forked from OSchip/llvm-project
2393 lines
123 KiB
LLVM
2393 lines
123 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc -march=amdgcn -mcpu=verde -verify-machineinstrs < %s | FileCheck -check-prefixes=VERDE %s
|
|
; RUN: llc -march=amdgcn -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck -check-prefixes=GFX6789 %s
|
|
; RUN: llc -march=amdgcn -mcpu=gfx1010 -verify-machineinstrs -show-mc-encoding < %s | FileCheck -check-prefixes=GFX10 %s
|
|
|
|
define amdgpu_ps <4 x float> @sample_1d(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, float %s) {
|
|
; VERDE-LABEL: sample_1d:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: s_mov_b64 s[12:13], exec
|
|
; VERDE-NEXT: s_wqm_b64 exec, exec
|
|
; VERDE-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; VERDE-NEXT: image_sample v[0:3], v0, s[0:7], s[8:11] dmask:0xf
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: sample_1d:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: s_mov_b64 s[12:13], exec
|
|
; GFX6789-NEXT: s_wqm_b64 exec, exec
|
|
; GFX6789-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; GFX6789-NEXT: image_sample v[0:3], v0, s[0:7], s[8:11] dmask:0xf
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_1d:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: s_mov_b32 s12, exec_lo ; encoding: [0x7e,0x03,0x8c,0xbe]
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_wqm_b32 exec_lo, exec_lo ; encoding: [0x7e,0x09,0xfe,0xbe]
|
|
; GFX10-NEXT: s_and_b32 exec_lo, exec_lo, s12 ; encoding: [0x7e,0x0c,0x7e,0x87]
|
|
; GFX10-NEXT: image_sample v[0:3], v0, s[0:7], s[8:11] dmask:0xf dim:SQ_RSRC_IMG_1D ; encoding: [0x00,0x0f,0x80,0xf0,0x00,0x00,0x40,0x00]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.1d.v4f32.f32(i32 15, float %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_1d_tfe(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, i32 addrspace(1)* inreg %out, float %s) {
|
|
; VERDE-LABEL: sample_1d_tfe:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: s_mov_b64 s[16:17], exec
|
|
; VERDE-NEXT: s_wqm_b64 exec, exec
|
|
; VERDE-NEXT: v_mov_b32_e32 v5, v0
|
|
; VERDE-NEXT: v_mov_b32_e32 v0, 0
|
|
; VERDE-NEXT: s_mov_b32 s15, 0xf000
|
|
; VERDE-NEXT: s_mov_b32 s14, -1
|
|
; VERDE-NEXT: v_mov_b32_e32 v1, v0
|
|
; VERDE-NEXT: v_mov_b32_e32 v2, v0
|
|
; VERDE-NEXT: v_mov_b32_e32 v3, v0
|
|
; VERDE-NEXT: v_mov_b32_e32 v4, v0
|
|
; VERDE-NEXT: s_and_b64 exec, exec, s[16:17]
|
|
; VERDE-NEXT: image_sample v[0:4], v5, s[0:7], s[8:11] dmask:0xf tfe
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: buffer_store_dword v4, off, s[12:15], 0
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0) expcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: sample_1d_tfe:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: s_mov_b64 s[14:15], exec
|
|
; GFX6789-NEXT: s_wqm_b64 exec, exec
|
|
; GFX6789-NEXT: v_mov_b32_e32 v5, v0
|
|
; GFX6789-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX6789-NEXT: v_mov_b32_e32 v6, s12
|
|
; GFX6789-NEXT: v_mov_b32_e32 v7, s13
|
|
; GFX6789-NEXT: v_mov_b32_e32 v1, v0
|
|
; GFX6789-NEXT: v_mov_b32_e32 v2, v0
|
|
; GFX6789-NEXT: v_mov_b32_e32 v3, v0
|
|
; GFX6789-NEXT: v_mov_b32_e32 v4, v0
|
|
; GFX6789-NEXT: s_and_b64 exec, exec, s[14:15]
|
|
; GFX6789-NEXT: image_sample v[0:4], v5, s[0:7], s[8:11] dmask:0xf tfe
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: global_store_dword v[6:7], v4, off
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_1d_tfe:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: s_mov_b32 s14, exec_lo ; encoding: [0x7e,0x03,0x8e,0xbe]
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_wqm_b32 exec_lo, exec_lo ; encoding: [0x7e,0x09,0xfe,0xbe]
|
|
; GFX10-NEXT: v_mov_b32_e32 v5, v0 ; encoding: [0x00,0x03,0x0a,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v0, 0 ; encoding: [0x80,0x02,0x00,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v6, s12 ; encoding: [0x0c,0x02,0x0c,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v7, s13 ; encoding: [0x0d,0x02,0x0e,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v1, v0 ; encoding: [0x00,0x03,0x02,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v2, v0 ; encoding: [0x00,0x03,0x04,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v3, v0 ; encoding: [0x00,0x03,0x06,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v4, v0 ; encoding: [0x00,0x03,0x08,0x7e]
|
|
; GFX10-NEXT: s_and_b32 exec_lo, exec_lo, s14 ; encoding: [0x7e,0x0e,0x7e,0x87]
|
|
; GFX10-NEXT: image_sample v[0:4], v5, s[0:7], s[8:11] dmask:0xf dim:SQ_RSRC_IMG_1D tfe ; encoding: [0x00,0x0f,0x81,0xf0,0x05,0x00,0x40,0x00]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: global_store_dword v[6:7], v4, off ; encoding: [0x00,0x80,0x70,0xdc,0x06,0x04,0x7d,0x00]
|
|
; GFX10-NEXT: s_waitcnt_vscnt null, 0x0 ; encoding: [0x00,0x00,0xfd,0xbb]
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call {<4 x float>,i32} @llvm.amdgcn.image.sample.1d.v4f32i32.f32(i32 15, float %s, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 1, i32 0)
|
|
%v.vec = extractvalue {<4 x float>, i32} %v, 0
|
|
%v.err = extractvalue {<4 x float>, i32} %v, 1
|
|
store i32 %v.err, i32 addrspace(1)* %out, align 4
|
|
ret <4 x float> %v.vec
|
|
}
|
|
|
|
define amdgpu_ps <2 x float> @sample_1d_tfe_adjust_writemask_1(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, i32 addrspace(1)* inreg %out, float %s) {
|
|
; VERDE-LABEL: sample_1d_tfe_adjust_writemask_1:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: s_mov_b64 s[12:13], exec
|
|
; VERDE-NEXT: s_wqm_b64 exec, exec
|
|
; VERDE-NEXT: v_mov_b32_e32 v2, v0
|
|
; VERDE-NEXT: v_mov_b32_e32 v0, 0
|
|
; VERDE-NEXT: v_mov_b32_e32 v1, v0
|
|
; VERDE-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; VERDE-NEXT: image_sample v[0:1], v2, s[0:7], s[8:11] dmask:0x1 tfe
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: sample_1d_tfe_adjust_writemask_1:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: s_mov_b64 s[12:13], exec
|
|
; GFX6789-NEXT: s_wqm_b64 exec, exec
|
|
; GFX6789-NEXT: v_mov_b32_e32 v2, v0
|
|
; GFX6789-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX6789-NEXT: v_mov_b32_e32 v1, v0
|
|
; GFX6789-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; GFX6789-NEXT: image_sample v[0:1], v2, s[0:7], s[8:11] dmask:0x1 tfe
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_1d_tfe_adjust_writemask_1:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: s_mov_b32 s12, exec_lo ; encoding: [0x7e,0x03,0x8c,0xbe]
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_wqm_b32 exec_lo, exec_lo ; encoding: [0x7e,0x09,0xfe,0xbe]
|
|
; GFX10-NEXT: v_mov_b32_e32 v2, v0 ; encoding: [0x00,0x03,0x04,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v0, 0 ; encoding: [0x80,0x02,0x00,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v1, v0 ; encoding: [0x00,0x03,0x02,0x7e]
|
|
; GFX10-NEXT: s_and_b32 exec_lo, exec_lo, s12 ; encoding: [0x7e,0x0c,0x7e,0x87]
|
|
; GFX10-NEXT: image_sample v[0:1], v2, s[0:7], s[8:11] dmask:0x1 dim:SQ_RSRC_IMG_1D tfe ; encoding: [0x00,0x01,0x81,0xf0,0x02,0x00,0x40,0x00]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call {<4 x float>,i32} @llvm.amdgcn.image.sample.1d.v4f32i32.f32(i32 15, float %s, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 1, i32 0)
|
|
%res.vec = extractvalue {<4 x float>,i32} %v, 0
|
|
%res.f = extractelement <4 x float> %res.vec, i32 0
|
|
%res.err = extractvalue {<4 x float>,i32} %v, 1
|
|
%res.errf = bitcast i32 %res.err to float
|
|
%res.tmp = insertelement <2 x float> undef, float %res.f, i32 0
|
|
%res = insertelement <2 x float> %res.tmp, float %res.errf, i32 1
|
|
ret <2 x float> %res
|
|
}
|
|
|
|
define amdgpu_ps <2 x float> @sample_1d_tfe_adjust_writemask_2(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, float %s) {
|
|
; VERDE-LABEL: sample_1d_tfe_adjust_writemask_2:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: s_mov_b64 s[12:13], exec
|
|
; VERDE-NEXT: s_wqm_b64 exec, exec
|
|
; VERDE-NEXT: v_mov_b32_e32 v2, v0
|
|
; VERDE-NEXT: v_mov_b32_e32 v0, 0
|
|
; VERDE-NEXT: v_mov_b32_e32 v1, v0
|
|
; VERDE-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; VERDE-NEXT: image_sample v[0:1], v2, s[0:7], s[8:11] dmask:0x2 tfe
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: sample_1d_tfe_adjust_writemask_2:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: s_mov_b64 s[12:13], exec
|
|
; GFX6789-NEXT: s_wqm_b64 exec, exec
|
|
; GFX6789-NEXT: v_mov_b32_e32 v2, v0
|
|
; GFX6789-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX6789-NEXT: v_mov_b32_e32 v1, v0
|
|
; GFX6789-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; GFX6789-NEXT: image_sample v[0:1], v2, s[0:7], s[8:11] dmask:0x2 tfe
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_1d_tfe_adjust_writemask_2:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: s_mov_b32 s12, exec_lo ; encoding: [0x7e,0x03,0x8c,0xbe]
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_wqm_b32 exec_lo, exec_lo ; encoding: [0x7e,0x09,0xfe,0xbe]
|
|
; GFX10-NEXT: v_mov_b32_e32 v2, v0 ; encoding: [0x00,0x03,0x04,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v0, 0 ; encoding: [0x80,0x02,0x00,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v1, v0 ; encoding: [0x00,0x03,0x02,0x7e]
|
|
; GFX10-NEXT: s_and_b32 exec_lo, exec_lo, s12 ; encoding: [0x7e,0x0c,0x7e,0x87]
|
|
; GFX10-NEXT: image_sample v[0:1], v2, s[0:7], s[8:11] dmask:0x2 dim:SQ_RSRC_IMG_1D tfe ; encoding: [0x00,0x02,0x81,0xf0,0x02,0x00,0x40,0x00]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call {<4 x float>,i32} @llvm.amdgcn.image.sample.1d.v4f32i32.f32(i32 15, float %s, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 1, i32 0)
|
|
%res.vec = extractvalue {<4 x float>,i32} %v, 0
|
|
%res.f = extractelement <4 x float> %res.vec, i32 1
|
|
%res.err = extractvalue {<4 x float>,i32} %v, 1
|
|
%res.errf = bitcast i32 %res.err to float
|
|
%res.tmp = insertelement <2 x float> undef, float %res.f, i32 0
|
|
%res = insertelement <2 x float> %res.tmp, float %res.errf, i32 1
|
|
ret <2 x float> %res
|
|
}
|
|
|
|
define amdgpu_ps <2 x float> @sample_1d_tfe_adjust_writemask_3(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, float %s) {
|
|
; VERDE-LABEL: sample_1d_tfe_adjust_writemask_3:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: s_mov_b64 s[12:13], exec
|
|
; VERDE-NEXT: s_wqm_b64 exec, exec
|
|
; VERDE-NEXT: v_mov_b32_e32 v2, v0
|
|
; VERDE-NEXT: v_mov_b32_e32 v0, 0
|
|
; VERDE-NEXT: v_mov_b32_e32 v1, v0
|
|
; VERDE-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; VERDE-NEXT: image_sample v[0:1], v2, s[0:7], s[8:11] dmask:0x4 tfe
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: sample_1d_tfe_adjust_writemask_3:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: s_mov_b64 s[12:13], exec
|
|
; GFX6789-NEXT: s_wqm_b64 exec, exec
|
|
; GFX6789-NEXT: v_mov_b32_e32 v2, v0
|
|
; GFX6789-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX6789-NEXT: v_mov_b32_e32 v1, v0
|
|
; GFX6789-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; GFX6789-NEXT: image_sample v[0:1], v2, s[0:7], s[8:11] dmask:0x4 tfe
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_1d_tfe_adjust_writemask_3:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: s_mov_b32 s12, exec_lo ; encoding: [0x7e,0x03,0x8c,0xbe]
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_wqm_b32 exec_lo, exec_lo ; encoding: [0x7e,0x09,0xfe,0xbe]
|
|
; GFX10-NEXT: v_mov_b32_e32 v2, v0 ; encoding: [0x00,0x03,0x04,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v0, 0 ; encoding: [0x80,0x02,0x00,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v1, v0 ; encoding: [0x00,0x03,0x02,0x7e]
|
|
; GFX10-NEXT: s_and_b32 exec_lo, exec_lo, s12 ; encoding: [0x7e,0x0c,0x7e,0x87]
|
|
; GFX10-NEXT: image_sample v[0:1], v2, s[0:7], s[8:11] dmask:0x4 dim:SQ_RSRC_IMG_1D tfe ; encoding: [0x00,0x04,0x81,0xf0,0x02,0x00,0x40,0x00]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call {<4 x float>,i32} @llvm.amdgcn.image.sample.1d.v4f32i32.f32(i32 15, float %s, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 1, i32 0)
|
|
%res.vec = extractvalue {<4 x float>,i32} %v, 0
|
|
%res.f = extractelement <4 x float> %res.vec, i32 2
|
|
%res.err = extractvalue {<4 x float>,i32} %v, 1
|
|
%res.errf = bitcast i32 %res.err to float
|
|
%res.tmp = insertelement <2 x float> undef, float %res.f, i32 0
|
|
%res = insertelement <2 x float> %res.tmp, float %res.errf, i32 1
|
|
ret <2 x float> %res
|
|
}
|
|
|
|
define amdgpu_ps <2 x float> @sample_1d_tfe_adjust_writemask_4(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, float %s) {
|
|
; VERDE-LABEL: sample_1d_tfe_adjust_writemask_4:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: s_mov_b64 s[12:13], exec
|
|
; VERDE-NEXT: s_wqm_b64 exec, exec
|
|
; VERDE-NEXT: v_mov_b32_e32 v2, v0
|
|
; VERDE-NEXT: v_mov_b32_e32 v0, 0
|
|
; VERDE-NEXT: v_mov_b32_e32 v1, v0
|
|
; VERDE-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; VERDE-NEXT: image_sample v[0:1], v2, s[0:7], s[8:11] dmask:0x8 tfe
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: sample_1d_tfe_adjust_writemask_4:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: s_mov_b64 s[12:13], exec
|
|
; GFX6789-NEXT: s_wqm_b64 exec, exec
