1 # RUN: llvm-mc -triple=amdgcn -mcpu=gfx940 -disassemble -show-encoding %s | FileCheck -strict-whitespace --check-prefix=GFX940 %s
3 # GFX940: global_load_dword v2, v[2:3], off sc0 ; encoding: [0x00,0x80,0x51,0xdc,0x02,0x00,0x7f,0x02]
4 0x00,0x80,0x51,0xdc,0x02,0x00,0x7f,0x02
6 # GFX940: global_load_dword v2, v[2:3], off sc1 ; encoding: [0x00,0x80,0x50,0xde,0x02,0x00,0x7f,0x02]
7 0x00,0x80,0x50,0xde,0x02,0x00,0x7f,0x02
9 # GFX940: global_load_dword v2, v[2:3], off nt ; encoding: [0x00,0x80,0x52,0xdc,0x02,0x00,0x7f,0x02]
10 0x00,0x80,0x52,0xdc,0x02,0x00,0x7f,0x02
12 # GFX940: s_load_dword s2, s[2:3], 0x0 glc ; encoding: [0x81,0x00,0x03,0xc0,0x00,0x00,0x00,0x00]
13 0x81,0x00,0x03,0xc0,0x00,0x00,0x00,0x00
15 # GFX940: buffer_load_dword v5, off, s[8:11], s3 sc0 nt sc1 ; encoding: [0x00,0xc0,0x52,0xe0,0x00,0x05,0x02,0x03]
16 0x00,0xc0,0x52,0xe0,0x00,0x05,0x02,0x03
18 # GFX940: flat_atomic_add_f32 v[2:3], v1 ; encoding: [0x00,0x00,0x34,0xdd,0x02,0x01,0x00,0x00]
19 0x00,0x00,0x34,0xdd,0x02,0x01,0x00,0x00
21 # GFX940: flat_atomic_add_f32 v[2:3], a1 ; encoding: [0x00,0x00,0x34,0xdd,0x02,0x01,0x80,0x00]
22 0x00,0x00,0x34,0xdd,0x02,0x01,0x80,0x00
24 # GFX940: flat_atomic_add_f32 v4, v[2:3], v1 sc0 ; encoding: [0x00,0x00,0x35,0xdd,0x02,0x01,0x00,0x04]
25 0x00,0x00,0x35,0xdd,0x02,0x01,0x00,0x04
27 # GFX940: flat_atomic_add_f32 a4, v[2:3], a1 sc0 ; encoding: [0x00,0x00,0x35,0xdd,0x02,0x01,0x80,0x04]
28 0x00,0x00,0x35,0xdd,0x02,0x01,0x80,0x04
30 # GFX940: flat_atomic_pk_add_f16 v4, v[2:3], v1 sc0 ; encoding: [0x00,0x00,0x39,0xdd,0x02,0x01,0x00,0x04]
31 0x00,0x00,0x39,0xdd,0x02,0x01,0x00,0x04
33 # GFX940: flat_atomic_pk_add_f16 a4, v[2:3], a1 sc0 ; encoding: [0x00,0x00,0x39,0xdd,0x02,0x01,0x80,0x04]
34 0x00,0x00,0x39,0xdd,0x02,0x01,0x80,0x04
36 # GFX940: flat_atomic_pk_add_f16 v[2:3], v1 ; encoding: [0x00,0x00,0x38,0xdd,0x02,0x01,0x00,0x00]
37 0x00,0x00,0x38,0xdd,0x02,0x01,0x00,0x00
39 # GFX940: flat_atomic_pk_add_f16 v[2:3], a1 ; encoding: [0x00,0x00,0x38,0xdd,0x02,0x01,0x80,0x00]
40 0x00,0x00,0x38,0xdd,0x02,0x01,0x80,0x00
42 # GFX940: flat_atomic_pk_add_bf16 v4, v[2:3], v1 sc0 ; encoding: [0x00,0x00,0x49,0xdd,0x02,0x01,0x00,0x04]
43 0x00,0x00,0x49,0xdd,0x02,0x01,0x00,0x04
45 # GFX940: flat_atomic_pk_add_bf16 a4, v[2:3], a1 sc0 ; encoding: [0x00,0x00,0x49,0xdd,0x02,0x01,0x80,0x04]
46 0x00,0x00,0x49,0xdd,0x02,0x01,0x80,0x04
48 # GFX940: flat_atomic_pk_add_bf16 v[2:3], v1 ; encoding: [0x00,0x00,0x48,0xdd,0x02,0x01,0x00,0x00]
49 0x00,0x00,0x48,0xdd,0x02,0x01,0x00,0x00
51 # GFX940: flat_atomic_pk_add_bf16 v[2:3], a1 ; encoding: [0x00,0x00,0x48,0xdd,0x02,0x01,0x80,0x00]
52 0x00,0x00,0x48,0xdd,0x02,0x01,0x80,0x00
54 # GFX940: global_atomic_pk_add_bf16 v4, v[2:3], v1, off sc0 ; encoding: [0x00,0x80,0x49,0xdd,0x02,0x01,0x7f,0x04]
55 0x00,0x80,0x49,0xdd,0x02,0x01,0x7f,0x04
57 # GFX940: global_atomic_pk_add_bf16 a4, v[2:3], a1, off sc0 ; encoding: [0x00,0x80,0x49,0xdd,0x02,0x01,0xff,0x04]
58 0x00,0x80,0x49,0xdd,0x02,0x01,0xff,0x04
60 # GFX940: global_atomic_pk_add_bf16 v[2:3], v1, off ; encoding: [0x00,0x80,0x48,0xdd,0x02,0x01,0x7f,0x00]
61 0x00,0x80,0x48,0xdd,0x02,0x01,0x7f,0x00
