinth(tcg_res, tcg_op, tcg_fpstatus);
+ break;
+ case 0x59: /* FRINTX */
+ gen_helper_advsimd_rinth_exact(tcg_res, tcg_op, tcg_fpstatus);
+ break;
+ default:
+ 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_op);
+ }
+
+ clear_vec_high(s, is_q, rd);
+ }
+
+ if (tcg_rmode) {
+ gen_helper_set_rmode(tcg_rmode, tcg_rmode, tcg_fpstatus);
+ tcg_temp_free_i32(tcg_rmode);
+ }
+
+ if (tcg_fpstatus) {
+ tcg_temp_free_ptr(tcg_fpstatus);
+ }
}
/* AdvSIMD scalar x indexed element
--
2.16.2
- [Qemu-devel] [PULL 08/42] arm/vexpress: Add proper display connector emulation, (continued)
- [Qemu-devel] [PULL 08/42] arm/vexpress: Add proper display connector emulation, Peter Maydell, 2018/03/01
- [Qemu-devel] [PULL 06/42] hw/i2c-ddc: Do not fail writes, Peter Maydell, 2018/03/01
- [Qemu-devel] [PULL 05/42] i2c: Move the bus class to i2c.h, Peter Maydell, 2018/03/01
- [Qemu-devel] [PULL 03/42] xilinx_spips: Use 8 dummy cycles with the QIOR/QIOR4 commands, Peter Maydell, 2018/03/01
- [Qemu-devel] [PULL 02/42] xilinx_spips: Enable only two slaves when reading/writing with stripe, Peter Maydell, 2018/03/01
- [Qemu-devel] [PULL 17/42] arm/translate-a64: add FP16 FADD/FABD/FSUB/FMUL/FDIV to simd_three_reg_same_fp16, Peter Maydell, 2018/03/01
- [Qemu-devel] [PULL 13/42] target/arm/helper: pass explicit fpst to set_rmode, Peter Maydell, 2018/03/01
- [Qemu-devel] [PULL 21/42] arm/translate-a64: add FP16 pairwise ops simd_three_reg_same_fp16, Peter Maydell, 2018/03/01
- [Qemu-devel] [PULL 24/42] arm/translate-a64: initial decode for simd_two_reg_misc_fp16, Peter Maydell, 2018/03/01
- [Qemu-devel] [PULL 22/42] arm/translate-a64: add FP16 FMULX/MLS/FMLA to simd_indexed, Peter Maydell, 2018/03/01
- [Qemu-devel] [PULL 25/42] arm/translate-a64: add FP16 FPRINTx to simd_two_reg_misc_fp16,
Peter Maydell <=
- [Qemu-devel] [PULL 26/42] arm/translate-a64: add FCVTxx to simd_two_reg_misc_fp16, Peter Maydell, 2018/03/01
- [Qemu-devel] [PULL 27/42] arm/translate-a64: add FP16 FCMxx (zero) to simd_two_reg_misc_fp16, Peter Maydell, 2018/03/01
- [Qemu-devel] [PULL 31/42] arm/translate-a64: add FP16 FRECPE, Peter Maydell, 2018/03/01
- [Qemu-devel] [PULL 28/42] arm/translate-a64: add FP16 SCVTF/UCVFT to simd_two_reg_misc_fp16, Peter Maydell, 2018/03/01
- [Qemu-devel] [PULL 40/42] target/arm: Enable ARM_V8_FP16 feature bit for the AArch64 "any" CPU, Peter Maydell, 2018/03/01
- [Qemu-devel] [PULL 30/42] arm/helper.c: re-factor recpe and add recepe_f16, Peter Maydell, 2018/03/01
- [Qemu-devel] [PULL 35/42] arm/translate-a64: add FP16 FRSQRTE to simd_two_reg_misc_fp16, Peter Maydell, 2018/03/01
- [Qemu-devel] [PULL 19/42] arm/translate-a64: add FP16 FMULA/X/S to simd_three_reg_same_fp16, Peter Maydell, 2018/03/01
- [Qemu-devel] [PULL 11/42] target/arm/cpu.h: update comment for half-precision values, Peter Maydell, 2018/03/01
- [Qemu-devel] [PULL 23/42] arm/translate-a64: add FP16 x2 ops for simd_indexed, Peter Maydell, 2018/03/01