1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
|
From a3c7553efdec661a8f7d7dfc0c0618a35fab005c Mon Sep 17 00:00:00 2001
From: Matheus Ferst <matheus.ferst@eldorado.org.br>
Date: Wed, 2 Mar 2022 06:51:38 +0100
Subject: [PATCH 20/21] target/ppc: move xs[n]madd[am][ds]p/xs[n]msub[am][ds]p
to decodetree
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
Upstream-Status: Backport
[https://git.qemu.org/?p=qemu.git;a=commit;h=e4318ab2e423c4caf9a88a4e99b5e234096b81a9]
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Matheus Ferst <matheus.ferst@eldorado.org.br>
Message-Id: <20220225210936.1749575-37-matheus.ferst@eldorado.org.br>
Signed-off-by: Cédric Le Goater <clg@kaod.org>
Signed-off-by: Xiangyu Chen <xiangyu.chen@windriver.com>
---
target/ppc/fpu_helper.c | 23 ++++++------
target/ppc/helper.h | 16 ++++-----
target/ppc/insn32.decode | 22 ++++++++++++
target/ppc/translate/vsx-impl.c.inc | 56 ++++++++++++++++++++++++-----
target/ppc/translate/vsx-ops.c.inc | 16 ---------
5 files changed, 90 insertions(+), 43 deletions(-)
diff --git a/target/ppc/fpu_helper.c b/target/ppc/fpu_helper.c
index 5cc7fb1dcb..853e5f6029 100644
--- a/target/ppc/fpu_helper.c
+++ b/target/ppc/fpu_helper.c
@@ -2036,10 +2036,11 @@ VSX_TSQRT(xvtsqrtsp, 4, float32, VsrW(i), -126, 23)
* maddflgs - flags for the float*muladd routine that control the
* various forms (madd, msub, nmadd, nmsub)
* sfprf - set FPRF
+ * r2sp - round intermediate double precision result to single precision
*/
#define VSX_MADD(op, nels, tp, fld, maddflgs, sfprf, r2sp) \
void helper_##op(CPUPPCState *env, ppc_vsr_t *xt, \
- ppc_vsr_t *xa, ppc_vsr_t *b, ppc_vsr_t *c) \
+ ppc_vsr_t *s1, ppc_vsr_t *s2, ppc_vsr_t *s3) \
{ \
ppc_vsr_t t = *xt; \
int i; \
@@ -2055,12 +2056,12 @@ void helper_##op(CPUPPCState *env, ppc_vsr_t *xt, \
* result to odd. \
*/ \
set_float_rounding_mode(float_round_to_zero, &tstat); \
- t.fld = tp##_muladd(xa->fld, b->fld, c->fld, \
+ t.fld = tp##_muladd(s1->fld, s3->fld, s2->fld, \
maddflgs, &tstat); \
t.fld |= (get_float_exception_flags(&tstat) & \
float_flag_inexact) != 0; \
} else { \
- t.fld = tp##_muladd(xa->fld, b->fld, c->fld, \
+ t.fld = tp##_muladd(s1->fld, s3->fld, s2->fld, \
maddflgs, &tstat); \
} \
env->fp_status.float_exception_flags |= tstat.float_exception_flags; \
@@ -2082,14 +2083,14 @@ void helper_##op(CPUPPCState *env, ppc_vsr_t *xt, \