63 # GFX940: global_atomic_pk_add_bf16 v[2:3], a1, off ; encoding: [0x00,0x80,0x48,0xdd,0x02,0x01,0xff,0x00]
64 0x00,0x80,0x48,0xdd,0x02,0x01,0xff,0x00
66 # GFX940: ds_pk_add_f16 v2, v1 ; encoding: [0x00,0x00,0x2e,0xd8,0x02,0x01,0x00,0x00]
67 0x00,0x00,0x2e,0xd8,0x02,0x01,0x00,0x00
69 # GFX940: ds_pk_add_f16 v2, a1 ; encoding: [0x00,0x00,0x2e,0xda,0x02,0x01,0x00,0x00]
70 0x00,0x00,0x2e,0xda,0x02,0x01,0x00,0x00
72 # GFX940: ds_pk_add_rtn_f16 v3, v2, v1 ; encoding: [0x00,0x00,0x6e,0xd9,0x02,0x01,0x00,0x03]
73 0x00,0x00,0x6e,0xd9,0x02,0x01,0x00,0x03
75 # GFX940: ds_pk_add_rtn_f16 a3, v2, a1 ; encoding: [0x00,0x00,0x6e,0xdb,0x02,0x01,0x00,0x03]
76 0x00,0x00,0x6e,0xdb,0x02,0x01,0x00,0x03
78 # GFX940: ds_pk_add_bf16 v2, v1 ; encoding: [0x00,0x00,0x30,0xd8,0x02,0x01,0x00,0x00]
79 0x00,0x00,0x30,0xd8,0x02,0x01,0x00,0x00
81 # GFX940: ds_pk_add_bf16 v2, a1 ; encoding: [0x00,0x00,0x30,0xda,0x02,0x01,0x00,0x00]
82 0x00,0x00,0x30,0xda,0x02,0x01,0x00,0x00
84 # GFX940: ds_pk_add_rtn_bf16 v3, v2, v1 ; encoding: [0x00,0x00,0x70,0xd9,0x02,0x01,0x00,0x03]
85 0x00,0x00,0x70,0xd9,0x02,0x01,0x00,0x03
87 # GFX940: ds_pk_add_rtn_bf16 a3, v2, a1 ; encoding: [0x00,0x00,0x70,0xdb,0x02,0x01,0x00,0x03]
88 0x00,0x00,0x70,0xdb,0x02,0x01,0x00,0x03
90 # GFX940: global_load_lds_dword v[2:3], off ; encoding: [0x00,0x80,0xa8,0xdc,0x02,0x00,0x7f,0x00]
91 0x00,0x80,0xa8,0xdc,0x02,0x00,0x7f,0x00
93 # GFX940: global_load_lds_dword v[2:3], off sc0 nt sc1 ; encoding: [0x00,0x80,0xab,0xde,0x02,0x00,0x7f,0x00]
94 0x00,0x80,0xab,0xde,0x02,0x00,0x7f,0x00
96 # GFX940: global_load_lds_dword v[2:3], off offset:4 ; encoding: [0x04,0x80,0xa8,0xdc,0x02,0x00,0x7f,0x00]
97 0x04,0x80,0xa8,0xdc,0x02,0x00,0x7f,0x00
99 # GFX940: global_load_lds_dword v2, s[4:5] offset:4 ; encoding: [0x04,0x80,0xa8,0xdc,0x02,0x00,0x04,0x00]
100 0x04,0x80,0xa8,0xdc,0x02,0x00,0x04,0x00
102 # GFX940: global_load_lds_ubyte v[2:3], off ; encoding: [0x00,0x80,0x98,0xdc,0x02,0x00,0x7f,0x00]
103 0x00,0x80,0x98,0xdc,0x02,0x00,0x7f,0x00
105 # GFX940: global_load_lds_sbyte v[2:3], off ; encoding: [0x00,0x80,0x9c,0xdc,0x02,0x00,0x7f,0x00]
106 0x00,0x80,0x9c,0xdc,0x02,0x00,0x7f,0x00
108 # GFX940: global_load_lds_sshort v[2:3], off ; encoding: [0x00,0x80,0xa4,0xdc,0x02,0x00,0x7f,0x00]
109 0x00,0x80,0xa4,0xdc,0x02,0x00,0x7f,0x00
111 # GFX940: global_load_lds_ushort v[2:3], off ; encoding: [0x00,0x80,0xa0,0xdc,0x02,0x00,0x7f,0x00]
112 0x00,0x80,0xa0,0xdc,0x02,0x00,0x7f,0x00
114 # GFX940: scratch_load_lds_dword v2, off ; encoding: [0x00,0x60,0xa8,0xdc,0x02,0x00,0x7f,0x00]
115 0x00,0x60,0xa8,0xdc,0x02,0x00,0x7f,0x00
117 # GFX940: scratch_load_lds_dword v2, s4 ; encoding: [0x00,0x60,0xa8,0xdc,0x02,0x00,0x04,0x00]
118 0x00,0x60,0xa8,0xdc,0x02,0x00,0x04,0x00
120 # GFX940: scratch_load_lds_dword v2, s4 offset:4 ; encoding: [0x04,0x60,0xa8,0xdc,0x02,0x00,0x04,0x00]
121 0x04,0x60,0xa8,0xdc,0x02,0x00,0x04,0x00
123 # GFX940: scratch_load_lds_dword off, s4 offset:4 ; encoding: [0x04,0x40,0xa8,0xdc,0x00,0x00,0x04,0x00]
124 0x04,0x40,0xa8,0xdc,0x00,0x00,0x04,0x00
126 # GFX940: scratch_load_lds_dword off, off offset:4 ; encoding: [0x04,0x40,0xa8,0xdc,0x00,0x00,0x7f,0x00]
127 0x04,0x40,0xa8,0xdc,0x00,0x00,0x7f,0x00
