forked from OSchip/llvm-project
1314 lines
64 KiB
LLVM
1314 lines
64 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc -march=amdgcn -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck -check-prefixes=GFX9 %s
|
|
; RUN: llc -march=amdgcn -mcpu=gfx1010 -verify-machineinstrs < %s | FileCheck -check-prefixes=GFX10 %s
|
|
|
|
define amdgpu_ps <4 x float> @sample_1d(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, half %s) {
|
|
; GFX9-LABEL: sample_1d:
|
|
; GFX9: ; %bb.0: ; %main_body
|
|
; GFX9-NEXT: s_mov_b64 s[12:13], exec
|
|
; GFX9-NEXT: s_wqm_b64 exec, exec
|
|
; GFX9-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; GFX9-NEXT: image_sample v[0:3], v0, s[0:7], s[8:11] dmask:0xf a16
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX9-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_1d:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: s_mov_b32 s12, exec_lo
|
|
; GFX10-NEXT: s_wqm_b32 exec_lo, exec_lo
|
|
; GFX10-NEXT: s_and_b32 exec_lo, exec_lo, s12
|
|
; GFX10-NEXT: image_sample v[0:3], v0, s[0:7], s[8:11] dmask:0xf dim:SQ_RSRC_IMG_1D a16
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.1d.v4f32.f16(i32 15, half %s, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 0, i32 0)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @sample_2d(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, half %s, half %t) {
|
|
; GFX9-LABEL: sample_2d:
|
|
; GFX9: ; %bb.0: ; %main_body
|
|
; GFX9-NEXT: s_mov_b64 s[12:13], exec
|
|
; GFX9-NEXT: s_wqm_b64 exec, exec
|
|
; GFX9-NEXT: v_and_b32_e32 v0, 0xffff, v0
|
|
; GFX9-NEXT: v_lshl_or_b32 v0, v1, 16, v0
|
|
; GFX9-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; GFX9-NEXT: image_sample v[0:3], v0, s[0:7], s[8:11] dmask:0xf a16
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX9-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_2d:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: s_mov_b32 s12, exec_lo
|
|
; GFX10-NEXT: s_wqm_b32 exec_lo, exec_lo
|
|
; GFX10-NEXT: v_and_b32_e32 v0, 0xffff, v0
|
|
; GFX10-NEXT: v_lshl_or_b32 v0, v1, 16, v0
|
|
; GFX10-NEXT: s_and_b32 exec_lo, exec_lo, s12
|
|
; GFX10-NEXT: image_sample v[0:3], v0, s[0:7], s[8:11] dmask:0xf dim:SQ_RSRC_IMG_2D a16
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.2d.v4f32.f16(i32 15, half %s, half %t, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 0, i32 0)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @sample_3d(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, half %s, half %t, half %r) {
|
|
; GFX9-LABEL: sample_3d:
|
|
; GFX9: ; %bb.0: ; %main_body
|
|
; GFX9-NEXT: s_mov_b64 s[12:13], exec
|
|
; GFX9-NEXT: s_wqm_b64 exec, exec
|
|
; GFX9-NEXT: v_and_b32_e32 v0, 0xffff, v0
|
|
; GFX9-NEXT: v_lshl_or_b32 v1, v1, 16, v0
|
|
; GFX9-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; GFX9-NEXT: image_sample v[0:3], v[1:2], s[0:7], s[8:11] dmask:0xf a16
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX9-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_3d:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: s_mov_b32 s12, exec_lo
|
|
; GFX10-NEXT: s_wqm_b32 exec_lo, exec_lo
|
|
; GFX10-NEXT: v_and_b32_e32 v0, 0xffff, v0
|
|
; GFX10-NEXT: v_lshl_or_b32 v1, v1, 16, v0
|
|
; GFX10-NEXT: s_and_b32 exec_lo, exec_lo, s12
|
|
; GFX10-NEXT: image_sample v[0:3], v[1:2], s[0:7], s[8:11] dmask:0xf dim:SQ_RSRC_IMG_3D a16
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.3d.v4f32.f16(i32 15, half %s, half %t, half %r, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 0, i32 0)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @sample_cube(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, half %s, half %t, half %face) {
|
|
; GFX9-LABEL: sample_cube:
|
|
; GFX9: ; %bb.0: ; %main_body
|
|
; GFX9-NEXT: s_mov_b64 s[12:13], exec
|
|
; GFX9-NEXT: s_wqm_b64 exec, exec
|
|
; GFX9-NEXT: v_and_b32_e32 v0, 0xffff, v0
|
|
; GFX9-NEXT: v_lshl_or_b32 v1, v1, 16, v0
|
|
; GFX9-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; GFX9-NEXT: image_sample v[0:3], v[1:2], s[0:7], s[8:11] dmask:0xf a16 da
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX9-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_cube:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: s_mov_b32 s12, exec_lo
|
|
; GFX10-NEXT: s_wqm_b32 exec_lo, exec_lo
|
|
; GFX10-NEXT: v_and_b32_e32 v0, 0xffff, v0
|
|
; GFX10-NEXT: v_lshl_or_b32 v1, v1, 16, v0
|
|
; GFX10-NEXT: s_and_b32 exec_lo, exec_lo, s12
|
|
; GFX10-NEXT: image_sample v[0:3], v[1:2], s[0:7], s[8:11] dmask:0xf dim:SQ_RSRC_IMG_CUBE a16
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.cube.v4f32.f16(i32 15, half %s, half %t, half %face, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 0, i32 0)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @sample_1darray(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, half %s, half %slice) {
|
|
; GFX9-LABEL: sample_1darray:
|
|
; GFX9: ; %bb.0: ; %main_body
|
|
; GFX9-NEXT: s_mov_b64 s[12:13], exec
|
|
; GFX9-NEXT: s_wqm_b64 exec, exec
|
|
; GFX9-NEXT: v_and_b32_e32 v0, 0xffff, v0
|
|
; GFX9-NEXT: v_lshl_or_b32 v0, v1, 16, v0
|
|
; GFX9-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; GFX9-NEXT: image_sample v[0:3], v0, s[0:7], s[8:11] dmask:0xf a16 da
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX9-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_1darray:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: s_mov_b32 s12, exec_lo
|
|
; GFX10-NEXT: s_wqm_b32 exec_lo, exec_lo
|
|
; GFX10-NEXT: v_and_b32_e32 v0, 0xffff, v0
|
|
; GFX10-NEXT: v_lshl_or_b32 v0, v1, 16, v0
|
|
; GFX10-NEXT: s_and_b32 exec_lo, exec_lo, s12
|
|
; GFX10-NEXT: image_sample v[0:3], v0, s[0:7], s[8:11] dmask:0xf dim:SQ_RSRC_IMG_1D_ARRAY a16
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.1darray.v4f32.f16(i32 15, half %s, half %slice, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 0, i32 0)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @sample_2darray(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, half %s, half %t, half %slice) {
|
|
; GFX9-LABEL: sample_2darray:
|
|
; GFX9: ; %bb.0: ; %main_body
|
|
; GFX9-NEXT: s_mov_b64 s[12:13], exec
|
|
; GFX9-NEXT: s_wqm_b64 exec, exec
|
|
; GFX9-NEXT: v_and_b32_e32 v0, 0xffff, v0
|
|
; GFX9-NEXT: v_lshl_or_b32 v1, v1, 16, v0
|
|
; GFX9-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; GFX9-NEXT: image_sample v[0:3], v[1:2], s[0:7], s[8:11] dmask:0xf a16 da
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX9-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_2darray:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: s_mov_b32 s12, exec_lo
|
|
; GFX10-NEXT: s_wqm_b32 exec_lo, exec_lo
|
|
; GFX10-NEXT: v_and_b32_e32 v0, 0xffff, v0
|
|
; GFX10-NEXT: v_lshl_or_b32 v1, v1, 16, v0
|
|
; GFX10-NEXT: s_and_b32 exec_lo, exec_lo, s12
|
|
; GFX10-NEXT: image_sample v[0:3], v[1:2], s[0:7], s[8:11] dmask:0xf dim:SQ_RSRC_IMG_2D_ARRAY a16
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.2darray.v4f32.f16(i32 15, half %s, half %t, half %slice, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 0, i32 0)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @sample_c_1d(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, float %zcompare, half %s) {
|
|
; GFX9-LABEL: sample_c_1d:
|
|
; GFX9: ; %bb.0: ; %main_body
|
|
; GFX9-NEXT: s_mov_b64 s[12:13], exec
|
|
; GFX9-NEXT: s_wqm_b64 exec, exec
|
|
; GFX9-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; GFX9-NEXT: image_sample_c v[0:3], v[0:1], s[0:7], s[8:11] dmask:0xf a16
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX9-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_c_1d:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: s_mov_b32 s12, exec_lo
