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
;RUN: llc < %s -march=amdgcn -mcpu=tonga -verify-machineinstrs | FileCheck %s

;CHECK-LABEL: {{^}}s_buffer_load_imm:
;CHECK-NOT: s_waitcnt;
;CHECK: s_buffer_load_dword s{{[0-9]+}}, s[{{[0-9]+:[0-9]+}}], 0x4
define amdgpu_ps void @s_buffer_load_imm(<4 x i32> inreg %desc) {
main_body:
  %load = call i32 @llvm.amdgcn.s.buffer.load.i32(<4 x i32> %desc, i32 4, i32 0)
  %bitcast = bitcast i32 %load to float
  call void @llvm.amdgcn.exp.f32(i32 0, i32 15, float %bitcast, float undef, float undef, float undef, i1 true, i1 true)
  ret void
}

;CHECK-LABEL: {{^}}s_buffer_load_index:
;CHECK-NOT: s_waitcnt;
;CHECK: s_buffer_load_dword s{{[0-9]+}}, s[{{[0-9]+:[0-9]+}}], s{{[0-9]+}}
define amdgpu_ps void @s_buffer_load_index(<4 x i32> inreg %desc, i32 inreg %index) {
main_body:
  %load = call i32 @llvm.amdgcn.s.buffer.load.i32(<4 x i32> %desc, i32 %index, i32 0)
  %bitcast = bitcast i32 %load to float
  call void @llvm.amdgcn.exp.f32(i32 0, i32 15, float %bitcast, float undef, float undef, float undef, i1 true, i1 true)
  ret void
}

;CHECK-LABEL: {{^}}s_buffer_loadx2_imm:
;CHECK-NOT: s_waitcnt;
;CHECK: s_buffer_load_dwordx2 s[{{[0-9]+:[0-9]+}}], s[{{[0-9]+:[0-9]+}}], 0x40
define amdgpu_ps void @s_buffer_loadx2_imm(<4 x i32> inreg %desc) {
main_body:
  %load = call <2 x i32> @llvm.amdgcn.s.buffer.load.v2i32(<4 x i32> %desc, i32 64, i32 0)
  %bitcast = bitcast <2 x i32> %load to <2 x float>
  %x = extractelement <2 x float> %bitcast, i32 0
  %y = extractelement <2 x float> %bitcast, i32 1
  call void @llvm.amdgcn.exp.f32(i32 0, i32 15, float %x, float %y, float undef, float undef, i1 true, i1 true)
  ret void
}

;CHECK-LABEL: {{^}}s_buffer_loadx2_index:
;CHECK-NOT: s_waitcnt;
;CHECK: s_buffer_load_dwordx2 s[{{[0-9]+:[0-9]+}}], s[{{[0-9]+:[0-9]+}}], s{{[0-9]+}}
define amdgpu_ps void @s_buffer_loadx2_index(<4 x i32> inreg %desc, i32 inreg %index) {
main_body:
  %load = call <2 x i32> @llvm.amdgcn.s.buffer.load.v2i32(<4 x i32> %desc, i32 %index, i32 0)
  %bitcast = bitcast <2 x i32> %load to <2 x float>
  %x = extractelement <2 x float> %bitcast, i32 0
  %y = extractelement <2 x float> %bitcast, i32 1
  call void @llvm.amdgcn.exp.f32(i32 0, i32 15, float %x, float %y, float undef, float undef, i1 true, i1 true)
  ret void
}

;CHECK-LABEL: {{^}}s_buffer_loadx4_imm:
;CHECK-NOT: s_waitcnt;
;CHECK: s_buffer_load_dwordx4 s[{{[0-9]+:[0-9]+}}], s[{{[0-9]+:[0-9]+}}], 0xc8
define amdgpu_ps void @s_buffer_loadx4_imm(<4 x i32> inreg %desc) {
main_body:
  %load = call <4 x i32> @llvm.amdgcn.s.buffer.load.v4i32(<4 x i32> %desc, i32 200, i32 0)
  %bitcast = bitcast <4 x i32> %load to <4 x float>
  %x = extractelement <4 x float> %bitcast, i32 0
  %y = extractelement <4 x float> %bitcast, i32 1
  %z = extractelement <4 x float> %bitcast, i32 2
  %w = extractelement <4 x float> %bitcast, i32 3
  call void @llvm.amdgcn.exp.f32(i32 0, i32 15, float %x, float %y, float %z, float %w, i1 true, i1 true)
  ret void
}

;CHECK-LABEL: {{^}}s_buffer_loadx4_index:
;CHECK-NOT: s_waitcnt;
;CHECK: s_buffer_load_dwordx4 s[{{[0-9]+:[0-9]+}}], s[{{[0-9]+:[0-9]+}}], s{{[0-9]+}}
define amdgpu_ps void @s_buffer_loadx4_index(<4 x i32> inreg %desc, i32 inreg %index) {
main_body:
  %load = call <4 x i32> @llvm.amdgcn.s.buffer.load.v4i32(<4 x i32> %desc, i32 %index, i32 0)
  %bitcast = bitcast <4 x i32> %load to <4 x float>
  %x = extractelement <4 x float> %bitcast, i32 0
  %y = extractelement <4 x float> %bitcast, i32 1
  %z = extractelement <4 x float> %bitcast, i32 2
  %w = extractelement <4 x float> %bitcast, i32 3
  call void @llvm.amdgcn.exp.f32(i32 0, i32 15, float %x, float %y, float %z, float %w, i1 true, i1 true)
  ret void
}