129 # GFX940: scratch_load_lds_dword off, off offset:4 ; encoding: [0x04,0x40,0xa8,0xdc,0x00,0x00,0x7f,0x00]
130 0x04,0x40,0xa8,0xdc,0x00,0x00,0x7f,0x00
132 # GFX940: scratch_load_lds_ubyte v2, off ; encoding: [0x00,0x60,0x98,0xdc,0x02,0x00,0x7f,0x00]
133 0x00,0x60,0x98,0xdc,0x02,0x00,0x7f,0x00
135 # GFX940: scratch_load_lds_sbyte v2, off ; encoding: [0x00,0x60,0x9c,0xdc,0x02,0x00,0x7f,0x00]
136 0x00,0x60,0x9c,0xdc,0x02,0x00,0x7f,0x00
138 # GFX940: scratch_load_lds_ushort v2, off ; encoding: [0x00,0x60,0xa0,0xdc,0x02,0x00,0x7f,0x00]
139 0x00,0x60,0xa0,0xdc,0x02,0x00,0x7f,0x00
141 # GFX940: scratch_load_lds_sshort v2, off ; encoding: [0x00,0x60,0xa4,0xdc,0x02,0x00,0x7f,0x00]
142 0x00,0x60,0xa4,0xdc,0x02,0x00,0x7f,0x00
144 # GFX940: s_getreg_b32 s1, hwreg(HW_REG_XCC_ID) ; encoding: [0x14,0xf8,0x81,0xb8]
147 # GFX940: s_getreg_b32 s1, hwreg(HW_REG_SQ_PERF_SNAPSHOT_DATA) ; encoding: [0x15,0xf8,0x81,0xb8]
150 # GFX940: s_getreg_b32 s1, hwreg(HW_REG_SQ_PERF_SNAPSHOT_DATA1) ; encoding: [0x16,0xf8,0x81,0xb8]
153 # GFX940: s_getreg_b32 s1, hwreg(HW_REG_SQ_PERF_SNAPSHOT_PC_LO) ; encoding: [0x17,0xf8,0x81,0xb8]
156 # GFX940: s_getreg_b32 s1, hwreg(HW_REG_SQ_PERF_SNAPSHOT_PC_HI) ; encoding: [0x18,0xf8,0x81,0xb8]
159 # GFX940: v_mov_b64_e32 v[2:3], v[4:5] ; encoding: [0x04,0x71,0x04,0x7e]
162 # GFX940: v_mov_b64_dpp v[2:3], v[4:5] row_newbcast:1 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0x70,0x04,0x7e,0x04,0x51,0x01,0xff]
163 0xfa,0x70,0x04,0x7e,0x04,0x51,0x01,0xff
165 # GFX940: v_mov_b64_e32 v[2:3], s[4:5] ; encoding: [0x04,0x70,0x04,0x7e]
168 # GFX940: v_mov_b64_e32 v[2:3], 1 ; encoding: [0x81,0x70,0x04,0x7e]
171 # GFX940: v_mov_b64_e32 v[2:3], 0x64 ; encoding: [0xff,0x70,0x04,0x7e,0x64,0x00,0x00,0x00]
172 0xff,0x70,0x04,0x7e,0x64,0x00,0x00,0x00
174 # GFX940: v_lshl_add_u64 v[2:3], s[4:5], v7, v[8:9] ; encoding: [0x02,0x00,0x08,0xd2,0x04,0x0e,0x22,0x04]
175 0x02,0x00,0x08,0xd2,0x04,0x0e,0x22,0x04
177 # GFX940: v_lshl_add_u64 v[2:3], v[4:5], 0, 1 ; encoding: [0x02,0x00,0x08,0xd2,0x04,0x01,0x05,0x02]
178 0x02,0x00,0x08,0xd2,0x04,0x01,0x05,0x02
180 # GFX940: v_lshl_add_u64 v[2:3], v[4:5], 3, s[2:3] ; encoding: [0x02,0x00,0x08,0xd2,0x04,0x07,0x09,0x00]
181 0x02,0x00,0x08,0xd2,0x04,0x07,0x09,0x00
183 # GFX940: v_lshl_add_u64 v[2:3], s[4:5], 4, v[2:3] ; encoding: [0x02,0x00,0x08,0xd2,0x04,0x08,0x09,0x04]
184 0x02,0x00,0x08,0xd2,0x04,0x08,0x09,0x04
186 # GFX940: buffer_wbl2 sc1 ; encoding: [0x00,0x80,0xa0,0xe0,0x00,0x00,0x00,0x00]
187 0x00,0x80,0xa0,0xe0,0x00,0x00,0x00,0x00
189 # GFX940: buffer_wbl2 sc0 ; encoding: [0x00,0x40,0xa0,0xe0,0x00,0x00,0x00,0x00]
190 0x00,0x40,0xa0,0xe0,0x00,0x00,0x00,0x00
192 # GFX940: buffer_wbl2 sc0 sc1 ; encoding: [0x00,0xc0,0xa0,0xe0,0x00,0x00,0x00,0x00]
193 0x00,0xc0,0xa0,0xe0,0x00,0x00,0x00,0x00
195 # GFX940: buffer_inv sc0 ; encoding: [0x00,0x40,0xa4,0xe0,0x00,0x00,0x00,0x00]
196 0x00,0x40,0xa4,0xe0,0x00,0x00,0x00,0x00
198 # GFX940: buffer_inv sc1 ; encoding: [0x00,0x80,0xa4,0xe0,0x00,0x00,0x00,0x00]
199 0x00,0x80,0xa4,0xe0,0x00,0x00,0x00,0x00
201 # GFX940: buffer_inv sc0 sc1 ; encoding: [0x00,0xc0,0xa4,0xe0,0x00,0x00,0x00,0x00]
202 0x00,0xc0,0xa4,0xe0,0x00,0x00,0x00,0x00
