Skip to content

Commit 34b6587

Browse files
authored
[AMDGPU] MC support for load monitor instructions on gfx1250 (#150496)
1 parent b82cf20 commit 34b6587

File tree

3 files changed

+199
-0
lines changed

3 files changed

+199
-0
lines changed

llvm/lib/Target/AMDGPU/FLATInstructions.td

Lines changed: 18 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -1193,6 +1193,16 @@ defm SCRATCH_LOAD_LDS_USHORT : FLAT_Scratch_Load_LDS_Pseudo <"scratch_load_lds_u
11931193
defm SCRATCH_LOAD_LDS_SSHORT : FLAT_Scratch_Load_LDS_Pseudo <"scratch_load_lds_sshort">;
11941194
defm SCRATCH_LOAD_LDS_DWORD : FLAT_Scratch_Load_LDS_Pseudo <"scratch_load_lds_dword">;
11951195

1196+
let SubtargetPredicate = isGFX125xOnly in {
1197+
defm FLAT_LOAD_MONITOR_B32 : FLAT_Flat_Load_Pseudo <"flat_load_monitor_b32", VGPR_32>;
1198+
defm FLAT_LOAD_MONITOR_B64 : FLAT_Flat_Load_Pseudo <"flat_load_monitor_b64", VReg_64>;
1199+
defm FLAT_LOAD_MONITOR_B128 : FLAT_Flat_Load_Pseudo <"flat_load_monitor_b128", VReg_128>;
1200+
1201+
defm GLOBAL_LOAD_MONITOR_B32 : FLAT_Global_Load_Pseudo <"global_load_monitor_b32", VGPR_32>;
1202+
defm GLOBAL_LOAD_MONITOR_B64 : FLAT_Global_Load_Pseudo <"global_load_monitor_b64", VReg_64>;
1203+
defm GLOBAL_LOAD_MONITOR_B128 : FLAT_Global_Load_Pseudo <"global_load_monitor_b128", VReg_128>;
1204+
} // End SubtargetPredicate = isGFX125xOnly
1205+
11961206
let SubtargetPredicate = isGFX12Plus in {
11971207
let Uses = [EXEC, M0] in {
11981208
defm GLOBAL_LOAD_BLOCK : FLAT_Global_Load_Pseudo <"global_load_block", VReg_1024>;
@@ -3268,6 +3278,14 @@ defm TENSOR_STOP : VFLAT_Real_gfx1250<0x06f>;
32683278
defm FLAT_PREFETCH_B8 : VFLAT_Real_AllAddr_gfx1250<0x05d>;
32693279
defm GLOBAL_PREFETCH_B8 : VFLAT_Real_AllAddr_gfx1250<0x05d>;
32703280

3281+
defm FLAT_LOAD_MONITOR_B32 : VFLAT_Real_AllAddr_gfx1250<0x070>;
3282+
defm FLAT_LOAD_MONITOR_B64 : VFLAT_Real_AllAddr_gfx1250<0x071>;
3283+
defm FLAT_LOAD_MONITOR_B128 : VFLAT_Real_AllAddr_gfx1250<0x072>;
3284+
3285+
defm GLOBAL_LOAD_MONITOR_B32 : VFLAT_Real_AllAddr_gfx1250<0x070>;
3286+
defm GLOBAL_LOAD_MONITOR_B64 : VFLAT_Real_AllAddr_gfx1250<0x071>;
3287+
defm GLOBAL_LOAD_MONITOR_B128 : VFLAT_Real_AllAddr_gfx1250<0x072>;
3288+
32713289
defm GLOBAL_LOAD_TR_B128_w32 : VFLAT_Real_AllAddr_gfx1250<0x057, "global_load_tr16_b128">;
32723290
defm GLOBAL_LOAD_TR_B64_w32 : VFLAT_Real_AllAddr_gfx1250<0x058, "global_load_tr8_b64">;
32733291

llvm/test/MC/AMDGPU/gfx1250_asm_vflat.s

Lines changed: 88 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -161,6 +161,94 @@ global_prefetch_b8 v[2:3], off offset:64 th:TH_LOAD_NT_RT scope:SCOPE_DEV
161161
// GFX1250: global_prefetch_b8 v[2:3], off offset:64 th:TH_LOAD_NT_RT scope:SCOPE_DEV ; encoding: [0x7c,0x40,0x17,0xee,0x00,0x00,0x48,0x00,0x02,0x40,0x00,0x00]
162162
// GFX12-ERR: :[[@LINE-2]]:{{[0-9]+}}: error: instruction not supported on this GPU
163163