|
|
; GFX10-NEXT: s_wqm_b32 exec_lo, exec_lo
|
|
; GFX10-NEXT: s_and_b32 exec_lo, exec_lo, s12
|
|
; GFX10-NEXT: image_sample_c v[0:3], v[0:1], s[0:7], s[8:11] dmask:0xf dim:SQ_RSRC_IMG_1D a16
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.c.1d.v4f32.f16(i32 15, float %zcompare, half %s, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 0, i32 0)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @sample_c_2d(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, float %zcompare, half %s, half %t) {
|
|
; GFX9-LABEL: sample_c_2d:
|
|
; GFX9: ; %bb.0: ; %main_body
|
|
; GFX9-NEXT: s_mov_b64 s[12:13], exec
|
|
; GFX9-NEXT: s_wqm_b64 exec, exec
|
|
; GFX9-NEXT: v_and_b32_e32 v1, 0xffff, v1
|
|
; GFX9-NEXT: v_lshl_or_b32 v1, v2, 16, v1
|
|
; GFX9-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; GFX9-NEXT: image_sample_c v[0:3], v[0:1], s[0:7], s[8:11] dmask:0xf a16
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX9-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_c_2d:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: s_mov_b32 s12, exec_lo
|
|
; GFX10-NEXT: s_wqm_b32 exec_lo, exec_lo
|
|
; GFX10-NEXT: v_and_b32_e32 v1, 0xffff, v1
|
|
; GFX10-NEXT: v_lshl_or_b32 v1, v2, 16, v1
|
|
; GFX10-NEXT: s_and_b32 exec_lo, exec_lo, s12
|
|
; GFX10-NEXT: image_sample_c v[0:3], v[0:1], s[0:7], s[8:11] dmask:0xf dim:SQ_RSRC_IMG_2D a16
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.c.2d.v4f32.f16(i32 15, float %zcompare, half %s, half %t, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 0, i32 0)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @sample_cl_1d(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, half %s, half %clamp) {
|
|
; GFX9-LABEL: sample_cl_1d:
|
|
; GFX9: ; %bb.0: ; %main_body
|
|
; GFX9-NEXT: s_mov_b64 s[12:13], exec
|
|
; GFX9-NEXT: s_wqm_b64 exec, exec
|
|
; GFX9-NEXT: v_and_b32_e32 v0, 0xffff, v0
|
|
; GFX9-NEXT: v_lshl_or_b32 v0, v1, 16, v0
|
|
; GFX9-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; GFX9-NEXT: image_sample_cl v[0:3], v0, s[0:7], s[8:11] dmask:0xf a16
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX9-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_cl_1d:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: s_mov_b32 s12, exec_lo
|
|
; GFX10-NEXT: s_wqm_b32 exec_lo, exec_lo
|
|
; GFX10-NEXT: v_and_b32_e32 v0, 0xffff, v0
|
|
; GFX10-NEXT: v_lshl_or_b32 v0, v1, 16, v0
|
|
; GFX10-NEXT: s_and_b32 exec_lo, exec_lo, s12
|
|
; GFX10-NEXT: image_sample_cl v[0:3], v0, s[0:7], s[8:11] dmask:0xf dim:SQ_RSRC_IMG_1D a16
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.cl.1d.v4f32.f16(i32 15, half %s, half %clamp, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 0, i32 0)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @sample_cl_2d(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, half %s, half %t, half %clamp) {
|
|
; GFX9-LABEL: sample_cl_2d:
|
|
; GFX9: ; %bb.0: ; %main_body
|
|
; GFX9-NEXT: s_mov_b64 s[12:13], exec
|
|
; GFX9-NEXT: s_wqm_b64 exec, exec
|
|
; GFX9-NEXT: v_and_b32_e32 v0, 0xffff, v0
|
|
; GFX9-NEXT: v_lshl_or_b32 v1, v1, 16, v0
|
|
; GFX9-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; GFX9-NEXT: image_sample_cl v[0:3], v[1:2], s[0:7], s[8:11] dmask:0xf a16
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX9-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_cl_2d:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: s_mov_b32 s12, exec_lo
|
|
; GFX10-NEXT: s_wqm_b32 exec_lo, exec_lo
|
|
; GFX10-NEXT: v_and_b32_e32 v0, 0xffff, v0
|
|
; GFX10-NEXT: v_lshl_or_b32 v1, v1, 16, v0
|
|
; GFX10-NEXT: s_and_b32 exec_lo, exec_lo, s12
|
|
; GFX10-NEXT: image_sample_cl v[0:3], v[1:2], s[0:7], s[8:11] dmask:0xf dim:SQ_RSRC_IMG_2D a16
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.cl.2d.v4f32.f16(i32 15, half %s, half %t, half %clamp, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 0, i32 0)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @sample_c_cl_1d(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, float %zcompare, half %s, half %clamp) {
|
|
; GFX9-LABEL: sample_c_cl_1d:
|
|
; GFX9: ; %bb.0: ; %main_body
|
|
; GFX9-NEXT: s_mov_b64 s[12:13], exec
|
|
; GFX9-NEXT: s_wqm_b64 exec, exec
|
|
; GFX9-NEXT: v_and_b32_e32 v1, 0xffff, v1
|
|
; GFX9-NEXT: v_lshl_or_b32 v1, v2, 16, v1
|
|
; GFX9-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; GFX9-NEXT: image_sample_c_cl v[0:3], v[0:1], s[0:7], s[8:11] dmask:0xf a16
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX9-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_c_cl_1d:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: s_mov_b32 s12, exec_lo
|
|
; GFX10-NEXT: s_wqm_b32 exec_lo, exec_lo
|
|
; GFX10-NEXT: v_and_b32_e32 v1, 0xffff, v1
|
|
; GFX10-NEXT: v_lshl_or_b32 v1, v2, 16, v1
|
|
; GFX10-NEXT: s_and_b32 exec_lo, exec_lo, s12
|
|
; GFX10-NEXT: image_sample_c_cl v[0:3], v[0:1], s[0:7], s[8:11] dmask:0xf dim:SQ_RSRC_IMG_1D a16
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.c.cl.1d.v4f32.f16(i32 15, float %zcompare, half %s, half %clamp, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 0, i32 0)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @sample_c_cl_2d(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, float %zcompare, half %s, half %t, half %clamp) {
|
|
; GFX9-LABEL: sample_c_cl_2d:
|
|
; GFX9: ; %bb.0: ; %main_body
|
|
; GFX9-NEXT: s_mov_b64 s[12:13], exec
|
|
; GFX9-NEXT: s_wqm_b64 exec, exec
|
|
; GFX9-NEXT: v_mov_b32_e32 v5, v3
|
|
; GFX9-NEXT: v_mov_b32_e32 v3, v0
|
|
; GFX9-NEXT: v_and_b32_e32 v0, 0xffff, v1
|
|
; GFX9-NEXT: v_lshl_or_b32 v4, v2, 16, v0
|
|
; GFX9-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; GFX9-NEXT: image_sample_c_cl v[0:3], v[3:5], s[0:7], s[8:11] dmask:0xf a16
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX9-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_c_cl_2d:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: s_mov_b32 s12, exec_lo
|
|
; GFX10-NEXT: s_wqm_b32 exec_lo, exec_lo
|
|
; GFX10-NEXT: v_and_b32_e32 v1, 0xffff, v1
|
|
; GFX10-NEXT: v_lshl_or_b32 v1, v2, 16, v1
|
|
; GFX10-NEXT: s_and_b32 exec_lo, exec_lo, s12
|
|
; GFX10-NEXT: image_sample_c_cl v[0:3], [v0, v1, v3], s[0:7], s[8:11] dmask:0xf dim:SQ_RSRC_IMG_2D a16
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.c.cl.2d.v4f32.f16(i32 15, float %zcompare, half %s, half %t, half %clamp, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 0, i32 0)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @sample_b_1d(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, float %bias, half %s) {
|
|
; GFX9-LABEL: sample_b_1d:
|
|
; GFX9: ; %bb.0: ; %main_body
|
|
; GFX9-NEXT: s_mov_b64 s[12:13], exec
|
|
; GFX9-NEXT: s_wqm_b64 exec, exec
|
|
; GFX9-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; GFX9-NEXT: image_sample_b v[0:3], v[0:1], s[0:7], s[8:11] dmask:0xf a16
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX9-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_b_1d:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: s_mov_b32 s12, exec_lo
|
|
; GFX10-NEXT: s_wqm_b32 exec_lo, exec_lo
|
|
; GFX10-NEXT: s_and_b32 exec_lo, exec_lo, s12
|
|
; GFX10-NEXT: image_sample_b v[0:3], v[0:1], s[0:7], s[8:11] dmask:0xf dim:SQ_RSRC_IMG_1D a16
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.b.1d.v4f32.f32.f16(i32 15, float %bias, half %s, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 0, i32 0)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @sample_b_2d(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, float %bias, half %s, half %t) {
|
|
