Lines Matching refs:out
15 define amdgpu_kernel void @merge_global_store_2_constants_i8(i8 addrspace(1)* %out) #0 {
16 %out.gep.1 = getelementptr i8, i8 addrspace(1)* %out, i32 1
18 store i8 123, i8 addrspace(1)* %out.gep.1
19 store i8 456, i8 addrspace(1)* %out, align 2
27 define amdgpu_kernel void @merge_global_store_2_constants_i8_natural_align(i8 addrspace(1)* %out) #…
28 %out.gep.1 = getelementptr i8, i8 addrspace(1)* %out, i32 1
30 store i8 123, i8 addrspace(1)* %out.gep.1
31 store i8 456, i8 addrspace(1)* %out
37 define amdgpu_kernel void @merge_global_store_2_constants_i16(i16 addrspace(1)* %out) #0 {
38 %out.gep.1 = getelementptr i16, i16 addrspace(1)* %out, i32 1
40 store i16 123, i16 addrspace(1)* %out.gep.1
41 store i16 456, i16 addrspace(1)* %out, align 4
47 define amdgpu_kernel void @merge_global_store_2_constants_0_i16(i16 addrspace(1)* %out) #0 {
48 %out.gep.1 = getelementptr i16, i16 addrspace(1)* %out, i32 1
50 store i16 0, i16 addrspace(1)* %out.gep.1
51 store i16 0, i16 addrspace(1)* %out, align 4
59 define amdgpu_kernel void @merge_global_store_2_constants_i16_natural_align(i16 addrspace(1)* %out)…
60 %out.gep.1 = getelementptr i16, i16 addrspace(1)* %out, i32 1
62 store i16 123, i16 addrspace(1)* %out.gep.1
63 store i16 456, i16 addrspace(1)* %out
71 define amdgpu_kernel void @merge_global_store_2_constants_i32(i32 addrspace(1)* %out) #0 {
72 %out.gep.1 = getelementptr i32, i32 addrspace(1)* %out, i32 1
74 store i32 123, i32 addrspace(1)* %out.gep.1
75 store i32 456, i32 addrspace(1)* %out
81 define amdgpu_kernel void @merge_global_store_2_constants_i32_f32(i32 addrspace(1)* %out) #0 {
82 %out.gep.1 = getelementptr i32, i32 addrspace(1)* %out, i32 1
83 %out.gep.1.bc = bitcast i32 addrspace(1)* %out.gep.1 to float addrspace(1)*
84 store float 1.0, float addrspace(1)* %out.gep.1.bc
85 store i32 456, i32 addrspace(1)* %out
93 define amdgpu_kernel void @merge_global_store_2_constants_f32_i32(float addrspace(1)* %out) #0 {
94 %out.gep.1 = getelementptr float, float addrspace(1)* %out, i32 1
95 %out.gep.1.bc = bitcast float addrspace(1)* %out.gep.1 to i32 addrspace(1)*
96 store i32 123, i32 addrspace(1)* %out.gep.1.bc
97 store float 4.0, float addrspace(1)* %out
107 define amdgpu_kernel void @merge_global_store_4_constants_i32(i32 addrspace(1)* %out) #0 {
108 %out.gep.1 = getelementptr i32, i32 addrspace(1)* %out, i32 1
109 %out.gep.2 = getelementptr i32, i32 addrspace(1)* %out, i32 2
110 %out.gep.3 = getelementptr i32, i32 addrspace(1)* %out, i32 3
112 store i32 123, i32 addrspace(1)* %out.gep.1
113 store i32 456, i32 addrspace(1)* %out.gep.2
114 store i32 333, i32 addrspace(1)* %out.gep.3
115 store i32 1234, i32 addrspace(1)* %out
121 define amdgpu_kernel void @merge_global_store_4_constants_f32_order(float addrspace(1)* %out) #0 {
122 %out.gep.1 = getelementptr float, float addrspace(1)* %out, i32 1
123 %out.gep.2 = getelementptr float, float addrspace(1)* %out, i32 2
124 %out.gep.3 = getelementptr float, float addrspace(1)* %out, i32 3
126 store float 8.0, float addrspace(1)* %out
127 store float 1.0, float addrspace(1)* %out.gep.1
128 store float 2.0, float addrspace(1)* %out.gep.2
129 store float 4.0, float addrspace(1)* %out.gep.3
133 ; First store is out of order.