204 # GFX940: buffer_atomic_swap v5, off, s[8:11], s3 sc0 ; encoding: [0x00,0x40,0x00,0xe1,0x00,0x05,0x02,0x03]
205 0x00,0x40,0x00,0xe1,0x00,0x05,0x02,0x03
207 # GFX940: buffer_atomic_swap v5, off, s[8:11], s3 nt ; encoding: [0x00,0x00,0x02,0xe1,0x00,0x05,0x02,0x03]
208 0x00,0x00,0x02,0xe1,0x00,0x05,0x02,0x03
210 # GFX940: v_fmac_f64_e32 v[4:5], v[2:3], v[4:5] ; encoding: [0x02,0x09,0x08,0x08]
213 # GFX940: v_fmac_f64_e32 v[254:255], v[2:3], v[4:5] ; encoding: [0x02,0x09,0xfc,0x09]
216 # GFX940: v_fmac_f64_e32 v[4:5], v[254:255], v[4:5] ; encoding: [0xfe,0x09,0x08,0x08]
219 # GFX940: v_fmac_f64_e32 v[4:5], flat_scratch, v[4:5] ; encoding: [0x66,0x08,0x08,0x08]
222 # GFX940: v_fmac_f64_e32 v[4:5], vcc, v[4:5] ; encoding: [0x6a,0x08,0x08,0x08]
225 # GFX940: v_fmac_f64_e32 v[4:5], exec, v[4:5] ; encoding: [0x7e,0x08,0x08,0x08]
228 # GFX940: v_fmac_f64_e32 v[4:5], 0, v[4:5] ; encoding: [0x80,0x08,0x08,0x08]
231 # GFX940: v_fmac_f64_e32 v[4:5], -1, v[4:5] ; encoding: [0xc1,0x08,0x08,0x08]
234 # GFX940: v_fmac_f64_e32 v[4:5], 0.5, v[4:5] ; encoding: [0xf0,0x08,0x08,0x08]
237 # GFX940: v_fmac_f64_e32 v[4:5], -4.0, v[4:5] ; encoding: [0xf7,0x08,0x08,0x08]
240 # GFX940: v_fmac_f64_e32 v[4:5], 0xaf123456, v[4:5] ; encoding: [0xff,0x08,0x08,0x08,0x56,0x34,0x12,0xaf]
241 0xff,0x08,0x08,0x08,0x56,0x34,0x12,0xaf
243 # GFX940: v_fmac_f64_e32 v[4:5], 0x3f717273, v[4:5] ; encoding: [0xff,0x08,0x08,0x08,0x73,0x72,0x71,0x3f]
244 0xff,0x08,0x08,0x08,0x73,0x72,0x71,0x3f
246 # GFX940: v_fmac_f64_e32 v[4:5], v[2:3], v[254:255] ; encoding: [0x02,0xfd,0x09,0x08]
249 # GFX940: v_fmac_f64_e64 v[4:5], v[2:3], v[8:9] ; encoding: [0x04,0x00,0x04,0xd1,0x02,0x11,0x02,0x00]
250 0x04,0x00,0x04,0xd1,0x02,0x11,0x02,0x00
252 # GFX940: v_fmac_f64_e64 v[254:255], v[2:3], v[8:9] ; encoding: [0xfe,0x00,0x04,0xd1,0x02,0x11,0x02,0x00]
253 0xfe,0x00,0x04,0xd1,0x02,0x11,0x02,0x00
255 # GFX940: v_fmac_f64_e64 v[4:5], v[254:255], v[8:9] ; encoding: [0x04,0x00,0x04,0xd1,0xfe,0x11,0x02,0x00]
256 0x04,0x00,0x04,0xd1,0xfe,0x11,0x02,0x00
258 # GFX940: v_fmac_f64_e64 v[4:5], flat_scratch, v[8:9] ; encoding: [0x04,0x00,0x04,0xd1,0x66,0x10,0x02,0x00]
259 0x04,0x00,0x04,0xd1,0x66,0x10,0x02,0x00
261 # GFX940: v_fmac_f64_e64 v[4:5], vcc, v[8:9] ; encoding: [0x04,0x00,0x04,0xd1,0x6a,0x10,0x02,0x00]
262 0x04,0x00,0x04,0xd1,0x6a,0x10,0x02,0x00
264 # GFX940: v_fmac_f64_e64 v[4:5], exec, v[8:9] ; encoding: [0x04,0x00,0x04,0xd1,0x7e,0x10,0x02,0x00]
265 0x04,0x00,0x04,0xd1,0x7e,0x10,0x02,0x00
267 # GFX940: v_fmac_f64_e64 v[4:5], 0, v[8:9] ; encoding: [0x04,0x00,0x04,0xd1,0x80,0x10,0x02,0x00]
268 0x04,0x00,0x04,0xd1,0x80,0x10,0x02,0x00
270 # GFX940: v_fmac_f64_e64 v[4:5], -1, v[8:9] ; encoding: [0x04,0x00,0x04,0xd1,0xc1,0x10,0x02,0x00]
271 0x04,0x00,0x04,0xd1,0xc1,0x10,0x02,0x00
273 # GFX940: v_fmac_f64_e64 v[4:5], 0.5, v[8:9] ; encoding: [0x04,0x00,0x04,0xd1,0xf0,0x10,0x02,0x00]
274 0x04,0x00,0x04,0xd1,0xf0,0x10,0x02,0x00
276 # GFX940: v_fmac_f64_e64 v[4:5], -4.0, v[8:9] ; encoding: [0x04,0x00,0x04,0xd1,0xf7,0x10,0x02,0x00]
277 0x04,0x00,0x04,0xd1,0xf7,0x10,0x02,0x00
279 # GFX940: v_fmac_f64_e64 v[4:5], v[2:3], v[254:255] ; encoding: [0x04,0x00,0x04,0xd1,0x02,0xfd,0x03,0x00]
280 0x04,0x00,0x04,0xd1,0x02,0xfd,0x03,0x00