|
|
; GFX6789-NEXT: v_mov_b32_e32 v2, v0
|
|
; GFX6789-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX6789-NEXT: v_mov_b32_e32 v1, v0
|
|
; GFX6789-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; GFX6789-NEXT: image_sample v[0:1], v2, s[0:7], s[8:11] dmask:0x8 tfe
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_1d_tfe_adjust_writemask_4:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: s_mov_b32 s12, exec_lo ; encoding: [0x7e,0x03,0x8c,0xbe]
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_wqm_b32 exec_lo, exec_lo ; encoding: [0x7e,0x09,0xfe,0xbe]
|
|
; GFX10-NEXT: v_mov_b32_e32 v2, v0 ; encoding: [0x00,0x03,0x04,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v0, 0 ; encoding: [0x80,0x02,0x00,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v1, v0 ; encoding: [0x00,0x03,0x02,0x7e]
|
|
; GFX10-NEXT: s_and_b32 exec_lo, exec_lo, s12 ; encoding: [0x7e,0x0c,0x7e,0x87]
|
|
; GFX10-NEXT: image_sample v[0:1], v2, s[0:7], s[8:11] dmask:0x8 dim:SQ_RSRC_IMG_1D tfe ; encoding: [0x00,0x08,0x81,0xf0,0x02,0x00,0x40,0x00]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call {<4 x float>,i32} @llvm.amdgcn.image.sample.1d.v4f32i32.f32(i32 15, float %s, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 1, i32 0)
|
|
%res.vec = extractvalue {<4 x float>,i32} %v, 0
|
|
%res.f = extractelement <4 x float> %res.vec, i32 3
|
|
%res.err = extractvalue {<4 x float>,i32} %v, 1
|
|
%res.errf = bitcast i32 %res.err to float
|
|
%res.tmp = insertelement <2 x float> undef, float %res.f, i32 0
|
|
%res = insertelement <2 x float> %res.tmp, float %res.errf, i32 1
|
|
ret <2 x float> %res
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @sample_1d_tfe_adjust_writemask_12(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, float %s) {
|
|
; VERDE-LABEL: sample_1d_tfe_adjust_writemask_12:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: s_mov_b64 s[12:13], exec
|
|
; VERDE-NEXT: s_wqm_b64 exec, exec
|
|
; VERDE-NEXT: v_mov_b32_e32 v3, v0
|
|
; VERDE-NEXT: v_mov_b32_e32 v0, 0
|
|
; VERDE-NEXT: v_mov_b32_e32 v1, v0
|
|
; VERDE-NEXT: v_mov_b32_e32 v2, v0
|
|
; VERDE-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; VERDE-NEXT: image_sample v[0:2], v3, s[0:7], s[8:11] dmask:0x3 tfe
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: sample_1d_tfe_adjust_writemask_12:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: s_mov_b64 s[12:13], exec
|
|
; GFX6789-NEXT: s_wqm_b64 exec, exec
|
|
; GFX6789-NEXT: v_mov_b32_e32 v3, v0
|
|
; GFX6789-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX6789-NEXT: v_mov_b32_e32 v1, v0
|
|
; GFX6789-NEXT: v_mov_b32_e32 v2, v0
|
|
; GFX6789-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; GFX6789-NEXT: image_sample v[0:2], v3, s[0:7], s[8:11] dmask:0x3 tfe
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_1d_tfe_adjust_writemask_12:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: s_mov_b32 s12, exec_lo ; encoding: [0x7e,0x03,0x8c,0xbe]
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_wqm_b32 exec_lo, exec_lo ; encoding: [0x7e,0x09,0xfe,0xbe]
|
|
; GFX10-NEXT: v_mov_b32_e32 v3, v0 ; encoding: [0x00,0x03,0x06,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v0, 0 ; encoding: [0x80,0x02,0x00,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v1, v0 ; encoding: [0x00,0x03,0x02,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v2, v0 ; encoding: [0x00,0x03,0x04,0x7e]
|
|
; GFX10-NEXT: s_and_b32 exec_lo, exec_lo, s12 ; encoding: [0x7e,0x0c,0x7e,0x87]
|
|
; GFX10-NEXT: image_sample v[0:2], v3, s[0:7], s[8:11] dmask:0x3 dim:SQ_RSRC_IMG_1D tfe ; encoding: [0x00,0x03,0x81,0xf0,0x03,0x00,0x40,0x00]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call {<4 x float>,i32} @llvm.amdgcn.image.sample.1d.v4f32i32.f32(i32 15, float %s, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 1, i32 0)
|
|
%res.vec = extractvalue {<4 x float>,i32} %v, 0
|
|
%res.f1 = extractelement <4 x float> %res.vec, i32 0
|
|
%res.f2 = extractelement <4 x float> %res.vec, i32 1
|
|
%res.err = extractvalue {<4 x float>,i32} %v, 1
|
|
%res.errf = bitcast i32 %res.err to float
|
|
%res.tmp1 = insertelement <4 x float> undef, float %res.f1, i32 0
|
|
%res.tmp2 = insertelement <4 x float> %res.tmp1, float %res.f2, i32 1
|
|
%res = insertelement <4 x float> %res.tmp2, float %res.errf, i32 2
|
|
ret <4 x float> %res
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @sample_1d_tfe_adjust_writemask_24(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, float %s) {
|
|
; VERDE-LABEL: sample_1d_tfe_adjust_writemask_24:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: s_mov_b64 s[12:13], exec
|
|
; VERDE-NEXT: s_wqm_b64 exec, exec
|
|
; VERDE-NEXT: v_mov_b32_e32 v3, v0
|
|
; VERDE-NEXT: v_mov_b32_e32 v0, 0
|
|
; VERDE-NEXT: v_mov_b32_e32 v1, v0
|
|
; VERDE-NEXT: v_mov_b32_e32 v2, v0
|
|
; VERDE-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; VERDE-NEXT: image_sample v[0:2], v3, s[0:7], s[8:11] dmask:0xa tfe
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: sample_1d_tfe_adjust_writemask_24:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: s_mov_b64 s[12:13], exec
|
|
; GFX6789-NEXT: s_wqm_b64 exec, exec
|
|
; GFX6789-NEXT: v_mov_b32_e32 v3, v0
|
|
; GFX6789-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX6789-NEXT: v_mov_b32_e32 v1, v0
|
|
; GFX6789-NEXT: v_mov_b32_e32 v2, v0
|
|
; GFX6789-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; GFX6789-NEXT: image_sample v[0:2], v3, s[0:7], s[8:11] dmask:0xa tfe
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_1d_tfe_adjust_writemask_24:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: s_mov_b32 s12, exec_lo ; encoding: [0x7e,0x03,0x8c,0xbe]
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_wqm_b32 exec_lo, exec_lo ; encoding: [0x7e,0x09,0xfe,0xbe]
|
|
; GFX10-NEXT: v_mov_b32_e32 v3, v0 ; encoding: [0x00,0x03,0x06,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v0, 0 ; encoding: [0x80,0x02,0x00,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v1, v0 ; encoding: [0x00,0x03,0x02,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v2, v0 ; encoding: [0x00,0x03,0x04,0x7e]
|
|
; GFX10-NEXT: s_and_b32 exec_lo, exec_lo, s12 ; encoding: [0x7e,0x0c,0x7e,0x87]
|
|
; GFX10-NEXT: image_sample v[0:2], v3, s[0:7], s[8:11] dmask:0xa dim:SQ_RSRC_IMG_1D tfe ; encoding: [0x00,0x0a,0x81,0xf0,0x03,0x00,0x40,0x00]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call {<4 x float>,i32} @llvm.amdgcn.image.sample.1d.v4f32i32.f32(i32 15, float %s, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 1, i32 0)
|
|
%res.vec = extractvalue {<4 x float>,i32} %v, 0
|
|
%res.f1 = extractelement <4 x float> %res.vec, i32 1
|
|
%res.f2 = extractelement <4 x float> %res.vec, i32 3
|
|
%res.err = extractvalue {<4 x float>,i32} %v, 1
|
|
%res.errf = bitcast i32 %res.err to float
|
|
%res.tmp1 = insertelement <4 x float> undef, float %res.f1, i32 0
|
|
%res.tmp2 = insertelement <4 x float> %res.tmp1, float %res.f2, i32 1
|
|
%res = insertelement <4 x float> %res.tmp2, float %res.errf, i32 2
|
|
ret <4 x float> %res
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @sample_1d_tfe_adjust_writemask_134(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, float %s) {
|
|
; VERDE-LABEL: sample_1d_tfe_adjust_writemask_134:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: s_mov_b64 s[12:13], exec
|
|
; VERDE-NEXT: s_wqm_b64 exec, exec
|
|
; VERDE-NEXT: v_mov_b32_e32 v4, v0
|
|
; VERDE-NEXT: v_mov_b32_e32 v0, 0
|
|
; VERDE-NEXT: v_mov_b32_e32 v1, v0
|
|
; VERDE-NEXT: v_mov_b32_e32 v2, v0
|
|
; VERDE-NEXT: v_mov_b32_e32 v3, v0
|
|
; VERDE-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; VERDE-NEXT: image_sample v[0:3], v4, s[0:7], s[8:11] dmask:0xd tfe
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: sample_1d_tfe_adjust_writemask_134:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: s_mov_b64 s[12:13], exec
|
|
; GFX6789-NEXT: s_wqm_b64 exec, exec
|
|
; GFX6789-NEXT: v_mov_b32_e32 v4, v0
|
|
; GFX6789-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX6789-NEXT: v_mov_b32_e32 v1, v0
|
|
; GFX6789-NEXT: v_mov_b32_e32 v2, v0
|
|
; GFX6789-NEXT: v_mov_b32_e32 v3, v0
|
|
; GFX6789-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; GFX6789-NEXT: image_sample v[0:3], v4, s[0:7], s[8:11] dmask:0xd tfe
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_1d_tfe_adjust_writemask_134:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: s_mov_b32 s12, exec_lo ; encoding: [0x7e,0x03,0x8c,0xbe]
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_wqm_b32 exec_lo, exec_lo ; encoding: [0x7e,0x09,0xfe,0xbe]
|
|
; GFX10-NEXT: v_mov_b32_e32 v4, v0 ; encoding: [0x00,0x03,0x08,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v0, 0 ; encoding: [0x80,0x02,0x00,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v1, v0 ; encoding: [0x00,0x03,0x02,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v2, v0 ; encoding: [0x00,0x03,0x04,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v3, v0 ; encoding: [0x00,0x03,0x06,0x7e]
|
|
; GFX10-NEXT: s_and_b32 exec_lo, exec_lo, s12 ; encoding: [0x7e,0x0c,0x7e,0x87]
|
|
; GFX10-NEXT: image_sample v[0:3], v4, s[0:7], s[8:11] dmask:0xd dim:SQ_RSRC_IMG_1D tfe ; encoding: [0x00,0x0d,0x81,0xf0,0x04,0x00,0x40,0x00]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call {<4 x float>,i32} @llvm.amdgcn.image.sample.1d.v4f32i32.f32(i32 15, float %s, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 1, i32 0)
|
|
%res.vec = extractvalue {<4 x float>,i32} %v, 0
|
|
%res.f1 = extractelement <4 x float> %res.vec, i32 0
|
|
%res.f2 = extractelement <4 x float> %res.vec, i32 2
|
|
%res.f3 = extractelement <4 x float> %res.vec, i32 3
|
|
%res.err = extractvalue {<4 x float>,i32} %v, 1
|
|
%res.errf = bitcast i32 %res.err to float
|
|
%res.tmp1 = insertelement <4 x float> undef, float %res.f1, i32 0
|
|
%res.tmp2 = insertelement <4 x float> %res.tmp1, float %res.f2, i32 1
|
|
%res.tmp3 = insertelement <4 x float> %res.tmp2, float %res.f3, i32 2
|
|
%res = insertelement <4 x float> %res.tmp3, float %res.errf, i32 3
|
|
ret <4 x float> %res
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @sample_1d_lwe(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, i32 addrspace(1)* inreg %out, float %s) {
|
|
; VERDE-LABEL: sample_1d_lwe:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: s_mov_b64 s[16:17], exec
|
|
; VERDE-NEXT: s_wqm_b64 exec, exec
|
|
; VERDE-NEXT: v_mov_b32_e32 v5, v0
|
|
; VERDE-NEXT: v_mov_b32_e32 v0, 0
|
|
; VERDE-NEXT: s_mov_b32 s15, 0xf000
|
|
; VERDE-NEXT: s_mov_b32 s14, -1
|
|
; VERDE-NEXT: v_mov_b32_e32 v1, v0
|
|
; VERDE-NEXT: v_mov_b32_e32 v2, v0
|
|
; VERDE-NEXT: v_mov_b32_e32 v3, v0
|
|
; VERDE-NEXT: v_mov_b32_e32 v4, v0
|
|
; VERDE-NEXT: s_and_b64 exec, exec, s[16:17]
|
|
; VERDE-NEXT: image_sample v[0:4], v5, s[0:7], s[8:11] dmask:0xf lwe
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: buffer_store_dword v4, off, s[12:15], 0
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0) expcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: sample_1d_lwe:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: s_mov_b64 s[14:15], exec
|
|
; GFX6789-NEXT: s_wqm_b64 exec, exec
|
|
; GFX6789-NEXT: v_mov_b32_e32 v5, v0
|
|
; GFX6789-NEXT: v_mov_b32_e32 v0, 0
|
|
; GFX6789-NEXT: v_mov_b32_e32 v6, s12
|
|
; GFX6789-NEXT: v_mov_b32_e32 v7, s13
|
|
; GFX6789-NEXT: v_mov_b32_e32 v1, v0
|
|
; GFX6789-NEXT: v_mov_b32_e32 v2, v0
|
|
; GFX6789-NEXT: v_mov_b32_e32 v3, v0
|
|
; GFX6789-NEXT: v_mov_b32_e32 v4, v0
|
|
; GFX6789-NEXT: s_and_b64 exec, exec, s[14:15]
|
|
; GFX6789-NEXT: image_sample v[0:4], v5, s[0:7], s[8:11] dmask:0xf lwe
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: global_store_dword v[6:7], v4, off
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_1d_lwe:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: s_mov_b32 s14, exec_lo ; encoding: [0x7e,0x03,0x8e,0xbe]
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_wqm_b32 exec_lo, exec_lo ; encoding: [0x7e,0x09,0xfe,0xbe]
|
|
; GFX10-NEXT: v_mov_b32_e32 v5, v0 ; encoding: [0x00,0x03,0x0a,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v0, 0 ; encoding: [0x80,0x02,0x00,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v6, s12 ; encoding: [0x0c,0x02,0x0c,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v7, s13 ; encoding: [0x0d,0x02,0x0e,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v1, v0 ; encoding: [0x00,0x03,0x02,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v2, v0 ; encoding: [0x00,0x03,0x04,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v3, v0 ; encoding: [0x00,0x03,0x06,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v4, v0 ; encoding: [0x00,0x03,0x08,0x7e]
|
|
; GFX10-NEXT: s_and_b32 exec_lo, exec_lo, s14 ; encoding: [0x7e,0x0e,0x7e,0x87]
|
|
; GFX10-NEXT: image_sample v[0:4], v5, s[0:7], s[8:11] dmask:0xf dim:SQ_RSRC_IMG_1D lwe ; encoding: [0x00,0x0f,0x82,0xf0,0x05,0x00,0x40,0x00]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: global_store_dword v[6:7], v4, off ; encoding: [0x00,0x80,0x70,0xdc,0x06,0x04,0x7d,0x00]
|
|
; GFX10-NEXT: s_waitcnt_vscnt null, 0x0 ; encoding: [0x00,0x00,0xfd,0xbb]