; GFX9-LABEL: sample_b_2d:
|
|
; GFX9: ; %bb.0: ; %main_body
|
|
; GFX9-NEXT: s_mov_b64 s[12:13], exec
|
|
; GFX9-NEXT: s_wqm_b64 exec, exec
|
|
; GFX9-NEXT: v_and_b32_e32 v1, 0xffff, v1
|
|
; GFX9-NEXT: v_lshl_or_b32 v1, v2, 16, v1
|
|
; GFX9-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; GFX9-NEXT: image_sample_b v[0:3], v[0:1], s[0:7], s[8:11] dmask:0xf a16
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX9-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_b_2d:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: s_mov_b32 s12, exec_lo
|
|
; GFX10-NEXT: s_wqm_b32 exec_lo, exec_lo
|
|
; GFX10-NEXT: v_and_b32_e32 v1, 0xffff, v1
|
|
; GFX10-NEXT: v_lshl_or_b32 v1, v2, 16, v1
|
|
; GFX10-NEXT: s_and_b32 exec_lo, exec_lo, s12
|
|
; GFX10-NEXT: image_sample_b v[0:3], v[0:1], s[0:7], s[8:11] dmask:0xf dim:SQ_RSRC_IMG_2D a16
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.b.2d.v4f32.f32.f16(i32 15, float %bias, half %s, half %t, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 0, i32 0)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @sample_c_b_1d(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, float %bias, float %zcompare, half %s) {
|
|
; GFX9-LABEL: sample_c_b_1d:
|
|
; GFX9: ; %bb.0: ; %main_body
|
|
; GFX9-NEXT: s_mov_b64 s[12:13], exec
|
|
; GFX9-NEXT: s_wqm_b64 exec, exec
|
|
; GFX9-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; GFX9-NEXT: image_sample_c_b v[0:3], v[0:2], s[0:7], s[8:11] dmask:0xf a16
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX9-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_c_b_1d:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: s_mov_b32 s12, exec_lo
|
|
; GFX10-NEXT: s_wqm_b32 exec_lo, exec_lo
|
|
; GFX10-NEXT: s_and_b32 exec_lo, exec_lo, s12
|
|
; GFX10-NEXT: image_sample_c_b v[0:3], v[0:2], s[0:7], s[8:11] dmask:0xf dim:SQ_RSRC_IMG_1D a16
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.c.b.1d.v4f32.f32.f16(i32 15, float %bias, float %zcompare, half %s, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 0, i32 0)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @sample_c_b_2d(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, float %bias, float %zcompare, half %s, half %t) {
|
|
; GFX9-LABEL: sample_c_b_2d:
|
|
; GFX9: ; %bb.0: ; %main_body
|
|
; GFX9-NEXT: s_mov_b64 s[12:13], exec
|
|
; GFX9-NEXT: s_wqm_b64 exec, exec
|
|
; GFX9-NEXT: v_and_b32_e32 v2, 0xffff, v2
|
|
; GFX9-NEXT: v_lshl_or_b32 v2, v3, 16, v2
|
|
; GFX9-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; GFX9-NEXT: image_sample_c_b v[0:3], v[0:2], s[0:7], s[8:11] dmask:0xf a16
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX9-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_c_b_2d:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: s_mov_b32 s12, exec_lo
|
|
; GFX10-NEXT: s_wqm_b32 exec_lo, exec_lo
|
|
; GFX10-NEXT: v_and_b32_e32 v2, 0xffff, v2
|
|
; GFX10-NEXT: v_lshl_or_b32 v2, v3, 16, v2
|
|
; GFX10-NEXT: s_and_b32 exec_lo, exec_lo, s12
|
|
; GFX10-NEXT: image_sample_c_b v[0:3], v[0:2], s[0:7], s[8:11] dmask:0xf dim:SQ_RSRC_IMG_2D a16
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.c.b.2d.v4f32.f32.f16(i32 15, float %bias, float %zcompare, half %s, half %t, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 0, i32 0)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @sample_b_cl_1d(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, float %bias, half %s, half %clamp) {
|
|
; GFX9-LABEL: sample_b_cl_1d:
|
|
; GFX9: ; %bb.0: ; %main_body
|
|
; GFX9-NEXT: s_mov_b64 s[12:13], exec
|
|
; GFX9-NEXT: s_wqm_b64 exec, exec
|
|
; GFX9-NEXT: v_and_b32_e32 v1, 0xffff, v1
|
|
; GFX9-NEXT: v_lshl_or_b32 v1, v2, 16, v1
|
|
; GFX9-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; GFX9-NEXT: image_sample_b_cl v[0:3], v[0:1], s[0:7], s[8:11] dmask:0xf a16
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX9-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_b_cl_1d:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: s_mov_b32 s12, exec_lo
|
|
; GFX10-NEXT: s_wqm_b32 exec_lo, exec_lo
|
|
; GFX10-NEXT: v_and_b32_e32 v1, 0xffff, v1
|
|
; GFX10-NEXT: v_lshl_or_b32 v1, v2, 16, v1
|
|
; GFX10-NEXT: s_and_b32 exec_lo, exec_lo, s12
|
|
; GFX10-NEXT: image_sample_b_cl v[0:3], v[0:1], s[0:7], s[8:11] dmask:0xf dim:SQ_RSRC_IMG_1D a16
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.b.cl.1d.v4f32.f32.f16(i32 15, float %bias, half %s, half %clamp, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 0, i32 0)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @sample_b_cl_2d(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, float %bias, half %s, half %t, half %clamp) {
|
|
; GFX9-LABEL: sample_b_cl_2d:
|
|
; GFX9: ; %bb.0: ; %main_body
|
|
; GFX9-NEXT: s_mov_b64 s[12:13], exec
|
|
; GFX9-NEXT: s_wqm_b64 exec, exec
|
|
; GFX9-NEXT: v_mov_b32_e32 v5, v3
|
|
; GFX9-NEXT: v_mov_b32_e32 v3, v0
|
|
; GFX9-NEXT: v_and_b32_e32 v0, 0xffff, v1
|
|
; GFX9-NEXT: v_lshl_or_b32 v4, v2, 16, v0
|
|
; GFX9-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; GFX9-NEXT: image_sample_b_cl v[0:3], v[3:5], s[0:7], s[8:11] dmask:0xf a16
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX9-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_b_cl_2d:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: s_mov_b32 s12, exec_lo
|
|
; GFX10-NEXT: s_wqm_b32 exec_lo, exec_lo
|
|
; GFX10-NEXT: v_and_b32_e32 v1, 0xffff, v1
|
|
; GFX10-NEXT: v_lshl_or_b32 v1, v2, 16, v1
|
|
; GFX10-NEXT: s_and_b32 exec_lo, exec_lo, s12
|
|
; GFX10-NEXT: image_sample_b_cl v[0:3], [v0, v1, v3], s[0:7], s[8:11] dmask:0xf dim:SQ_RSRC_IMG_2D a16
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.b.cl.2d.v4f32.f32.f16(i32 15, float %bias, half %s, half %t, half %clamp, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 0, i32 0)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @sample_c_b_cl_1d(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, float %bias, float %zcompare, half %s, half %clamp) {
|
|
; GFX9-LABEL: sample_c_b_cl_1d:
|
|
; GFX9: ; %bb.0: ; %main_body
|
|
; GFX9-NEXT: s_mov_b64 s[12:13], exec
|
|
; GFX9-NEXT: s_wqm_b64 exec, exec
|
|
; GFX9-NEXT: v_and_b32_e32 v2, 0xffff, v2
|
|
; GFX9-NEXT: v_lshl_or_b32 v2, v3, 16, v2
|
|
; GFX9-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; GFX9-NEXT: image_sample_c_b_cl v[0:3], v[0:2], s[0:7], s[8:11] dmask:0xf a16
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX9-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_c_b_cl_1d:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: s_mov_b32 s12, exec_lo
|
|
; GFX10-NEXT: s_wqm_b32 exec_lo, exec_lo
|
|
; GFX10-NEXT: v_and_b32_e32 v2, 0xffff, v2
|
|
; GFX10-NEXT: v_lshl_or_b32 v2, v3, 16, v2
|
|
; GFX10-NEXT: s_and_b32 exec_lo, exec_lo, s12
|
|
; GFX10-NEXT: image_sample_c_b_cl v[0:3], v[0:2], s[0:7], s[8:11] dmask:0xf dim:SQ_RSRC_IMG_1D a16
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.c.b.cl.1d.v4f32.f32.f16(i32 15, float %bias, float %zcompare, half %s, half %clamp, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 0, i32 0)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @sample_c_b_cl_2d(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, float %bias, float %zcompare, half %s, half %t, half %clamp) {
|
|
; GFX9-LABEL: sample_c_b_cl_2d:
|
|
; GFX9: ; %bb.0: ; %main_body
|
|
; GFX9-NEXT: s_mov_b64 s[12:13], exec
|
|
; GFX9-NEXT: s_wqm_b64 exec, exec
|
|
; GFX9-NEXT: v_mov_b32_e32 v7, v4
|
|
; GFX9-NEXT: v_mov_b32_e32 v4, v0
|
|
; GFX9-NEXT: v_and_b32_e32 v0, 0xffff, v2
|
|
; GFX9-NEXT: v_mov_b32_e32 v5, v1
|
|
; GFX9-NEXT: v_lshl_or_b32 v6, v3, 16, v0
|
|
