91 lines · plain
1; RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -amdgpu-codegenprepare-break-large-phis=false < %s | FileCheck %s2 3; CHECK-LABEL: {{^}}_amdgpu_ps_main:4;5; This test case used to hit an assertion in SIOptimizeVGPRLiveRange because of a vector with dead lanes6; leading to an effectively dead INSERT_SUBREG.7 8 9define dllexport amdgpu_ps void @_amdgpu_ps_main(i32 %descTable2) #0 {10.entry:11 %i2 = zext i32 %descTable2 to i6412 %i4 = inttoptr i64 %i2 to ptr addrspace(4)13 %i159 = call reassoc nnan nsz arcp contract afn <4 x float> @llvm.amdgcn.image.sample.d.2d.v4f32.f32.f32(i32 15, float poison, float poison, float poison, float poison, float poison, float poison, <8 x i32> poison, <4 x i32> poison, i1 false, i32 0, i32 0)14 %i1540 = shufflevector <4 x float> %i159, <4 x float> poison, <3 x i32> <i32 0, i32 1, i32 2>15 %i1526 = call i32 @llvm.amdgcn.s.buffer.load.i32(<4 x i32> poison, i32 2688, i32 0)16 %i1746 = load <4 x i32>, ptr addrspace(4) %i4, align 1617 br label %bb175018 19bb1750: ; preds = %bb1897, %.entry20 %__llpc_global_proxy_r3.12.vec.extract2358295 = phi i32 [ 0, %.entry ], [ %__llpc_global_proxy_r3.12.vec.extract2358, %bb1897 ]21 %__llpc_global_proxy_r13.20293 = phi <4 x i32> [ poison, %.entry ], [ %__llpc_global_proxy_r13.22, %bb1897 ]22 %__llpc_global_proxy_r10.19291 = phi <4 x i32> [ poison, %.entry ], [ %i1914, %bb1897 ]23 %i1751 = call float @llvm.amdgcn.struct.buffer.load.format.f32(<4 x i32> %i1746, i32 poison, i32 0, i32 0, i32 0)24 %i1754 = shufflevector <4 x i32> %__llpc_global_proxy_r10.19291, <4 x i32> poison, <4 x i32> <i32 0, i32 1, i32 2, i32 7>25 %__llpc_global_proxy_r7.12.vec.extract1953260 = bitcast float %i1751 to i3226 %i1760 = or i32 %__llpc_global_proxy_r7.12.vec.extract1953260, %__llpc_global_proxy_r3.12.vec.extract235829527 %i1786 = call i32 @llvm.amdgcn.s.buffer.load.i32(<4 x i32> poison, i32 %i1760, i32 0)28 %__llpc_global_proxy_r11.12.vec.insert1237 = insertelement <4 x i32> %i1754, i32 %i1786, i64 329 %.not2783 = icmp eq i32 %i1786, 030 br i1 %.not2783, label %bb1789, label %bb178731 32bb1787: ; preds = %bb175033 %i1788 = shufflevector <4 x i32> <i32 0, i32 0, i32 0, i32 poison>, <4 x i32> %__llpc_global_proxy_r13.20293, <4 x i32> <i32 0, i32 1, i32 2, i32 7>34 br label %bb189735 36bb1789: ; preds = %bb175037 %i1796 = call reassoc nnan nsz arcp contract afn float @llvm.amdgcn.fmed3.f32(float poison, float 0.000000e+00, float 1.000000e+00)38 %i1797 = fmul reassoc nnan nsz arcp contract afn float %i1796, %i179639 %i1800 = fdiv reassoc nnan nsz arcp contract afn float %i1797, 0.000000e+0040 %i1801 = bitcast float %i1800 to i3241 %__llpc_global_proxy_r11.12.vec.insert1245 = insertelement <4 x i32> %__llpc_global_proxy_r11.12.vec.insert1237, i32 poison, i64 342 %i1818 = call reassoc nnan nsz arcp contract afn float @llvm.amdgcn.fmed3.f32(float poison, float 0.000000e+00, float 1.000000e+00)43 %i1819 = bitcast float %i1818 to i3244 %i1878 = shufflevector <4 x i32> %__llpc_global_proxy_r11.12.vec.insert1245, <4 x i32> poison, <3 x i32> <i32 3, i32 3, i32 3>45 %i1879 = bitcast <3 x i32> %i1878 to <3 x float>46 %i1881 = fmul reassoc nnan nsz arcp contract afn <3 x float> %i1540, %i187947 %i1882 = call <3 x i32> @llvm.amdgcn.s.buffer.load.v3i32(<4 x i32> poison, i32 poison, i32 0)48 %i1883 = shufflevector <3 x i32> %i1882, <3 x i32> poison, <4 x i32> <i32 0, i32 1, i32 2, i32 poison>49 %i1884 = bitcast <4 x i32> %i1883 to <4 x float>50 %i1885 = shufflevector <4 x float> %i1884, <4 x float> poison, <3 x i32> <i32 0, i32 1, i32 2>51 %i1886 = insertelement <3 x i32> poison, i32 %i1819, i64 052 %i1887 = bitcast <3 x i32> %i1886 to <3 x float>53 %i1888 = insertelement <3 x i32> poison, i32 %i1801, i64 054 %i1889 = bitcast <3 x i32> %i1888 to <3 x float>55 %i1890 = fmul reassoc nnan nsz arcp contract afn <3 x float> %i1887, %i188956 %i1891 = shufflevector <3 x float> %i1890, <3 x float> poison, <3 x i32> zeroinitializer57 %i1892 = fmul reassoc nnan nsz arcp contract afn <3 x float> %i1885, %i189158 %i1893 = fmul reassoc nnan nsz arcp contract afn <3 x float> %i1892, %i188159 %i1894 = bitcast <3 x float> %i1893 to <3 x i32>60 %i1895 = shufflevector <3 x i32> %i1894, <3 x i32> poison, <4 x i32> <i32 0, i32 1, i32 2, i32 poison>61 %i1896 = insertelement <4 x i32> %i1895, i32 %i1819, i64 362 br label %bb189763 64bb1897: ; preds = %bb1789, %bb178765 %__llpc_global_proxy_r11.19 = phi <4 x i32> [ %__llpc_global_proxy_r11.12.vec.insert1237, %bb1787 ], [ %__llpc_global_proxy_r11.12.vec.insert1245, %bb1789 ]66 %__llpc_global_proxy_r13.22 = phi <4 x i32> [ %i1788, %bb1787 ], [ %i1896, %bb1789 ]67 %i1898 = shufflevector <4 x i32> %__llpc_global_proxy_r11.19, <4 x i32> poison, <3 x i32> <i32 0, i32 1, i32 2>68 %i1899 = bitcast <3 x i32> %i1898 to <3 x float>69 %i1900 = shufflevector <4 x i32> %__llpc_global_proxy_r13.22, <4 x i32> poison, <3 x i32> <i32 0, i32 1, i32 2>70 %i1901 = bitcast <3 x i32> %i1900 to <3 x float>71 %i1902 = fadd reassoc nnan nsz arcp contract afn <3 x float> %i1901, %i189972 %i1903 = bitcast <3 x float> %i1902 to <3 x i32>73 %i1907 = shufflevector <3 x i32> %i1903, <3 x i32> poison, <4 x i32> <i32 0, i32 1, i32 2, i32 poison>74 %i1908 = shufflevector <4 x i32> %i1907, <4 x i32> %__llpc_global_proxy_r11.19, <4 x i32> <i32 0, i32 1, i32 2, i32 7>75 %i1914 = shufflevector <4 x i32> %i1908, <4 x i32> poison, <4 x i32> <i32 0, i32 1, i32 2, i32 7>76 %__llpc_global_proxy_r3.12.vec.extract2358 = extractelement <2 x i32> zeroinitializer, i64 177 %.not2780.not = icmp ult i32 %__llpc_global_proxy_r3.12.vec.extract2358, %i152678 br i1 %.not2780.not, label %bb1750, label %._crit_edge29879 80._crit_edge298: ; preds = %bb189781 ret void82}83 84declare <4 x float> @llvm.amdgcn.image.sample.d.2d.v4f32.f32.f32(i32 immarg, float, float, float, float, float, float, <8 x i32>, <4 x i32>, i1 immarg, i32 immarg, i32 immarg)85declare float @llvm.amdgcn.fmed3.f32(float, float, float)86declare float @llvm.amdgcn.struct.buffer.load.format.f32(<4 x i32>, i32, i32, i32, i32 immarg)87declare i32 @llvm.amdgcn.s.buffer.load.i32(<4 x i32>, i32, i32 immarg)88declare <3 x i32> @llvm.amdgcn.s.buffer.load.v3i32(<4 x i32>, i32, i32 immarg)89 90attributes #0 = { "target-features"=",+wavefrontsize64,+cumode" }91