reference, declarationdefinition
definition → references, declarations, derived classes, virtual overrides
reference to multiple definitions → definitions
unreferenced
    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
; RUN: llc -O0 -march=amdgcn -mcpu=gfx900 -amdgpu-dpp-combine=false -verify-machineinstrs < %s | FileCheck -check-prefixes=GFX9,GFX9-O0 %s
; RUN: llc -march=amdgcn -mcpu=gfx900 -amdgpu-dpp-combine=false -verify-machineinstrs < %s | FileCheck -check-prefixes=GFX9,GFX9-O3 %s

define amdgpu_cs void @no_cfg(<4 x i32> inreg %tmp14) {
  %tmp100 = call <2 x float> @llvm.amdgcn.raw.buffer.load.v2f32(<4 x i32> %tmp14, i32 0, i32 0, i32 0)
  %tmp101 = bitcast <2 x float> %tmp100 to <2 x i32>
  %tmp102 = extractelement <2 x i32> %tmp101, i32 0
  %tmp103 = extractelement <2 x i32> %tmp101, i32 1
  %tmp105 = tail call i32 @llvm.amdgcn.set.inactive.i32(i32 %tmp102, i32 0)
  %tmp107 = tail call i32 @llvm.amdgcn.set.inactive.i32(i32 %tmp103, i32 0)

; GFX9: v_mov_b32_dpp v[[FIRST_MOV:[0-9]+]], v{{[0-9]+}} row_bcast:31 row_mask:0xc bank_mask:0xf
; GFX9: v_add_u32_e32 v[[FIRST_ADD:[0-9]+]], v{{[0-9]+}}, v[[FIRST_MOV]]
; GFX9: v_mov_b32_e32 v[[FIRST:[0-9]+]], v[[FIRST_ADD]]
  %tmp120 = tail call i32 @llvm.amdgcn.update.dpp.i32(i32 0, i32 %tmp105, i32 323, i32 12, i32 15, i1 false)
  %tmp121 = add i32 %tmp105, %tmp120
  %tmp122 = tail call i32 @llvm.amdgcn.wwm.i32(i32 %tmp121)

; GFX9: v_mov_b32_dpp v[[SECOND_MOV:[0-9]+]], v{{[0-9]+}} row_bcast:31 row_mask:0xc bank_mask:0xf
; GFX9: v_add_u32_e32 v[[SECOND_ADD:[0-9]+]], v{{[0-9]+}}, v[[SECOND_MOV]]
; GFX9: v_mov_b32_e32 v[[SECOND:[0-9]+]], v[[SECOND_ADD]]
  %tmp135 = tail call i32 @llvm.amdgcn.update.dpp.i32(i32 0, i32 %tmp107, i32 323, i32 12, i32 15, i1 false)
  %tmp136 = add i32 %tmp107, %tmp135
  %tmp137 = tail call i32 @llvm.amdgcn.wwm.i32(i32 %tmp136)

; GFX9-O3: v_cmp_eq_u32_e32 vcc, v[[FIRST]], v[[SECOND]]
; GFX9-O0: v_cmp_eq_u32_e64 s{{\[}}{{[0-9]+}}:{{[0-9]+}}{{\]}}, v[[FIRST]], v[[SECOND]]
  %tmp138 = icmp eq i32 %tmp122, %tmp137
  %tmp139 = sext i1 %tmp138 to i32
  %tmp140 = shl nsw i32 %tmp139, 1
  %tmp141 = and i32 %tmp140, 2
  %tmp145 = bitcast i32 %tmp141 to float
  call void @llvm.amdgcn.raw.buffer.store.f32(float %tmp145, <4 x i32> %tmp14, i32 4, i32 0, i32 0)
  ret void
}

define amdgpu_cs void @cfg(<4 x i32> inreg %tmp14, i32 %arg) {
entry:
  %tmp100 = call <2 x float> @llvm.amdgcn.raw.buffer.load.v2f32(<4 x i32> %tmp14, i32 0, i32 0, i32 0)
  %tmp101 = bitcast <2 x float> %tmp100 to <2 x i32>
  %tmp102 = extractelement <2 x i32> %tmp101, i32 0
  %tmp105 = tail call i32 @llvm.amdgcn.set.inactive.i32(i32 %tmp102, i32 0)