do_float_check_status(env, GETPC()); \
}
-VSX_MADD(xsmadddp, 1, float64, VsrD(0), MADD_FLGS, 1, 0)
-VSX_MADD(xsmsubdp, 1, float64, VsrD(0), MSUB_FLGS, 1, 0)
-VSX_MADD(xsnmadddp, 1, float64, VsrD(0), NMADD_FLGS, 1, 0)
-VSX_MADD(xsnmsubdp, 1, float64, VsrD(0), NMSUB_FLGS, 1, 0)
-VSX_MADD(xsmaddsp, 1, float64, VsrD(0), MADD_FLGS, 1, 1)
-VSX_MADD(xsmsubsp, 1, float64, VsrD(0), MSUB_FLGS, 1, 1)
-VSX_MADD(xsnmaddsp, 1, float64, VsrD(0), NMADD_FLGS, 1, 1)
-VSX_MADD(xsnmsubsp, 1, float64, VsrD(0), NMSUB_FLGS, 1, 1)
+VSX_MADD(XSMADDDP, 1, float64, VsrD(0), MADD_FLGS, 1, 0)
+VSX_MADD(XSMSUBDP, 1, float64, VsrD(0), MSUB_FLGS, 1, 0)
+VSX_MADD(XSNMADDDP, 1, float64, VsrD(0), NMADD_FLGS, 1, 0)
+VSX_MADD(XSNMSUBDP, 1, float64, VsrD(0), NMSUB_FLGS, 1, 0)
+VSX_MADD(XSMADDSP, 1, float64, VsrD(0), MADD_FLGS, 1, 1)
+VSX_MADD(XSMSUBSP, 1, float64, VsrD(0), MSUB_FLGS, 1, 1)
+VSX_MADD(XSNMADDSP, 1, float64, VsrD(0), NMADD_FLGS, 1, 1)
+VSX_MADD(XSNMSUBSP, 1, float64, VsrD(0), NMSUB_FLGS, 1, 1)
VSX_MADD(xvmadddp, 2, float64, VsrD(i), MADD_FLGS, 0, 0)
VSX_MADD(xvmsubdp, 2, float64, VsrD(i), MSUB_FLGS, 0, 0)
diff --git a/target/ppc/helper.h b/target/ppc/helper.h
index ef5bdd38a7..e147b37644 100644
--- a/target/ppc/helper.h
+++ b/target/ppc/helper.h
@@ -376,10 +376,10 @@ DEF_HELPER_3(xssqrtdp, void, env, vsr, vsr)
DEF_HELPER_3(xsrsqrtedp, void, env, vsr, vsr)
DEF_HELPER_4(xstdivdp, void, env, i32, vsr, vsr)
DEF_HELPER_3(xstsqrtdp, void, env, i32, vsr)
-DEF_HELPER_5(xsmadddp, void, env, vsr, vsr, vsr, vsr)
-DEF_HELPER_5(xsmsubdp, void, env, vsr, vsr, vsr, vsr)
-DEF_HELPER_5(xsnmadddp, void, env, vsr, vsr, vsr, vsr)
-DEF_HELPER_5(xsnmsubdp, void, env, vsr, vsr, vsr, vsr)
+DEF_HELPER_5(XSMADDDP, void, env, vsr, vsr, vsr, vsr)
+DEF_HELPER_5(XSMSUBDP, void, env, vsr, vsr, vsr, vsr)
+DEF_HELPER_5(XSNMADDDP, void, env, vsr, vsr, vsr, vsr)
+DEF_HELPER_5(XSNMSUBDP, void, env, vsr, vsr, vsr, vsr)
DEF_HELPER_4(xscmpeqdp, void, env, vsr, vsr, vsr)
DEF_HELPER_4(xscmpgtdp, void, env, vsr, vsr, vsr)
DEF_HELPER_4(xscmpgedp, void, env, vsr, vsr, vsr)
@@ -439,10 +439,10 @@ DEF_HELPER_3(xsresp, void, env, vsr, vsr)
DEF_HELPER_2(xsrsp, i64, env, i64)
DEF_HELPER_3(xssqrtsp, void, env, vsr, vsr)
DEF_HELPER_3(xsrsqrtesp, void, env, vsr, vsr)
-DEF_HELPER_5(xsmaddsp, void, env, vsr, vsr, vsr, vsr)
-DEF_HELPER_5(xsmsubsp, void, env, vsr, vsr, vsr, vsr)