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call {<4 x float>,i32} @llvm.amdgcn.image.sample.1d.v4f32i32.f32(i32 15, float %s, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 2, i32 0)
|
|
%v.vec = extractvalue {<4 x float>, i32} %v, 0
|
|
%v.err = extractvalue {<4 x float>, i32} %v, 1
|
|
store i32 %v.err, i32 addrspace(1)* %out, align 4
|
|
ret <4 x float> %v.vec
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @sample_2d(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, float %s, float %t) {
|
|
; VERDE-LABEL: sample_2d:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: s_mov_b64 s[12:13], exec
|
|
; VERDE-NEXT: s_wqm_b64 exec, exec
|
|
; VERDE-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; VERDE-NEXT: image_sample v[0:3], v[0:1], s[0:7], s[8:11] dmask:0xf
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: sample_2d:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: s_mov_b64 s[12:13], exec
|
|
; GFX6789-NEXT: s_wqm_b64 exec, exec
|
|
; GFX6789-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; GFX6789-NEXT: image_sample v[0:3], v[0:1], s[0:7], s[8:11] dmask:0xf
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_2d:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: s_mov_b32 s12, exec_lo ; encoding: [0x7e,0x03,0x8c,0xbe]
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_wqm_b32 exec_lo, exec_lo ; encoding: [0x7e,0x09,0xfe,0xbe]
|
|
; GFX10-NEXT: s_and_b32 exec_lo, exec_lo, s12 ; encoding: [0x7e,0x0c,0x7e,0x87]
|
|
; GFX10-NEXT: image_sample v[0:3], v[0:1], s[0:7], s[8:11] dmask:0xf dim:SQ_RSRC_IMG_2D ; encoding: [0x08,0x0f,0x80,0xf0,0x00,0x00,0x40,0x00]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.2d.v4f32.f32(i32 15, float %s, float %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, float %s, float %t, float %r) {
|
|
; VERDE-LABEL: sample_3d:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: s_mov_b64 s[12:13], exec
|
|
; VERDE-NEXT: s_wqm_b64 exec, exec
|
|
; VERDE-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; VERDE-NEXT: image_sample v[0:3], v[0:2], s[0:7], s[8:11] dmask:0xf
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: sample_3d:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: s_mov_b64 s[12:13], exec
|
|
; GFX6789-NEXT: s_wqm_b64 exec, exec
|
|
; GFX6789-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; GFX6789-NEXT: image_sample v[0:3], v[0:2], s[0:7], s[8:11] dmask:0xf
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_3d:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: s_mov_b32 s12, exec_lo ; encoding: [0x7e,0x03,0x8c,0xbe]
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_wqm_b32 exec_lo, exec_lo ; encoding: [0x7e,0x09,0xfe,0xbe]
|
|
; GFX10-NEXT: s_and_b32 exec_lo, exec_lo, s12 ; encoding: [0x7e,0x0c,0x7e,0x87]
|
|
; GFX10-NEXT: image_sample v[0:3], v[0:2], s[0:7], s[8:11] dmask:0xf dim:SQ_RSRC_IMG_3D ; encoding: [0x10,0x0f,0x80,0xf0,0x00,0x00,0x40,0x00]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.3d.v4f32.f32(i32 15, float %s, float %t, float %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, float %s, float %t, float %face) {
|
|
; VERDE-LABEL: sample_cube:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: s_mov_b64 s[12:13], exec
|
|
; VERDE-NEXT: s_wqm_b64 exec, exec
|
|
; VERDE-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; VERDE-NEXT: image_sample v[0:3], v[0:2], s[0:7], s[8:11] dmask:0xf da
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: sample_cube:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: s_mov_b64 s[12:13], exec
|
|
; GFX6789-NEXT: s_wqm_b64 exec, exec
|
|
; GFX6789-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; GFX6789-NEXT: image_sample v[0:3], v[0:2], s[0:7], s[8:11] dmask:0xf da
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_cube:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: s_mov_b32 s12, exec_lo ; encoding: [0x7e,0x03,0x8c,0xbe]
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_wqm_b32 exec_lo, exec_lo ; encoding: [0x7e,0x09,0xfe,0xbe]
|
|
; GFX10-NEXT: s_and_b32 exec_lo, exec_lo, s12 ; encoding: [0x7e,0x0c,0x7e,0x87]
|
|
; GFX10-NEXT: image_sample v[0:3], v[0:2], s[0:7], s[8:11] dmask:0xf dim:SQ_RSRC_IMG_CUBE ; encoding: [0x18,0x0f,0x80,0xf0,0x00,0x00,0x40,0x00]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.cube.v4f32.f32(i32 15, float %s, float %t, float %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, float %s, float %slice) {
|
|
; VERDE-LABEL: sample_1darray:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: s_mov_b64 s[12:13], exec
|
|
; VERDE-NEXT: s_wqm_b64 exec, exec
|
|
; VERDE-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; VERDE-NEXT: image_sample v[0:3], v[0:1], s[0:7], s[8:11] dmask:0xf da
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: sample_1darray:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: s_mov_b64 s[12:13], exec
|
|
; GFX6789-NEXT: s_wqm_b64 exec, exec
|
|
; GFX6789-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; GFX6789-NEXT: image_sample v[0:3], v[0:1], s[0:7], s[8:11] dmask:0xf da
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_1darray:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: s_mov_b32 s12, exec_lo ; encoding: [0x7e,0x03,0x8c,0xbe]
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_wqm_b32 exec_lo, exec_lo ; encoding: [0x7e,0x09,0xfe,0xbe]
|
|
; GFX10-NEXT: s_and_b32 exec_lo, exec_lo, s12 ; encoding: [0x7e,0x0c,0x7e,0x87]
|
|
; GFX10-NEXT: image_sample v[0:3], v[0:1], s[0:7], s[8:11] dmask:0xf dim:SQ_RSRC_IMG_1D_ARRAY ; encoding: [0x20,0x0f,0x80,0xf0,0x00,0x00,0x40,0x00]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.1darray.v4f32.f32(i32 15, float %s, float %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, float %s, float %t, float %slice) {
|
|
; VERDE-LABEL: sample_2darray:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: s_mov_b64 s[12:13], exec
|
|
; VERDE-NEXT: s_wqm_b64 exec, exec
|
|
; VERDE-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; VERDE-NEXT: image_sample v[0:3], v[0:2], s[0:7], s[8:11] dmask:0xf da
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: sample_2darray:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: s_mov_b64 s[12:13], exec
|
|
; GFX6789-NEXT: s_wqm_b64 exec, exec
|
|
; GFX6789-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; GFX6789-NEXT: image_sample v[0:3], v[0:2], s[0:7], s[8:11] dmask:0xf da
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_2darray:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: s_mov_b32 s12, exec_lo ; encoding: [0x7e,0x03,0x8c,0xbe]
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_wqm_b32 exec_lo, exec_lo ; encoding: [0x7e,0x09,0xfe,0xbe]
|
|
; GFX10-NEXT: s_and_b32 exec_lo, exec_lo, s12 ; encoding: [0x7e,0x0c,0x7e,0x87]
|
|
; GFX10-NEXT: image_sample v[0:3], v[0:2], s[0:7], s[8:11] dmask:0xf dim:SQ_RSRC_IMG_2D_ARRAY ; encoding: [0x28,0x0f,0x80,0xf0,0x00,0x00,0x40,0x00]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.2darray.v4f32.f32(i32 15, float %s, float %t, float %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, float %s) {
|
|
; VERDE-LABEL: sample_c_1d:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: s_mov_b64 s[12:13], exec
|
|
; VERDE-NEXT: s_wqm_b64 exec, exec
|
|
; VERDE-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; VERDE-NEXT: image_sample_c v[0:3], v[0:1], s[0:7], s[8:11] dmask:0xf
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: sample_c_1d:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: s_mov_b64 s[12:13], exec
|
|
; GFX6789-NEXT: s_wqm_b64 exec, exec
|
|
; GFX6789-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; GFX6789-NEXT: image_sample_c v[0:3], v[0:1], s[0:7], s[8:11] dmask:0xf
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_c_1d:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: s_mov_b32 s12, exec_lo ; encoding: [0x7e,0x03,0x8c,0xbe]
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_wqm_b32 exec_lo, exec_lo ; encoding: [0x7e,0x09,0xfe,0xbe]
|
|
; GFX10-NEXT: s_and_b32 exec_lo, exec_lo, s12 ; encoding: [0x7e,0x0c,0x7e,0x87]
|
|
; GFX10-NEXT: image_sample_c v[0:3], v[0:1], s[0:7], s[8:11] dmask:0xf dim:SQ_RSRC_IMG_1D ; encoding: [0x00,0x0f,0xa0,0xf0,0x00,0x00,0x40,0x00]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.c.1d.v4f32.f32(i32 15, float %zcompare, float %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, float %s, float %t) {
|
|
; VERDE-LABEL: sample_c_2d:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: s_mov_b64 s[12:13], exec
|
|
; VERDE-NEXT: s_wqm_b64 exec, exec
|
|
; VERDE-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; VERDE-NEXT: image_sample_c v[0:3], v[0:2], s[0:7], s[8:11] dmask:0xf
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: sample_c_2d:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: s_mov_b64 s[12:13], exec
|
|
; GFX6789-NEXT: s_wqm_b64 exec, exec
|
|
; GFX6789-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; GFX6789-NEXT: image_sample_c v[0:3], v[0:2], s[0:7], s[8:11] dmask:0xf
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_c_2d:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: s_mov_b32 s12, exec_lo ; encoding: [0x7e,0x03,0x8c,0xbe]
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_wqm_b32 exec_lo, exec_lo ; encoding: [0x7e,0x09,0xfe,0xbe]
|
|
; GFX10-NEXT: s_and_b32 exec_lo, exec_lo, s12 ; encoding: [0x7e,0x0c,0x7e,0x87]
|
|
; GFX10-NEXT: image_sample_c v[0:3], v[0:2], s[0:7], s[8:11] dmask:0xf dim:SQ_RSRC_IMG_2D ; encoding: [0x08,0x0f,0xa0,0xf0,0x00,0x00,0x40,0x00]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.c.2d.v4f32.f32(i32 15, float %zcompare, float %s, float %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, float %s, float %clamp) {
|
|
; VERDE-LABEL: sample_cl_1d:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: s_mov_b64 s[12:13], exec
|
|
; VERDE-NEXT: s_wqm_b64 exec, exec
|
|
; VERDE-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; VERDE-NEXT: image_sample_cl v[0:3], v[0:1], s[0:7], s[8:11] dmask:0xf
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: sample_cl_1d:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: s_mov_b64 s[12:13], exec
|
|
; GFX6789-NEXT: s_wqm_b64 exec, exec
|
|
; GFX6789-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; GFX6789-NEXT: image_sample_cl v[0:3], v[0:1], s[0:7], s[8:11] dmask:0xf
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_cl_1d:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: s_mov_b32 s12, exec_lo ; encoding: [0x7e,0x03,0x8c,0xbe]
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_wqm_b32 exec_lo, exec_lo ; encoding: [0x7e,0x09,0xfe,0xbe]
|
|
; GFX10-NEXT: s_and_b32 exec_lo, exec_lo, s12 ; encoding: [0x7e,0x0c,0x7e,0x87]
|
|
; GFX10-NEXT: image_sample_cl v[0:3], v[0:1], s[0:7], s[8:11] dmask:0xf dim:SQ_RSRC_IMG_1D ; encoding: [0x00,0x0f,0x84,0xf0,0x00,0x00,0x40,0x00]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.cl.1d.v4f32.f32(i32 15, float %s, float %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, float %s, float %t, float %clamp) {
|
|
; VERDE-LABEL: sample_cl_2d:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: s_mov_b64 s[12:13], exec
|
|
; VERDE-NEXT: s_wqm_b64 exec, exec
|
|
; VERDE-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; VERDE-NEXT: image_sample_cl v[0:3], v[0:2], s[0:7], s[8:11] dmask:0xf
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: sample_cl_2d:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: s_mov_b64 s[12:13], exec
|
|
; GFX6789-NEXT: s_wqm_b64 exec, exec
|
|
; GFX6789-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; GFX6789-NEXT: image_sample_cl v[0:3], v[0:2], s[0:7], s[8:11] dmask:0xf
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_cl_2d:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: s_mov_b32 s12, exec_lo ; encoding: [0x7e,0x03,0x8c,0xbe]
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_wqm_b32 exec_lo, exec_lo ; encoding: [0x7e,0x09,0xfe,0xbe]
|
|
; GFX10-NEXT: s_and_b32 exec_lo, exec_lo, s12 ; encoding: [0x7e,0x0c,0x7e,0x87]
|
|
; GFX10-NEXT: image_sample_cl v[0:3], v[0:2], s[0:7], s[8:11] dmask:0xf dim:SQ_RSRC_IMG_2D ; encoding: [0x08,0x0f,0x84,0xf0,0x00,0x00,0x40,0x00]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.cl.2d.v4f32.f32(i32 15, float %s, float %t, float %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, float %s, float %clamp) {
|
|
; VERDE-LABEL: sample_c_cl_1d:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: s_mov_b64 s[12:13], exec
|
|
; VERDE-NEXT: s_wqm_b64 exec, exec
|
|
; VERDE-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; VERDE-NEXT: image_sample_c_cl v[0:3], v[0:2], s[0:7], s[8:11] dmask:0xf
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: sample_c_cl_1d:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: s_mov_b64 s[12:13], exec
|
|
; GFX6789-NEXT: s_wqm_b64 exec, exec
|
|
; GFX6789-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; GFX6789-NEXT: image_sample_c_cl v[0:3], v[0:2], s[0:7], s[8:11] dmask:0xf
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-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 ; encoding: [0x7e,0x03,0x8c,0xbe]
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_wqm_b32 exec_lo, exec_lo ; encoding: [0x7e,0x09,0xfe,0xbe]
|
|