;CHECK-LABEL: {{^}}s_buffer_load_imm_mergex2:
;CHECK-NOT: s_waitcnt;
;CHECK: s_buffer_load_dwordx2 s[{{[0-9]+:[0-9]+}}], s[{{[0-9]+:[0-9]+}}], 0x4
define amdgpu_ps void @s_buffer_load_imm_mergex2(<4 x i32> inreg %desc) {
main_body:
  %load0 = call i32 @llvm.amdgcn.s.buffer.load.i32(<4 x i32> %desc, i32 4, i32 0)
  %load1 = call i32 @llvm.amdgcn.s.buffer.load.i32(<4 x i32> %desc, i32 8, i32 0)
  %x = bitcast i32 %load0 to float
  %y = bitcast i32 %load1 to float
  call void @llvm.amdgcn.exp.f32(i32 0, i32 15, float %x, float %y, float undef, float undef, i1 true, i1 true)
  ret void
}

;CHECK-LABEL: {{^}}s_buffer_load_imm_mergex4:
;CHECK-NOT: s_waitcnt;
;CHECK: s_buffer_load_dwordx4 s[{{[0-9]+:[0-9]+}}], s[{{[0-9]+:[0-9]+}}], 0x8
define amdgpu_ps void @s_buffer_load_imm_mergex4(<4 x i32> inreg %desc) {
main_body:
  %load0 = call i32 @llvm.amdgcn.s.buffer.load.i32(<4 x i32> %desc, i32 8, i32 0)
  %load1 = call i32 @llvm.amdgcn.s.buffer.load.i32(<4 x i32> %desc, i32 12, i32 0)
  %load2 = call i32 @llvm.amdgcn.s.buffer.load.i32(<4 x i32> %desc, i32 16, i32 0)
  %load3 = call i32 @llvm.amdgcn.s.buffer.load.i32(<4 x i32> %desc, i32 20, i32 0)
  %x = bitcast i32 %load0 to float
  %y = bitcast i32 %load1 to float
  %z = bitcast i32 %load2 to float
  %w = bitcast i32 %load3 to float
  call void @llvm.amdgcn.exp.f32(i32 0, i32 15, float %x, float %y, float %z, float %w, i1 true, i1 true)
  ret void
}

;CHECK-LABEL: {{^}}s_buffer_load_index_across_bb:
;CHECK-NOT: s_waitcnt;
;CHECK: v_or_b32
;CHECK: buffer_load_dword v{{[0-9]+}}, v{{[0-9]+}}, s[{{[0-9]+:[0-9]+}}], 0 offen
define amdgpu_ps void @s_buffer_load_index_across_bb(<4 x i32> inreg %desc, i32 %index) {
main_body:
  %tmp = shl i32 %index, 4
  br label %bb1

bb1:                                              ; preds = %main_body
  %tmp1 = or i32 %tmp, 8
  %load = call i32 @llvm.amdgcn.s.buffer.load.i32(<4 x i32> %desc, i32 %tmp1, i32 0)
  %bitcast = bitcast i32 %load to float
  call void @llvm.amdgcn.exp.f32(i32 0, i32 15, float %bitcast, float undef, float undef, float undef, i1 true, i1 true)
  ret void
}

;CHECK-LABEL: {{^}}s_buffer_load_index_across_bb_merged:
;CHECK-NOT: s_waitcnt;
;CHECK: v_or_b32
;CHECK: v_or_b32
;CHECK: buffer_load_dword v{{[0-9]+}}, v{{[0-9]+}}, s[{{[0-9]+:[0-9]+}}], 0 offen
;CHECK: buffer_load_dword v{{[0-9]+}}, v{{[0-9]+}}, s[{{[0-9]+:[0-9]+}}], 0 offen
define amdgpu_ps void @s_buffer_load_index_across_bb_merged(<4 x i32> inreg %desc, i32 %index) {
main_body:
  %tmp = shl i32 %index, 4
  br label %bb1

bb1:                                              ; preds = %main_body
  %tmp1 = or i32 %tmp, 8
  %load = call i32 @llvm.amdgcn.s.buffer.load.i32(<4 x i32> %desc, i32 %tmp1, i32 0)
  %tmp2 = or i32 %tmp1, 4
  %load2 = tail call i32 @llvm.amdgcn.s.buffer.load.i32(<4 x i32> %desc, i32 %tmp2, i32 0)
  %bitcast = bitcast i32 %load to float
  %bitcast2 = bitcast i32 %load2 to float
  call void @llvm.amdgcn.exp.f32(i32 0, i32 15, float %bitcast, float %bitcast2, float undef, float undef, i1 true, i1 true)
  ret void
}

declare void @llvm.amdgcn.exp.f32(i32, i32, float, float, float, float, i1, i1)
declare i32 @llvm.amdgcn.s.buffer.load.i32(<4 x 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)