; GFX9-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; GFX9-NEXT: image_sample_c_b_cl v[0:3], v[4:7], s[0:7], s[8:11] dmask:0xf a16
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX9-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_c_b_cl_2d:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: s_mov_b32 s12, exec_lo
|
|
; GFX10-NEXT: s_wqm_b32 exec_lo, exec_lo
|
|
; GFX10-NEXT: v_and_b32_e32 v2, 0xffff, v2
|
|
; GFX10-NEXT: v_lshl_or_b32 v2, v3, 16, v2
|
|
; GFX10-NEXT: s_and_b32 exec_lo, exec_lo, s12
|
|
; GFX10-NEXT: image_sample_c_b_cl v[0:3], [v0, v1, v2, v4], s[0:7], s[8:11] dmask:0xf dim:SQ_RSRC_IMG_2D a16
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.c.b.cl.2d.v4f32.f32.f16(i32 15, float %bias, float %zcompare, half %s, half %t, half %clamp, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 0, i32 0)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @sample_d_1d(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, half %dsdh, half %dsdv, half %s) {
|
|
; GFX9-LABEL: sample_d_1d:
|
|
; GFX9: ; %bb.0: ; %main_body
|
|
; GFX9-NEXT: image_sample_d v[0:3], v[0:2], s[0:7], s[8:11] dmask:0xf a16
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX9-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_d_1d:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: image_sample_d v[0:3], v[0:2], s[0:7], s[8:11] dmask:0xf dim:SQ_RSRC_IMG_1D a16
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.d.1d.v4f32.f16.f16(i32 15, half %dsdh, half %dsdv, half %s, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 0, i32 0)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @sample_d_2d(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, half %dsdh, half %dtdh, half %dsdv, half %dtdv, half %s, half %t) {
|
|
; GFX9-LABEL: sample_d_2d:
|
|
; GFX9: ; %bb.0: ; %main_body
|
|
; GFX9-NEXT: v_mov_b32_e32 v6, 0xffff
|
|
; GFX9-NEXT: v_and_b32_e32 v4, v6, v4
|
|
; GFX9-NEXT: v_and_b32_e32 v2, v6, v2
|
|
; GFX9-NEXT: v_and_b32_e32 v0, v6, v0
|
|
; GFX9-NEXT: v_lshl_or_b32 v3, v3, 16, v2
|
|
; GFX9-NEXT: v_lshl_or_b32 v4, v5, 16, v4
|
|
; GFX9-NEXT: v_lshl_or_b32 v2, v1, 16, v0
|
|
; GFX9-NEXT: image_sample_d v[0:3], v[2:4], s[0:7], s[8:11] dmask:0xf a16
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX9-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_d_2d:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: v_mov_b32_e32 v7, 0xffff
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: v_and_b32_e32 v4, v7, v4
|
|
; GFX10-NEXT: v_and_b32_e32 v2, v7, v2
|
|
; GFX10-NEXT: v_and_b32_e32 v0, v7, v0
|
|
; GFX10-NEXT: v_lshl_or_b32 v4, v5, 16, v4
|
|
; GFX10-NEXT: v_lshl_or_b32 v3, v3, 16, v2
|
|
; GFX10-NEXT: v_lshl_or_b32 v2, v1, 16, v0
|
|
; GFX10-NEXT: image_sample_d v[0:3], v[2:4], s[0:7], s[8:11] dmask:0xf dim:SQ_RSRC_IMG_2D a16
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.d.2d.v4f32.f16.f16(i32 15, half %dsdh, half %dtdh, half %dsdv, half %dtdv, half %s, half %t, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 0, i32 0)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @sample_d_3d(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, half %dsdh, half %dtdh, half %drdh, half %dsdv, half %dtdv, half %drdv, half %s, half %t, half %r) {
|
|
; GFX9-LABEL: sample_d_3d:
|
|
; GFX9: ; %bb.0: ; %main_body
|
|
; GFX9-NEXT: v_mov_b32_e32 v12, v8
|
|
; GFX9-NEXT: v_mov_b32_e32 v8, v2
|
|
; GFX9-NEXT: v_mov_b32_e32 v2, 0xffff
|
|
; GFX9-NEXT: v_mov_b32_e32 v10, v5
|
|
; GFX9-NEXT: v_and_b32_e32 v5, v2, v6
|
|
; GFX9-NEXT: v_and_b32_e32 v3, v2, v3
|
|
; GFX9-NEXT: v_and_b32_e32 v0, v2, v0
|
|
; GFX9-NEXT: v_lshl_or_b32 v11, v7, 16, v5
|
|
; GFX9-NEXT: v_lshl_or_b32 v9, v4, 16, v3
|
|
; GFX9-NEXT: v_lshl_or_b32 v7, v1, 16, v0
|
|
; GFX9-NEXT: image_sample_d v[0:3], v[7:14], s[0:7], s[8:11] dmask:0xf a16
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX9-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_d_3d:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: v_mov_b32_e32 v9, 0xffff
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: v_and_b32_e32 v6, v9, v6
|
|
; GFX10-NEXT: v_and_b32_e32 v3, v9, v3
|
|
; GFX10-NEXT: v_and_b32_e32 v0, v9, v0
|
|
; GFX10-NEXT: v_lshl_or_b32 v6, v7, 16, v6
|
|
; GFX10-NEXT: v_lshl_or_b32 v3, v4, 16, v3
|
|
; GFX10-NEXT: v_lshl_or_b32 v0, v1, 16, v0
|
|
; GFX10-NEXT: image_sample_d v[0:3], [v0, v2, v3, v5, v6, v8], s[0:7], s[8:11] dmask:0xf dim:SQ_RSRC_IMG_3D a16
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.d.3d.v4f32.f16.f16(i32 15, half %dsdh, half %dtdh, half %drdh, half %dsdv, half %dtdv, half %drdv, half %s, half %t, half %r, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 0, i32 0)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @sample_c_d_1d(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, float %zcompare, half %dsdh, half %dsdv, half %s) {
|
|
; GFX9-LABEL: sample_c_d_1d:
|
|
; GFX9: ; %bb.0: ; %main_body
|
|
; GFX9-NEXT: image_sample_c_d v[0:3], v[0:3], s[0:7], s[8:11] dmask:0xf a16
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX9-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_c_d_1d:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: image_sample_c_d v[0:3], v[0:3], s[0:7], s[8:11] dmask:0xf dim:SQ_RSRC_IMG_1D a16
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.c.d.1d.v4f32.f32.f16(i32 15, float %zcompare, half %dsdh, half %dsdv, half %s, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 0, i32 0)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @sample_c_d_2d(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, float %zcompare, half %dsdh, half %dtdh, half %dsdv, half %dtdv, half %s, half %t) {
|
|
; GFX9-LABEL: sample_c_d_2d:
|
|
; GFX9: ; %bb.0: ; %main_body
|
|
; GFX9-NEXT: v_mov_b32_e32 v9, 0xffff
|
|
; GFX9-NEXT: v_mov_b32_e32 v8, v2
|
|
; GFX9-NEXT: v_mov_b32_e32 v7, v3
|
|
; GFX9-NEXT: v_and_b32_e32 v2, v9, v5
|
|
; GFX9-NEXT: v_and_b32_e32 v1, v9, v1
|
|
; GFX9-NEXT: v_lshl_or_b32 v3, v6, 16, v2
|
|
; GFX9-NEXT: v_and_b32_e32 v2, v9, v7
|
|
; GFX9-NEXT: v_lshl_or_b32 v2, v4, 16, v2
|
|
; GFX9-NEXT: v_lshl_or_b32 v1, v8, 16, v1
|
|
; GFX9-NEXT: image_sample_c_d v[0:3], v[0:3], s[0:7], s[8:11] dmask:0xf a16
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX9-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_c_d_2d:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: v_mov_b32_e32 v10, 0xffff
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: v_and_b32_e32 v5, v10, v5
|
|
; GFX10-NEXT: v_and_b32_e32 v3, v10, v3
|
|
; GFX10-NEXT: v_and_b32_e32 v1, v10, v1
|
|
; GFX10-NEXT: v_lshl_or_b32 v5, v6, 16, v5
|
|
; GFX10-NEXT: v_lshl_or_b32 v3, v4, 16, v3
|
|
; GFX10-NEXT: v_lshl_or_b32 v2, v2, 16, v1
|
|
; GFX10-NEXT: image_sample_c_d v[0:3], [v0, v2, v3, v5], s[0:7], s[8:11] dmask:0xf dim:SQ_RSRC_IMG_2D a16
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.c.d.2d.v4f32.f32.f16(i32 15, float %zcompare, half %dsdh, half %dtdh, half %dsdv, half %dtdv, half %s, half %t, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 0, i32 0)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @sample_d_cl_1d(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, half %dsdh, half %dsdv, half %s, half %clamp) {
|
|
; GFX9-LABEL: sample_d_cl_1d:
|
|
; GFX9: ; %bb.0: ; %main_body
|
|
; GFX9-NEXT: v_and_b32_e32 v2, 0xffff, v2
|
|
; GFX9-NEXT: v_lshl_or_b32 v2, v3, 16, v2
|
|
; GFX9-NEXT: image_sample_d_cl v[0:3], v[0:2], s[0:7], s[8:11] dmask:0xf a16
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX9-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_d_cl_1d:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: v_and_b32_e32 v2, 0xffff, v2