; GFX10-NEXT: s_and_b32 exec_lo, exec_lo, s12 ; encoding: [0x7e,0x0c,0x7e,0x87]
|
|
; GFX10-NEXT: image_sample_c_cl v[0:3], v[0:2], s[0:7], s[8:11] dmask:0xf dim:SQ_RSRC_IMG_1D ; encoding: [0x00,0x0f,0xa4,0xf0,0x00,0x00,0x40,0x00]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.c.cl.1d.v4f32.f32(i32 15, float %zcompare, float %s, float %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, float %s, float %t, float %clamp) {
|
|
; VERDE-LABEL: sample_c_cl_2d:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: s_mov_b64 s[12:13], exec
|
|
; VERDE-NEXT: s_wqm_b64 exec, exec
|
|
; VERDE-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; VERDE-NEXT: image_sample_c_cl v[0:3], v[0:3], s[0:7], s[8:11] dmask:0xf
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: sample_c_cl_2d:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: s_mov_b64 s[12:13], exec
|
|
; GFX6789-NEXT: s_wqm_b64 exec, exec
|
|
; GFX6789-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; GFX6789-NEXT: image_sample_c_cl v[0:3], v[0:3], s[0:7], s[8:11] dmask:0xf
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-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 ; encoding: [0x7e,0x03,0x8c,0xbe]
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_wqm_b32 exec_lo, exec_lo ; encoding: [0x7e,0x09,0xfe,0xbe]
|
|
; GFX10-NEXT: s_and_b32 exec_lo, exec_lo, s12 ; encoding: [0x7e,0x0c,0x7e,0x87]
|
|
; GFX10-NEXT: image_sample_c_cl v[0:3], v[0:3], s[0:7], s[8:11] dmask:0xf dim:SQ_RSRC_IMG_2D ; encoding: [0x08,0x0f,0xa4,0xf0,0x00,0x00,0x40,0x00]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.c.cl.2d.v4f32.f32(i32 15, float %zcompare, float %s, float %t, float %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, float %s) {
|
|
; VERDE-LABEL: sample_b_1d:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: s_mov_b64 s[12:13], exec
|
|
; VERDE-NEXT: s_wqm_b64 exec, exec
|
|
; VERDE-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; VERDE-NEXT: image_sample_b v[0:3], v[0:1], s[0:7], s[8:11] dmask:0xf
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: sample_b_1d:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: s_mov_b64 s[12:13], exec
|
|
; GFX6789-NEXT: s_wqm_b64 exec, exec
|
|
; GFX6789-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; GFX6789-NEXT: image_sample_b v[0:3], v[0:1], s[0:7], s[8:11] dmask:0xf
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_b_1d:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: s_mov_b32 s12, exec_lo ; encoding: [0x7e,0x03,0x8c,0xbe]
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_wqm_b32 exec_lo, exec_lo ; encoding: [0x7e,0x09,0xfe,0xbe]
|
|
; GFX10-NEXT: s_and_b32 exec_lo, exec_lo, s12 ; encoding: [0x7e,0x0c,0x7e,0x87]
|
|
; GFX10-NEXT: image_sample_b v[0:3], v[0:1], s[0:7], s[8:11] dmask:0xf dim:SQ_RSRC_IMG_1D ; encoding: [0x00,0x0f,0x94,0xf0,0x00,0x00,0x40,0x00]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.b.1d.v4f32.f32.f32(i32 15, float %bias, float %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, float %s, float %t) {
|
|
; VERDE-LABEL: sample_b_2d:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: s_mov_b64 s[12:13], exec
|
|
; VERDE-NEXT: s_wqm_b64 exec, exec
|
|
; VERDE-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; VERDE-NEXT: image_sample_b v[0:3], v[0:2], s[0:7], s[8:11] dmask:0xf
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: sample_b_2d:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: s_mov_b64 s[12:13], exec
|
|
; GFX6789-NEXT: s_wqm_b64 exec, exec
|
|
; GFX6789-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; GFX6789-NEXT: image_sample_b v[0:3], v[0:2], s[0:7], s[8:11] dmask:0xf
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_b_2d:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: s_mov_b32 s12, exec_lo ; encoding: [0x7e,0x03,0x8c,0xbe]
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_wqm_b32 exec_lo, exec_lo ; encoding: [0x7e,0x09,0xfe,0xbe]
|
|
; GFX10-NEXT: s_and_b32 exec_lo, exec_lo, s12 ; encoding: [0x7e,0x0c,0x7e,0x87]
|
|
; GFX10-NEXT: image_sample_b v[0:3], v[0:2], s[0:7], s[8:11] dmask:0xf dim:SQ_RSRC_IMG_2D ; encoding: [0x08,0x0f,0x94,0xf0,0x00,0x00,0x40,0x00]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.b.2d.v4f32.f32.f32(i32 15, float %bias, float %s, float %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, float %s) {
|
|
; VERDE-LABEL: sample_c_b_1d:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: s_mov_b64 s[12:13], exec
|
|
; VERDE-NEXT: s_wqm_b64 exec, exec
|
|
; VERDE-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; VERDE-NEXT: image_sample_c_b v[0:3], v[0:2], s[0:7], s[8:11] dmask:0xf
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: sample_c_b_1d:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: s_mov_b64 s[12:13], exec
|
|
; GFX6789-NEXT: s_wqm_b64 exec, exec
|
|
; GFX6789-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; GFX6789-NEXT: image_sample_c_b v[0:3], v[0:2], s[0:7], s[8:11] dmask:0xf
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-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 ; encoding: [0x7e,0x03,0x8c,0xbe]
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_wqm_b32 exec_lo, exec_lo ; encoding: [0x7e,0x09,0xfe,0xbe]
|
|
; GFX10-NEXT: s_and_b32 exec_lo, exec_lo, s12 ; encoding: [0x7e,0x0c,0x7e,0x87]
|
|
; 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 ; encoding: [0x00,0x0f,0xb4,0xf0,0x00,0x00,0x40,0x00]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.c.b.1d.v4f32.f32.f32(i32 15, float %bias, float %zcompare, float %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, float %s, float %t) {
|
|
; VERDE-LABEL: sample_c_b_2d:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: s_mov_b64 s[12:13], exec
|
|
; VERDE-NEXT: s_wqm_b64 exec, exec
|
|
; VERDE-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; VERDE-NEXT: image_sample_c_b v[0:3], v[0:3], s[0:7], s[8:11] dmask:0xf
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: sample_c_b_2d:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: s_mov_b64 s[12:13], exec
|
|
; GFX6789-NEXT: s_wqm_b64 exec, exec
|
|
; GFX6789-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; GFX6789-NEXT: image_sample_c_b v[0:3], v[0:3], s[0:7], s[8:11] dmask:0xf
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-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 ; encoding: [0x7e,0x03,0x8c,0xbe]
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_wqm_b32 exec_lo, exec_lo ; encoding: [0x7e,0x09,0xfe,0xbe]
|
|
; GFX10-NEXT: s_and_b32 exec_lo, exec_lo, s12 ; encoding: [0x7e,0x0c,0x7e,0x87]
|
|
; GFX10-NEXT: image_sample_c_b v[0:3], v[0:3], s[0:7], s[8:11] dmask:0xf dim:SQ_RSRC_IMG_2D ; encoding: [0x08,0x0f,0xb4,0xf0,0x00,0x00,0x40,0x00]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.c.b.2d.v4f32.f32.f32(i32 15, float %bias, float %zcompare, float %s, float %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, float %s, float %clamp) {
|
|
; VERDE-LABEL: sample_b_cl_1d:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: s_mov_b64 s[12:13], exec
|
|
; VERDE-NEXT: s_wqm_b64 exec, exec
|
|
; VERDE-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; VERDE-NEXT: image_sample_b_cl v[0:3], v[0:2], s[0:7], s[8:11] dmask:0xf
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: sample_b_cl_1d:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: s_mov_b64 s[12:13], exec
|
|
; GFX6789-NEXT: s_wqm_b64 exec, exec
|
|
; GFX6789-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; GFX6789-NEXT: image_sample_b_cl v[0:3], v[0:2], s[0:7], s[8:11] dmask:0xf
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-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 ; encoding: [0x7e,0x03,0x8c,0xbe]
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_wqm_b32 exec_lo, exec_lo ; encoding: [0x7e,0x09,0xfe,0xbe]
|
|
; GFX10-NEXT: s_and_b32 exec_lo, exec_lo, s12 ; encoding: [0x7e,0x0c,0x7e,0x87]
|
|
; GFX10-NEXT: image_sample_b_cl v[0:3], v[0:2], s[0:7], s[8:11] dmask:0xf dim:SQ_RSRC_IMG_1D ; encoding: [0x00,0x0f,0x98,0xf0,0x00,0x00,0x40,0x00]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.b.cl.1d.v4f32.f32.f32(i32 15, float %bias, float %s, float %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, float %s, float %t, float %clamp) {
|
|
; VERDE-LABEL: sample_b_cl_2d:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: s_mov_b64 s[12:13], exec
|
|
; VERDE-NEXT: s_wqm_b64 exec, exec
|
|
; VERDE-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; VERDE-NEXT: image_sample_b_cl v[0:3], v[0:3], s[0:7], s[8:11] dmask:0xf
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: sample_b_cl_2d:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: s_mov_b64 s[12:13], exec
|
|
; GFX6789-NEXT: s_wqm_b64 exec, exec
|
|
; GFX6789-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; GFX6789-NEXT: image_sample_b_cl v[0:3], v[0:3], s[0:7], s[8:11] dmask:0xf
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-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 ; encoding: [0x7e,0x03,0x8c,0xbe]
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_wqm_b32 exec_lo, exec_lo ; encoding: [0x7e,0x09,0xfe,0xbe]
|
|
; GFX10-NEXT: s_and_b32 exec_lo, exec_lo, s12 ; encoding: [0x7e,0x0c,0x7e,0x87]
|
|
; GFX10-NEXT: image_sample_b_cl v[0:3], v[0:3], s[0:7], s[8:11] dmask:0xf dim:SQ_RSRC_IMG_2D ; encoding: [0x08,0x0f,0x98,0xf0,0x00,0x00,0x40,0x00]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.b.cl.2d.v4f32.f32.f32(i32 15, float %bias, float %s, float %t, float %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, float %s, float %clamp) {
|
|
; VERDE-LABEL: sample_c_b_cl_1d:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: s_mov_b64 s[12:13], exec
|
|
; VERDE-NEXT: s_wqm_b64 exec, exec
|
|
; VERDE-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; VERDE-NEXT: image_sample_c_b_cl v[0:3], v[0:3], s[0:7], s[8:11] dmask:0xf
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: sample_c_b_cl_1d:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: s_mov_b64 s[12:13], exec
|
|
; GFX6789-NEXT: s_wqm_b64 exec, exec
|
|
; GFX6789-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; GFX6789-NEXT: image_sample_c_b_cl v[0:3], v[0:3], s[0:7], s[8:11] dmask:0xf
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-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 ; encoding: [0x7e,0x03,0x8c,0xbe]
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_wqm_b32 exec_lo, exec_lo ; encoding: [0x7e,0x09,0xfe,0xbe]
|
|
; GFX10-NEXT: s_and_b32 exec_lo, exec_lo, s12 ; encoding: [0x7e,0x0c,0x7e,0x87]
|
|
; GFX10-NEXT: image_sample_c_b_cl v[0:3], v[0:3], s[0:7], s[8:11] dmask:0xf dim:SQ_RSRC_IMG_1D ; encoding: [0x00,0x0f,0xb8,0xf0,0x00,0x00,0x40,0x00]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.c.b.cl.1d.v4f32.f32.f32(i32 15, float %bias, float %zcompare, float %s, float %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, float %s, float %t, float %clamp) {
|
|
; VERDE-LABEL: sample_c_b_cl_2d:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: s_mov_b64 s[12:13], exec
|
|
; VERDE-NEXT: s_wqm_b64 exec, exec
|
|
; VERDE-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; VERDE-NEXT: image_sample_c_b_cl v[0:3], v[0:7], s[0:7], s[8:11] dmask:0xf
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: sample_c_b_cl_2d:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: s_mov_b64 s[12:13], exec
|
|
; GFX6789-NEXT: s_wqm_b64 exec, exec
|
|
; GFX6789-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; GFX6789-NEXT: image_sample_c_b_cl v[0:3], v[0:7], s[0:7], s[8:11] dmask:0xf
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-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 ; encoding: [0x7e,0x03,0x8c,0xbe]
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_wqm_b32 exec_lo, exec_lo ; encoding: [0x7e,0x09,0xfe,0xbe]
|
|
; GFX10-NEXT: s_and_b32 exec_lo, exec_lo, s12 ; encoding: [0x7e,0x0c,0x7e,0x87]
|
|
; GFX10-NEXT: image_sample_c_b_cl v[0:3], v[0:7], s[0:7], s[8:11] dmask:0xf dim:SQ_RSRC_IMG_2D ; encoding: [0x08,0x0f,0xb8,0xf0,0x00,0x00,0x40,0x00]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.c.b.cl.2d.v4f32.f32.f32(i32 15, float %bias, float %zcompare, float %s, float %t, float %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, float %dsdh, float %dsdv, float %s) {
|
|
; VERDE-LABEL: sample_d_1d:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: image_sample_d v[0:3], v[0:2], s[0:7], s[8:11] dmask:0xf
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: sample_d_1d:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: image_sample_d v[0:3], v[0:2], s[0:7], s[8:11] dmask:0xf
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-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 ; encoding: [0x00,0x0f,0x88,0xf0,0x00,0x00,0x40,0x00]
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.d.1d.v4f32.f32.f32(i32 15, float %dsdh, float %dsdv, float %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, float %dsdh, float %dtdh, float %dsdv, float %dtdv, float %s, float %t) {
|
|
; VERDE-LABEL: sample_d_2d:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: image_sample_d v[0:3], v[0:7], s[0:7], s[8:11] dmask:0xf