136 define amdgpu_kernel void @merge_global_store_4_constants_f32(float addrspace(1)* %out) #0 {
137 %out.gep.1 = getelementptr float, float addrspace(1)* %out, i32 1
138 %out.gep.2 = getelementptr float, float addrspace(1)* %out, i32 2
139 %out.gep.3 = getelementptr float, float addrspace(1)* %out, i32 3
141 store float 1.0, float addrspace(1)* %out.gep.1
142 store float 2.0, float addrspace(1)* %out.gep.2
143 store float 4.0, float addrspace(1)* %out.gep.3
144 store float 8.0, float addrspace(1)* %out
151 define amdgpu_kernel void @merge_global_store_4_constants_mixed_i32_f32(float addrspace(1)* %out) #…
152 %out.gep.1 = getelementptr float, float addrspace(1)* %out, i32 1
153 %out.gep.2 = getelementptr float, float addrspace(1)* %out, i32 2
154 %out.gep.3 = getelementptr float, float addrspace(1)* %out, i32 3
156 %out.gep.1.bc = bitcast float addrspace(1)* %out.gep.1 to i32 addrspace(1)*
157 %out.gep.3.bc = bitcast float addrspace(1)* %out.gep.3 to i32 addrspace(1)*
159 store i32 11, i32 addrspace(1)* %out.gep.1.bc
160 store float 2.0, float addrspace(1)* %out.gep.2
161 store i32 17, i32 addrspace(1)* %out.gep.3.bc
162 store float 8.0, float addrspace(1)* %out
172 define amdgpu_kernel void @merge_global_store_3_constants_i32(i32 addrspace(1)* %out) #0 {
173 %out.gep.1 = getelementptr i32, i32 addrspace(1)* %out, i32 1
174 %out.gep.2 = getelementptr i32, i32 addrspace(1)* %out, i32 2
176 store i32 123, i32 addrspace(1)* %out.gep.1
177 store i32 456, i32 addrspace(1)* %out.gep.2
178 store i32 1234, i32 addrspace(1)* %out
184 define amdgpu_kernel void @merge_global_store_2_constants_i64(i64 addrspace(1)* %out) #0 {
185 %out.gep.1 = getelementptr i64, i64 addrspace(1)* %out, i64 1
187 store i64 123, i64 addrspace(1)* %out.gep.1
188 store i64 456, i64 addrspace(1)* %out
195 define amdgpu_kernel void @merge_global_store_4_constants_i64(i64 addrspace(1)* %out) #0 {
196 %out.gep.1 = getelementptr i64, i64 addrspace(1)* %out, i64 1
197 %out.gep.2 = getelementptr i64, i64 addrspace(1)* %out, i64 2
198 %out.gep.3 = getelementptr i64, i64 addrspace(1)* %out, i64 3
200 store i64 123, i64 addrspace(1)* %out.gep.1
201 store i64 456, i64 addrspace(1)* %out.gep.2
202 store i64 333, i64 addrspace(1)* %out.gep.3
203 store i64 1234, i64 addrspace(1)* %out
210 define amdgpu_kernel void @merge_global_store_2_adjacent_loads_i32(i32 addrspace(1)* %out, i32 addr…
211 %out.gep.1 = getelementptr i32, i32 addrspace(1)* %out, i32 1
217 store i32 %lo, i32 addrspace(1)* %out
218 store i32 %hi, i32 addrspace(1)* %out.gep.1
225 …d @merge_global_store_2_adjacent_loads_i32_nonzero_base(i32 addrspace(1)* %out, i32 addrspace(1)* …
229 %out.gep.0 = getelementptr i32, i32 addrspace(1)* %out, i32 2
230 %out.gep.1 = getelementptr i32, i32 addrspace(1)* %out, i32 3