164+
global_load_monitor_b32 v1, v[2:3], off
165+
// GFX1250: global_load_monitor_b32 v1, v[2:3], off ; encoding: [0x7c,0x00,0x1c,0xee,0x01,0x00,0x00,0x00,0x02,0x00,0x00,0x00]
166+
// GFX12-ERR: :[[@LINE-2]]:{{[0-9]+}}: error: instruction not supported on this GPU
167+
168+
global_load_monitor_b32 v1, v[2:3], off offset:64
169+
// GFX1250: global_load_monitor_b32 v1, v[2:3], off offset:64 ; encoding: [0x7c,0x00,0x1c,0xee,0x01,0x00,0x00,0x00,0x02,0x40,0x00,0x00]
170+
// GFX12-ERR: :[[@LINE-2]]:{{[0-9]+}}: error: instruction not supported on this GPU
171+
172+
global_load_monitor_b32 v1, v[2:3], off offset:-64 th:TH_LOAD_NT_HT scope:SCOPE_DEV
173+
// GFX1250: global_load_monitor_b32 v1, v[2:3], off offset:-64 th:TH_LOAD_NT_HT scope:SCOPE_DEV ; encoding: [0x7c,0x00,0x1c,0xee,0x01,0x00,0x68,0x00,0x02,0xc0,0xff,0xff]
174+
// GFX12-ERR: :[[@LINE-2]]:{{[0-9]+}}: error: instruction not supported on this GPU
175+
176+
global_load_monitor_b32 v1, v2, s[0:1]
177+
// GFX1250: global_load_monitor_b32 v1, v2, s[0:1] ; encoding: [0x00,0x00,0x1c,0xee,0x01,0x00,0x00,0x00,0x02,0x00,0x00,0x00]
178+
// GFX12-ERR: :[[@LINE-2]]:{{[0-9]+}}: error: instruction not supported on this GPU
179+
180+
global_load_monitor_b32 v1, v2, s[0:1] offset:64
181+
// GFX1250: global_load_monitor_b32 v1, v2, s[0:1] offset:64 ; encoding: [0x00,0x00,0x1c,0xee,0x01,0x00,0x00,0x00,0x02,0x40,0x00,0x00]
182+
// GFX12-ERR: :[[@LINE-2]]:{{[0-9]+}}: error: instruction not supported on this GPU
183+
184+
global_load_monitor_b32 v1, v2, s[0:1] offset:-64 th:TH_LOAD_BYPASS scope:SCOPE_SYS
185+
// GFX1250: global_load_monitor_b32 v1, v2, s[0:1] offset:-64 th:TH_LOAD_BYPASS scope:SCOPE_SYS ; encoding: [0x00,0x00,0x1c,0xee,0x01,0x00,0x3c,0x00,0x02,0xc0,0xff,0xff]
186+
// GFX12-ERR: :[[@LINE-2]]:{{[0-9]+}}: error: instruction not supported on this GPU
187+
188+
global_load_monitor_b64 v[0:1], v[2:3], off
189+
// GFX1250: global_load_monitor_b64 v[0:1], v[2:3], off ; encoding: [0x7c,0x40,0x1c,0xee,0x00,0x00,0x00,0x00,0x02,0x00,0x00,0x00]
190+
// GFX12-ERR: :[[@LINE-2]]:{{[0-9]+}}: error: instruction not supported on this GPU
191+
192+
global_load_monitor_b64 v[0:1], v[2:3], off offset:64
193+
// GFX1250: global_load_monitor_b64 v[0:1], v[2:3], off offset:64 ; encoding: [0x7c,0x40,0x1c,0xee,0x00,0x00,0x00,0x00,0x02,0x40,0x00,0x00]