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: sample_d_2d:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: image_sample_d v[0:3], v[0:7], s[0:7], s[8:11] dmask:0xf
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_d_2d:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: image_sample_d v[0:3], v[0:7], s[0:7], s[8:11] dmask:0xf dim:SQ_RSRC_IMG_2D ; encoding: [0x08,0x0f,0x88,0xf0,0x00,0x00,0x40,0x00]
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.d.2d.v4f32.f32.f32(i32 15, float %dsdh, float %dtdh, float %dsdv, float %dtdv, float %s, float %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_d_1d(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, float %zcompare, float %dsdh, float %dsdv, float %s) {
|
|
; VERDE-LABEL: sample_c_d_1d:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: image_sample_c_d v[0:3], v[0:3], s[0:7], s[8:11] dmask:0xf
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: sample_c_d_1d:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: image_sample_c_d v[0:3], v[0:3], s[0:7], s[8:11] dmask:0xf
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-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 ; encoding: [0x00,0x0f,0xa8,0xf0,0x00,0x00,0x40,0x00]
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.c.d.1d.v4f32.f32.f32(i32 15, float %zcompare, float %dsdh, float %dsdv, float %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, float %dsdh, float %dtdh, float %dsdv, float %dtdv, float %s, float %t) {
|
|
; VERDE-LABEL: sample_c_d_2d:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: image_sample_c_d v[0:3], v[0:7], s[0:7], s[8:11] dmask:0xf
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: sample_c_d_2d:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: image_sample_c_d v[0:3], v[0:7], s[0:7], s[8:11] dmask:0xf
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_c_d_2d:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: image_sample_c_d v[0:3], v[0:7], s[0:7], s[8:11] dmask:0xf dim:SQ_RSRC_IMG_2D ; encoding: [0x08,0x0f,0xa8,0xf0,0x00,0x00,0x40,0x00]
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.c.d.2d.v4f32.f32.f32(i32 15, float %zcompare, float %dsdh, float %dtdh, float %dsdv, float %dtdv, float %s, float %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, float %dsdh, float %dsdv, float %s, float %clamp) {
|
|
; VERDE-LABEL: sample_d_cl_1d:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: image_sample_d_cl v[0:3], v[0:3], s[0:7], s[8:11] dmask:0xf
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: sample_d_cl_1d:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: image_sample_d_cl v[0:3], v[0:3], s[0:7], s[8:11] dmask:0xf
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_d_cl_1d:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: image_sample_d_cl v[0:3], v[0:3], s[0:7], s[8:11] dmask:0xf dim:SQ_RSRC_IMG_1D ; encoding: [0x00,0x0f,0x8c,0xf0,0x00,0x00,0x40,0x00]
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.d.cl.1d.v4f32.f32.f32(i32 15, float %dsdh, float %dsdv, float %s, float %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, float %dsdh, float %dtdh, float %dsdv, float %dtdv, float %s, float %t, float %clamp) {
|
|
; VERDE-LABEL: sample_d_cl_2d:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: image_sample_d_cl v[0:3], v[0:7], s[0:7], s[8:11] dmask:0xf
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: sample_d_cl_2d:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: image_sample_d_cl v[0:3], v[0:7], s[0:7], s[8:11] dmask:0xf
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_d_cl_2d:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: image_sample_d_cl v[0:3], v[0:7], s[0:7], s[8:11] dmask:0xf dim:SQ_RSRC_IMG_2D ; encoding: [0x08,0x0f,0x8c,0xf0,0x00,0x00,0x40,0x00]
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.d.cl.2d.v4f32.f32.f32(i32 15, float %dsdh, float %dtdh, float %dsdv, float %dtdv, float %s, float %t, float %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, float %dsdh, float %dsdv, float %s, float %clamp) {
|
|
; VERDE-LABEL: sample_c_d_cl_1d:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: image_sample_c_d_cl v[0:3], v[0:7], s[0:7], s[8:11] dmask:0xf
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: sample_c_d_cl_1d:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: image_sample_c_d_cl v[0:3], v[0:7], s[0:7], s[8:11] dmask:0xf
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_c_d_cl_1d:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: image_sample_c_d_cl v[0:3], v[0:7], s[0:7], s[8:11] dmask:0xf dim:SQ_RSRC_IMG_1D ; encoding: [0x00,0x0f,0xac,0xf0,0x00,0x00,0x40,0x00]
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.c.d.cl.1d.v4f32.f32.f32(i32 15, float %zcompare, float %dsdh, float %dsdv, float %s, float %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, float %dsdh, float %dtdh, float %dsdv, float %dtdv, float %s, float %t, float %clamp) {
|
|
; VERDE-LABEL: sample_c_d_cl_2d:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: image_sample_c_d_cl v[0:3], v[0:7], s[0:7], s[8:11] dmask:0xf
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: sample_c_d_cl_2d:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: image_sample_c_d_cl v[0:3], v[0:7], s[0:7], s[8:11] dmask:0xf
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_c_d_cl_2d:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: image_sample_c_d_cl v[0:3], v[0:7], s[0:7], s[8:11] dmask:0xf dim:SQ_RSRC_IMG_2D ; encoding: [0x08,0x0f,0xac,0xf0,0x00,0x00,0x40,0x00]
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.c.d.cl.2d.v4f32.f32.f32(i32 15, float %zcompare, float %dsdh, float %dtdh, float %dsdv, float %dtdv, float %s, float %t, float %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, float %dsdh, float %dsdv, float %s) {
|
|
; VERDE-LABEL: sample_cd_1d:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: image_sample_cd v[0:3], v[0:2], s[0:7], s[8:11] dmask:0xf
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: sample_cd_1d:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: image_sample_cd v[0:3], v[0:2], s[0:7], s[8:11] dmask:0xf
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-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 ; encoding: [0x00,0x0f,0xa0,0xf1,0x00,0x00,0x40,0x00]
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.cd.1d.v4f32.f32.f32(i32 15, float %dsdh, float %dsdv, float %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, float %dsdh, float %dtdh, float %dsdv, float %dtdv, float %s, float %t) {
|
|
; VERDE-LABEL: sample_cd_2d:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: image_sample_cd v[0:3], v[0:7], s[0:7], s[8:11] dmask:0xf
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: sample_cd_2d:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: image_sample_cd v[0:3], v[0:7], s[0:7], s[8:11] dmask:0xf
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_cd_2d:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: image_sample_cd v[0:3], v[0:7], s[0:7], s[8:11] dmask:0xf dim:SQ_RSRC_IMG_2D ; encoding: [0x08,0x0f,0xa0,0xf1,0x00,0x00,0x40,0x00]
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.cd.2d.v4f32.f32.f32(i32 15, float %dsdh, float %dtdh, float %dsdv, float %dtdv, float %s, float %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, float %dsdh, float %dsdv, float %s) {
|
|
; VERDE-LABEL: sample_c_cd_1d:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: image_sample_c_cd v[0:3], v[0:3], s[0:7], s[8:11] dmask:0xf
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: sample_c_cd_1d:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: image_sample_c_cd v[0:3], v[0:3], s[0:7], s[8:11] dmask:0xf
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-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 ; encoding: [0x00,0x0f,0xa8,0xf1,0x00,0x00,0x40,0x00]
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.c.cd.1d.v4f32.f32.f32(i32 15, float %zcompare, float %dsdh, float %dsdv, float %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, float %dsdh, float %dtdh, float %dsdv, float %dtdv, float %s, float %t) {
|
|
; VERDE-LABEL: sample_c_cd_2d:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: image_sample_c_cd v[0:3], v[0:7], s[0:7], s[8:11] dmask:0xf
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: sample_c_cd_2d:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: image_sample_c_cd v[0:3], v[0:7], s[0:7], s[8:11] dmask:0xf
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_c_cd_2d:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: image_sample_c_cd v[0:3], v[0:7], s[0:7], s[8:11] dmask:0xf dim:SQ_RSRC_IMG_2D ; encoding: [0x08,0x0f,0xa8,0xf1,0x00,0x00,0x40,0x00]
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.c.cd.2d.v4f32.f32.f32(i32 15, float %zcompare, float %dsdh, float %dtdh, float %dsdv, float %dtdv, float %s, float %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, float %dsdh, float %dsdv, float %s, float %clamp) {
|
|
; VERDE-LABEL: sample_cd_cl_1d:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: image_sample_cd_cl v[0:3], v[0:3], s[0:7], s[8:11] dmask:0xf
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: sample_cd_cl_1d:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: image_sample_cd_cl v[0:3], v[0:3], s[0:7], s[8:11] dmask:0xf
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_cd_cl_1d:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: image_sample_cd_cl v[0:3], v[0:3], s[0:7], s[8:11] dmask:0xf dim:SQ_RSRC_IMG_1D ; encoding: [0x00,0x0f,0xa4,0xf1,0x00,0x00,0x40,0x00]
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.cd.cl.1d.v4f32.f32.f32(i32 15, float %dsdh, float %dsdv, float %s, float %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, float %dsdh, float %dtdh, float %dsdv, float %dtdv, float %s, float %t, float %clamp) {
|
|
; VERDE-LABEL: sample_cd_cl_2d:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: image_sample_cd_cl v[0:3], v[0:7], s[0:7], s[8:11] dmask:0xf
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: sample_cd_cl_2d:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: image_sample_cd_cl v[0:3], v[0:7], s[0:7], s[8:11] dmask:0xf
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_cd_cl_2d:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: image_sample_cd_cl v[0:3], v[0:7], s[0:7], s[8:11] dmask:0xf dim:SQ_RSRC_IMG_2D ; encoding: [0x08,0x0f,0xa4,0xf1,0x00,0x00,0x40,0x00]
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.cd.cl.2d.v4f32.f32.f32(i32 15, float %dsdh, float %dtdh, float %dsdv, float %dtdv, float %s, float %t, float %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, float %dsdh, float %dsdv, float %s, float %clamp) {
|
|
; VERDE-LABEL: sample_c_cd_cl_1d:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: image_sample_c_cd_cl v[0:3], v[0:7], s[0:7], s[8:11] dmask:0xf
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: sample_c_cd_cl_1d:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: image_sample_c_cd_cl v[0:3], v[0:7], s[0:7], s[8:11] dmask:0xf
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_c_cd_cl_1d:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: image_sample_c_cd_cl v[0:3], v[0:7], s[0:7], s[8:11] dmask:0xf dim:SQ_RSRC_IMG_1D ; encoding: [0x00,0x0f,0xac,0xf1,0x00,0x00,0x40,0x00]
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.c.cd.cl.1d.v4f32.f32.f32(i32 15, float %zcompare, float %dsdh, float %dsdv, float %s, float %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, float %dsdh, float %dtdh, float %dsdv, float %dtdv, float %s, float %t, float %clamp) {
|
|
; VERDE-LABEL: sample_c_cd_cl_2d:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: image_sample_c_cd_cl v[0:3], v[0:7], s[0:7], s[8:11] dmask:0xf
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: sample_c_cd_cl_2d:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: image_sample_c_cd_cl v[0:3], v[0:7], s[0:7], s[8:11] dmask:0xf
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_c_cd_cl_2d:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: image_sample_c_cd_cl v[0:3], v[0:7], s[0:7], s[8:11] dmask:0xf dim:SQ_RSRC_IMG_2D ; encoding: [0x08,0x0f,0xac,0xf1,0x00,0x00,0x40,0x00]
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.c.cd.cl.2d.v4f32.f32.f32(i32 15, float %zcompare, float %dsdh, float %dtdh, float %dsdv, float %dtdv, float %s, float %t, float %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, float %s, float %lod) {
|
|
; VERDE-LABEL: sample_l_1d:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: image_sample_l v[0:3], v[0:1], s[0:7], s[8:11] dmask:0xf
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: sample_l_1d:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: image_sample_l v[0:3], v[0:1], s[0:7], s[8:11] dmask:0xf
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_l_1d:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: image_sample_l v[0:3], v[0:1], s[0:7], s[8:11] dmask:0xf dim:SQ_RSRC_IMG_1D ; encoding: [0x00,0x0f,0x90,0xf0,0x00,0x00,0x40,0x00]
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.l.1d.v4f32.f32(i32 15, float %s, float %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, float %s, float %t, float %lod) {
|
|