234 store i32 %lo, i32 addrspace(1)* %out.gep.0
235 store i32 %hi, i32 addrspace(1)* %out.gep.1
242 define amdgpu_kernel void @merge_global_store_2_adjacent_loads_shuffle_i32(i32 addrspace(1)* %out, …
243 %out.gep.1 = getelementptr i32, i32 addrspace(1)* %out, i32 1
249 store i32 %hi, i32 addrspace(1)* %out
250 store i32 %lo, i32 addrspace(1)* %out.gep.1
257 define amdgpu_kernel void @merge_global_store_4_adjacent_loads_i32(i32 addrspace(1)* %out, i32 addr…
258 %out.gep.1 = getelementptr i32, i32 addrspace(1)* %out, i32 1
259 %out.gep.2 = getelementptr i32, i32 addrspace(1)* %out, i32 2
260 %out.gep.3 = getelementptr i32, i32 addrspace(1)* %out, i32 3
270 store i32 %x, i32 addrspace(1)* %out
271 store i32 %y, i32 addrspace(1)* %out.gep.1
272 store i32 %z, i32 addrspace(1)* %out.gep.2
273 store i32 %w, i32 addrspace(1)* %out.gep.3
286 define amdgpu_kernel void @merge_global_store_3_adjacent_loads_i32(i32 addrspace(1)* %out, i32 addr…
287 %out.gep.1 = getelementptr i32, i32 addrspace(1)* %out, i32 1
288 %out.gep.2 = getelementptr i32, i32 addrspace(1)* %out, i32 2
296 store i32 %x, i32 addrspace(1)* %out
297 store i32 %y, i32 addrspace(1)* %out.gep.1
298 store i32 %z, i32 addrspace(1)* %out.gep.2
305 define amdgpu_kernel void @merge_global_store_4_adjacent_loads_f32(float addrspace(1)* %out, float …
306 %out.gep.1 = getelementptr float, float addrspace(1)* %out, i32 1
307 %out.gep.2 = getelementptr float, float addrspace(1)* %out, i32 2
308 %out.gep.3 = getelementptr float, float addrspace(1)* %out, i32 3
318 store float %x, float addrspace(1)* %out
319 store float %y, float addrspace(1)* %out.gep.1
320 store float %z, float addrspace(1)* %out.gep.2
321 store float %w, float addrspace(1)* %out.gep.3
328 …d @merge_global_store_4_adjacent_loads_i32_nonzero_base(i32 addrspace(1)* %out, i32 addrspace(1)* …
333 %out.gep.0 = getelementptr i32, i32 addrspace(1)* %out, i32 7
334 %out.gep.1 = getelementptr i32, i32 addrspace(1)* %out, i32 8
335 %out.gep.2 = getelementptr i32, i32 addrspace(1)* %out, i32 9
336 %out.gep.3 = getelementptr i32, i32 addrspace(1)* %out, i32 10
343 store i32 %x, i32 addrspace(1)* %out.gep.0
344 store i32 %y, i32 addrspace(1)* %out.gep.1
345 store i32 %z, i32 addrspace(1)* %out.gep.2
346 store i32 %w, i32 addrspace(1)* %out.gep.3
354 define amdgpu_kernel void @merge_global_store_4_adjacent_loads_inverse_i32(i32 addrspace(1)* %out, …
355 %out.gep.1 = getelementptr i32, i32 addrspace(1)* %out, i32 1
356 %out.gep.2 = getelementptr i32, i32 addrspace(1)* %out, i32 2
357 %out.gep.3 = getelementptr i32, i32 addrspace(1)* %out, i32 3
370 store i32 %w, i32 addrspace(1)* %out.gep.3
371 store i32 %z, i32 addrspace(1)* %out.gep.2
372 store i32 %y, i32 addrspace(1)* %out.gep.1
373 store i32 %x, i32 addrspace(1)* %out
385 define amdgpu_kernel void @merge_global_store_4_adjacent_loads_shuffle_i32(i32 addrspace(1)* %out, …