194+
// GFX12-ERR: :[[@LINE-2]]:{{[0-9]+}}: error: instruction not supported on this GPU
195+
196+
global_load_monitor_b64 v[0:1], v[2:3], off offset:-64 th:TH_LOAD_HT scope:SCOPE_SE
197+
// GFX1250: global_load_monitor_b64 v[0:1], v[2:3], off offset:-64 th:TH_LOAD_HT scope:SCOPE_SE ; encoding: [0x7c,0x40,0x1c,0xee,0x00,0x00,0x24,0x00,0x02,0xc0,0xff,0xff]
198+
// GFX12-ERR: :[[@LINE-2]]:{{[0-9]+}}: error: instruction not supported on this GPU
199+
200+
global_load_monitor_b64 v[0:1], v2, s[0:1]
201+
// GFX1250: encoding: [0x00,0x40,0x1c,0xee,0x00,0x00,0x00,0x00,0x02,0x00,0x00,0x00]
202+
// GFX12-ERR: :[[@LINE-2]]:{{[0-9]+}}: error: instruction not supported on this GPU
203+
204+
global_load_monitor_b64 v[0:1], v2, s[0:1] offset:64
205+
// GFX1250: global_load_monitor_b64 v[0:1], v2, s[0:1] offset:64 ; encoding: [0x00,0x40,0x1c,0xee,0x00,0x00,0x00,0x00,0x02,0x40,0x00,0x00]
206+
// GFX12-ERR: :[[@LINE-2]]:{{[0-9]+}}: error: instruction not supported on this GPU
207+
208+
global_load_monitor_b64 v[0:1], v2, s[0:1] offset:-64 th:TH_LOAD_BYPASS scope:SCOPE_SYS
209+
// GFX1250: global_load_monitor_b64 v[0:1], v2, s[0:1] offset:-64 th:TH_LOAD_BYPASS scope:SCOPE_SYS ; encoding: [0x00,0x40,0x1c,0xee,0x00,0x00,0x3c,0x00,0x02,0xc0,0xff,0xff]
210+
// GFX12-ERR: :[[@LINE-2]]:{{[0-9]+}}: error: instruction not supported on this GPU
211+
212+
global_load_monitor_b128 v[0:3], v[4:5], off
213+
// GFX1250: global_load_monitor_b128 v[0:3], v[4:5], off ; encoding: [0x7c,0x80,0x1c,0xee,0x00,0x00,0x00,0x00,0x04,0x00,0x00,0x00]
214+
// GFX12-ERR: :[[@LINE-2]]:{{[0-9]+}}: error: instruction not supported on this GPU
215+
216+
global_load_monitor_b128 v[0:3], v[4:5], off offset:64
217+
// GFX1250: global_load_monitor_b128 v[0:3], v[4:5], off offset:64 ; encoding: [0x7c,0x80,0x1c,0xee,0x00,0x00,0x00,0x00,0x04,0x40,0x00,0x00]
218+
// GFX12-ERR: :[[@LINE-2]]:{{[0-9]+}}: error: instruction not supported on this GPU
219+
220+
global_load_monitor_b128 v[0:3], v[4:5], off offset:-64 th:TH_LOAD_NT
221+
// GFX1250: global_load_monitor_b128 v[0:3], v[4:5], off offset:-64 th:TH_LOAD_NT ; encoding: [0x7c,0x80,0x1c,0xee,0x00,0x00,0x10,0x00,0x04,0xc0,0xff,0xff]
222+
// GFX12-ERR: :[[@LINE-2]]:{{[0-9]+}}: error: instruction not supported on this GPU
223+
224+
global_load_monitor_b128 v[0:3], v4, s[0:1]