; VERDE-LABEL: sample_l_2d:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: image_sample_l v[0:3], v[0:2], s[0:7], s[8:11] dmask:0xf
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: sample_l_2d:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: image_sample_l v[0:3], v[0:2], s[0:7], s[8:11] dmask:0xf
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_l_2d:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: image_sample_l v[0:3], v[0:2], s[0:7], s[8:11] dmask:0xf dim:SQ_RSRC_IMG_2D ; encoding: [0x08,0x0f,0x90,0xf0,0x00,0x00,0x40,0x00]
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.l.2d.v4f32.f32(i32 15, float %s, float %t, float %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, float %s, float %lod) {
|
|
; VERDE-LABEL: sample_c_l_1d:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: image_sample_c_l v[0:3], v[0:2], s[0:7], s[8:11] dmask:0xf
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: sample_c_l_1d:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: image_sample_c_l v[0:3], v[0:2], s[0:7], s[8:11] dmask:0xf
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_c_l_1d:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: image_sample_c_l v[0:3], v[0:2], s[0:7], s[8:11] dmask:0xf dim:SQ_RSRC_IMG_1D ; encoding: [0x00,0x0f,0xb0,0xf0,0x00,0x00,0x40,0x00]
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.c.l.1d.v4f32.f32(i32 15, float %zcompare, float %s, float %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, float %s, float %t, float %lod) {
|
|
; VERDE-LABEL: sample_c_l_2d:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: image_sample_c_l v[0:3], v[0:3], s[0:7], s[8:11] dmask:0xf
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: sample_c_l_2d:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: image_sample_c_l v[0:3], v[0:3], s[0:7], s[8:11] dmask:0xf
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_c_l_2d:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: image_sample_c_l v[0:3], v[0:3], s[0:7], s[8:11] dmask:0xf dim:SQ_RSRC_IMG_2D ; encoding: [0x08,0x0f,0xb0,0xf0,0x00,0x00,0x40,0x00]
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.c.l.2d.v4f32.f32(i32 15, float %zcompare, float %s, float %t, float %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, float %s) {
|
|
; VERDE-LABEL: sample_lz_1d:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: image_sample_lz v[0:3], v0, s[0:7], s[8:11] dmask:0xf
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: sample_lz_1d:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: image_sample_lz v[0:3], v0, s[0:7], s[8:11] dmask:0xf
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-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 ; encoding: [0x00,0x0f,0x9c,0xf0,0x00,0x00,0x40,0x00]
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.lz.1d.v4f32.f32(i32 15, float %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, float %s, float %t) {
|
|
; VERDE-LABEL: sample_lz_2d:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: image_sample_lz v[0:3], v[0:1], s[0:7], s[8:11] dmask:0xf
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: sample_lz_2d:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: image_sample_lz v[0:3], v[0:1], s[0:7], s[8:11] dmask:0xf
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_lz_2d:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: image_sample_lz v[0:3], v[0:1], s[0:7], s[8:11] dmask:0xf dim:SQ_RSRC_IMG_2D ; encoding: [0x08,0x0f,0x9c,0xf0,0x00,0x00,0x40,0x00]
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.lz.2d.v4f32.f32(i32 15, float %s, float %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, float %s) {
|
|
; VERDE-LABEL: sample_c_lz_1d:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: image_sample_c_lz v[0:3], v[0:1], s[0:7], s[8:11] dmask:0xf
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: sample_c_lz_1d:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: image_sample_c_lz v[0:3], v[0:1], s[0:7], s[8:11] dmask:0xf
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-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 ; encoding: [0x00,0x0f,0xbc,0xf0,0x00,0x00,0x40,0x00]
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.c.lz.1d.v4f32.f32(i32 15, float %zcompare, float %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, float %s, float %t) {
|
|
; VERDE-LABEL: sample_c_lz_2d:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: image_sample_c_lz v[0:3], v[0:2], s[0:7], s[8:11] dmask:0xf
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: sample_c_lz_2d:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: image_sample_c_lz v[0:3], v[0:2], s[0:7], s[8:11] dmask:0xf
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_c_lz_2d:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: image_sample_c_lz v[0:3], v[0:2], s[0:7], s[8:11] dmask:0xf dim:SQ_RSRC_IMG_2D ; encoding: [0x08,0x0f,0xbc,0xf0,0x00,0x00,0x40,0x00]
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.c.lz.2d.v4f32.f32(i32 15, float %zcompare, float %s, float %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, float %dsdh, float %dtdh, float %dsdv, float %dtdv, float %s, float %t, float %slice) {
|
|
; VERDE-LABEL: sample_c_d_o_2darray_V1:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: image_sample_c_d_o v0, v[0:15], s[0:7], s[8:11] dmask:0x4 da
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: sample_c_d_o_2darray_V1:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: image_sample_c_d_o v0, v[0:15], s[0:7], s[8:11] dmask:0x4 da
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_c_d_o_2darray_V1:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: image_sample_c_d_o v0, v[0:15], s[0:7], s[8:11] dmask:0x4 dim:SQ_RSRC_IMG_2D_ARRAY ; encoding: [0x28,0x04,0xe8,0xf0,0x00,0x00,0x40,0x00]
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call float @llvm.amdgcn.image.sample.c.d.o.2darray.f32.f32.f32(i32 4, i32 %offset, float %zcompare, float %dsdh, float %dtdh, float %dsdv, float %dtdv, float %s, float %t, float %slice, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 0, i32 0)
|
|
ret float %v
|
|
}
|
|
|
|
define amdgpu_ps float @sample_c_d_o_2darray_V1_tfe(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, i32 %offset, float %zcompare, float %dsdh, float %dtdh, float %dsdv, float %dtdv, float %s, float %t, float %slice, i32 addrspace(1)* inreg %out) {
|
|
; VERDE-LABEL: sample_c_d_o_2darray_V1_tfe:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: v_mov_b32_e32 v9, 0
|
|
; VERDE-NEXT: v_mov_b32_e32 v10, v9
|
|
; VERDE-NEXT: image_sample_c_d_o v[9:10], v[0:15], s[0:7], s[8:11] dmask:0x4 tfe da
|
|
; VERDE-NEXT: s_mov_b32 s15, 0xf000
|
|
; VERDE-NEXT: s_mov_b32 s14, -1
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: v_mov_b32_e32 v0, v9
|
|
; VERDE-NEXT: buffer_store_dword v10, off, s[12:15], 0
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0) expcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: sample_c_d_o_2darray_V1_tfe:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: v_mov_b32_e32 v9, 0
|
|
; GFX6789-NEXT: v_mov_b32_e32 v10, v9
|
|
; GFX6789-NEXT: image_sample_c_d_o v[9:10], v[0:15], s[0:7], s[8:11] dmask:0x4 tfe da
|
|
; GFX6789-NEXT: v_mov_b32_e32 v0, s12
|
|
; GFX6789-NEXT: v_mov_b32_e32 v1, s13
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: global_store_dword v[0:1], v10, off
|
|
; GFX6789-NEXT: v_mov_b32_e32 v0, v9
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_c_d_o_2darray_V1_tfe:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: v_mov_b32_e32 v10, v0 ; encoding: [0x00,0x03,0x14,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v0, 0 ; encoding: [0x80,0x02,0x00,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v9, v1 ; encoding: [0x01,0x03,0x12,0x7e]
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: v_mov_b32_e32 v1, v0 ; encoding: [0x00,0x03,0x02,0x7e]
|
|
; GFX10-NEXT: image_sample_c_d_o v[0:1], [v10, v9, v2, v3, v4, v5, v6, v7, v8], s[0:7], s[8:11] dmask:0x4 dim:SQ_RSRC_IMG_2D_ARRAY tfe ; encoding: [0x2c,0x04,0xe9,0xf0,0x0a,0x00,0x40,0x00,0x09,0x02,0x03,0x04,0x05,0x06,0x07,0x08]
|
|
; GFX10-NEXT: v_mov_b32_e32 v2, s12 ; encoding: [0x0c,0x02,0x04,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v3, s13 ; encoding: [0x0d,0x02,0x06,0x7e]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: global_store_dword v[2:3], v1, off ; encoding: [0x00,0x80,0x70,0xdc,0x02,0x01,0x7d,0x00]
|
|
; GFX10-NEXT: s_waitcnt_vscnt null, 0x0 ; encoding: [0x00,0x00,0xfd,0xbb]
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call {float,i32} @llvm.amdgcn.image.sample.c.d.o.2darray.f32i32.f32.f32(i32 4, i32 %offset, float %zcompare, float %dsdh, float %dtdh, float %dsdv, float %dtdv, float %s, float %t, float %slice, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 1, i32 0)
|
|
%v.vec = extractvalue {float, i32} %v, 0
|
|
%v.err = extractvalue {float, i32} %v, 1
|
|
store i32 %v.err, i32 addrspace(1)* %out, align 4
|
|
ret float %v.vec
|
|
}
|
|
|
|
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, float %dsdh, float %dtdh, float %dsdv, float %dtdv, float %s, float %t, float %slice) {
|
|
; VERDE-LABEL: sample_c_d_o_2darray_V2:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: image_sample_c_d_o v[0:1], v[0:15], s[0:7], s[8:11] dmask:0x6 da
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: sample_c_d_o_2darray_V2:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: image_sample_c_d_o v[0:1], v[0:15], s[0:7], s[8:11] dmask:0x6 da
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_c_d_o_2darray_V2:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: image_sample_c_d_o v[0:1], v[0:15], s[0:7], s[8:11] dmask:0x6 dim:SQ_RSRC_IMG_2D_ARRAY ; encoding: [0x28,0x06,0xe8,0xf0,0x00,0x00,0x40,0x00]
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <2 x float> @llvm.amdgcn.image.sample.c.d.o.2darray.v2f32.f32.f32(i32 6, i32 %offset, float %zcompare, float %dsdh, float %dtdh, float %dsdv, float %dtdv, float %s, float %t, float %slice, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 0, i32 0)
|
|
ret <2 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @sample_c_d_o_2darray_V2_tfe(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, i32 %offset, float %zcompare, float %dsdh, float %dtdh, float %dsdv, float %dtdv, float %s, float %t, float %slice) {
|
|
; VERDE-LABEL: sample_c_d_o_2darray_V2_tfe:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: v_mov_b32_e32 v9, 0
|
|
; VERDE-NEXT: v_mov_b32_e32 v10, v9
|
|
; VERDE-NEXT: v_mov_b32_e32 v11, v9
|
|
; VERDE-NEXT: image_sample_c_d_o v[9:11], v[0:15], s[0:7], s[8:11] dmask:0x6 tfe da
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: v_mov_b32_e32 v0, v9
|
|
; VERDE-NEXT: v_mov_b32_e32 v1, v10
|
|
; VERDE-NEXT: v_mov_b32_e32 v2, v11
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: sample_c_d_o_2darray_V2_tfe:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: v_mov_b32_e32 v9, 0
|
|
; GFX6789-NEXT: v_mov_b32_e32 v10, v9
|
|
; GFX6789-NEXT: v_mov_b32_e32 v11, v9
|
|
; GFX6789-NEXT: image_sample_c_d_o v[9:11], v[0:15], s[0:7], s[8:11] dmask:0x6 tfe da
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: v_mov_b32_e32 v0, v9
|
|
; GFX6789-NEXT: v_mov_b32_e32 v1, v10
|
|
; GFX6789-NEXT: v_mov_b32_e32 v2, v11
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_c_d_o_2darray_V2_tfe:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: v_mov_b32_e32 v11, v0 ; encoding: [0x00,0x03,0x16,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v0, 0 ; encoding: [0x80,0x02,0x00,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v9, v2 ; encoding: [0x02,0x03,0x12,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v10, v1 ; encoding: [0x01,0x03,0x14,0x7e]
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: v_mov_b32_e32 v1, v0 ; encoding: [0x00,0x03,0x02,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v2, v0 ; encoding: [0x00,0x03,0x04,0x7e]
|
|
; GFX10-NEXT: image_sample_c_d_o v[0:2], [v11, v10, v9, v3, v4, v5, v6, v7, v8], s[0:7], s[8:11] dmask:0x6 dim:SQ_RSRC_IMG_2D_ARRAY tfe ; encoding: [0x2c,0x06,0xe9,0xf0,0x0b,0x00,0x40,0x00,0x0a,0x09,0x03,0x04,0x05,0x06,0x07,0x08]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call {<2 x float>, i32} @llvm.amdgcn.image.sample.c.d.o.2darray.v2f32i32.f32.f32(i32 6, i32 %offset, float %zcompare, float %dsdh, float %dtdh, float %dsdv, float %dtdv, float %s, float %t, float %slice, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 1, i32 0)
|
|
%v.vec = extractvalue {<2 x float>, i32} %v, 0
|
|
%v.f1 = extractelement <2 x float> %v.vec, i32 0
|
|
%v.f2 = extractelement <2 x float> %v.vec, i32 1
|
|
%v.err = extractvalue {<2 x float>, i32} %v, 1
|
|
%v.errf = bitcast i32 %v.err to float
|
|
%res.0 = insertelement <4 x float> undef, float %v.f1, i32 0
|
|
%res.1 = insertelement <4 x float> %res.0, float %v.f2, i32 1
|
|
%res.2 = insertelement <4 x float> %res.1, float %v.errf, i32 2
|
|
ret <4 x float> %res.2
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @sample_1d_unorm(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, float %s) {
|
|
; VERDE-LABEL: sample_1d_unorm:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: s_mov_b64 s[12:13], exec
|
|
; VERDE-NEXT: s_wqm_b64 exec, exec
|
|