-DEF_HELPER_5(xsnmaddsp, void, env, vsr, vsr, vsr, vsr)
-DEF_HELPER_5(xsnmsubsp, void, env, vsr, vsr, vsr, vsr)
+DEF_HELPER_5(XSMADDSP, void, env, vsr, vsr, vsr, vsr)
+DEF_HELPER_5(XSMSUBSP, void, env, vsr, vsr, vsr, vsr)
+DEF_HELPER_5(XSNMADDSP, void, env, vsr, vsr, vsr, vsr)
+DEF_HELPER_5(XSNMSUBSP, void, env, vsr, vsr, vsr, vsr)
DEF_HELPER_4(xvadddp, void, env, vsr, vsr, vsr)
DEF_HELPER_4(xvsubdp, void, env, vsr, vsr, vsr)
diff --git a/target/ppc/insn32.decode b/target/ppc/insn32.decode
index 8bdc059a4c..0ff8818084 100644
--- a/target/ppc/insn32.decode
+++ b/target/ppc/insn32.decode
@@ -451,6 +451,28 @@ STXVX 011111 ..... ..... ..... 0110001100 . @X_TSX
LXVPX 011111 ..... ..... ..... 0101001101 - @X_TSXP
STXVPX 011111 ..... ..... ..... 0111001101 - @X_TSXP
+## VSX Scalar Multiply-Add Instructions
+
+XSMADDADP 111100 ..... ..... ..... 00100001 . . . @XX3
+XSMADDMDP 111100 ..... ..... ..... 00101001 . . . @XX3
+XSMADDASP 111100 ..... ..... ..... 00000001 . . . @XX3
+XSMADDMSP 111100 ..... ..... ..... 00001001 . . . @XX3
+
+XSMSUBADP 111100 ..... ..... ..... 00110001 . . . @XX3
+XSMSUBMDP 111100 ..... ..... ..... 00111001 . . . @XX3
+XSMSUBASP 111100 ..... ..... ..... 00010001 . . . @XX3
+XSMSUBMSP 111100 ..... ..... ..... 00011001 . . . @XX3
+
+XSNMADDASP 111100 ..... ..... ..... 10000001 . . . @XX3
+XSNMADDMSP 111100 ..... ..... ..... 10001001 . . . @XX3
+XSNMADDADP 111100 ..... ..... ..... 10100001 . . . @XX3
+XSNMADDMDP 111100 ..... ..... ..... 10101001 . . . @XX3
+
+XSNMSUBASP 111100 ..... ..... ..... 10010001 . . . @XX3
+XSNMSUBMSP 111100 ..... ..... ..... 10011001 . . . @XX3
+XSNMSUBADP 111100 ..... ..... ..... 10110001 . . . @XX3
+XSNMSUBMDP 111100 ..... ..... ..... 10111001 . . . @XX3
+
## VSX splat instruction
XXSPLTIB 111100 ..... 00 ........ 0101101000 . @X_imm8
diff --git a/target/ppc/translate/vsx-impl.c.inc b/target/ppc/translate/vsx-impl.c.inc
index 99c8a57e50..90d3ac665b 100644
--- a/target/ppc/translate/vsx-impl.c.inc
+++ b/target/ppc/translate/vsx-impl.c.inc
@@ -1201,6 +1201,54 @@ GEN_VSX_HELPER_2(xvtstdcdp, 0x14, 0x1E, 0, PPC2_VSX)
GEN_VSX_HELPER_X3(xxperm, 0x08, 0x03, 0, PPC2_ISA300)
GEN_VSX_HELPER_X3(xxpermr, 0x08, 0x07, 0, PPC2_ISA300)
+static bool do_xsmadd(DisasContext *ctx, int tgt, int src1, int src2, int src3,
+ void (*gen_helper)(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_ptr))
+{