; GFX9: v_mov_b32_dpp v[[FIRST_MOV:[0-9]+]], v{{[0-9]+}} row_bcast:31 row_mask:0xc bank_mask:0xf
; GFX9: v_add_u32_e32 v[[FIRST_ADD:[0-9]+]], v{{[0-9]+}}, v[[FIRST_MOV]]
; GFX9: v_mov_b32_e32 v[[FIRST:[0-9]+]], v[[FIRST_ADD]]
; GFX9-O0: buffer_store_dword v[[FIRST]], off, s{{\[}}{{[0-9]+}}:{{[0-9]+}}{{\]}}, s[[FIRST_SGPR_OFFSET:[0-9]+]] offset:[[FIRST_IMM_OFFSET:[0-9]+]]
  %tmp120 = tail call i32 @llvm.amdgcn.update.dpp.i32(i32 0, i32 %tmp105, i32 323, i32 12, i32 15, i1 false)
  %tmp121 = add i32 %tmp105, %tmp120
  %tmp122 = tail call i32 @llvm.amdgcn.wwm.i32(i32 %tmp121)

  %cond = icmp eq i32 %arg, 0
  br i1 %cond, label %if, label %merge
if:
  %tmp103 = extractelement <2 x i32> %tmp101, i32 1
  %tmp107 = tail call i32 @llvm.amdgcn.set.inactive.i32(i32 %tmp103, i32 0)

; GFX9: v_mov_b32_dpp v[[SECOND_MOV:[0-9]+]], v{{[0-9]+}} row_bcast:31 row_mask:0xc bank_mask:0xf
; GFX9: v_add_u32_e32 v[[SECOND_ADD:[0-9]+]], v{{[0-9]+}}, v[[SECOND_MOV]]
; GFX9: v_mov_b32_e32 v[[SECOND:[0-9]+]], v[[SECOND_ADD]]
; GFX9-O0: buffer_store_dword v[[SECOND]], off, s{{\[}}{{[0-9]+}}:{{[0-9]+}}{{\]}}, s[[SECOND_SGPR_OFFSET:[0-9]+]] offset:[[SECOND_IMM_OFFSET:[0-9]+]]
  %tmp135 = tail call i32 @llvm.amdgcn.update.dpp.i32(i32 0, i32 %tmp107, i32 323, i32 12, i32 15, i1 false)
  %tmp136 = add i32 %tmp107, %tmp135
  %tmp137 = tail call i32 @llvm.amdgcn.wwm.i32(i32 %tmp136)
  br label %merge

merge:
  %merge_value = phi i32 [ 0, %entry ], [%tmp137, %if ]
; GFX9-O3: v_cmp_eq_u32_e32 vcc, v[[FIRST]], v[[SECOND]]
; GFX9-O0: buffer_load_dword v[[SECOND:[0-9]+]], off, s{{\[}}{{[0-9]+}}:{{[0-9]+}}{{\]}}, s[[SECOND_SGPR_OFFSET]] offset:[[SECOND_IMM_OFFSET]]
; GFX9-O0: buffer_load_dword v[[FIRST:[0-9]+]], off, s{{\[}}{{[0-9]+}}:{{[0-9]+}}{{\]}}, s[[FIRST_SGPR_OFFSET]] offset:[[FIRST_IMM_OFFSET]]
; GFX9-O0: v_cmp_eq_u32_e64 s{{\[}}{{[0-9]+}}:{{[0-9]+}}{{\]}}, v[[FIRST]], v[[SECOND]]
  %tmp138 = icmp eq i32 %tmp122, %merge_value
  %tmp139 = sext i1 %tmp138 to i32
  %tmp140 = shl nsw i32 %tmp139, 1
  %tmp141 = and i32 %tmp140, 2
  %tmp145 = bitcast i32 %tmp141 to float
  call void @llvm.amdgcn.raw.buffer.store.f32(float %tmp145, <4 x i32> %tmp14, i32 4, i32 0, i32 0)
  ret void
}

