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
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+amx-int8 -mattr=+avx512f -verify-machineinstrs | FileCheck %s
@buf = dso_local global [3072 x i8] zeroinitializer, align 16
define dso_local void @test1(i16 signext %0, i16 signext %1) nounwind {
; CHECK-LABEL: test1:
; CHECK: # %bb.0:
; CHECK-NEXT: vpxord %zmm0, %zmm0, %zmm0
; CHECK-NEXT: vmovdqu64 %zmm0, -{{[0-9]+}}(%rsp)
; CHECK-NEXT: movb $1, -{{[0-9]+}}(%rsp)
; CHECK-NEXT: movw $8, -{{[0-9]+}}(%rsp)
; CHECK-NEXT: movb $8, -{{[0-9]+}}(%rsp)
; CHECK-NEXT: movw %si, -{{[0-9]+}}(%rsp)
; CHECK-NEXT: movb %dil, -{{[0-9]+}}(%rsp)
; CHECK-NEXT: movw %si, -{{[0-9]+}}(%rsp)
; CHECK-NEXT: movb %dil, -{{[0-9]+}}(%rsp)
; CHECK-NEXT: ldtilecfg -{{[0-9]+}}(%rsp)
; CHECK-NEXT: movl $buf, %eax
; CHECK-NEXT: movl $32, %ecx
; CHECK-NEXT: movw $8, %dx
; CHECK-NEXT: tileloadd (%rax,%rcx), %tmm0
; CHECK-NEXT: movl $buf+1024, %eax
; CHECK-NEXT: tileloadd (%rax,%rcx), %tmm1
; CHECK-NEXT: movl $buf+2048, %eax
; CHECK-NEXT: tileloadd (%rax,%rcx), %tmm2
; CHECK-NEXT: tdpbssd %tmm1, %tmm0, %tmm2
; CHECK-NEXT: tilestored %tmm2, (%rax,%rcx)
; CHECK-NEXT: tilerelease
; CHECK-NEXT: vzeroupper
; CHECK-NEXT: jmp foo # TAILCALL
%3 = tail call x86_amx @llvm.x86.tileloadd64.internal(i16 %0, i16 8, i8* getelementptr inbounds ([3072 x i8], [3072 x i8]* @buf, i64 0, i64 0), i64 32)
%4 = tail call x86_amx @llvm.x86.tileloadd64.internal(i16 8, i16 %1, i8* getelementptr inbounds ([3072 x i8], [3072 x i8]* @buf, i64 0, i64 1024), i64 32)
%5 = tail call x86_amx @llvm.x86.tileloadd64.internal(i16 %0, i16 %1, i8* getelementptr inbounds ([3072 x i8], [3072 x i8]* @buf, i64 0, i64 2048), i64 32)
%6 = tail call x86_amx @llvm.x86.tdpbssd.internal(i16 %0, i16 %1, i16 8, x86_amx %5, x86_amx %3, x86_amx %4)
call void @llvm.dbg.value(metadata x86_amx %6, metadata !DILocalVariable(name: "1", scope: !2), metadata !DIExpression()), !dbg !3
tail call void @llvm.x86.tilestored64.internal(i16 %0, i16 %1, i8* getelementptr inbounds ([3072 x i8], [3072 x i8]* @buf, i64 0, i64 2048), i64 32, x86_amx %6)
tail call void @foo()
ret void
}
define dso_local void @test2(i16 signext %0, i16 signext %1) nounwind {
; CHECK-LABEL: test2:
; CHECK: # %bb.0:
; CHECK-NEXT: pushq %rbp
; CHECK-NEXT: pushq %rbx
; CHECK-NEXT: subq $72, %rsp
; CHECK-NEXT: movl %esi, %ebx
; CHECK-NEXT: movl %edi, %ebp
; CHECK-NEXT: vpxord %zmm0, %zmm0, %zmm0
; CHECK-NEXT: vmovdqu64 %zmm0, {{[0-9]+}}(%rsp)
; CHECK-NEXT: movb $1, {{[0-9]+}}(%rsp)
; CHECK-NEXT: movw $8, {{[0-9]+}}(%rsp)
; CHECK-NEXT: movb $8, {{[0-9]+}}(%rsp)
; CHECK-NEXT: movw $8, {{[0-9]+}}(%rsp)
; CHECK-NEXT: movb $8, {{[0-9]+}}(%rsp)
; CHECK-NEXT: movw %bx, {{[0-9]+}}(%rsp)