282 # GFX940: v_fmac_f64_e64 v[4:5], v[2:3], flat_scratch ; encoding: [0x04,0x00,0x04,0xd1,0x02,0xcd,0x00,0x00]
283 0x04,0x00,0x04,0xd1,0x02,0xcd,0x00,0x00
285 # GFX940: v_fmac_f64_e64 v[4:5], v[2:3], vcc ; encoding: [0x04,0x00,0x04,0xd1,0x02,0xd5,0x00,0x00]
286 0x04,0x00,0x04,0xd1,0x02,0xd5,0x00,0x00
288 # GFX940: v_fmac_f64_e64 v[4:5], v[2:3], exec ; encoding: [0x04,0x00,0x04,0xd1,0x02,0xfd,0x00,0x00]
289 0x04,0x00,0x04,0xd1,0x02,0xfd,0x00,0x00
291 # GFX940: v_fmac_f64_e64 v[4:5], v[2:3], 0 ; encoding: [0x04,0x00,0x04,0xd1,0x02,0x01,0x01,0x00]
292 0x04,0x00,0x04,0xd1,0x02,0x01,0x01,0x00
294 # GFX940: v_fmac_f64_e64 v[4:5], v[2:3], -1 ; encoding: [0x04,0x00,0x04,0xd1,0x02,0x83,0x01,0x00]
295 0x04,0x00,0x04,0xd1,0x02,0x83,0x01,0x00
297 # GFX940: v_fmac_f64_e64 v[4:5], v[2:3], 0.5 ; encoding: [0x04,0x00,0x04,0xd1,0x02,0xe1,0x01,0x00]
298 0x04,0x00,0x04,0xd1,0x02,0xe1,0x01,0x00
300 # GFX940: v_fmac_f64_e64 v[4:5], v[2:3], -4.0 ; encoding: [0x04,0x00,0x04,0xd1,0x02,0xef,0x01,0x00]
301 0x04,0x00,0x04,0xd1,0x02,0xef,0x01,0x00
303 # GFX940: v_fmac_f64_e64 v[4:5], -v[2:3], v[8:9] ; encoding: [0x04,0x00,0x04,0xd1,0x02,0x11,0x02,0x20]
304 0x04,0x00,0x04,0xd1,0x02,0x11,0x02,0x20
306 # GFX940: v_fmac_f64_e64 v[4:5], v[2:3], -v[8:9] ; encoding: [0x04,0x00,0x04,0xd1,0x02,0x11,0x02,0x40]
307 0x04,0x00,0x04,0xd1,0x02,0x11,0x02,0x40
309 # GFX940: v_fmac_f64_e64 v[4:5], -v[2:3], -v[8:9] ; encoding: [0x04,0x00,0x04,0xd1,0x02,0x11,0x02,0x60]
310 0x04,0x00,0x04,0xd1,0x02,0x11,0x02,0x60
312 # GFX940: v_fmac_f64_e64 v[4:5], |v[2:3]|, v[8:9] ; encoding: [0x04,0x01,0x04,0xd1,0x02,0x11,0x02,0x00]
313 0x04,0x01,0x04,0xd1,0x02,0x11,0x02,0x00
315 # GFX940: v_fmac_f64_e64 v[4:5], v[2:3], |v[8:9]| ; encoding: [0x04,0x02,0x04,0xd1,0x02,0x11,0x02,0x00]
316 0x04,0x02,0x04,0xd1,0x02,0x11,0x02,0x00
318 # GFX940: v_fmac_f64_e64 v[4:5], |v[2:3]|, |v[8:9]| ; encoding: [0x04,0x03,0x04,0xd1,0x02,0x11,0x02,0x00]
319 0x04,0x03,0x04,0xd1,0x02,0x11,0x02,0x00
321 # GFX940: v_fmac_f64_e64 v[4:5], v[2:3], v[8:9] clamp ; encoding: [0x04,0x80,0x04,0xd1,0x02,0x11,0x02,0x00]
322 0x04,0x80,0x04,0xd1,0x02,0x11,0x02,0x00
324 # GFX940: v_fmac_f64_e64 v[4:5], v[2:3], v[8:9] mul:2 ; encoding: [0x04,0x00,0x04,0xd1,0x02,0x11,0x02,0x08]
325 0x04,0x00,0x04,0xd1,0x02,0x11,0x02,0x08
327 # GFX940: v_fmac_f64_e64 v[4:5], v[2:3], v[8:9] mul:4 ; encoding: [0x04,0x00,0x04,0xd1,0x02,0x11,0x02,0x10]
328 0x04,0x00,0x04,0xd1,0x02,0x11,0x02,0x10
330 # GFX940: v_fmac_f64_e64 v[4:5], v[2:3], v[8:9] div:2 ; encoding: [0x04,0x00,0x04,0xd1,0x02,0x11,0x02,0x18]
331 0x04,0x00,0x04,0xd1,0x02,0x11,0x02,0x18
333 # GFX940: v_fmamk_f32 v0, v2, 0x42c80000, v3 ; encoding: [0x02,0x07,0x00,0x2e,0x00,0x00,0xc8,0x42]
334 0x02,0x07,0x00,0x2e,0x00,0x00,0xc8,0x42
336 # GFX940: v_fmaak_f32 v0, v2, v3, 0x42c80000 ; encoding: [0x02,0x07,0x00,0x30,0x00,0x00,0xc8,0x42]
337 0x02,0x07,0x00,0x30,0x00,0x00,0xc8,0x42
339 # GFX940: global_atomic_add_f32 v0, v[0:1], v2, off sc0 sc1 ; encoding: [0x00,0x80,0x35,0xdf,0x00,0x02,0x7f,0x00]
340 0x00,0x80,0x35,0xdf,0x00,0x02,0x7f,0x00
342 # GFX940: global_atomic_add_f32 v[0:1], v2, off sc1 ; encoding: [0x00,0x80,0x34,0xdf,0x00,0x02,0x7f,0x00]
343 0x00,0x80,0x34,0xdf,0x00,0x02,0x7f,0x00