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: v_lshl_or_b32 v2, v3, 16, v2
|
|
; GFX10-NEXT: image_sample_d_cl v[0:3], v[0:2], s[0:7], s[8:11] dmask:0xf dim:SQ_RSRC_IMG_1D a16
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.d.cl.1d.v4f32.f16.f16(i32 15, half %dsdh, half %dsdv, half %s, half %clamp, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 0, i32 0)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @sample_d_cl_2d(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, half %dsdh, half %dtdh, half %dsdv, half %dtdv, half %s, half %t, half %clamp) {
|
|
; GFX9-LABEL: sample_d_cl_2d:
|
|
; GFX9: ; %bb.0: ; %main_body
|
|
; GFX9-NEXT: v_mov_b32_e32 v7, 0xffff
|
|
; GFX9-NEXT: v_and_b32_e32 v4, v7, v4
|
|
; GFX9-NEXT: v_and_b32_e32 v2, v7, v2
|
|
; GFX9-NEXT: v_and_b32_e32 v0, v7, v0
|
|
; GFX9-NEXT: v_lshl_or_b32 v5, v5, 16, v4
|
|
; GFX9-NEXT: v_lshl_or_b32 v4, v3, 16, v2
|
|
; GFX9-NEXT: v_lshl_or_b32 v3, v1, 16, v0
|
|
; GFX9-NEXT: image_sample_d_cl v[0:3], v[3:6], s[0:7], s[8:11] dmask:0xf a16
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX9-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_d_cl_2d:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: v_mov_b32_e32 v7, 0xffff
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: v_and_b32_e32 v4, v7, v4
|
|
; GFX10-NEXT: v_and_b32_e32 v2, v7, v2
|
|
; GFX10-NEXT: v_and_b32_e32 v0, v7, v0
|
|
; GFX10-NEXT: v_lshl_or_b32 v4, v5, 16, v4
|
|
; GFX10-NEXT: v_lshl_or_b32 v5, v3, 16, v2
|
|
; GFX10-NEXT: v_lshl_or_b32 v3, v1, 16, v0
|
|
; GFX10-NEXT: image_sample_d_cl v[0:3], [v3, v5, v4, v6], s[0:7], s[8:11] dmask:0xf dim:SQ_RSRC_IMG_2D a16
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.d.cl.2d.v4f32.f16.f16(i32 15, half %dsdh, half %dtdh, half %dsdv, half %dtdv, half %s, half %t, half %clamp, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 0, i32 0)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @sample_c_d_cl_1d(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, float %zcompare, half %dsdh, half %dsdv, half %s, half %clamp) {
|
|
; GFX9-LABEL: sample_c_d_cl_1d:
|
|
; GFX9: ; %bb.0: ; %main_body
|
|
; GFX9-NEXT: v_and_b32_e32 v3, 0xffff, v3
|
|
; GFX9-NEXT: v_lshl_or_b32 v3, v4, 16, v3
|
|
; GFX9-NEXT: image_sample_c_d_cl v[0:3], v[0:3], s[0:7], s[8:11] dmask:0xf a16
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX9-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_c_d_cl_1d:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: v_and_b32_e32 v3, 0xffff, v3
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: v_lshl_or_b32 v3, v4, 16, v3
|
|
; GFX10-NEXT: image_sample_c_d_cl v[0:3], v[0:3], s[0:7], s[8:11] dmask:0xf dim:SQ_RSRC_IMG_1D a16
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.c.d.cl.1d.v4f32.f32.f16(i32 15, float %zcompare, half %dsdh, half %dsdv, half %s, half %clamp, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 0, i32 0)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @sample_c_d_cl_2d(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, float %zcompare, half %dsdh, half %dtdh, half %dsdv, half %dtdv, half %s, half %t, half %clamp) {
|
|
; GFX9-LABEL: sample_c_d_cl_2d:
|
|
; GFX9: ; %bb.0: ; %main_body
|
|
; GFX9-NEXT: v_mov_b32_e32 v11, v7
|
|
; GFX9-NEXT: v_mov_b32_e32 v7, v0
|
|
; GFX9-NEXT: v_mov_b32_e32 v0, 0xffff
|
|
; GFX9-NEXT: v_and_b32_e32 v5, v0, v5
|
|
; GFX9-NEXT: v_and_b32_e32 v3, v0, v3
|
|
; GFX9-NEXT: v_and_b32_e32 v0, v0, v1
|
|
; GFX9-NEXT: v_lshl_or_b32 v10, v6, 16, v5
|
|
; GFX9-NEXT: v_lshl_or_b32 v9, v4, 16, v3
|
|
; GFX9-NEXT: v_lshl_or_b32 v8, v2, 16, v0
|
|
; GFX9-NEXT: image_sample_c_d_cl v[0:3], v[7:14], s[0:7], s[8:11] dmask:0xf a16
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX9-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_c_d_cl_2d:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: v_mov_b32_e32 v8, 0xffff
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: v_and_b32_e32 v5, v8, v5
|
|
; GFX10-NEXT: v_and_b32_e32 v3, v8, v3
|
|
; GFX10-NEXT: v_and_b32_e32 v1, v8, v1
|
|
; GFX10-NEXT: v_lshl_or_b32 v5, v6, 16, v5
|
|
; GFX10-NEXT: v_lshl_or_b32 v3, v4, 16, v3
|
|
; GFX10-NEXT: v_lshl_or_b32 v2, v2, 16, v1
|
|
; GFX10-NEXT: image_sample_c_d_cl v[0:3], [v0, v2, v3, v5, v7], s[0:7], s[8:11] dmask:0xf dim:SQ_RSRC_IMG_2D a16
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.c.d.cl.2d.v4f32.f32.f16(i32 15, float %zcompare, half %dsdh, half %dtdh, half %dsdv, half %dtdv, half %s, half %t, half %clamp, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 0, i32 0)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @sample_cd_1d(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, half %dsdh, half %dsdv, half %s) {
|
|
; GFX9-LABEL: sample_cd_1d:
|
|
; GFX9: ; %bb.0: ; %main_body
|
|
; GFX9-NEXT: image_sample_cd v[0:3], v[0:2], s[0:7], s[8:11] dmask:0xf a16
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX9-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_cd_1d:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: image_sample_cd v[0:3], v[0:2], s[0:7], s[8:11] dmask:0xf dim:SQ_RSRC_IMG_1D a16
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.cd.1d.v4f32.f16.f16(i32 15, half %dsdh, half %dsdv, half %s, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 0, i32 0)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @sample_cd_2d(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, half %dsdh, half %dtdh, half %dsdv, half %dtdv, half %s, half %t) {
|
|
; GFX9-LABEL: sample_cd_2d:
|
|
; GFX9: ; %bb.0: ; %main_body
|
|
; GFX9-NEXT: v_mov_b32_e32 v6, 0xffff
|
|
; GFX9-NEXT: v_and_b32_e32 v4, v6, v4
|
|
; GFX9-NEXT: v_and_b32_e32 v2, v6, v2
|
|
; GFX9-NEXT: v_and_b32_e32 v0, v6, v0
|
|
; GFX9-NEXT: v_lshl_or_b32 v3, v3, 16, v2
|
|
; GFX9-NEXT: v_lshl_or_b32 v4, v5, 16, v4
|
|
; GFX9-NEXT: v_lshl_or_b32 v2, v1, 16, v0
|
|
; GFX9-NEXT: image_sample_cd v[0:3], v[2:4], s[0:7], s[8:11] dmask:0xf a16
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX9-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_cd_2d:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: v_mov_b32_e32 v7, 0xffff
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: v_and_b32_e32 v4, v7, v4
|
|
; GFX10-NEXT: v_and_b32_e32 v2, v7, v2
|
|
; GFX10-NEXT: v_and_b32_e32 v0, v7, v0
|
|
; GFX10-NEXT: v_lshl_or_b32 v4, v5, 16, v4
|
|
; GFX10-NEXT: v_lshl_or_b32 v3, v3, 16, v2
|
|
; GFX10-NEXT: v_lshl_or_b32 v2, v1, 16, v0
|
|
; GFX10-NEXT: image_sample_cd v[0:3], v[2:4], s[0:7], s[8:11] dmask:0xf dim:SQ_RSRC_IMG_2D a16
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.cd.2d.v4f32.f16.f16(i32 15, half %dsdh, half %dtdh, half %dsdv, half %dtdv, half %s, half %t, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 0, i32 0)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @sample_c_cd_1d(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, float %zcompare, half %dsdh, half %dsdv, half %s) {
|
|
; GFX9-LABEL: sample_c_cd_1d:
|
|
; GFX9: ; %bb.0: ; %main_body
|
|
; GFX9-NEXT: image_sample_c_cd v[0:3], v[0:3], s[0:7], s[8:11] dmask:0xf a16
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX9-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_c_cd_1d:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: image_sample_c_cd v[0:3], v[0:3], s[0:7], s[8:11] dmask:0xf dim:SQ_RSRC_IMG_1D a16
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.c.cd.1d.v4f32.f32.f16(i32 15, float %zcompare, half %dsdh, half %dsdv, half %s, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 0, i32 0)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @sample_c_cd_2d(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, float %zcompare, half %dsdh, half %dtdh, half %dsdv, half %dtdv, half %s, half %t) {