; CHECK-NEXT: movb %bpl, {{[0-9]+}}(%rsp)
; CHECK-NEXT: movw %bx, {{[0-9]+}}(%rsp)
; CHECK-NEXT: movb %bpl, {{[0-9]+}}(%rsp)
; CHECK-NEXT: movw %bx, {{[0-9]+}}(%rsp)
; CHECK-NEXT: movb %bpl, {{[0-9]+}}(%rsp)
; CHECK-NEXT: vzeroupper
; CHECK-NEXT: callq foo
; CHECK-NEXT: ldtilecfg {{[0-9]+}}(%rsp)
; CHECK-NEXT: xorl %eax, %eax
; CHECK-NEXT: testb %al, %al
; CHECK-NEXT: jne .LBB1_3
; CHECK-NEXT: # %bb.1: # %if.true
; CHECK-NEXT: movw $8, %ax
; CHECK-NEXT: tilezero %tmm0
; CHECK-NEXT: movl $32, %ecx
; CHECK-NEXT: movl $buf+1024, %edx
; CHECK-NEXT: tileloadd (%rdx,%rcx), %tmm1
; CHECK-NEXT: movl $buf+2048, %edx
; CHECK-NEXT: tileloadd (%rdx,%rcx), %tmm2
; CHECK-NEXT: tdpbssd %tmm2, %tmm1, %tmm0
; CHECK-NEXT: tilestored %tmm0, (%rdx,%rcx)
; CHECK-NEXT: jmp .LBB1_2
; CHECK-NEXT: .LBB1_3: # %if.false
; CHECK-NEXT: movl $buf, %eax
; CHECK-NEXT: movl $32, %ecx
; CHECK-NEXT: movw $8, %dx
; CHECK-NEXT: tileloadd (%rax,%rcx), %tmm3
; CHECK-NEXT: movl $buf+1024, %eax
; CHECK-NEXT: tileloadd (%rax,%rcx), %tmm4
; CHECK-NEXT: movl $buf+2048, %eax
; CHECK-NEXT: tileloadd (%rax,%rcx), %tmm2
; CHECK-NEXT: tdpbssd %tmm2, %tmm4, %tmm3
; CHECK-NEXT: tilestored %tmm3, (%rax,%rcx)
; CHECK-NEXT: .LBB1_2: # %if.true
; CHECK-NEXT: addq $72, %rsp
; CHECK-NEXT: popq %rbx
; CHECK-NEXT: popq %rbp
; CHECK-NEXT: tilerelease
; CHECK-NEXT: retq
call void @foo()
br i1 undef, label %if.true, label %if.false
if.true:
%t1 = tail call x86_amx @llvm.x86.tilezero.internal(i16 %0, i16 8)
%t2 = tail call x86_amx @llvm.x86.tileloadd64.internal(i16 8, i16 %1, i8* getelementptr inbounds ([3072 x i8], [3072 x i8]* @buf, i64 0, i64 1024), i64 32)
%t3 = tail call x86_amx @llvm.x86.tileloadd64.internal(i16 %0, i16 %1, i8* getelementptr inbounds ([3072 x i8], [3072 x i8]* @buf, i64 0, i64 2048), i64 32)
%t4 = tail call x86_amx @llvm.x86.tdpbssd.internal(i16 %0, i16 %1, i16 8, x86_amx %t1, x86_amx %t2, x86_amx %t3)
tail call void @llvm.x86.tilestored64.internal(i16 %0, i16 %1, i8* getelementptr inbounds ([3072 x i8], [3072 x i8]* @buf, i64 0, i64 2048), i64 32, x86_amx %t4)
br label %exit
if.false:
%t5 = tail call x86_amx @llvm.x86.tileloadd64.internal(i16 %0, i16 8, i8* getelementptr inbounds ([3072 x i8], [3072 x i8]* @buf, i64 0, i64 0), i64 32)
%t6 = tail call x86_amx @llvm.x86.tileloadd64.internal(i16 8, i16 %1, i8* getelementptr inbounds ([3072 x i8], [3072 x i8]* @buf, i64 0, i64 1024), i64 32)
%t7 = tail call x86_amx @llvm.x86.tileloadd64.internal(i16 %0, i16 %1, i8* getelementptr inbounds ([3072 x i8], [3072 x i8]* @buf, i64 0, i64 2048), i64 32)
%t8 = tail call x86_amx @llvm.x86.tdpbssd.internal(i16 %0, i16 %1, i16 8, x86_amx %t5, x86_amx %t6, x86_amx %t7)