345 # GFX940: global_atomic_add_f32 v0, v2, s[0:1] sc1 ; encoding: [0x00,0x80,0x34,0xdf,0x00,0x02,0x00,0x00]
346 0x00,0x80,0x34,0xdf,0x00,0x02,0x00,0x00
348 # GFX940: global_atomic_add_f32 v1, v0, v2, s[0:1] sc0 sc1 ; encoding: [0x00,0x80,0x35,0xdf,0x00,0x02,0x00,0x01]
349 0x00,0x80,0x35,0xdf,0x00,0x02,0x00,0x01
351 # GFX940: global_atomic_pk_add_f16 v0, v[0:1], v2, off sc0 sc1 ; encoding: [0x00,0x80,0x39,0xdf,0x00,0x02,0x7f,0x00]
352 0x00,0x80,0x39,0xdf,0x00,0x02,0x7f,0x00
354 # GFX940: flat_atomic_add_f64 v[0:1], v[0:1], v[2:3] sc0 sc1 ; encoding: [0x00,0x00,0x3d,0xdf,0x00,0x02,0x00,0x00]
355 0x00,0x00,0x3d,0xdf,0x00,0x02,0x00,0x00
357 # GFX940: flat_atomic_add_f64 v[0:1], v[2:3] sc1 ; encoding: [0x00,0x00,0x3c,0xdf,0x00,0x02,0x00,0x00]
358 0x00,0x00,0x3c,0xdf,0x00,0x02,0x00,0x00
360 # GFX940: flat_atomic_min_f64 v[0:1], v[2:3] sc1 ; encoding: [0x00,0x00,0x40,0xdf,0x00,0x02,0x00,0x00]
361 0x00,0x00,0x40,0xdf,0x00,0x02,0x00,0x00
363 # GFX940: flat_atomic_max_f64 v[0:1], v[2:3] sc1 ; encoding: [0x00,0x00,0x44,0xdf,0x00,0x02,0x00,0x00]
364 0x00,0x00,0x44,0xdf,0x00,0x02,0x00,0x00
366 # GFX940: global_atomic_add_f64 v[0:1], v[2:3], off sc1 ; encoding: [0x00,0x80,0x3c,0xdf,0x00,0x02,0x7f,0x00]
367 0x00,0x80,0x3c,0xdf,0x00,0x02,0x7f,0x00
369 # GFX940: global_atomic_min_f64 v[0:1], v[2:3], off sc1 ; encoding: [0x00,0x80,0x40,0xdf,0x00,0x02,0x7f,0x00]
370 0x00,0x80,0x40,0xdf,0x00,0x02,0x7f,0x00
372 # GFX940: global_atomic_max_f64 v[0:1], v[2:3], off sc1 ; encoding: [0x00,0x80,0x44,0xdf,0x00,0x02,0x7f,0x00]
373 0x00,0x80,0x44,0xdf,0x00,0x02,0x7f,0x00
375 # GFX940: buffer_atomic_add_f32 v4, off, s[8:11], s3 sc1 ; encoding: [0x00,0x80,0x34,0xe1,0x00,0x04,0x02,0x03]
376 0x00,0x80,0x34,0xe1,0x00,0x04,0x02,0x03
378 # GFX940: buffer_atomic_pk_add_f16 v4, off, s[8:11], s3 sc1 ; encoding: [0x00,0x80,0x38,0xe1,0x00,0x04,0x02,0x03]
379 0x00,0x80,0x38,0xe1,0x00,0x04,0x02,0x03
381 # GFX940: buffer_atomic_add_f64 v[4:5], off, s[8:11], s3 sc1 ; encoding: [0x00,0x80,0x3c,0xe1,0x00,0x04,0x02,0x03]
382 0x00,0x80,0x3c,0xe1,0x00,0x04,0x02,0x03
384 # GFX940: buffer_atomic_max_f64 v[4:5], off, s[8:11], s3 sc1 ; encoding: [0x00,0x80,0x44,0xe1,0x00,0x04,0x02,0x03]
385 0x00,0x80,0x44,0xe1,0x00,0x04,0x02,0x03
387 # GFX940: buffer_atomic_min_f64 v[4:5], off, s[8:11], s3 sc1 ; encoding: [0x00,0x80,0x40,0xe1,0x00,0x04,0x02,0x03]
388 0x00,0x80,0x40,0xe1,0x00,0x04,0x02,0x03
390 # GFX940: v_cvt_f32_bf8_e32 v1, s3 ; encoding: [0x03,0xaa,0x02,0x7e]
393 # GFX940: v_cvt_f32_bf8_e32 v1, 3 ; encoding: [0x83,0xaa,0x02,0x7e]
396 # GFX940: v_cvt_f32_bf8_e32 v1, v3 ; encoding: [0x03,0xab,0x02,0x7e]
399 # GFX940: v_cvt_f32_bf8_sdwa v1, s3 src0_sel:BYTE_1 ; encoding: [0xf9,0xaa,0x02,0x7e,0x03,0x06,0x81,0x00]
400 0xf9,0xaa,0x02,0x7e,0x03,0x06,0x81,0x00
402 # GFX940: v_cvt_f32_bf8_dpp v1, v3 quad_perm:[0,2,1,1] row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xaa,0x02,0x7e,0x03,0x58,0x00,0xff]
403 0xfa,0xaa,0x02,0x7e,0x03,0x58,0x00,0xff
405 # GFX940: v_cvt_f32_bf8_e64 v1, s3 mul:2 ; encoding: [0x01,0x00,0x95,0xd1,0x03,0x00,0x00,0x08]
406 0x01,0x00,0x95,0xd1,0x03,0x00,0x00,0x08
408 # GFX940: v_cvt_f32_bf8_sdwa v1, s3 clamp mul:2 src0_sel:BYTE_1 ; encoding: [0xf9,0xaa,0x02,0x7e,0x03,0x66,0x81,0x00]
