Lines Matching +full:0 +full:x2f0
4 define void @main(i1 %arg) #0 {
6 ; CHECK: ; %bb.0: ; %bb
7 ; CHECK-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
9 ; CHECK-NEXT: buffer_store_dword v5, off, s[0:3], s32 ; 4-byte Folded Spill
10 ; CHECK-NEXT: buffer_store_dword v6, off, s[0:3], s32 offset:4 ; 4-byte Folded Spill
11 ; CHECK-NEXT: buffer_store_dword v7, off, s[0:3], s32 offset:8 ; 4-byte Folded Spill
13 ; CHECK-NEXT: v_writelane_b32 v5, s30, 0
31 ; CHECK-NEXT: s_movk_i32 s4, 0xf0
34 ; CHECK-NEXT: s_load_dwordx16 s[36:51], s[4:5], 0x0
36 ; CHECK-NEXT: s_mov_b64 s[4:5], 0
37 ; CHECK-NEXT: s_load_dwordx4 s[28:31], s[4:5], 0x0
38 ; CHECK-NEXT: s_movk_i32 s20, 0x130
40 ; CHECK-NEXT: s_waitcnt lgkmcnt(0)
41 ; CHECK-NEXT: v_writelane_b32 v7, s36, 0
52 ; CHECK-NEXT: s_load_dwordx16 s[4:19], s[20:21], 0x0
55 ; CHECK-NEXT: s_mov_b32 s20, 0
56 ; CHECK-NEXT: v_mov_b32_e32 v1, 0
65 ; CHECK-NEXT: image_sample_lz v3, v[2:3], s[44:51], s[20:23] dmask:0x1
67 ; CHECK-NEXT: s_waitcnt lgkmcnt(0)
74 ; CHECK-NEXT: image_sample_lz v4, v[1:2], s[4:11], s[20:23] dmask:0x1
91 ; CHECK-NEXT: s_load_dwordx8 s[4:11], s[26:27], 0x0
97 ; CHECK-NEXT: s_waitcnt lgkmcnt(0)
110 ; CHECK-NEXT: s_movk_i32 s28, 0x1f0
111 ; CHECK-NEXT: s_movk_i32 s30, 0x2f0
117 ; CHECK-NEXT: s_load_dwordx16 s[52:67], s[28:29], 0x0
118 ; CHECK-NEXT: s_load_dwordx16 s[4:19], s[30:31], 0x0
122 ; CHECK-NEXT: s_waitcnt vmcnt(0)
128 ; CHECK-NEXT: v_readlane_b32 s36, v7, 0
142 ; CHECK-NEXT: image_sample_lz v3, v[1:2], s[44:51], s[20:23] dmask:0x1
143 ; CHECK-NEXT: v_mov_b32_e32 v2, 0
159 ; CHECK-NEXT: s_waitcnt lgkmcnt(0)
160 ; CHECK-NEXT: image_sample_lz v4, v[1:2], s[60:67], s[40:43] dmask:0x1
162 ; CHECK-NEXT: image_sample_lz v1, v[1:2], s[12:19], s[20:23] dmask:0x1
163 ; CHECK-NEXT: s_waitcnt vmcnt(0)
170 ; CHECK-NEXT: s_waitcnt lgkmcnt(0)
197 ; CHECK-NEXT: v_writelane_b32 v6, s60, 0
219 ; CHECK-NEXT: s_mov_b32 s8, 0
222 ; CHECK-NEXT: v_readlane_b32 s36, v7, 0
241 ; CHECK-NEXT: image_sample_lz v2, v[0:1], s[36:43], s[8:11] dmask:0x1
251 ; CHECK-NEXT: v_mov_b32_e32 v3, 0
256 ; CHECK-NEXT: image_sample_lz v0, v[0:1], s[44:51], s[12:15] dmask:0x1
262 ; CHECK-NEXT: buffer_store_dwordx3 v[2:4], off, s[8:11], 0
264 ; CHECK-NEXT: buffer_store_dwordx4 v[0:3], off, s[8:11], 0
287 ; CHECK-NEXT: s_mov_b32 s8, 0
304 ; CHECK-NEXT: image_sample_lz v3, v[1:2], s[36:43], s[8:11] dmask:0x1
305 ; CHECK-NEXT: image_sample_lz v4, v[1:2], s[52:59], s[8:11] dmask:0x1
308 ; CHECK-NEXT: s_and_b64 vcc, exec, 0
309 ; CHECK-NEXT: v_readlane_b32 s44, v6, 0
323 ; CHECK-NEXT: s_waitcnt vmcnt(0)
326 ; CHECK-NEXT: v_mov_b32_e32 v1, 0