; VERDE-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; VERDE-NEXT: image_sample v[0:3], v0, s[0:7], s[8:11] dmask:0xf unorm
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: sample_1d_unorm:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: s_mov_b64 s[12:13], exec
|
|
; GFX6789-NEXT: s_wqm_b64 exec, exec
|
|
; GFX6789-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; GFX6789-NEXT: image_sample v[0:3], v0, s[0:7], s[8:11] dmask:0xf unorm
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_1d_unorm:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: s_mov_b32 s12, exec_lo ; encoding: [0x7e,0x03,0x8c,0xbe]
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_wqm_b32 exec_lo, exec_lo ; encoding: [0x7e,0x09,0xfe,0xbe]
|
|
; GFX10-NEXT: s_and_b32 exec_lo, exec_lo, s12 ; encoding: [0x7e,0x0c,0x7e,0x87]
|
|
; GFX10-NEXT: image_sample v[0:3], v0, s[0:7], s[8:11] dmask:0xf dim:SQ_RSRC_IMG_1D unorm ; encoding: [0x00,0x1f,0x80,0xf0,0x00,0x00,0x40,0x00]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.1d.v4f32.f32(i32 15, float %s, <8 x i32> %rsrc, <4 x i32> %samp, i1 1, i32 0, i32 0)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @sample_1d_glc(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, float %s) {
|
|
; VERDE-LABEL: sample_1d_glc:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: s_mov_b64 s[12:13], exec
|
|
; VERDE-NEXT: s_wqm_b64 exec, exec
|
|
; VERDE-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; VERDE-NEXT: image_sample v[0:3], v0, s[0:7], s[8:11] dmask:0xf glc
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: sample_1d_glc:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: s_mov_b64 s[12:13], exec
|
|
; GFX6789-NEXT: s_wqm_b64 exec, exec
|
|
; GFX6789-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; GFX6789-NEXT: image_sample v[0:3], v0, s[0:7], s[8:11] dmask:0xf glc
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_1d_glc:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: s_mov_b32 s12, exec_lo ; encoding: [0x7e,0x03,0x8c,0xbe]
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_wqm_b32 exec_lo, exec_lo ; encoding: [0x7e,0x09,0xfe,0xbe]
|
|
; GFX10-NEXT: s_and_b32 exec_lo, exec_lo, s12 ; encoding: [0x7e,0x0c,0x7e,0x87]
|
|
; GFX10-NEXT: image_sample v[0:3], v0, s[0:7], s[8:11] dmask:0xf dim:SQ_RSRC_IMG_1D glc ; encoding: [0x00,0x2f,0x80,0xf0,0x00,0x00,0x40,0x00]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.1d.v4f32.f32(i32 15, float %s, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 0, i32 1)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @sample_1d_slc(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, float %s) {
|
|
; VERDE-LABEL: sample_1d_slc:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: s_mov_b64 s[12:13], exec
|
|
; VERDE-NEXT: s_wqm_b64 exec, exec
|
|
; VERDE-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; VERDE-NEXT: image_sample v[0:3], v0, s[0:7], s[8:11] dmask:0xf slc
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: sample_1d_slc:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: s_mov_b64 s[12:13], exec
|
|
; GFX6789-NEXT: s_wqm_b64 exec, exec
|
|
; GFX6789-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; GFX6789-NEXT: image_sample v[0:3], v0, s[0:7], s[8:11] dmask:0xf slc
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_1d_slc:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: s_mov_b32 s12, exec_lo ; encoding: [0x7e,0x03,0x8c,0xbe]
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_wqm_b32 exec_lo, exec_lo ; encoding: [0x7e,0x09,0xfe,0xbe]
|
|
; GFX10-NEXT: s_and_b32 exec_lo, exec_lo, s12 ; encoding: [0x7e,0x0c,0x7e,0x87]
|
|
; GFX10-NEXT: image_sample v[0:3], v0, s[0:7], s[8:11] dmask:0xf dim:SQ_RSRC_IMG_1D slc ; encoding: [0x00,0x0f,0x80,0xf2,0x00,0x00,0x40,0x00]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.1d.v4f32.f32(i32 15, float %s, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 0, i32 2)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @sample_1d_glc_slc(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, float %s) {
|
|
; VERDE-LABEL: sample_1d_glc_slc:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: s_mov_b64 s[12:13], exec
|
|
; VERDE-NEXT: s_wqm_b64 exec, exec
|
|
; VERDE-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; VERDE-NEXT: image_sample v[0:3], v0, s[0:7], s[8:11] dmask:0xf glc slc
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: sample_1d_glc_slc:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: s_mov_b64 s[12:13], exec
|
|
; GFX6789-NEXT: s_wqm_b64 exec, exec
|
|
; GFX6789-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; GFX6789-NEXT: image_sample v[0:3], v0, s[0:7], s[8:11] dmask:0xf glc slc
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: sample_1d_glc_slc:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: s_mov_b32 s12, exec_lo ; encoding: [0x7e,0x03,0x8c,0xbe]
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_wqm_b32 exec_lo, exec_lo ; encoding: [0x7e,0x09,0xfe,0xbe]
|
|
; GFX10-NEXT: s_and_b32 exec_lo, exec_lo, s12 ; encoding: [0x7e,0x0c,0x7e,0x87]
|
|
; GFX10-NEXT: image_sample v[0:3], v0, s[0:7], s[8:11] dmask:0xf dim:SQ_RSRC_IMG_1D glc slc ; encoding: [0x00,0x2f,0x80,0xf2,0x00,0x00,0x40,0x00]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call <4 x float> @llvm.amdgcn.image.sample.1d.v4f32.f32(i32 15, float %s, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 0, i32 3)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps float @adjust_writemask_sample_0(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, float %s) {
|
|
; VERDE-LABEL: adjust_writemask_sample_0:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: s_mov_b64 s[12:13], exec
|
|
; VERDE-NEXT: s_wqm_b64 exec, exec
|
|
; VERDE-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; VERDE-NEXT: image_sample v0, v0, s[0:7], s[8:11] dmask:0x1
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: adjust_writemask_sample_0:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: s_mov_b64 s[12:13], exec
|
|
; GFX6789-NEXT: s_wqm_b64 exec, exec
|
|
; GFX6789-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; GFX6789-NEXT: image_sample v0, v0, s[0:7], s[8:11] dmask:0x1
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: adjust_writemask_sample_0:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: s_mov_b32 s12, exec_lo ; encoding: [0x7e,0x03,0x8c,0xbe]
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_wqm_b32 exec_lo, exec_lo ; encoding: [0x7e,0x09,0xfe,0xbe]
|
|
; GFX10-NEXT: s_and_b32 exec_lo, exec_lo, s12 ; encoding: [0x7e,0x0c,0x7e,0x87]
|
|
; GFX10-NEXT: image_sample v0, v0, s[0:7], s[8:11] dmask:0x1 dim:SQ_RSRC_IMG_1D ; encoding: [0x00,0x01,0x80,0xf0,0x00,0x00,0x40,0x00]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%r = call <4 x float> @llvm.amdgcn.image.sample.1d.v4f32.f32(i32 15, float %s, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 0, i32 0)
|
|
%elt0 = extractelement <4 x float> %r, i32 0
|
|
ret float %elt0
|
|
}
|
|
|
|
define amdgpu_ps <2 x float> @adjust_writemask_sample_01(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, float %s) {
|
|
; VERDE-LABEL: adjust_writemask_sample_01:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: s_mov_b64 s[12:13], exec
|
|
; VERDE-NEXT: s_wqm_b64 exec, exec
|
|
; VERDE-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; VERDE-NEXT: image_sample v[0:1], v0, s[0:7], s[8:11] dmask:0x3
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: adjust_writemask_sample_01:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: s_mov_b64 s[12:13], exec
|
|
; GFX6789-NEXT: s_wqm_b64 exec, exec
|
|
; GFX6789-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; GFX6789-NEXT: image_sample v[0:1], v0, s[0:7], s[8:11] dmask:0x3
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: adjust_writemask_sample_01:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: s_mov_b32 s12, exec_lo ; encoding: [0x7e,0x03,0x8c,0xbe]
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_wqm_b32 exec_lo, exec_lo ; encoding: [0x7e,0x09,0xfe,0xbe]
|
|
; GFX10-NEXT: s_and_b32 exec_lo, exec_lo, s12 ; encoding: [0x7e,0x0c,0x7e,0x87]
|
|
; GFX10-NEXT: image_sample v[0:1], v0, s[0:7], s[8:11] dmask:0x3 dim:SQ_RSRC_IMG_1D ; encoding: [0x00,0x03,0x80,0xf0,0x00,0x00,0x40,0x00]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%r = call <4 x float> @llvm.amdgcn.image.sample.1d.v4f32.f32(i32 15, float %s, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 0, i32 0)
|
|
%out = shufflevector <4 x float> %r, <4 x float> undef, <2 x i32> <i32 0, i32 1>
|
|
ret <2 x float> %out
|
|
}
|
|
|
|
define amdgpu_ps <3 x float> @adjust_writemask_sample_012(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, float %s) {
|
|
; VERDE-LABEL: adjust_writemask_sample_012:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: s_mov_b64 s[12:13], exec
|
|
; VERDE-NEXT: s_wqm_b64 exec, exec
|
|
; VERDE-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; VERDE-NEXT: image_sample v[0:2], v0, s[0:7], s[8:11] dmask:0x7
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: adjust_writemask_sample_012:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: s_mov_b64 s[12:13], exec
|
|
; GFX6789-NEXT: s_wqm_b64 exec, exec
|
|
; GFX6789-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; GFX6789-NEXT: image_sample v[0:2], v0, s[0:7], s[8:11] dmask:0x7
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: adjust_writemask_sample_012:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: s_mov_b32 s12, exec_lo ; encoding: [0x7e,0x03,0x8c,0xbe]
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_wqm_b32 exec_lo, exec_lo ; encoding: [0x7e,0x09,0xfe,0xbe]
|
|
; GFX10-NEXT: s_and_b32 exec_lo, exec_lo, s12 ; encoding: [0x7e,0x0c,0x7e,0x87]
|
|
; GFX10-NEXT: image_sample v[0:2], v0, s[0:7], s[8:11] dmask:0x7 dim:SQ_RSRC_IMG_1D ; encoding: [0x00,0x07,0x80,0xf0,0x00,0x00,0x40,0x00]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%r = call <4 x float> @llvm.amdgcn.image.sample.1d.v4f32.f32(i32 15, float %s, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 0, i32 0)
|
|
%out = shufflevector <4 x float> %r, <4 x float> undef, <3 x i32> <i32 0, i32 1, i32 2>
|
|
ret <3 x float> %out
|
|
}
|
|
|
|
define amdgpu_ps <2 x float> @adjust_writemask_sample_12(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, float %s) {
|
|
; VERDE-LABEL: adjust_writemask_sample_12:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: s_mov_b64 s[12:13], exec
|
|
; VERDE-NEXT: s_wqm_b64 exec, exec
|
|
; VERDE-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; VERDE-NEXT: image_sample v[0:1], v0, s[0:7], s[8:11] dmask:0x6
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: adjust_writemask_sample_12:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: s_mov_b64 s[12:13], exec
|
|
; GFX6789-NEXT: s_wqm_b64 exec, exec
|
|
; GFX6789-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; GFX6789-NEXT: image_sample v[0:1], v0, s[0:7], s[8:11] dmask:0x6
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: adjust_writemask_sample_12:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: s_mov_b32 s12, exec_lo ; encoding: [0x7e,0x03,0x8c,0xbe]
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_wqm_b32 exec_lo, exec_lo ; encoding: [0x7e,0x09,0xfe,0xbe]
|
|
; GFX10-NEXT: s_and_b32 exec_lo, exec_lo, s12 ; encoding: [0x7e,0x0c,0x7e,0x87]
|
|
; GFX10-NEXT: image_sample v[0:1], v0, s[0:7], s[8:11] dmask:0x6 dim:SQ_RSRC_IMG_1D ; encoding: [0x00,0x06,0x80,0xf0,0x00,0x00,0x40,0x00]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%r = call <4 x float> @llvm.amdgcn.image.sample.1d.v4f32.f32(i32 15, float %s, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 0, i32 0)
|
|
%out = shufflevector <4 x float> %r, <4 x float> undef, <2 x i32> <i32 1, i32 2>
|
|
ret <2 x float> %out
|
|
}
|
|
|
|
define amdgpu_ps <2 x float> @adjust_writemask_sample_03(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, float %s) {
|
|
; VERDE-LABEL: adjust_writemask_sample_03:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: s_mov_b64 s[12:13], exec
|
|
; VERDE-NEXT: s_wqm_b64 exec, exec
|
|
; VERDE-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; VERDE-NEXT: image_sample v[0:1], v0, s[0:7], s[8:11] dmask:0x9
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: adjust_writemask_sample_03:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: s_mov_b64 s[12:13], exec
|
|
; GFX6789-NEXT: s_wqm_b64 exec, exec
|
|
; GFX6789-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; GFX6789-NEXT: image_sample v[0:1], v0, s[0:7], s[8:11] dmask:0x9
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: adjust_writemask_sample_03:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: s_mov_b32 s12, exec_lo ; encoding: [0x7e,0x03,0x8c,0xbe]
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_wqm_b32 exec_lo, exec_lo ; encoding: [0x7e,0x09,0xfe,0xbe]
|
|
; GFX10-NEXT: s_and_b32 exec_lo, exec_lo, s12 ; encoding: [0x7e,0x0c,0x7e,0x87]
|
|
; GFX10-NEXT: image_sample v[0:1], v0, s[0:7], s[8:11] dmask:0x9 dim:SQ_RSRC_IMG_1D ; encoding: [0x00,0x09,0x80,0xf0,0x00,0x00,0x40,0x00]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%r = call <4 x float> @llvm.amdgcn.image.sample.1d.v4f32.f32(i32 15, float %s, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 0, i32 0)