tail call void @llvm.x86.tilestored64.internal(i16 %0, i16 %1, i8* getelementptr inbounds ([3072 x i8], [3072 x i8]* @buf, i64 0, i64 2048), i64 32, x86_amx %t8)
br label %exit
exit:
ret void
}
define dso_local void @test3(i16 signext %0, i16 signext %1) nounwind {
; CHECK-LABEL: test3:
; CHECK: # %bb.0:
; CHECK-NEXT: vpxord %zmm0, %zmm0, %zmm0
; CHECK-NEXT: vmovdqu64 %zmm0, -{{[0-9]+}}(%rsp)
; CHECK-NEXT: movb $1, -{{[0-9]+}}(%rsp)
; CHECK-NEXT: movw %si, -{{[0-9]+}}(%rsp)
; CHECK-NEXT: movb %dil, -{{[0-9]+}}(%rsp)
; CHECK-NEXT: xorl %eax, %eax
; CHECK-NEXT: testb %al, %al
; CHECK-NEXT: jne .LBB2_2
; CHECK-NEXT: # %bb.1: # %if.true
; CHECK-NEXT: incl %edi
; CHECK-NEXT: jmp .LBB2_3
; CHECK-NEXT: .LBB2_2: # %if.false
; CHECK-NEXT: decl %edi
; CHECK-NEXT: .LBB2_3: # %exit
; CHECK-NEXT: movb %dil, -{{[0-9]+}}(%rsp)
; CHECK-NEXT: ldtilecfg -{{[0-9]+}}(%rsp)
; CHECK-NEXT: tilezero %tmm0
; CHECK-NEXT: movl $buf, %eax
; CHECK-NEXT: movl $32, %ecx
; CHECK-NEXT: tilestored %tmm0, (%rax,%rcx)
; CHECK-NEXT: tilerelease
; CHECK-NEXT: vzeroupper
; CHECK-NEXT: retq
br i1 undef, label %if.true, label %if.false
if.true:
%3 = add i16 %0, 1
br label %exit
if.false:
%4 = sub i16 %0, 1
br label %exit
exit:
%5 = phi i16 [ %3, %if.true ], [ %4, %if.false ]
%6 = tail call x86_amx @llvm.x86.tilezero.internal(i16 %5, i16 %1)
tail call void @llvm.x86.tilestored64.internal(i16 %5, i16 %1, i8* getelementptr inbounds ([3072 x i8], [3072 x i8]* @buf, i64 0, i64 0), i64 32, x86_amx %6)
ret void
}
define dso_local void @test4(i16 signext %0, i16 signext %1) nounwind {
; CHECK-LABEL: test4:
; CHECK: # %bb.0:
; CHECK-NEXT: vpxord %zmm0, %zmm0, %zmm0
; CHECK-NEXT: vmovdqu64 %zmm0, -{{[0-9]+}}(%rsp)
; CHECK-NEXT: movb $1, -{{[0-9]+}}(%rsp)
; CHECK-NEXT: movw %si, -{{[0-9]+}}(%rsp)
; CHECK-NEXT: movb %dil, -{{[0-9]+}}(%rsp)
; CHECK-NEXT: xorl %eax, %eax
; CHECK-NEXT: testb %al, %al
; CHECK-NEXT: jne .LBB3_3
; CHECK-NEXT: # %bb.1: # %if.true
; CHECK-NEXT: incl %edi
; CHECK-NEXT: movb %dil, -{{[0-9]+}}(%rsp)
; CHECK-NEXT: ldtilecfg -{{[0-9]+}}(%rsp)
; CHECK-NEXT: xorl %eax, %eax
; CHECK-NEXT: testb %al, %al
; CHECK-NEXT: jne .LBB3_4
; CHECK-NEXT: .LBB3_2: # %amx2
; CHECK-NEXT: movl $32, %eax
; CHECK-NEXT: movl $buf+1024, %ecx
; CHECK-NEXT: tileloadd (%rcx,%rax), %tmm0
; CHECK-NEXT: movl $buf, %ecx
; CHECK-NEXT: tilestored %tmm0, (%rcx,%rax)
; CHECK-NEXT: tilerelease
; CHECK-NEXT: vzeroupper
; CHECK-NEXT: retq
; CHECK-NEXT: .LBB3_3: # %if.false
; CHECK-NEXT: decl %edi
; CHECK-NEXT: movb %dil, -{{[0-9]+}}(%rsp)
; CHECK-NEXT: ldtilecfg -{{[0-9]+}}(%rsp)
; CHECK-NEXT: xorl %eax, %eax
; CHECK-NEXT: testb %al, %al
; CHECK-NEXT: jne .LBB3_2
; CHECK-NEXT: .LBB3_4: # %amx1
; CHECK-NEXT: tilezero %tmm0
; CHECK-NEXT: movl $buf, %eax
; CHECK-NEXT: movl $32, %ecx