409 0xf9,0xaa,0x02,0x7e,0x03,0x66,0x81,0x00
411 # GFX940: v_cvt_f32_bf8_e64 v1, s3 clamp ; encoding: [0x01,0x80,0x95,0xd1,0x03,0x00,0x00,0x00]
412 0x01,0x80,0x95,0xd1,0x03,0x00,0x00,0x00
414 # GFX940: v_cvt_f32_fp8_e32 v1, s3 ; encoding: [0x03,0xa8,0x02,0x7e]
417 # GFX940: v_cvt_f32_fp8_e32 v1, 3 ; encoding: [0x83,0xa8,0x02,0x7e]
420 # GFX940: v_cvt_f32_fp8_e32 v1, v3 ; encoding: [0x03,0xa9,0x02,0x7e]
423 # GFX940: v_cvt_f32_fp8_sdwa v1, s3 src0_sel:BYTE_1 ; encoding: [0xf9,0xa8,0x02,0x7e,0x03,0x06,0x81,0x00]
424 0xf9,0xa8,0x02,0x7e,0x03,0x06,0x81,0x00
426 # GFX940: v_cvt_f32_fp8_dpp v1, v3 quad_perm:[0,2,1,1] row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xa8,0x02,0x7e,0x03,0x58,0x00,0xff]
427 0xfa,0xa8,0x02,0x7e,0x03,0x58,0x00,0xff
429 # GFX940: v_cvt_f32_fp8_e64 v1, s3 mul:2 ; encoding: [0x01,0x00,0x94,0xd1,0x03,0x00,0x00,0x08]
430 0x01,0x00,0x94,0xd1,0x03,0x00,0x00,0x08
432 # GFX940: v_cvt_f32_fp8_sdwa v1, s3 clamp mul:2 src0_sel:BYTE_1 ; encoding: [0xf9,0xa8,0x02,0x7e,0x03,0x66,0x81,0x00]
433 0xf9,0xa8,0x02,0x7e,0x03,0x66,0x81,0x00
435 # GFX940: v_cvt_f32_fp8_e64 v1, s3 clamp ; encoding: [0x01,0x80,0x94,0xd1,0x03,0x00,0x00,0x00]
436 0x01,0x80,0x94,0xd1,0x03,0x00,0x00,0x00
438 # GFX940: v_cvt_f32_fp8_sdwa v1, 3 src0_sel:BYTE_1 ; encoding: [0xf9,0xa8,0x02,0x7e,0x83,0x06,0x81,0x00]
439 0xf9,0xa8,0x02,0x7e,0x83,0x06,0x81,0x00
441 # GFX940: v_cvt_pk_f32_bf8_e32 v[2:3], s3 ; encoding: [0x03,0xae,0x04,0x7e]
444 # GFX940: v_cvt_pk_f32_bf8_e32 v[2:3], 3 ; encoding: [0x83,0xae,0x04,0x7e]
447 # GFX940: v_cvt_pk_f32_bf8_e32 v[2:3], v3 ; encoding: [0x03,0xaf,0x04,0x7e]
450 # GFX940: v_cvt_pk_f32_bf8_sdwa v[2:3], s3 src0_sel:WORD_1 ; encoding: [0xf9,0xae,0x04,0x7e,0x03,0x06,0x85,0x00]
451 0xf9,0xae,0x04,0x7e,0x03,0x06,0x85,0x00
453 # GFX940: v_cvt_pk_f32_bf8_dpp v[0:1], v3 row_newbcast:3 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xae,0x00,0x7e,0x03,0x53,0x01,0xff]
454 0xfa,0xae,0x00,0x7e,0x03,0x53,0x01,0xff
456 # GFX940: v_cvt_pk_f32_bf8_e64 v[2:3], s3 mul:2 ; encoding: [0x02,0x00,0x97,0xd1,0x03,0x00,0x00,0x08]
457 0x02,0x00,0x97,0xd1,0x03,0x00,0x00,0x08
459 # GFX940: v_cvt_pk_f32_bf8_sdwa v[2:3], s3 clamp mul:2 src0_sel:WORD_1 ; encoding: [0xf9,0xae,0x04,0x7e,0x03,0x66,0x85,0x00]
460 0xf9,0xae,0x04,0x7e,0x03,0x66,0x85,0x00
462 # GFX940: v_cvt_pk_f32_bf8_e64 v[2:3], s3 clamp ; encoding: [0x02,0x80,0x97,0xd1,0x03,0x00,0x00,0x00]
463 0x02,0x80,0x97,0xd1,0x03,0x00,0x00,0x00
465 # GFX940: v_cvt_pk_f32_fp8_e32 v[2:3], s3 ; encoding: [0x03,0xac,0x04,0x7e]
468 # GFX940: v_cvt_pk_f32_fp8_e32 v[2:3], 3 ; encoding: [0x83,0xac,0x04,0x7e]
471 # GFX940: v_cvt_pk_f32_fp8_e32 v[2:3], v3 ; encoding: [0x03,0xad,0x04,0x7e]
474 # GFX940: v_cvt_pk_f32_fp8_sdwa v[2:3], s3 src0_sel:WORD_1 ; encoding: [0xf9,0xac,0x04,0x7e,0x03,0x06,0x85,0x00]
475 0xf9,0xac,0x04,0x7e,0x03,0x06,0x85,0x00
477 # GFX940: v_cvt_pk_f32_fp8_sdwa v[2:3], 3 src0_sel:WORD_1 ; encoding: [0xf9,0xac,0x04,0x7e,0x83,0x06,0x85,0x00]
478 0xf9,0xac,0x04,0x7e,0x83,0x06,0x85,0x00
480 # GFX940: v_cvt_pk_f32_fp8_dpp v[0:1], v3 row_newbcast:3 row_mask:0xf bank_mask:0xf ; encoding: [0xfa,0xac,0x00,0x7e,0x03,0x53,0x01,0xff]