define i32 @called(i32 %a) noinline {
; GFX9: v_add_u32_e32 v1, v0, v0
  %add = add i32 %a, %a
; GFX9: v_mul_lo_u32 v0, v1, v0
  %mul = mul i32 %add, %a
; GFX9: v_sub_u32_e32 v0, v0, v1
  %sub = sub i32 %mul, %add
  ret i32 %sub
}

define amdgpu_kernel void @call(<4 x i32> inreg %tmp14, i32 inreg %arg) {
; GFX9-O0: v_mov_b32_e32 v0, s2
; GFX9-O3: v_mov_b32_e32 v2, s0
; GFX9-NEXT: s_not_b64 exec, exec
; GFX9-O0-NEXT: v_mov_b32_e32 v0, s3
; GFX9-O3-NEXT: v_mov_b32_e32 v2, 0
; GFX9-NEXT: s_not_b64 exec, exec
  %tmp107 = tail call i32 @llvm.amdgcn.set.inactive.i32(i32 %arg, i32 0)
; GFX9-O0: buffer_store_dword v0
; GFX9-O3: v_mov_b32_e32 v0, v2
; GFX9: s_swappc_b64
  %tmp134 = call i32 @called(i32 %tmp107)
; GFX9-O0: buffer_load_dword v1
; GFX9-O3: v_mov_b32_e32 v1, v0
; GFX9-O0: v_add_u32_e32 v0, v0, v1
; GFX9-O3: v_add_u32_e32 v1, v1, v2
  %tmp136 = add i32 %tmp134, %tmp107
  %tmp137 = tail call i32 @llvm.amdgcn.wwm.i32(i32 %tmp136)
; GFX9-O0: buffer_store_dword v2
; GFX9-O3: buffer_store_dword v0
  call void @llvm.amdgcn.raw.buffer.store.i32(i32 %tmp137, <4 x i32> %tmp14, i32 4, i32 0, i32 0)
  ret void
}

define i64 @called_i64(i64 %a) noinline {
  %add = add i64 %a, %a
  %mul = mul i64 %add, %a
  %sub = sub i64 %mul, %add
  ret i64 %sub
}

define amdgpu_kernel void @call_i64(<4 x i32> inreg %tmp14, i64 inreg %arg) {
; GFX9-O0: v_mov_b32_e32 v0, s0
; GFX9-O0: v_mov_b32_e32 v1, s1
; GFX9-O3: v_mov_b32_e32 v7, s1
; GFX9-O3: v_mov_b32_e32 v6, s0
; GFX9-NEXT: s_not_b64 exec, exec
; GFX9-O0-NEXT: v_mov_b32_e32 v0, s2
; GFX9-O0-NEXT: v_mov_b32_e32 v1, s3
; GFX9-O3-NEXT: v_mov_b32_e32 v6, 0
; GFX9-O3-NEXT: v_mov_b32_e32 v7, 0
; GFX9-NEXT: s_not_b64 exec, exec
  %tmp107 = tail call i64 @llvm.amdgcn.set.inactive.i64(i64 %arg, i64 0)
; GFX9-O0: buffer_store_dword v0
; GFX9-O0: buffer_store_dword v1
; GFX9: s_swappc_b64
  %tmp134 = call i64 @called_i64(i64 %tmp107)
; GFX9-O0: buffer_load_dword v6
; GFX9-O0: buffer_load_dword v7
  %tmp136 = add i64 %tmp134, %tmp107
  %tmp137 = tail call i64 @llvm.amdgcn.wwm.i64(i64 %tmp136)
  %tmp138 = bitcast i64 %tmp137 to <2 x i32>
  call void @llvm.amdgcn.raw.buffer.store.v2i32(<2 x i32> %tmp138, <4 x i32> %tmp14, i32 4, i32 0, i32 0)
  ret void
}