; CHECK-NEXT: tilestored %tmm0, (%rax,%rcx)
; CHECK-NEXT: tilerelease
; CHECK-NEXT: vzeroupper
; CHECK-NEXT: retq
br i1 undef, label %if.true, label %if.false
if.true:
%3 = add i16 %0, 1
br i1 undef, label %amx1, label %amx2
if.false:
%4 = sub i16 %0, 1
br i1 undef, label %amx2, label %amx1
amx1:
%5 = phi i16 [ %3, %if.true ], [ %4, %if.false ]
%6 = tail call x86_amx @llvm.x86.tilezero.internal(i16 %5, i16 %1)
tail call void @llvm.x86.tilestored64.internal(i16 %5, i16 %1, i8* getelementptr inbounds ([3072 x i8], [3072 x i8]* @buf, i64 0, i64 0), i64 32, x86_amx %6)
br label %exit
amx2:
%7 = phi i16 [ %3, %if.true ], [ %4, %if.false ]
%8 = tail call x86_amx @llvm.x86.tileloadd64.internal(i16 %7, i16 %1, i8* getelementptr inbounds ([3072 x i8], [3072 x i8]* @buf, i64 0, i64 1024), i64 32)
tail call void @llvm.x86.tilestored64.internal(i16 %7, i16 %1, i8* getelementptr inbounds ([3072 x i8], [3072 x i8]* @buf, i64 0, i64 0), i64 32, x86_amx %8)
br label %exit
exit:
ret void
}
define dso_local void @test5(i16 signext %0, i16 signext %1) nounwind {
; CHECK-LABEL: test5:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: # kill: def $esi killed $esi def $rsi
; CHECK-NEXT: vpxord %zmm0, %zmm0, %zmm0
; CHECK-NEXT: vmovdqu64 %zmm0, -{{[0-9]+}}(%rsp)
; CHECK-NEXT: movb $1, -{{[0-9]+}}(%rsp)
; CHECK-NEXT: movw %si, -{{[0-9]+}}(%rsp)
; CHECK-NEXT: movb %dil, -{{[0-9]+}}(%rsp)
; CHECK-NEXT: xorl %eax, %eax
; CHECK-NEXT: movl $buf, %r8d
; CHECK-NEXT: movl $32, %edx
; CHECK-NEXT: leal -1(%rsi), %ecx
; CHECK-NEXT: jmp .LBB4_1
; CHECK-NEXT: .p2align 4, 0x90
; CHECK-NEXT: .LBB4_3: # %if.false
; CHECK-NEXT: # in Loop: Header=BB4_1 Depth=1
; CHECK-NEXT: movl %ecx, %esi
; CHECK-NEXT: movw %cx, -{{[0-9]+}}(%rsp)
; CHECK-NEXT: cmpw $7, %si
; CHECK-NEXT: jne .LBB4_5
; CHECK-NEXT: .LBB4_1: # %loop.bb1
; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
; CHECK-NEXT: ldtilecfg -{{[0-9]+}}(%rsp)
; CHECK-NEXT: testb %al, %al
; CHECK-NEXT: jne .LBB4_3
; CHECK-NEXT: # %bb.2: # %if.true
; CHECK-NEXT: # in Loop: Header=BB4_1 Depth=1
; CHECK-NEXT: tilezero %tmm0
; CHECK-NEXT: tilestored %tmm0, (%r8,%rdx)
; CHECK-NEXT: cmpw $7, %si
; CHECK-NEXT: je .LBB4_1
; CHECK-NEXT: .LBB4_5: # %exit
; CHECK-NEXT: tilerelease
; CHECK-NEXT: vzeroupper
; CHECK-NEXT: retq
entry:
br label %loop.bb1
loop.bb1:
%2 = phi i16 [ %1, %entry ], [ %5, %loop.bb2 ]
br i1 undef, label %if.true, label %if.false
if.true:
%3 = tail call x86_amx @llvm.x86.tilezero.internal(i16 %0, i16 %2)
tail call void @llvm.x86.tilestored64.internal(i16 %0, i16 %2, i8* getelementptr inbounds ([3072 x i8], [3072 x i8]* @buf, i64 0, i64 0), i64 32, x86_amx %3)
br label %loop.bb2
if.false:
%4 = sub i16 %1, 1
br label %loop.bb2
loop.bb2:
%5 = phi i16 [ %2, %if.true ], [ %4, %if.false ]
%6 = icmp eq i16 %5, 7
br i1 %6, label %loop.bb1, label %exit
exit:
ret void
}
define dso_local void @test6(i16 signext %0) nounwind {
; CHECK-LABEL: test6:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: # kill: def $edi killed $edi def $rdi
; CHECK-NEXT: vpxord %zmm0, %zmm0, %zmm0
; CHECK-NEXT: vmovdqu64 %zmm0, -{{[0-9]+}}(%rsp)
; CHECK-NEXT: movb $1, -{{[0-9]+}}(%rsp)
; CHECK-NEXT: movb %dil, -{{[0-9]+}}(%rsp)
; CHECK-NEXT: xorl %r8d, %r8d
; CHECK-NEXT: movl $buf, %ecx
; CHECK-NEXT: movl $32, %edx
; CHECK-NEXT: xorl %esi, %esi
; CHECK-NEXT: jmp .LBB5_1
; CHECK-NEXT: .p2align 4, 0x90
; CHECK-NEXT: .LBB5_3: # %if.false
; CHECK-NEXT: # in Loop: Header=BB5_1 Depth=1
; CHECK-NEXT: decl %esi
; CHECK-NEXT: .LBB5_4: # %loop.bb2
; CHECK-NEXT: # in Loop: Header=BB5_1 Depth=1
; CHECK-NEXT: leal (%rdi,%rsi), %eax
; CHECK-NEXT: movw %ax, -{{[0-9]+}}(%rsp)
; CHECK-NEXT: cmpw $7, %si
; CHECK-NEXT: ldtilecfg -{{[0-9]+}}(%rsp)
; CHECK-NEXT: tilezero %tmm0
; CHECK-NEXT: tilestored %tmm0, (%rcx,%rdx)
; CHECK-NEXT: jne .LBB5_5
; CHECK-NEXT: .LBB5_1: # %loop.bb1
; CHECK-NEXT: # =>This Inner Loop Header: Depth=1
; CHECK-NEXT: testb %r8b, %r8b
; CHECK-NEXT: jne .LBB5_3
; CHECK-NEXT: # %bb.2: # %if.true
; CHECK-NEXT: # in Loop: Header=BB5_1 Depth=1
; CHECK-NEXT: incl %esi
; CHECK-NEXT: jmp .LBB5_4
; CHECK-NEXT: .LBB5_5: # %exit
; CHECK-NEXT: tilerelease
; CHECK-NEXT: vzeroupper
; CHECK-NEXT: retq
entry:
br label %loop.bb1
loop.bb1:
%1 = phi i16 [ 0, %entry ], [ %4, %loop.bb2 ]
br i1 undef, label %if.true, label %if.false
if.true:
%2 = add i16 %1, 1
br label %loop.bb2
if.false:
%3 = sub i16 %1, 1
br label %loop.bb2
loop.bb2:
%4 = phi i16 [ %2, %if.true ], [ %3, %if.false ]
%5 = icmp eq i16 %4, 7
%6 = add i16 %0, %4
%7 = tail call x86_amx @llvm.x86.tilezero.internal(i16 %0, i16 %6)
tail call void @llvm.x86.tilestored64.internal(i16 %0, i16 %6, i8* getelementptr inbounds ([3072 x i8], [3072 x i8]* @buf, i64 0, i64 0), i64 32, x86_amx %7)
br i1 %5, label %loop.bb1, label %exit
exit:
ret void
}
declare dso_local void @foo() nounwind
declare void @llvm.dbg.value(metadata, metadata, metadata)
declare x86_amx @llvm.x86.tilezero.internal(i16, i16)
declare x86_amx @llvm.x86.tileloadd64.internal(i16, i16, i8*, i64)
declare x86_amx @llvm.x86.tdpbssd.internal(i16, i16, i16, x86_amx, x86_amx, x86_amx)
declare void @llvm.x86.tilestored64.internal(i16, i16, i8*, i64, x86_amx)
!llvm.dbg.cu = !{!0}
!llvm.module.flags = !{!1}
!0 = distinct !DICompileUnit(language: DW_LANG_C, file: !DIFile(filename: "1", directory: "1"))
!1 = !{i32 2, !"Debug Info Version", i32 3}
!2 = distinct !DISubprogram(unit: !0)
!3 = !DILocation(line: 1, column: 1, scope: !2)
|