225+
// GFX1250: global_load_monitor_b128 v[0:3], v4, s[0:1] ; encoding: [0x00,0x80,0x1c,0xee,0x00,0x00,0x00,0x00,0x04,0x00,0x00,0x00]
226+
// GFX12-ERR: :[[@LINE-2]]:{{[0-9]+}}: error: instruction not supported on this GPU
227+
228+
global_load_monitor_b128 v[0:3], v4, s[0:1] offset:64
229+
// GFX1250: global_load_monitor_b128 v[0:3], v4, s[0:1] offset:64 ; encoding: [0x00,0x80,0x1c,0xee,0x00,0x00,0x00,0x00,0x04,0x40,0x00,0x00]
230+
// GFX12-ERR: :[[@LINE-2]]:{{[0-9]+}}: error: instruction not supported on this GPU
231+
232+
global_load_monitor_b128 v[0:3], v4, s[0:1] offset:-64 th:TH_LOAD_BYPASS scope:SCOPE_SYS
233+
// GFX1250: global_load_monitor_b128 v[0:3], v4, s[0:1] offset:-64 th:TH_LOAD_BYPASS scope:SCOPE_SYS ; encoding: [0x00,0x80,0x1c,0xee,0x00,0x00,0x3c,0x00,0x04,0xc0,0xff,0xff]
234+
// GFX12-ERR: :[[@LINE-2]]:{{[0-9]+}}: error: instruction not supported on this GPU
235+
236+
global_load_monitor_b32 v1, v2, s[4:5] offset:64 scale_offset
237+
// GFX1250: global_load_monitor_b32 v1, v2, s[4:5] offset:64 scale_offset ; encoding: [0x04,0x00,0x1c,0xee,0x01,0x00,0x01,0x00,0x02,0x40,0x00,0x00]
238+
// GFX12-ERR: :[[@LINE-2]]:{{[0-9]+}}: error: instruction not supported on this GPU
239+
240+
global_load_monitor_b64 v[2:3], v2, s[4:5] offset:64 scale_offset
241+
// GFX1250: global_load_monitor_b64 v[2:3], v2, s[4:5] offset:64 scale_offset ; encoding: [0x04,0x40,0x1c,0xee,0x02,0x00,0x01,0x00,0x02,0x40,0x00,0x00]
242+
// GFX12-ERR: :[[@LINE-2]]:{{[0-9]+}}: error: instruction not supported on this GPU
243+
244+
flat_load_monitor_b32 v1, v[2:3]
245+
// GFX1250: flat_load_monitor_b32 v1, v[2:3] ; encoding: [0x7c,0x00,0x1c,0xec,0x01,0x00,0x00,0x00,0x02,0x00,0x00,0x00]
246+
// GFX12-ERR: :[[@LINE-2]]:{{[0-9]+}}: error: instruction not supported on this GPU
247+
248+
flat_load_monitor_b32 v1, v[2:3] offset:64
249+
// GFX1250: flat_load_monitor_b32 v1, v[2:3] offset:64 ; encoding: [0x7c,0x00,0x1c,0xec,0x01,0x00,0x00,0x00,0x02,0x40,0x00,0x00]
250+
// GFX12-ERR: :[[@LINE-2]]:{{[0-9]+}}: error: instruction not supported on this GPU
251+
164252
tensor_save s[0:1]
165253
// GFX1250: tensor_save s[0:1] ; encoding: [0x00,0x80,0x1b,0xee,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00]
166254
// GFX12-ERR: :[[@LINE-2]]:{{[0-9]+}}: error: instruction not supported on this GPU