481 0xfa,0xac,0x00,0x7e,0x03,0x53,0x01,0xff
483 # GFX940: v_cvt_pk_f32_fp8_e64 v[2:3], s3 mul:2 ; encoding: [0x02,0x00,0x96,0xd1,0x03,0x00,0x00,0x08]
484 0x02,0x00,0x96,0xd1,0x03,0x00,0x00,0x08
486 # GFX940: v_cvt_pk_f32_fp8_sdwa v[2:3], s3 clamp mul:2 src0_sel:WORD_1 ; encoding: [0xf9,0xac,0x04,0x7e,0x03,0x66,0x85,0x00]
487 0xf9,0xac,0x04,0x7e,0x03,0x66,0x85,0x00
489 # GFX940: v_cvt_pk_f32_fp8_e64 v[2:3], s3 clamp ; encoding: [0x02,0x80,0x96,0xd1,0x03,0x00,0x00,0x00]
490 0x02,0x80,0x96,0xd1,0x03,0x00,0x00,0x00
492 # GFX940: v_cvt_pk_bf8_f32 v1, v2, v3 ; encoding: [0x01,0x00,0xa3,0xd2,0x02,0x07,0x02,0x00]
493 0x01,0x00,0xa3,0xd2,0x02,0x07,0x02,0x00
495 # GFX940: v_cvt_pk_bf8_f32 v1, -v2, |v3| ; encoding: [0x01,0x02,0xa3,0xd2,0x02,0x07,0x02,0x20]
496 0x01,0x02,0xa3,0xd2,0x02,0x07,0x02,0x20
498 # GFX940: v_cvt_pk_bf8_f32 v1, s2, 3 ; encoding: [0x01,0x00,0xa3,0xd2,0x02,0x06,0x01,0x00]
499 0x01,0x00,0xa3,0xd2,0x02,0x06,0x01,0x00
501 # GFX940: v_cvt_pk_bf8_f32 v1, v2, v3 op_sel:[0,0,1] ; encoding: [0x01,0x40,0xa3,0xd2,0x02,0x07,0x02,0x00]
502 0x01,0x40,0xa3,0xd2,0x02,0x07,0x02,0x00
504 # GFX940: v_cvt_pk_fp8_f32 v1, v2, v3 ; encoding: [0x01,0x00,0xa2,0xd2,0x02,0x07,0x02,0x00]
505 0x01,0x00,0xa2,0xd2,0x02,0x07,0x02,0x00
507 # GFX940: v_cvt_pk_fp8_f32 v1, -v2, |v3| ; encoding: [0x01,0x02,0xa2,0xd2,0x02,0x07,0x02,0x20]
508 0x01,0x02,0xa2,0xd2,0x02,0x07,0x02,0x20
510 # GFX940: v_cvt_pk_fp8_f32 v1, s2, 3 ; encoding: [0x01,0x00,0xa2,0xd2,0x02,0x06,0x01,0x00]
511 0x01,0x00,0xa2,0xd2,0x02,0x06,0x01,0x00
513 # GFX940: v_cvt_pk_fp8_f32 v1, v2, v3 op_sel:[0,0,1] ; encoding: [0x01,0x40,0xa2,0xd2,0x02,0x07,0x02,0x00]
514 0x01,0x40,0xa2,0xd2,0x02,0x07,0x02,0x00
516 # GFX940: v_cvt_sr_bf8_f32 v1, v2, v3 ; encoding: [0x01,0x00,0xa5,0xd2,0x02,0x07,0x02,0x00]
517 0x01,0x00,0xa5,0xd2,0x02,0x07,0x02,0x00
519 # GFX940: v_cvt_sr_bf8_f32 v1, s2, 3 ; encoding: [0x01,0x00,0xa5,0xd2,0x02,0x06,0x01,0x00]
520 0x01,0x00,0xa5,0xd2,0x02,0x06,0x01,0x00
522 # GFX940: v_cvt_sr_bf8_f32 v1, v2, v3 op_sel:[0,0,1,1] ; encoding: [0x01,0x60,0xa5,0xd2,0x02,0x07,0x02,0x00]
523 0x01,0x60,0xa5,0xd2,0x02,0x07,0x02,0x00
525 # GFX940: v_cvt_sr_bf8_f32 v1, v2, v3 op_sel:[0,0,0,1] ; encoding: [0x01,0x40,0xa5,0xd2,0x02,0x07,0x02,0x00]
526 0x01,0x40,0xa5,0xd2,0x02,0x07,0x02,0x00
528 # GFX940: v_cvt_sr_bf8_f32 v1, -|s2|, v3 ; encoding: [0x01,0x01,0xa5,0xd2,0x02,0x06,0x02,0x20]
529 0x01,0x01,0xa5,0xd2,0x02,0x06,0x02,0x20
531 # GFX940: v_cvt_sr_fp8_f32 v1, v2, v3 ; encoding: [0x01,0x00,0xa4,0xd2,0x02,0x07,0x02,0x00]
532 0x01,0x00,0xa4,0xd2,0x02,0x07,0x02,0x00
534 # GFX940: v_cvt_sr_fp8_f32 v1, s2, 3 ; encoding: [0x01,0x00,0xa4,0xd2,0x02,0x06,0x01,0x00]
535 0x01,0x00,0xa4,0xd2,0x02,0x06,0x01,0x00
537 # GFX940: v_cvt_sr_fp8_f32 v1, v2, v3 op_sel:[0,0,1,1] ; encoding: [0x01,0x60,0xa4,0xd2,0x02,0x07,0x02,0x00]
538 0x01,0x60,0xa4,0xd2,0x02,0x07,0x02,0x00
540 # GFX940: v_cvt_sr_fp8_f32 v1, v2, v3 op_sel:[0,0,0,1] ; encoding: [0x01,0x40,0xa4,0xd2,0x02,0x07,0x02,0x00]
541 0x01,0x40,0xa4,0xd2,0x02,0x07,0x02,0x00
543 # GFX940: v_cvt_sr_fp8_f32 v1, -|s2|, v3 ; encoding: [0x01,0x01,0xa4,0xd2,0x02,0x06,0x02,0x20]
544 0x01,0x01,0xa4,0xd2,0x02,0x06,0x02,0x20