370 ; CHECK-NEXT: v_readlane_b32 s30, v5, 0
372 ; CHECK-NEXT: buffer_load_dword v5, off, s[0:3], s32 ; 4-byte Folded Reload
373 ; CHECK-NEXT: buffer_load_dword v6, off, s[0:3], s32 offset:4 ; 4-byte Folded Reload
374 ; CHECK-NEXT: buffer_load_dword v7, off, s[0:3], s32 offset:8 ; 4-byte Folded Reload
376 ; CHECK-NEXT: s_waitcnt vmcnt(0)
405 %i26 = extractelement <4 x float> %i25, i64 0
406 %i27 = call float @llvm.amdgcn.image.sample.lz.2d.f32.f32(i32 1, float %i26, float 0.000000e+00, <8 x i32> %i12, <4 x i32> zeroinitializer, i1 false, i32 0, i32 0)
407 %i28 = call <4 x float> @llvm.amdgcn.image.sample.lz.2d.v4f32.f32(i32 1, float 0.000000e+00, float 0.000000e+00, <8 x i32> %i14, <4 x i32> zeroinitializer, i1 false, i32 0, i32 0)
408 %i29 = extractelement <4 x float> %i28, i64 0
410 %i31 = call <4 x float> @llvm.amdgcn.image.sample.lz.2d.v4f32.f32(i32 1, float 0.000000e+00, float 0.000000e+00, <8 x i32> %i16, <4 x i32> %i6, i1 false, i32 0, i32 0)
418 %i35 = call <2 x float> @llvm.amdgcn.image.sample.lz.2d.v2f32.f32(i32 1, float 0.000000e+00, float 0.000000e+00, <8 x i32> %i18, <4 x i32> zeroinitializer, i1 false, i32 0, i32 0)
419 %i36 = extractelement <2 x float> %i35, i64 0
420 %i37 = call <2 x float> @llvm.amdgcn.image.sample.lz.2d.v2f32.f32(i32 1, float 0.000000e+00, float 0.000000e+00, <8 x i32> %i22, <4 x i32> zeroinitializer, i1 false, i32 0, i32 0)
421 %i38 = extractelement <2 x float> %i37, i64 0
429 %i44 = call float @llvm.amdgcn.image.sample.lz.2d.f32.f32(i32 1, float 0.000000e+00, float 0.000000e+00, <8 x i32> %i10, <4 x i32> zeroinitializer, i1 false, i32 0, i32 0)
431 %i46 = insertelement <3 x i32> zeroinitializer, i32 %i45, i64 0
432 call void @llvm.amdgcn.raw.buffer.store.v3i32(<3 x i32> %i46, <4 x i32> zeroinitializer, i32 0, i32 0, i32 0)
434 call void @llvm.amdgcn.raw.buffer.store.v4i32(<4 x i32> %i47, <4 x i32> zeroinitializer, i32 0, i32 0, i32 0)
438 %i49 = call float @llvm.amdgcn.image.sample.lz.2d.f32.f32(i32 1, float 0.000000e+00, float 0.000000e+00, <8 x i32> %i12, <4 x i32> zeroinitializer, i1 false, i32 0, i32 0)
443 %i52 = call <2 x float> @llvm.amdgcn.image.sample.lz.2d.v2f32.f32(i32 1, float %i51, float 0.000000e+00, <8 x i32> %i20, <4 x i32> %i8, i1 false, i32 0, i32 0)
444 %i53 = extractelement <2 x float> %i52, i64 0
445 %i54 = call <2 x float> @llvm.amdgcn.image.sample.lz.2d.v2f32.f32(i32 1, float %i51, float 0.000000e+00, <8 x i32> %i24, <4 x i32> zeroinitializer, i1 false, i32 0, i32 0)
446 %i55 = extractelement <2 x float> %i54, i64 0
460 attributes #0 = { "amdgpu-waves-per-eu"="10,10" }