+ TCGv_ptr t, s1, s2, s3;
+
+ t = gen_vsr_ptr(tgt);
+ s1 = gen_vsr_ptr(src1);
+ s2 = gen_vsr_ptr(src2);
+ s3 = gen_vsr_ptr(src3);
+
+ gen_helper(cpu_env, t, s1, s2, s3);
+
+ tcg_temp_free_ptr(t);
+ tcg_temp_free_ptr(s1);
+ tcg_temp_free_ptr(s2);
+ tcg_temp_free_ptr(s3);
+
+ return true;
+}
+
+static bool do_xsmadd_XX3(DisasContext *ctx, arg_XX3 *a, bool type_a,
+ void (*gen_helper)(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_ptr))
+{
+ REQUIRE_VSX(ctx);
+
+ if (type_a) {
+ return do_xsmadd(ctx, a->xt, a->xa, a->xt, a->xb, gen_helper);
+ }
+ return do_xsmadd(ctx, a->xt, a->xa, a->xb, a->xt, gen_helper);
+}
+
+TRANS_FLAGS2(VSX, XSMADDADP, do_xsmadd_XX3, true, gen_helper_XSMADDDP)
+TRANS_FLAGS2(VSX, XSMADDMDP, do_xsmadd_XX3, false, gen_helper_XSMADDDP)
+TRANS_FLAGS2(VSX, XSMSUBADP, do_xsmadd_XX3, true, gen_helper_XSMSUBDP)
+TRANS_FLAGS2(VSX, XSMSUBMDP, do_xsmadd_XX3, false, gen_helper_XSMSUBDP)
+TRANS_FLAGS2(VSX, XSNMADDADP, do_xsmadd_XX3, true, gen_helper_XSNMADDDP)
+TRANS_FLAGS2(VSX, XSNMADDMDP, do_xsmadd_XX3, false, gen_helper_XSNMADDDP)
+TRANS_FLAGS2(VSX, XSNMSUBADP, do_xsmadd_XX3, true, gen_helper_XSNMSUBDP)
+TRANS_FLAGS2(VSX, XSNMSUBMDP, do_xsmadd_XX3, false, gen_helper_XSNMSUBDP)
+TRANS_FLAGS2(VSX207, XSMADDASP, do_xsmadd_XX3, true, gen_helper_XSMADDSP)
+TRANS_FLAGS2(VSX207, XSMADDMSP, do_xsmadd_XX3, false, gen_helper_XSMADDSP)
+TRANS_FLAGS2(VSX207, XSMSUBASP, do_xsmadd_XX3, true, gen_helper_XSMSUBSP)
+TRANS_FLAGS2(VSX207, XSMSUBMSP, do_xsmadd_XX3, false, gen_helper_XSMSUBSP)
+TRANS_FLAGS2(VSX207, XSNMADDASP, do_xsmadd_XX3, true, gen_helper_XSNMADDSP)
+TRANS_FLAGS2(VSX207, XSNMADDMSP, do_xsmadd_XX3, false, gen_helper_XSNMADDSP)
+TRANS_FLAGS2(VSX207, XSNMSUBASP, do_xsmadd_XX3, true, gen_helper_XSNMSUBSP)
+TRANS_FLAGS2(VSX207, XSNMSUBMSP, do_xsmadd_XX3, false, gen_helper_XSNMSUBSP)
+
#define GEN_VSX_HELPER_VSX_MADD(name, op1, aop, mop, inval, type) \
static void gen_##name(DisasContext *ctx) \
{ \
@@ -1231,14 +1279,6 @@ static void gen_##name(DisasContext *ctx) \
tcg_temp_free_ptr(c); \
}
-GEN_VSX_HELPER_VSX_MADD(xsmadddp, 0x04, 0x04, 0x05, 0, PPC2_VSX)
-GEN_VSX_HELPER_VSX_MADD(xsmsubdp, 0x04, 0x06, 0x07, 0, PPC2_VSX)
-GEN_VSX_HELPER_VSX_MADD(xsnmadddp, 0x04, 0x14, 0x15, 0, PPC2_VSX)
-GEN_VSX_HELPER_VSX_MADD(xsnmsubdp, 0x04, 0x16, 0x17, 0, PPC2_VSX)
-GEN_VSX_HELPER_VSX_MADD(xsmaddsp, 0x04, 0x00, 0x01, 0, PPC2_VSX207)