|
|
; GFX9-LABEL: sample_c_cd_2d:
|
|
; GFX9: ; %bb.0: ; %main_body
|
|
; GFX9-NEXT: v_mov_b32_e32 v9, 0xffff
|
|
; GFX9-NEXT: v_mov_b32_e32 v8, v2
|
|
; GFX9-NEXT: v_mov_b32_e32 v7, v3
|
|
; GFX9-NEXT: v_and_b32_e32 v2, v9, v5
|
|
; GFX9-NEXT: v_and_b32_e32 v1, v9, v1
|
|
; GFX9-NEXT: v_lshl_or_b32 v3, v6, 16, v2
|
|
; GFX9-NEXT: v_and_b32_e32 v2, v9, v7
|
|
; GFX9-NEXT: v_lshl_or_b32 v2, v4, 16, v2
|
|
; GFX9-NEXT: v_lshl_or_b32 v1, v8, 16, v1
|
|
; GFX9-NEXT: image_sample_c_cd v[0:3], v[0:3], s[0:7], s[8:11] dmask:0xf a16
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX9-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_c_cd_2d:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: v_mov_b32_e32 v10, 0xffff
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: v_and_b32_e32 v5, v10, v5
|
|
; GFX10-NEXT: v_and_b32_e32 v3, v10, v3
|
|
; GFX10-NEXT: v_and_b32_e32 v1, v10, v1
|
|
; GFX10-NEXT: v_lshl_or_b32 v5, v6, 16, v5
|
|
; GFX10-NEXT: v_lshl_or_b32 v3, v4, 16, v3
|
|
; GFX10-NEXT: v_lshl_or_b32 v2, v2, 16, v1
|
|
; GFX10-NEXT: image_sample_c_cd v[0:3], [v0, v2, v3, v5], s[0:7], s[8:11] dmask:0xf dim:SQ_RSRC_IMG_2D a16
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.c.cd.2d.v4f32.f32.f16(i32 15, float %zcompare, half %dsdh, half %dtdh, half %dsdv, half %dtdv, half %s, half %t, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 0, i32 0)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @sample_cd_cl_1d(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, half %dsdh, half %dsdv, half %s, half %clamp) {
|
|
; GFX9-LABEL: sample_cd_cl_1d:
|
|
; GFX9: ; %bb.0: ; %main_body
|
|
; GFX9-NEXT: v_and_b32_e32 v2, 0xffff, v2
|
|
; GFX9-NEXT: v_lshl_or_b32 v2, v3, 16, v2
|
|
; GFX9-NEXT: image_sample_cd_cl v[0:3], v[0:2], s[0:7], s[8:11] dmask:0xf a16
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX9-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_cd_cl_1d:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: v_and_b32_e32 v2, 0xffff, v2
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: v_lshl_or_b32 v2, v3, 16, v2
|
|
; GFX10-NEXT: image_sample_cd_cl v[0:3], v[0:2], s[0:7], s[8:11] dmask:0xf dim:SQ_RSRC_IMG_1D a16
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.cd.cl.1d.v4f32.f16.f16(i32 15, half %dsdh, half %dsdv, half %s, half %clamp, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 0, i32 0)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @sample_cd_cl_2d(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, half %dsdh, half %dtdh, half %dsdv, half %dtdv, half %s, half %t, half %clamp) {
|
|
; GFX9-LABEL: sample_cd_cl_2d:
|
|
; GFX9: ; %bb.0: ; %main_body
|
|
; GFX9-NEXT: v_mov_b32_e32 v7, 0xffff
|
|
; GFX9-NEXT: v_and_b32_e32 v4, v7, v4
|
|
; GFX9-NEXT: v_and_b32_e32 v2, v7, v2
|
|
; GFX9-NEXT: v_and_b32_e32 v0, v7, v0
|
|
; GFX9-NEXT: v_lshl_or_b32 v5, v5, 16, v4
|
|
; GFX9-NEXT: v_lshl_or_b32 v4, v3, 16, v2
|
|
; GFX9-NEXT: v_lshl_or_b32 v3, v1, 16, v0
|
|
; GFX9-NEXT: image_sample_cd_cl v[0:3], v[3:6], s[0:7], s[8:11] dmask:0xf a16
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX9-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_cd_cl_2d:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: v_mov_b32_e32 v7, 0xffff
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: v_and_b32_e32 v4, v7, v4
|
|
; GFX10-NEXT: v_and_b32_e32 v2, v7, v2
|
|
; GFX10-NEXT: v_and_b32_e32 v0, v7, v0
|
|
; GFX10-NEXT: v_lshl_or_b32 v4, v5, 16, v4
|
|
; GFX10-NEXT: v_lshl_or_b32 v5, v3, 16, v2
|
|
; GFX10-NEXT: v_lshl_or_b32 v3, v1, 16, v0
|
|
; GFX10-NEXT: image_sample_cd_cl v[0:3], [v3, v5, v4, v6], s[0:7], s[8:11] dmask:0xf dim:SQ_RSRC_IMG_2D a16
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.cd.cl.2d.v4f32.f16.f16(i32 15, half %dsdh, half %dtdh, half %dsdv, half %dtdv, half %s, half %t, half %clamp, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 0, i32 0)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @sample_c_cd_cl_1d(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, float %zcompare, half %dsdh, half %dsdv, half %s, half %clamp) {
|
|
; GFX9-LABEL: sample_c_cd_cl_1d:
|
|
; GFX9: ; %bb.0: ; %main_body
|
|
; GFX9-NEXT: v_and_b32_e32 v3, 0xffff, v3
|
|
; GFX9-NEXT: v_lshl_or_b32 v3, v4, 16, v3
|
|
; GFX9-NEXT: image_sample_c_cd_cl v[0:3], v[0:3], s[0:7], s[8:11] dmask:0xf a16
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX9-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_c_cd_cl_1d:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: v_and_b32_e32 v3, 0xffff, v3
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: v_lshl_or_b32 v3, v4, 16, v3
|
|
; GFX10-NEXT: image_sample_c_cd_cl v[0:3], v[0:3], s[0:7], s[8:11] dmask:0xf dim:SQ_RSRC_IMG_1D a16
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.c.cd.cl.1d.v4f32.f32.f16(i32 15, float %zcompare, half %dsdh, half %dsdv, half %s, half %clamp, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 0, i32 0)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @sample_c_cd_cl_2d(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, float %zcompare, half %dsdh, half %dtdh, half %dsdv, half %dtdv, half %s, half %t, half %clamp) {
|
|
; GFX9-LABEL: sample_c_cd_cl_2d:
|
|
; GFX9: ; %bb.0: ; %main_body
|
|
; GFX9-NEXT: v_mov_b32_e32 v11, v7
|
|
; GFX9-NEXT: v_mov_b32_e32 v7, v0
|
|
; GFX9-NEXT: v_mov_b32_e32 v0, 0xffff
|
|
; GFX9-NEXT: v_and_b32_e32 v5, v0, v5
|
|
; GFX9-NEXT: v_and_b32_e32 v3, v0, v3
|
|
; GFX9-NEXT: v_and_b32_e32 v0, v0, v1
|
|
; GFX9-NEXT: v_lshl_or_b32 v10, v6, 16, v5
|
|
; GFX9-NEXT: v_lshl_or_b32 v9, v4, 16, v3
|
|
; GFX9-NEXT: v_lshl_or_b32 v8, v2, 16, v0
|
|
; GFX9-NEXT: image_sample_c_cd_cl v[0:3], v[7:14], s[0:7], s[8:11] dmask:0xf a16
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX9-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_c_cd_cl_2d:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: v_mov_b32_e32 v8, 0xffff
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: v_and_b32_e32 v5, v8, v5
|
|
; GFX10-NEXT: v_and_b32_e32 v3, v8, v3
|
|
; GFX10-NEXT: v_and_b32_e32 v1, v8, v1
|
|
; GFX10-NEXT: v_lshl_or_b32 v5, v6, 16, v5
|
|
; GFX10-NEXT: v_lshl_or_b32 v3, v4, 16, v3
|
|
; GFX10-NEXT: v_lshl_or_b32 v2, v2, 16, v1
|
|
; GFX10-NEXT: image_sample_c_cd_cl v[0:3], [v0, v2, v3, v5, v7], s[0:7], s[8:11] dmask:0xf dim:SQ_RSRC_IMG_2D a16
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.c.cd.cl.2d.v4f32.f32.f16(i32 15, float %zcompare, half %dsdh, half %dtdh, half %dsdv, half %dtdv, half %s, half %t, half %clamp, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 0, i32 0)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @sample_l_1d(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, half %s, half %lod) {
|
|
; GFX9-LABEL: sample_l_1d:
|
|
; GFX9: ; %bb.0: ; %main_body
|
|
; GFX9-NEXT: v_and_b32_e32 v0, 0xffff, v0
|
|
; GFX9-NEXT: v_lshl_or_b32 v0, v1, 16, v0
|
|
; GFX9-NEXT: image_sample_l v[0:3], v0, s[0:7], s[8:11] dmask:0xf a16
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX9-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_l_1d:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: v_and_b32_e32 v0, 0xffff, v0
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: v_lshl_or_b32 v0, v1, 16, v0
|
|
; GFX10-NEXT: image_sample_l v[0:3], v0, s[0:7], s[8:11] dmask:0xf dim:SQ_RSRC_IMG_1D a16
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.l.1d.v4f32.f16(i32 15, half %s, half %lod, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 0, i32 0)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @sample_l_2d(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, half %s, half %t, half %lod) {