386 %out.gep.1 = getelementptr i32, i32 addrspace(1)* %out, i32 1
387 %out.gep.2 = getelementptr i32, i32 addrspace(1)* %out, i32 2
388 %out.gep.3 = getelementptr i32, i32 addrspace(1)* %out, i32 3
401 store i32 %w, i32 addrspace(1)* %out
402 store i32 %z, i32 addrspace(1)* %out.gep.1
403 store i32 %y, i32 addrspace(1)* %out.gep.2
404 store i32 %x, i32 addrspace(1)* %out.gep.3
413 define amdgpu_kernel void @merge_global_store_4_adjacent_loads_i8(i8 addrspace(1)* %out, i8 addrspa…
414 %out.gep.1 = getelementptr i8, i8 addrspace(1)* %out, i8 1
415 %out.gep.2 = getelementptr i8, i8 addrspace(1)* %out, i8 2
416 %out.gep.3 = getelementptr i8, i8 addrspace(1)* %out, i8 3
426 store i8 %x, i8 addrspace(1)* %out, align 4
427 store i8 %y, i8 addrspace(1)* %out.gep.1
428 store i8 %z, i8 addrspace(1)* %out.gep.2
429 store i8 %w, i8 addrspace(1)* %out.gep.3
443 …id @merge_global_store_4_adjacent_loads_i8_natural_align(i8 addrspace(1)* %out, i8 addrspace(1)* %…
444 %out.gep.1 = getelementptr i8, i8 addrspace(1)* %out, i8 1
445 %out.gep.2 = getelementptr i8, i8 addrspace(1)* %out, i8 2
446 %out.gep.3 = getelementptr i8, i8 addrspace(1)* %out, i8 3
456 store i8 %x, i8 addrspace(1)* %out
457 store i8 %y, i8 addrspace(1)* %out.gep.1
458 store i8 %z, i8 addrspace(1)* %out.gep.2
459 store i8 %w, i8 addrspace(1)* %out.gep.3
467 define amdgpu_kernel void @merge_global_store_4_vector_elts_loads_v4i32(i32 addrspace(1)* %out, <4 …
468 %out.gep.1 = getelementptr i32, i32 addrspace(1)* %out, i32 1
469 %out.gep.2 = getelementptr i32, i32 addrspace(1)* %out, i32 2
470 %out.gep.3 = getelementptr i32, i32 addrspace(1)* %out, i32 3
478 store i32 %x, i32 addrspace(1)* %out
479 store i32 %y, i32 addrspace(1)* %out.gep.1
480 store i32 %z, i32 addrspace(1)* %out.gep.2
481 store i32 %w, i32 addrspace(1)* %out.gep.3
488 define amdgpu_kernel void @merge_local_store_2_constants_i8(i8 addrspace(3)* %out) #0 {
489 %out.gep.1 = getelementptr i8, i8 addrspace(3)* %out, i32 1
491 store i8 123, i8 addrspace(3)* %out.gep.1
492 store i8 456, i8 addrspace(3)* %out, align 2
500 define amdgpu_kernel void @merge_local_store_2_constants_i32(i32 addrspace(3)* %out) #0 {
501 %out.gep.1 = getelementptr i32, i32 addrspace(3)* %out, i32 1
503 store i32 123, i32 addrspace(3)* %out.gep.1
504 store i32 456, i32 addrspace(3)* %out
518 define amdgpu_kernel void @merge_local_store_4_constants_i32(i32 addrspace(3)* %out) #0 {
519 %out.gep.1 = getelementptr i32, i32 addrspace(3)* %out, i32 1
520 %out.gep.2 = getelementptr i32, i32 addrspace(3)* %out, i32 2
521 %out.gep.3 = getelementptr i32, i32 addrspace(3)* %out, i32 3
523 store i32 123, i32 addrspace(3)* %out.gep.1
524 store i32 456, i32 addrspace(3)* %out.gep.2
525 store i32 333, i32 addrspace(3)* %out.gep.3