define amdgpu_cs void @_amdgpu_cs_main(<4 x i32> inreg %desc, i32 %index) {
  %tmp17 = shl i32 %index, 5
; GFX9: buffer_load_dwordx4
  %tmp18 = tail call <4 x i32> @llvm.amdgcn.s.buffer.load.v4i32(<4 x i32> %desc, i32 %tmp17, i32 0)
  %.i0.upto1.bc = bitcast <4 x i32> %tmp18 to <2 x i64>
  %tmp19 = or i32 %tmp17, 16
; GFX9: buffer_load_dwordx2
  %tmp20 = tail call <2 x i32> @llvm.amdgcn.s.buffer.load.v2i32(<4 x i32> %desc, i32 %tmp19, i32 0)
  %.i0.upto1.extract = extractelement <2 x i64> %.i0.upto1.bc, i32 0
  %tmp22 = tail call i64 @llvm.amdgcn.set.inactive.i64(i64 %.i0.upto1.extract, i64 9223372036854775807)
  %tmp97 = tail call i64 @llvm.amdgcn.wwm.i64(i64 %tmp22)
  %.i1.upto1.extract = extractelement <2 x i64> %.i0.upto1.bc, i32 1
  %tmp99 = tail call i64 @llvm.amdgcn.set.inactive.i64(i64 %.i1.upto1.extract, i64 9223372036854775807)
  %tmp174 = tail call i64 @llvm.amdgcn.wwm.i64(i64 %tmp99)
  %.i25 = bitcast <2 x i32> %tmp20 to i64
  %tmp176 = tail call i64 @llvm.amdgcn.set.inactive.i64(i64 %.i25, i64 9223372036854775807)
  %tmp251 = tail call i64 @llvm.amdgcn.wwm.i64(i64 %tmp176)
  %.cast = bitcast i64 %tmp97 to <2 x float>
  %.cast6 = bitcast i64 %tmp174 to <2 x float>
  %.cast7 = bitcast i64 %tmp251 to <2 x float>
  %tmp254 = shufflevector <2 x float> %.cast, <2 x float> %.cast6, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
; GFX9: buffer_store_dwordx4
  tail call void @llvm.amdgcn.raw.buffer.store.v4f32(<4 x float> %tmp254, <4 x i32> %desc, i32 %tmp17, i32 0, i32 0)
  ; GFX9: buffer_store_dwordx2
  tail call void @llvm.amdgcn.raw.buffer.store.v2f32(<2 x float> %.cast7, <4 x i32> %desc, i32 %tmp19, i32 0, i32 0)
  ret void
}

declare i32 @llvm.amdgcn.wwm.i32(i32)
declare i64 @llvm.amdgcn.wwm.i64(i64)
declare i32 @llvm.amdgcn.set.inactive.i32(i32, i32)
declare i64 @llvm.amdgcn.set.inactive.i64(i64, i64)
declare i32 @llvm.amdgcn.update.dpp.i32(i32, i32, i32, i32, i32, i1)
declare <2 x float> @llvm.amdgcn.raw.buffer.load.v2f32(<4 x i32>, i32, i32, i32)
declare void @llvm.amdgcn.raw.buffer.store.f32(float, <4 x i32>, i32, i32, i32)
declare void @llvm.amdgcn.raw.buffer.store.i32(i32, <4 x i32>, i32, i32, i32)
declare void @llvm.amdgcn.raw.buffer.store.v2i32(<2 x i32>, <4 x i32>, i32, i32, i32)
declare void @llvm.amdgcn.raw.buffer.store.v2f32(<2 x float>, <4 x i32>, i32, i32, i32)
declare void @llvm.amdgcn.raw.buffer.store.v4f32(<4 x float>, <4 x i32>, i32, i32, i32)
declare <2 x i32> @llvm.amdgcn.s.buffer.load.v2i32(<4 x i32>, i32, i32)
declare <4 x i32> @llvm.amdgcn.s.buffer.load.v4i32(<4 x i32>, i32, i32)