|
|
%out = shufflevector <4 x float> %r, <4 x float> undef, <2 x i32> <i32 0, i32 3>
|
|
ret <2 x float> %out
|
|
}
|
|
|
|
define amdgpu_ps <2 x float> @adjust_writemask_sample_13(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, float %s) {
|
|
; VERDE-LABEL: adjust_writemask_sample_13:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: s_mov_b64 s[12:13], exec
|
|
; VERDE-NEXT: s_wqm_b64 exec, exec
|
|
; VERDE-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; VERDE-NEXT: image_sample v[0:1], v0, s[0:7], s[8:11] dmask:0xa
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: adjust_writemask_sample_13:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: s_mov_b64 s[12:13], exec
|
|
; GFX6789-NEXT: s_wqm_b64 exec, exec
|
|
; GFX6789-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; GFX6789-NEXT: image_sample v[0:1], v0, s[0:7], s[8:11] dmask:0xa
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: adjust_writemask_sample_13:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: s_mov_b32 s12, exec_lo ; encoding: [0x7e,0x03,0x8c,0xbe]
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_wqm_b32 exec_lo, exec_lo ; encoding: [0x7e,0x09,0xfe,0xbe]
|
|
; GFX10-NEXT: s_and_b32 exec_lo, exec_lo, s12 ; encoding: [0x7e,0x0c,0x7e,0x87]
|
|
; GFX10-NEXT: image_sample v[0:1], v0, s[0:7], s[8:11] dmask:0xa dim:SQ_RSRC_IMG_1D ; encoding: [0x00,0x0a,0x80,0xf0,0x00,0x00,0x40,0x00]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%r = call <4 x float> @llvm.amdgcn.image.sample.1d.v4f32.f32(i32 15, float %s, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 0, i32 0)
|
|
%out = shufflevector <4 x float> %r, <4 x float> undef, <2 x i32> <i32 1, i32 3>
|
|
ret <2 x float> %out
|
|
}
|
|
|
|
define amdgpu_ps <3 x float> @adjust_writemask_sample_123(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, float %s) {
|
|
; VERDE-LABEL: adjust_writemask_sample_123:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: s_mov_b64 s[12:13], exec
|
|
; VERDE-NEXT: s_wqm_b64 exec, exec
|
|
; VERDE-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; VERDE-NEXT: image_sample v[0:2], v0, s[0:7], s[8:11] dmask:0xe
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: adjust_writemask_sample_123:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: s_mov_b64 s[12:13], exec
|
|
; GFX6789-NEXT: s_wqm_b64 exec, exec
|
|
; GFX6789-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; GFX6789-NEXT: image_sample v[0:2], v0, s[0:7], s[8:11] dmask:0xe
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: adjust_writemask_sample_123:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: s_mov_b32 s12, exec_lo ; encoding: [0x7e,0x03,0x8c,0xbe]
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_wqm_b32 exec_lo, exec_lo ; encoding: [0x7e,0x09,0xfe,0xbe]
|
|
; GFX10-NEXT: s_and_b32 exec_lo, exec_lo, s12 ; encoding: [0x7e,0x0c,0x7e,0x87]
|
|
; GFX10-NEXT: image_sample v[0:2], v0, s[0:7], s[8:11] dmask:0xe dim:SQ_RSRC_IMG_1D ; encoding: [0x00,0x0e,0x80,0xf0,0x00,0x00,0x40,0x00]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%r = call <4 x float> @llvm.amdgcn.image.sample.1d.v4f32.f32(i32 15, float %s, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 0, i32 0)
|
|
%out = shufflevector <4 x float> %r, <4 x float> undef, <3 x i32> <i32 1, i32 2, i32 3>
|
|
ret <3 x float> %out
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @adjust_writemask_sample_none_enabled(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, float %s) {
|
|
; VERDE-LABEL: adjust_writemask_sample_none_enabled:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: adjust_writemask_sample_none_enabled:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: adjust_writemask_sample_none_enabled:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%r = call <4 x float> @llvm.amdgcn.image.sample.1d.v4f32.f32(i32 0, float %s, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 0, i32 0)
|
|
ret <4 x float> %r
|
|
}
|
|
|
|
define amdgpu_ps <2 x float> @adjust_writemask_sample_123_to_12(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, float %s) {
|
|
; VERDE-LABEL: adjust_writemask_sample_123_to_12:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: s_mov_b64 s[12:13], exec
|
|
; VERDE-NEXT: s_wqm_b64 exec, exec
|
|
; VERDE-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; VERDE-NEXT: image_sample v[0:1], v0, s[0:7], s[8:11] dmask:0x6
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: adjust_writemask_sample_123_to_12:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: s_mov_b64 s[12:13], exec
|
|
; GFX6789-NEXT: s_wqm_b64 exec, exec
|
|
; GFX6789-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; GFX6789-NEXT: image_sample v[0:1], v0, s[0:7], s[8:11] dmask:0x6
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: adjust_writemask_sample_123_to_12:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: s_mov_b32 s12, exec_lo ; encoding: [0x7e,0x03,0x8c,0xbe]
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_wqm_b32 exec_lo, exec_lo ; encoding: [0x7e,0x09,0xfe,0xbe]
|
|
; GFX10-NEXT: s_and_b32 exec_lo, exec_lo, s12 ; encoding: [0x7e,0x0c,0x7e,0x87]
|
|
; GFX10-NEXT: image_sample v[0:1], v0, s[0:7], s[8:11] dmask:0x6 dim:SQ_RSRC_IMG_1D ; encoding: [0x00,0x06,0x80,0xf0,0x00,0x00,0x40,0x00]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%r = call <4 x float> @llvm.amdgcn.image.sample.1d.v4f32.f32(i32 14, float %s, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 0, i32 0)
|
|
%out = shufflevector <4 x float> %r, <4 x float> undef, <2 x i32> <i32 0, i32 1>
|
|
ret <2 x float> %out
|
|
}
|
|
|
|
define amdgpu_ps <2 x float> @adjust_writemask_sample_013_to_13(<8 x i32> inreg %rsrc, <4 x i32> inreg %samp, float %s) {
|
|
; VERDE-LABEL: adjust_writemask_sample_013_to_13:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: s_mov_b64 s[12:13], exec
|
|
; VERDE-NEXT: s_wqm_b64 exec, exec
|
|
; VERDE-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; VERDE-NEXT: image_sample v[0:1], v0, s[0:7], s[8:11] dmask:0xa
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: adjust_writemask_sample_013_to_13:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: s_mov_b64 s[12:13], exec
|
|
; GFX6789-NEXT: s_wqm_b64 exec, exec
|
|
; GFX6789-NEXT: s_and_b64 exec, exec, s[12:13]
|
|
; GFX6789-NEXT: image_sample v[0:1], v0, s[0:7], s[8:11] dmask:0xa
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: adjust_writemask_sample_013_to_13:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: s_mov_b32 s12, exec_lo ; encoding: [0x7e,0x03,0x8c,0xbe]
|
|
; GFX10-NEXT: ; implicit-def: $vcc_hi
|
|
; GFX10-NEXT: s_wqm_b32 exec_lo, exec_lo ; encoding: [0x7e,0x09,0xfe,0xbe]
|
|
; GFX10-NEXT: s_and_b32 exec_lo, exec_lo, s12 ; encoding: [0x7e,0x0c,0x7e,0x87]
|
|
; GFX10-NEXT: image_sample v[0:1], v0, s[0:7], s[8:11] dmask:0xa dim:SQ_RSRC_IMG_1D ; encoding: [0x00,0x0a,0x80,0xf0,0x00,0x00,0x40,0x00]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%r = call <4 x float> @llvm.amdgcn.image.sample.1d.v4f32.f32(i32 11, float %s, <8 x i32> %rsrc, <4 x i32> %samp, i1 0, i32 0, i32 0)
|
|
%out = shufflevector <4 x float> %r, <4 x float> undef, <2 x i32> <i32 1, i32 2>
|
|
ret <2 x float> %out
|
|
}
|
|
|
|
declare <4 x float> @llvm.amdgcn.image.sample.1d.v4f32.f32(i32, float, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare {<4 x float>,i32} @llvm.amdgcn.image.sample.1d.v4f32i32.f32(i32, float, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.2d.v4f32.f32(i32, float, float, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.3d.v4f32.f32(i32, float, float, float, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.cube.v4f32.f32(i32, float, float, float, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.1darray.v4f32.f32(i32, float, float, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.2darray.v4f32.f32(i32, float, float, float, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
|
|
declare <4 x float> @llvm.amdgcn.image.sample.c.1d.v4f32.f32(i32, float, float, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.c.2d.v4f32.f32(i32, float, float, float, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.cl.1d.v4f32.f32(i32, float, float, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.cl.2d.v4f32.f32(i32, float, float, float, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.c.cl.1d.v4f32.f32(i32, float, float, float, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.c.cl.2d.v4f32.f32(i32, float, float, float, float, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
|
|
declare <4 x float> @llvm.amdgcn.image.sample.b.1d.v4f32.f32.f32(i32, float, float, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.b.2d.v4f32.f32.f32(i32, float, float, float, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.c.b.1d.v4f32.f32.f32(i32, float, float, float, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.c.b.2d.v4f32.f32.f32(i32, float, float, float, float, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.b.cl.1d.v4f32.f32.f32(i32, float, float, float, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.b.cl.2d.v4f32.f32.f32(i32, float, float, float, float, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.c.b.cl.1d.v4f32.f32.f32(i32, float, float, float, float, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.c.b.cl.2d.v4f32.f32.f32(i32, float, float, float, float, float, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
|
|
declare <4 x float> @llvm.amdgcn.image.sample.d.1d.v4f32.f32.f32(i32, float, float, float, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.d.2d.v4f32.f32.f32(i32, float, float, float, float, float, float, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.c.d.1d.v4f32.f32.f32(i32, float, float, float, float, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.c.d.2d.v4f32.f32.f32(i32, float, float, float, float, float, float, float, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.d.cl.1d.v4f32.f32.f32(i32, float, float, float, float, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.d.cl.2d.v4f32.f32.f32(i32, float, float, float, float, float, float, float, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.c.d.cl.1d.v4f32.f32.f32(i32, float, float, float, float, float, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.c.d.cl.2d.v4f32.f32.f32(i32, float, float, float, float, float, float, float, float, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
|
|
declare <4 x float> @llvm.amdgcn.image.sample.cd.1d.v4f32.f32.f32(i32, float, float, float, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.cd.2d.v4f32.f32.f32(i32, float, float, float, float, float, float, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.c.cd.1d.v4f32.f32.f32(i32, float, float, float, float, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.c.cd.2d.v4f32.f32.f32(i32, float, float, float, float, float, float, float, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.cd.cl.1d.v4f32.f32.f32(i32, float, float, float, float, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.cd.cl.2d.v4f32.f32.f32(i32, float, float, float, float, float, float, float, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.c.cd.cl.1d.v4f32.f32.f32(i32, float, float, float, float, float, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.c.cd.cl.2d.v4f32.f32.f32(i32, float, float, float, float, float, float, float, float, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
|
|
declare <4 x float> @llvm.amdgcn.image.sample.l.1d.v4f32.f32(i32, float, float, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.l.2d.v4f32.f32(i32, float, float, float, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.c.l.1d.v4f32.f32(i32, float, float, float, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.c.l.2d.v4f32.f32(i32, float, float, float, float, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
|
|
declare <4 x float> @llvm.amdgcn.image.sample.lz.1d.v4f32.f32(i32, float, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.lz.2d.v4f32.f32(i32, float, float, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.c.lz.1d.v4f32.f32(i32, float, float, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.sample.c.lz.2d.v4f32.f32(i32, float, float, float, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
|
|
declare float @llvm.amdgcn.image.sample.c.d.o.2darray.f32.f32.f32(i32, i32, float, float, float, float, float, float, float, float, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare {float, i32} @llvm.amdgcn.image.sample.c.d.o.2darray.f32i32.f32.f32(i32, i32, float, float, float, float, float, float, float, float, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare <2 x float> @llvm.amdgcn.image.sample.c.d.o.2darray.v2f32.f32.f32(i32, i32, float, float, float, float, float, float, float, float, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
declare {<2 x float>, i32} @llvm.amdgcn.image.sample.c.d.o.2darray.v2f32i32.f32.f32(i32, i32, float, float, float, float, float, float, float, float, <8 x i32>, <4 x i32>, i1, i32, i32) #1
|
|
|
|
attributes #0 = { nounwind }
|
|
attributes #1 = { nounwind readonly }
|
|
attributes #2 = { nounwind readnone }
|