-GEN_VSX_HELPER_VSX_MADD(xsmsubsp, 0x04, 0x02, 0x03, 0, PPC2_VSX207)
-GEN_VSX_HELPER_VSX_MADD(xsnmaddsp, 0x04, 0x10, 0x11, 0, PPC2_VSX207)
-GEN_VSX_HELPER_VSX_MADD(xsnmsubsp, 0x04, 0x12, 0x13, 0, PPC2_VSX207)
GEN_VSX_HELPER_VSX_MADD(xvmadddp, 0x04, 0x0C, 0x0D, 0, PPC2_VSX)
GEN_VSX_HELPER_VSX_MADD(xvmsubdp, 0x04, 0x0E, 0x0F, 0, PPC2_VSX)
GEN_VSX_HELPER_VSX_MADD(xvnmadddp, 0x04, 0x1C, 0x1D, 0, PPC2_VSX)
diff --git a/target/ppc/translate/vsx-ops.c.inc b/target/ppc/translate/vsx-ops.c.inc
index c974324c4c..ef0200eead 100644
--- a/target/ppc/translate/vsx-ops.c.inc
+++ b/target/ppc/translate/vsx-ops.c.inc
@@ -186,14 +186,6 @@ GEN_XX2FORM(xssqrtdp, 0x16, 0x04, PPC2_VSX),
GEN_XX2FORM(xsrsqrtedp, 0x14, 0x04, PPC2_VSX),
GEN_XX3FORM(xstdivdp, 0x14, 0x07, PPC2_VSX),
GEN_XX2FORM(xstsqrtdp, 0x14, 0x06, PPC2_VSX),
-GEN_XX3FORM_NAME(xsmadddp, "xsmaddadp", 0x04, 0x04, PPC2_VSX),
-GEN_XX3FORM_NAME(xsmadddp, "xsmaddmdp", 0x04, 0x05, PPC2_VSX),
-GEN_XX3FORM_NAME(xsmsubdp, "xsmsubadp", 0x04, 0x06, PPC2_VSX),
-GEN_XX3FORM_NAME(xsmsubdp, "xsmsubmdp", 0x04, 0x07, PPC2_VSX),
-GEN_XX3FORM_NAME(xsnmadddp, "xsnmaddadp", 0x04, 0x14, PPC2_VSX),
-GEN_XX3FORM_NAME(xsnmadddp, "xsnmaddmdp", 0x04, 0x15, PPC2_VSX),
-GEN_XX3FORM_NAME(xsnmsubdp, "xsnmsubadp", 0x04, 0x16, PPC2_VSX),
-GEN_XX3FORM_NAME(xsnmsubdp, "xsnmsubmdp", 0x04, 0x17, PPC2_VSX),
GEN_XX3FORM(xscmpeqdp, 0x0C, 0x00, PPC2_ISA300),
GEN_XX3FORM(xscmpgtdp, 0x0C, 0x01, PPC2_ISA300),
GEN_XX3FORM(xscmpgedp, 0x0C, 0x02, PPC2_ISA300),
@@ -235,14 +227,6 @@ GEN_XX2FORM(xsresp, 0x14, 0x01, PPC2_VSX207),
GEN_XX2FORM(xsrsp, 0x12, 0x11, PPC2_VSX207),
GEN_XX2FORM(xssqrtsp, 0x16, 0x00, PPC2_VSX207),
GEN_XX2FORM(xsrsqrtesp, 0x14, 0x00, PPC2_VSX207),
-GEN_XX3FORM_NAME(xsmaddsp, "xsmaddasp", 0x04, 0x00, PPC2_VSX207),
-GEN_XX3FORM_NAME(xsmaddsp, "xsmaddmsp", 0x04, 0x01, PPC2_VSX207),
-GEN_XX3FORM_NAME(xsmsubsp, "xsmsubasp", 0x04, 0x02, PPC2_VSX207),
-GEN_XX3FORM_NAME(xsmsubsp, "xsmsubmsp", 0x04, 0x03, PPC2_VSX207),
-GEN_XX3FORM_NAME(xsnmaddsp, "xsnmaddasp", 0x04, 0x10, PPC2_VSX207),
-GEN_XX3FORM_NAME(xsnmaddsp, "xsnmaddmsp", 0x04, 0x11, PPC2_VSX207),
-GEN_XX3FORM_NAME(xsnmsubsp, "xsnmsubasp", 0x04, 0x12, PPC2_VSX207),
-GEN_XX3FORM_NAME(xsnmsubsp, "xsnmsubmsp", 0x04, 0x13, PPC2_VSX207),
GEN_XX2FORM(xscvsxdsp, 0x10, 0x13, PPC2_VSX207),
GEN_XX2FORM(xscvuxdsp, 0x10, 0x12, PPC2_VSX207),
--
2.17.1
|