526 store i32 1234, i32 addrspace(3)* %out
536 define amdgpu_kernel void @merge_global_store_5_constants_i32(i32 addrspace(1)* %out) {
537 store i32 9, i32 addrspace(1)* %out, align 4
538 %idx1 = getelementptr inbounds i32, i32 addrspace(1)* %out, i64 1
540 %idx2 = getelementptr inbounds i32, i32 addrspace(1)* %out, i64 2
542 %idx3 = getelementptr inbounds i32, i32 addrspace(1)* %out, i64 3
544 %idx4 = getelementptr inbounds i32, i32 addrspace(1)* %out, i64 4
552 define amdgpu_kernel void @merge_global_store_6_constants_i32(i32 addrspace(1)* %out) {
553 store i32 13, i32 addrspace(1)* %out, align 4
554 %idx1 = getelementptr inbounds i32, i32 addrspace(1)* %out, i64 1
556 %idx2 = getelementptr inbounds i32, i32 addrspace(1)* %out, i64 2
558 %idx3 = getelementptr inbounds i32, i32 addrspace(1)* %out, i64 3
560 %idx4 = getelementptr inbounds i32, i32 addrspace(1)* %out, i64 4
562 %idx5 = getelementptr inbounds i32, i32 addrspace(1)* %out, i64 5
571 define amdgpu_kernel void @merge_global_store_7_constants_i32(i32 addrspace(1)* %out) {
572 store i32 34, i32 addrspace(1)* %out, align 4
573 %idx1 = getelementptr inbounds i32, i32 addrspace(1)* %out, i64 1
575 %idx2 = getelementptr inbounds i32, i32 addrspace(1)* %out, i64 2
577 %idx3 = getelementptr inbounds i32, i32 addrspace(1)* %out, i64 3
579 %idx4 = getelementptr inbounds i32, i32 addrspace(1)* %out, i64 4
581 %idx5 = getelementptr inbounds i32, i32 addrspace(1)* %out, i64 5
583 %idx6 = getelementptr inbounds i32, i32 addrspace(1)* %out, i64 6
592 define amdgpu_kernel void @merge_global_store_8_constants_i32(i32 addrspace(1)* %out) {
593 store i32 34, i32 addrspace(1)* %out, align 4
594 %idx1 = getelementptr inbounds i32, i32 addrspace(1)* %out, i64 1
596 %idx2 = getelementptr inbounds i32, i32 addrspace(1)* %out, i64 2
598 %idx3 = getelementptr inbounds i32, i32 addrspace(1)* %out, i64 3
600 %idx4 = getelementptr inbounds i32, i32 addrspace(1)* %out, i64 4
602 %idx5 = getelementptr inbounds i32, i32 addrspace(1)* %out, i64 5
604 %idx6 = getelementptr inbounds i32, i32 addrspace(1)* %out, i64 6
606 %idx7 = getelementptr inbounds i32, i32 addrspace(1)* %out, i64 7
628 define amdgpu_kernel void @copy_v3i32_align4(<3 x i32> addrspace(1)* noalias %out, <3 x i32> addrsp…
630 store <3 x i32> %vec, <3 x i32> addrspace(1)* %out
644 define amdgpu_kernel void @copy_v3i64_align4(<3 x i64> addrspace(1)* noalias %out, <3 x i64> addrsp…
646 store <3 x i64> %vec, <3 x i64> addrspace(1)* %out
662 define amdgpu_kernel void @copy_v3f32_align4(<3 x float> addrspace(1)* noalias %out, <3 x float> ad…
665 store <3 x float> %fadd, <3 x float> addrspace(1)* %out
679 define amdgpu_kernel void @copy_v3f64_align4(<3 x double> addrspace(1)* noalias %out, <3 x double> …
682 store <3 x double> %fadd, <3 x double> addrspace(1)* %out