|
|
; GFX9-LABEL: sample_l_2d:
|
|
; GFX9: ; %bb.0: ; %main_body
|
|
; GFX9-NEXT: v_and_b32_e32 v0, 0xffff, v0
|
|
; GFX9-NEXT: v_lshl_or_b32 v1, v1, 16, v0
|
|
; GFX9-NEXT: image_sample_l v[0:3], v[1:2], s[0:7], s[8:11] dmask:0xf a16
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX9-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_l_2d:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: v_and_b32_e32 v0, 0xffff, v0
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: v_lshl_or_b32 v1, v1, 16, v0
|
|
; GFX10-NEXT: image_sample_l v[0:3], v[1:2], s[0:7], s[8:11] dmask:0xf dim:SQ_RSRC_IMG_2D a16
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.l.2d.v4f32.f16(i32 15, half %s, half %t, half %lod, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 0, i32 0)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @sample_c_l_1d(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, float %zcompare, half %s, half %lod) {
|
|
; GFX9-LABEL: sample_c_l_1d:
|
|
; GFX9: ; %bb.0: ; %main_body
|
|
; GFX9-NEXT: v_and_b32_e32 v1, 0xffff, v1
|
|
; GFX9-NEXT: v_lshl_or_b32 v1, v2, 16, v1
|
|
; GFX9-NEXT: image_sample_c_l v[0:3], v[0:1], s[0:7], s[8:11] dmask:0xf a16
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX9-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_c_l_1d:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: v_and_b32_e32 v1, 0xffff, v1
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: v_lshl_or_b32 v1, v2, 16, v1
|
|
; GFX10-NEXT: image_sample_c_l v[0:3], v[0:1], s[0:7], s[8:11] dmask:0xf dim:SQ_RSRC_IMG_1D a16
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.c.l.1d.v4f32.f16(i32 15, float %zcompare, half %s, half %lod, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 0, i32 0)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @sample_c_l_2d(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, float %zcompare, half %s, half %t, half %lod) {
|
|
; GFX9-LABEL: sample_c_l_2d:
|
|
; GFX9: ; %bb.0: ; %main_body
|
|
; GFX9-NEXT: v_mov_b32_e32 v5, v3
|
|
; GFX9-NEXT: v_mov_b32_e32 v3, v0
|
|
; GFX9-NEXT: v_and_b32_e32 v0, 0xffff, v1
|
|
; GFX9-NEXT: v_lshl_or_b32 v4, v2, 16, v0
|
|
; GFX9-NEXT: image_sample_c_l v[0:3], v[3:5], s[0:7], s[8:11] dmask:0xf a16
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX9-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_c_l_2d:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: v_and_b32_e32 v1, 0xffff, v1
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: v_lshl_or_b32 v1, v2, 16, v1
|
|
; GFX10-NEXT: image_sample_c_l v[0:3], [v0, v1, v3], s[0:7], s[8:11] dmask:0xf dim:SQ_RSRC_IMG_2D a16
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.c.l.2d.v4f32.f16(i32 15, float %zcompare, half %s, half %t, half %lod, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 0, i32 0)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @sample_lz_1d(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, half %s) {
|
|
; GFX9-LABEL: sample_lz_1d:
|
|
; GFX9: ; %bb.0: ; %main_body
|
|
; GFX9-NEXT: image_sample_lz v[0:3], v0, s[0:7], s[8:11] dmask:0xf a16
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX9-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_lz_1d:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: image_sample_lz v[0:3], v0, s[0:7], s[8:11] dmask:0xf dim:SQ_RSRC_IMG_1D a16
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.lz.1d.v4f32.f16(i32 15, half %s, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 0, i32 0)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @sample_lz_2d(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, half %s, half %t) {
|
|
; GFX9-LABEL: sample_lz_2d:
|
|
; GFX9: ; %bb.0: ; %main_body
|
|
; GFX9-NEXT: v_and_b32_e32 v0, 0xffff, v0
|
|
; GFX9-NEXT: v_lshl_or_b32 v0, v1, 16, v0
|
|
; GFX9-NEXT: image_sample_lz v[0:3], v0, s[0:7], s[8:11] dmask:0xf a16
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX9-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_lz_2d:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: v_and_b32_e32 v0, 0xffff, v0
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: v_lshl_or_b32 v0, v1, 16, v0
|
|
; GFX10-NEXT: image_sample_lz v[0:3], v0, s[0:7], s[8:11] dmask:0xf dim:SQ_RSRC_IMG_2D a16
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.lz.2d.v4f32.f16(i32 15, half %s, half %t, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 0, i32 0)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @sample_c_lz_1d(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, float %zcompare, half %s) {
|
|
; GFX9-LABEL: sample_c_lz_1d:
|
|
; GFX9: ; %bb.0: ; %main_body
|
|
; GFX9-NEXT: image_sample_c_lz v[0:3], v[0:1], s[0:7], s[8:11] dmask:0xf a16
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX9-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_c_lz_1d:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: image_sample_c_lz v[0:3], v[0:1], s[0:7], s[8:11] dmask:0xf dim:SQ_RSRC_IMG_1D a16
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.c.lz.1d.v4f32.f16(i32 15, float %zcompare, half %s, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 0, i32 0)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @sample_c_lz_2d(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, float %zcompare, half %s, half %t) {
|
|
; GFX9-LABEL: sample_c_lz_2d:
|
|
; GFX9: ; %bb.0: ; %main_body
|
|
; GFX9-NEXT: v_and_b32_e32 v1, 0xffff, v1
|
|
; GFX9-NEXT: v_lshl_or_b32 v1, v2, 16, v1
|
|
; GFX9-NEXT: image_sample_c_lz v[0:3], v[0:1], s[0:7], s[8:11] dmask:0xf a16
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX9-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_c_lz_2d:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: v_and_b32_e32 v1, 0xffff, v1
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: v_lshl_or_b32 v1, v2, 16, v1
|
|
; GFX10-NEXT: image_sample_c_lz v[0:3], v[0:1], s[0:7], s[8:11] dmask:0xf dim:SQ_RSRC_IMG_2D a16
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.c.lz.2d.v4f32.f16(i32 15, float %zcompare, half %s, half %t, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 0, i32 0)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps float @sample_c_d_o_2darray_V1(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, i32 %offset, float %zcompare, half %dsdh, half %dtdh, half %dsdv, half %dtdv, half %s, half %t, half %slice) {
|
|
; GFX9-LABEL: sample_c_d_o_2darray_V1:
|
|
; GFX9: ; %bb.0: ; %main_body
|
|
; GFX9-NEXT: v_mov_b32_e32 v13, v8
|
|
; GFX9-NEXT: v_mov_b32_e32 v8, v0
|
|
; GFX9-NEXT: v_mov_b32_e32 v0, 0xffff
|
|
; GFX9-NEXT: v_mov_b32_e32 v9, v1
|
|
; GFX9-NEXT: v_and_b32_e32 v1, v0, v6
|
|
; GFX9-NEXT: v_lshl_or_b32 v12, v7, 16, v1
|
|
; GFX9-NEXT: v_and_b32_e32 v1, v0, v4
|
|
; GFX9-NEXT: v_and_b32_e32 v0, v0, v2
|
|
; GFX9-NEXT: v_lshl_or_b32 v11, v5, 16, v1
|
|
; GFX9-NEXT: v_lshl_or_b32 v10, v3, 16, v0
|
|
; GFX9-NEXT: image_sample_c_d_o v0, v[8:15], s[0:7], s[8:11] dmask:0x4 a16 da
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX9-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_c_d_o_2darray_V1:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: v_mov_b32_e32 v9, 0xffff
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: v_and_b32_e32 v6, v9, v6
|
|
; GFX10-NEXT: v_and_b32_e32 v4, v9, v4
|
|
; GFX10-NEXT: v_and_b32_e32 v2, v9, v2
|
|
; GFX10-NEXT: v_lshl_or_b32 v6, v7, 16, v6
|
|
; GFX10-NEXT: v_lshl_or_b32 v4, v5, 16, v4
|
|
; GFX10-NEXT: v_lshl_or_b32 v3, v3, 16, v2
|
|
; GFX10-NEXT: image_sample_c_d_o v0, [v0, v1, v3, v4, v6, v8], s[0:7], s[8:11] dmask:0x4 dim:SQ_RSRC_IMG_2D_ARRAY a16