llvm/test/MC/Disassembler/AMDGPU/gfx1250_dasm_vflat.txt

Lines changed: 93 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -3084,6 +3084,99 @@
30843084
# GFX1250: global_prefetch_b8 v[2:3], off th:TH_LOAD_BYPASS scope:SCOPE_SYS ; encoding: [0x7c,0x40,0x17,0xee,0x00,0x00,0x3c,0x00,0x02,0x00,0x00,0x00]
30853085
0x7c,0x40,0x17,0xee,0x00,0x00,0x3c,0x00,0x02,0x00,0x00,0x00
30863086

3087+
# GFX1250: flat_load_monitor_b128 v[0:3], v[4:5] ; encoding: [0x7c,0x80,0x1c,0xec,0x00,0x00,0x00,0x00,0x04,0x00,0x00,0x00]
3088+
0x7c,0x80,0x1c,0xec,0x00,0x00,0x00,0x00,0x04,0x00,0x00,0x00
3089+
3090+
# GFX1250: flat_load_monitor_b128 v[0:3], v[4:5] offset:64 ; encoding: [0x7c,0x80,0x1c,0xec,0x00,0x00,0x00,0x00,0x04,0x40,0x00,0x00]
3091+
0x7c,0x80,0x1c,0xec,0x00,0x00,0x00,0x00,0x04,0x40,0x00,0x00
3092+
3093+
# GFX1250: flat_load_monitor_b128 v[0:3], v[4:5] offset:-64 th:TH_LOAD_BYPASS scope:SCOPE_SYS ; encoding: [0x7c,0x80,0x1c,0xec,0x00,0x00,0x3c,0x00,0x04,0xc0,0xff,0xff]
3094+
0x7c,0x80,0x1c,0xec,0x00,0x00,0x3c,0x00,0x04,0xc0,0xff,0xff
3095+
3096+
# GFX1250: flat_load_monitor_b32 v1, v[2:3] ; encoding: [0x7c,0x00,0x1c,0xec,0x01,0x00,0x00,0x00,0x02,0x00,0x00,0x00]
3097+
0x7c,0x00,0x1c,0xec,0x01,0x00,0x00,0x00,0x02,0x00,0x00,0x00
3098+
3099+
# GFX1250: flat_load_monitor_b32 v1, v[2:3] offset:64 ; encoding: [0x7c,0x00,0x1c,0xec,0x01,0x00,0x00,0x00,0x02,0x40,0x00,0x00]
3100+
0x7c,0x00,0x1c,0xec,0x01,0x00,0x00,0x00,0x02,0x40,0x00,0x00
3101+
3102+
# GFX1250: flat_load_monitor_b32 v1, v[2:3] offset:-64 th:TH_LOAD_BYPASS scope:SCOPE_SYS ; encoding: [0x7c,0x00,0x1c,0xec,0x01,0x00,0x3c,0x00,0x02,0xc0,0xff,0xff]
3103+
0x7c,0x00,0x1c,0xec,0x01,0x00,0x3c,0x00,0x02,0xc0,0xff,0xff
3104+
3105+
# GFX1250: flat_load_monitor_b64 v[0:1], v[2:3] ; encoding: [0x7c,0x40,0x1c,0xec,0x00,0x00,0x00,0x00,0x02,0x00,0x00,0x00]
3106+
0x7c,0x40,0x1c,0xec,0x00,0x00,0x00,0x00,0x02,0x00,0x00,0x00
3107+
3108+
# GFX1250: flat_load_monitor_b64 v[0:1], v[2:3] offset:64 ; encoding: [0x7c,0x40,0x1c,0xec,0x00,0x00,0x00,0x00,0x02,0x40,0x00,0x00]
3109+
0x7c,0x40,0x1c,0xec,0x00,0x00,0x00,0x00,0x02,0x40,0x00,0x00
3110+
3111+
# GFX1250: flat_load_monitor_b64 v[0:1], v[2:3] offset:-64 th:TH_LOAD_BYPASS scope:SCOPE_SYS ; encoding: [0x7c,0x40,0x1c,0xec,0x00,0x00,0x3c,0x00,0x02,0xc0,0xff,0xff]
3112+
0x7c,0x40,0x1c,0xec,0x00,0x00,0x3c,0x00,0x02,0xc0,0xff,0xff
3113+
3114+
# GFX1250: flat_load_monitor_b32 v1, v2, s[4:5] offset:64 scale_offset ; encoding: [0x04,0x00,0x1c,0xec,0x01,0x00,0x01,0x00,0x02,0x40,0x00,0x00]
3115+