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call float @llvm.amdgcn.image.sample.c.d.o.2darray.f32.f16.f16(i32 4, i32 %offset, float %zcompare, half %dsdh, half %dtdh, half %dsdv, half %dtdv, half %s, half %t, half %slice, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 0, i32 0)
|
|
ret float %v
|
|
}
|
|
|
|
define amdgpu_ps <2 x float> @sample_c_d_o_2darray_V2(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, i32 %offset, float %zcompare, half %dsdh, half %dtdh, half %dsdv, half %dtdv, half %s, half %t, half %slice) {
|
|
; GFX9-LABEL: sample_c_d_o_2darray_V2:
|
|
; GFX9: ; %bb.0: ; %main_body
|
|
; GFX9-NEXT: v_mov_b32_e32 v13, v8
|
|
; GFX9-NEXT: v_mov_b32_e32 v8, v0
|
|
; GFX9-NEXT: v_mov_b32_e32 v0, 0xffff
|
|
; GFX9-NEXT: v_mov_b32_e32 v9, v1
|
|
; GFX9-NEXT: v_and_b32_e32 v1, v0, v6
|
|
; GFX9-NEXT: v_lshl_or_b32 v12, v7, 16, v1
|
|
; GFX9-NEXT: v_and_b32_e32 v1, v0, v4
|
|
; GFX9-NEXT: v_and_b32_e32 v0, v0, v2
|
|
; GFX9-NEXT: v_lshl_or_b32 v11, v5, 16, v1
|
|
; GFX9-NEXT: v_lshl_or_b32 v10, v3, 16, v0
|
|
; GFX9-NEXT: image_sample_c_d_o v[0:1], v[8:15], s[0:7], s[8:11] dmask:0x6 a16 da
|
|
; GFX9-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX9-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_c_d_o_2darray_V2:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: v_mov_b32_e32 v9, 0xffff
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: v_and_b32_e32 v6, v9, v6
|
|
; GFX10-NEXT: v_and_b32_e32 v4, v9, v4
|
|
; GFX10-NEXT: v_and_b32_e32 v2, v9, v2
|
|
; GFX10-NEXT: v_lshl_or_b32 v6, v7, 16, v6
|
|
; GFX10-NEXT: v_lshl_or_b32 v4, v5, 16, v4
|
|
; GFX10-NEXT: v_lshl_or_b32 v3, v3, 16, v2
|
|
; GFX10-NEXT: image_sample_c_d_o v[0:1], [v0, v1, v3, v4, v6, v8], s[0:7], s[8:11] dmask:0x6 dim:SQ_RSRC_IMG_2D_ARRAY a16
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <2 x float> @llvm.amdgcn.image.sample.c.d.o.2darray.v2f32.f32.f16(i32 6, i32 %offset, float %zcompare, half %dsdh, half %dtdh, half %dsdv, half %dtdv, half %s, half %t, half %slice, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 0, i32 0)
|
|
ret <2 x float> %v
|
|
}
|
|
|
|
declare <4 x float> @llvm.amdgcn.image.sample.1d.v4f32.f16(i32, half, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <8 x float> @llvm.amdgcn.image.sample.1d.v8f32.f16(i32, half, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.2d.v4f32.f16(i32, half, half, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.3d.v4f32.f16(i32, half, half, half, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.cube.v4f32.f16(i32, half, half, half, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.1darray.v4f32.f16(i32, half, half, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.2darray.v4f32.f16(i32, half, half, half, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
|
|
declare <4 x float> @llvm.amdgcn.image.sample.c.1d.v4f32.f16(i32, float, half, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.c.2d.v4f32.f16(i32, float, half, half, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.cl.1d.v4f32.f16(i32, half, half, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.cl.2d.v4f32.f16(i32, half, half, half, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.c.cl.1d.v4f32.f16(i32, float, half, half, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.c.cl.2d.v4f32.f16(i32, float, half, half, half, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
|
|
declare <4 x float> @llvm.amdgcn.image.sample.b.1d.v4f32.f32.f16(i32, float, half, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.b.2d.v4f32.f32.f16(i32, float, half, half, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.c.b.1d.v4f32.f32.f16(i32, float, float, half, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.c.b.2d.v4f32.f32.f16(i32, float, float, half, half, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.b.cl.1d.v4f32.f32.f16(i32, float, half, half, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.b.cl.2d.v4f32.f32.f16(i32, float, half, half, half, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.c.b.cl.1d.v4f32.f32.f16(i32, float, float, half, half, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.c.b.cl.2d.v4f32.f32.f16(i32, float, float, half, half, half, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
|
|
declare <4 x float> @llvm.amdgcn.image.sample.d.1d.v4f32.f16.f16(i32, half, half, half, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.d.2d.v4f32.f16.f16(i32, half, half, half, half, half, half, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.d.3d.v4f32.f16.f16(i32, half, half, half, half, half, half, half, half, half, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.c.d.1d.v4f32.f32.f16(i32, float, half, half, half, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.c.d.2d.v4f32.f32.f16(i32, float, half, half, half, half, half, half, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.d.cl.1d.v4f32.f16.f16(i32, half, half, half, half, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.d.cl.2d.v4f32.f16.f16(i32, half, half, half, half, half, half, half, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.c.d.cl.1d.v4f32.f32.f16(i32, float, half, half, half, half, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.c.d.cl.2d.v4f32.f32.f16(i32, float, half, half, half, half, half, half, half, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
|
|
declare <4 x float> @llvm.amdgcn.image.sample.cd.1d.v4f32.f16.f16(i32, half, half, half, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.cd.2d.v4f32.f16.f16(i32, half, half, half, half, half, half, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.c.cd.1d.v4f32.f32.f16(i32, float, half, half, half, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.c.cd.2d.v4f32.f32.f16(i32, float, half, half, half, half, half, half, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.cd.cl.1d.v4f32.f16.f16(i32, half, half, half, half, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.cd.cl.2d.v4f32.f16.f16(i32, half, half, half, half, half, half, half, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.c.cd.cl.1d.v4f32.f32.f16(i32, float, half, half, half, half, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.c.cd.cl.2d.v4f32.f32.f16(i32, float, half, half, half, half, half, half, half, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
|
|
declare <4 x float> @llvm.amdgcn.image.sample.l.1d.v4f32.f16(i32, half, half, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.l.2d.v4f32.f16(i32, half, half, half, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.c.l.1d.v4f32.f16(i32, float, half, half, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.c.l.2d.v4f32.f16(i32, float, half, half, half, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
|
|
declare <4 x float> @llvm.amdgcn.image.sample.lz.1d.v4f32.f16(i32, half, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.lz.2d.v4f32.f16(i32, half, half, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.c.lz.1d.v4f32.f16(i32, float, half, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.c.lz.2d.v4f32.f16(i32, float, half, half, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
|
|
declare float @llvm.amdgcn.image.sample.c.d.o.2darray.f32.f16.f16(i32, i32, float, half, half, half, half, half, half, half, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <2 x float> @llvm.amdgcn.image.sample.c.d.o.2darray.v2f32.f32.f16(i32, i32, float, half, half, half, half, half, half, half, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
|
|
attributes #0 = { nounwind }
|
|
attributes #1 = { nounwind readonly }
|
|
attributes #2 = { nounwind readnone }
|