0x04,0x00,0x1c,0xec,0x01,0x00,0x01,0x00,0x02,0x40,0x00,0x00
3116+
3117+
# GFX1250: flat_load_monitor_b64 v[2:3], v2, s[4:5] offset:64 scale_offset ; encoding: [0x04,0x40,0x1c,0xec,0x02,0x00,0x01,0x00,0x02,0x40,0x00,0x00]
3118+
0x04,0x40,0x1c,0xec,0x02,0x00,0x01,0x00,0x02,0x40,0x00,0x00
3119+
3120+
# GFX1250: global_load_monitor_b128 v[0:3], v[4:5], off ; encoding: [0x7c,0x80,0x1c,0xee,0x00,0x00,0x00,0x00,0x04,0x00,0x00,0x00]
3121+
0x7c,0x80,0x1c,0xee,0x00,0x00,0x00,0x00,0x04,0x00,0x00,0x00
3122+
3123+
# GFX1250: global_load_monitor_b128 v[0:3], v[4:5], off offset:64 ; encoding: [0x7c,0x80,0x1c,0xee,0x00,0x00,0x00,0x00,0x04,0x40,0x00,0x00]
3124+
0x7c,0x80,0x1c,0xee,0x00,0x00,0x00,0x00,0x04,0x40,0x00,0x00
3125+
3126+
# GFX1250: global_load_monitor_b128 v[0:3], v[4:5], off offset:-64 th:TH_LOAD_NT ; encoding: [0x7c,0x80,0x1c,0xee,0x00,0x00,0x10,0x00,0x04,0xc0,0xff,0xff]
3127+
0x7c,0x80,0x1c,0xee,0x00,0x00,0x10,0x00,0x04,0xc0,0xff,0xff
3128+
3129+
# GFX1250: global_load_monitor_b128 v[0:3], v4, s[0:1] ; encoding: [0x00,0x80,0x1c,0xee,0x00,0x00,0x00,0x00,0x04,0x00,0x00,0x00]
3130+
0x00,0x80,0x1c,0xee,0x00,0x00,0x00,0x00,0x04,0x00,0x00,0x00
3131+
3132+
# GFX1250: global_load_monitor_b128 v[0:3], v4, s[0:1] offset:64 ; encoding: [0x00,0x80,0x1c,0xee,0x00,0x00,0x00,0x00,0x04,0x40,0x00,0x00]
3133+
0x00,0x80,0x1c,0xee,0x00,0x00,0x00,0x00,0x04,0x40,0x00,0x00
3134+
3135+
# GFX1250: global_load_monitor_b128 v[0:3], v4, s[0:1] offset:-64 th:TH_LOAD_BYPASS scope:SCOPE_SYS ; encoding: [0x00,0x80,0x1c,0xee,0x00,0x00,0x3c,0x00,0x04,0xc0,0xff,0xff]
3136+
0x00,0x80,0x1c,0xee,0x00,0x00,0x3c,0x00,0x04,0xc0,0xff,0xff
3137+
3138+
# GFX1250: global_load_monitor_b32 v1, v[2:3], off ; encoding: [0x7c,0x00,0x1c,0xee,0x01,0x00,0x00,0x00,0x02,0x00,0x00,0x00]
3139+
0x7c,0x00,0x1c,0xee,0x01,0x00,0x00,0x00,0x02,0x00,0x00,0x00
3140+
3141+
# GFX1250: global_load_monitor_b32 v1, v[2:3], off offset:64 ; encoding: [0x7c,0x00,0x1c,0xee,0x01,0x00,0x00,0x00,0x02,0x40,0x00,0x00]
3142+
0x7c,0x00,0x1c,0xee,0x01,0x00,0x00,0x00,0x02,0x40,0x00,0x00
3143+
3144+
# GFX1250: global_load_monitor_b32 v1, v[2:3], off offset:-64 th:TH_LOAD_NT_HT scope:SCOPE_DEV ; encoding: [0x7c,0x00,0x1c,0xee,0x01,0x00,0x68,0x00,0x02,0xc0,0xff,0xff]
3145+
0x7c,0x00,0x1c,0xee,0x01,0x00,0x68,0x00,0x02,0xc0,0xff,0xff
3146+
3147+
# GFX1250: global_load_monitor_b32 v1, v2, s[0:1] ; encoding: [0x00,0x00,0x1c,0xee,0x01,0x00,0x00,0x00,0x02,0x00,0x00,0x00]
3148+
0x00,0x00,0x1c,0xee,0x01,0x00,0x00,0x00,0x02,0x00,0x00,0x00
3149+
3150+
# GFX1250: global_load_monitor_b32 v1, v2, s[0:1] offset:64 ; encoding: [0x00,0x00,0x1c,0xee,0x01,0x00,0x00,0x00,0x02,0x40,0x00,0x00]
3151+
0x00,0x00,0x1c,0xee,0x01,0x00,0x00,0x00,0x02,0x40,0x00,0x00
3152+
3153+
# GFX1250: global_load_monitor_b32 v1, v2, s[0:1] offset:-64 th:TH_LOAD_BYPASS scope:SCOPE_SYS ; encoding: [0x00,0x00,0x1c,0xee,0x01,0x00,0x3c,0x00,0x02,0xc0,0xff,0xff]
3154+
0x00,0x00,0x1c,0xee,0x01,0x00,0x3c,0x00,0x02,0xc0,0xff,0xff
3155+
3156+
# GFX1250: global_load_monitor_b64 v[0:1], v[2:3], off ; encoding: [0x7c,0x40,0x1c,0xee,0x00,0x00,0x00,0x00,0x02,0x00,0x00,0x00]
3157+
0x7c,0x40,0x1c,0xee,0x00,0x00,0x00,0x00,0x02,0x00,0x00,0x00
3158+
3159+
# GFX1250: global_load_monitor_b64 v[0:1], v[2:3], off offset:64 ; encoding: [0x7c,0x40,0x1c,0xee,0x00,0x00,0x00,0x00,0x02,0x40,0x00,0x00]
3160+
0x7c,0x40,0x1c,0xee,0x00,0x00,0x00,0x00,0x02,0x40,0x00,0x00
3161+
3162+
# GFX1250: global_load_monitor_b64 v[0:1], v[2:3], off offset:-64 th:TH_LOAD_HT scope:SCOPE_SE ; encoding: [0x7c,0x40,0x1c,0xee,0x00,0x00,0x24,0x00,0x02,0xc0,0xff,0xff]
3163+
0x7c,0x40,0x1c,0xee,0x00,0x00,0x24,0x00,0x02,0xc0,0xff,0xff
3164+
3165+
# GFX1250: global_load_monitor_b64 v[0:1], v2, s[0:1] ; encoding: [0x00,0x40,0x1c,0xee,0x00,0x00,0x00,0x00,0x02,0x00,0x00,0x00]
3166+
0x00,0x40,0x1c,0xee,0x00,0x00,0x00,0x00,0x02,0x00,0x00,0x00
3167+
3168+
# GFX1250: global_load_monitor_b64 v[0:1], v2, s[0:1] offset:64 ; encoding: [0x00,0x40,0x1c,0xee,0x00,0x00,0x00,0x00,0x02,0x40,0x00,0x00]
3169+
0x00,0x40,0x1c,0xee,0x00,0x00,0x00,0x00,0x02,0x40,0x00,0x00
3170+
3171+
# GFX1250: global_load_monitor_b64 v[0:1], v2, s[0:1] offset:-64 th:TH_LOAD_BYPASS scope:SCOPE_SYS ; encoding: [0x00,0x40,0x1c,0xee,0x00,0x00,0x3c,0x00,0x02,0xc0,0xff,0xff]
3172+
0x00,0x40,0x1c,0xee,0x00,0x00,0x3c,0x00,0x02,0xc0,0xff,0xff
3173+
3174+
# GFX1250: global_load_monitor_b32 v1, v2, s[4:5] offset:64 scale_offset ; encoding: [0x04,0x00,0x1c,0xee,0x01,0x00,0x01,0x00,0x02,0x40,0x00,0x00]
3175+
0x04,0x00,0x1c,0xee,0x01,0x00,0x01,0x00,0x02,0x40,0x00,0x00
3176+
3177+
# GFX1250: global_load_monitor_b64 v[2:3], v2, s[4:5] offset:64 scale_offset ; encoding: [0x04,0x40,0x1c,0xee,0x02,0x00,0x01,0x00,0x02,0x40,0x00,0x00]
3178+
0x04,0x40,0x1c,0xee,0x02,0x00,0x01,0x00,0x02,0x40,0x00,0x00
3179+
30873180
# GFX1250: tensor_save s[0:1] ; encoding: [0x00,0x80,0x1b,0xee,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00]
30883181
0x00,0x80,0x1b,0xee,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
30893182

0 commit comments

Comments
 (0)