forked from OSchip/llvm-project
3553 lines
155 KiB
LLVM
3553 lines
155 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=fiji -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefixes=FIJI %s
|
|
; RUN: llc -march=amdgcn -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck -check-prefixes=GFX6789 %s
|
|
; RUN: llc -march=amdgcn -mcpu=gfx900 -mattr=-enable-prt-strict-null -verify-machineinstrs < %s | FileCheck -check-prefixes=NOPRT %s
|
|
; RUN: llc -march=amdgcn -mcpu=gfx1010 -verify-machineinstrs -show-mc-encoding < %s | FileCheck -check-prefixes=GFX10 %s
|
|
|
|
define amdgpu_ps <4 x float> @load_1d(<8 x i32> inreg %rsrc, i32 %s) {
|
|
; VERDE-LABEL: load_1d:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: image_load v[0:3], v0, s[0:7] dmask:0xf unorm
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; FIJI-LABEL: load_1d:
|
|
; FIJI: ; %bb.0: ; %main_body
|
|
; FIJI-NEXT: image_load v[0:3], v0, s[0:7] dmask:0xf unorm
|
|
; FIJI-NEXT: s_waitcnt vmcnt(0)
|
|
; FIJI-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: load_1d:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: image_load v[0:3], v0, s[0:7] dmask:0xf unorm
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; NOPRT-LABEL: load_1d:
|
|
; NOPRT: ; %bb.0: ; %main_body
|
|
; NOPRT-NEXT: image_load v[0:3], v0, s[0:7] dmask:0xf unorm
|
|
; NOPRT-NEXT: s_waitcnt vmcnt(0)
|
|
; NOPRT-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: load_1d:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: image_load v[0:3], v0, s[0:7] dmask:0xf dim:SQ_RSRC_IMG_1D unorm ; encoding: [0x00,0x1f,0x00,0xf0,0x00,0x00,0x00,0x00]
|
|
; 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.load.1d.v4f32.i32(i32 15, i32 %s, <8 x i32> %rsrc, i32 0, i32 0)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @load_1d_tfe(<8 x i32> inreg %rsrc, i32 addrspace(1)* inreg %out, i32 %s) {
|
|
; VERDE-LABEL: load_1d_tfe:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: v_mov_b32_e32 v5, 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: v_mov_b32_e32 v4, v0
|
|
; VERDE-NEXT: image_load v[0:4], v5, s[0:7] dmask:0xf unorm tfe
|
|
; VERDE-NEXT: s_mov_b32 s11, 0xf000
|
|
; VERDE-NEXT: s_mov_b32 s10, -1
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: buffer_store_dword v4, off, s[8:11], 0
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0) expcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; FIJI-LABEL: load_1d_tfe:
|
|
; FIJI: ; %bb.0: ; %main_body
|
|
; FIJI-NEXT: v_mov_b32_e32 v5, v0
|
|
; FIJI-NEXT: v_mov_b32_e32 v0, 0
|
|
; FIJI-NEXT: v_mov_b32_e32 v1, v0
|
|
; FIJI-NEXT: v_mov_b32_e32 v2, v0
|
|
; FIJI-NEXT: v_mov_b32_e32 v3, v0
|
|
; FIJI-NEXT: v_mov_b32_e32 v4, v0
|
|
; FIJI-NEXT: image_load v[0:4], v5, s[0:7] dmask:0xf unorm tfe
|
|
; FIJI-NEXT: s_mov_b32 s11, 0xf000
|
|
; FIJI-NEXT: s_mov_b32 s10, -1
|
|
; FIJI-NEXT: s_waitcnt vmcnt(0)
|
|
; FIJI-NEXT: buffer_store_dword v4, off, s[8:11], 0
|
|
; FIJI-NEXT: s_waitcnt vmcnt(0)
|
|
; FIJI-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: load_1d_tfe:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: v_mov_b32_e32 v6, 0
|
|
; GFX6789-NEXT: v_mov_b32_e32 v5, v0
|
|
; GFX6789-NEXT: v_mov_b32_e32 v7, v6
|
|
; GFX6789-NEXT: v_mov_b32_e32 v8, v6
|
|
; GFX6789-NEXT: v_mov_b32_e32 v9, v6
|
|
; GFX6789-NEXT: v_mov_b32_e32 v10, v6
|
|
; GFX6789-NEXT: v_mov_b32_e32 v0, v6
|
|
; GFX6789-NEXT: v_mov_b32_e32 v1, v7
|
|
; GFX6789-NEXT: v_mov_b32_e32 v2, v8
|
|
; GFX6789-NEXT: v_mov_b32_e32 v3, v9
|
|
; GFX6789-NEXT: v_mov_b32_e32 v4, v10
|
|
; GFX6789-NEXT: image_load v[0:4], v5, s[0:7] dmask:0xf unorm tfe
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: global_store_dword v6, v4, s[8:9]
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; NOPRT-LABEL: load_1d_tfe:
|
|
; NOPRT: ; %bb.0: ; %main_body
|
|
; NOPRT-NEXT: v_mov_b32_e32 v4, 0
|
|
; NOPRT-NEXT: image_load v[0:4], v0, s[0:7] dmask:0xf unorm tfe
|
|
; NOPRT-NEXT: v_mov_b32_e32 v5, 0
|
|
; NOPRT-NEXT: s_waitcnt vmcnt(0)
|
|
; NOPRT-NEXT: global_store_dword v5, v4, s[8:9]
|
|
; NOPRT-NEXT: s_waitcnt vmcnt(0)
|
|
; NOPRT-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: load_1d_tfe:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: v_mov_b32_e32 v6, 0 ; encoding: [0x80,0x02,0x0c,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v5, v0 ; encoding: [0x00,0x03,0x0a,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v7, v6 ; encoding: [0x06,0x03,0x0e,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v8, v6 ; encoding: [0x06,0x03,0x10,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v9, v6 ; encoding: [0x06,0x03,0x12,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v10, v6 ; encoding: [0x06,0x03,0x14,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v0, v6 ; encoding: [0x06,0x03,0x00,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v1, v7 ; encoding: [0x07,0x03,0x02,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v2, v8 ; encoding: [0x08,0x03,0x04,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v3, v9 ; encoding: [0x09,0x03,0x06,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v4, v10 ; encoding: [0x0a,0x03,0x08,0x7e]
|
|
; GFX10-NEXT: image_load v[0:4], v5, s[0:7] dmask:0xf dim:SQ_RSRC_IMG_1D unorm tfe ; encoding: [0x00,0x1f,0x01,0xf0,0x05,0x00,0x00,0x00]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: global_store_dword v6, v4, s[8:9] ; encoding: [0x00,0x80,0x70,0xdc,0x06,0x04,0x08,0x00]
|
|
; 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.load.1d.v4f32i32.i32(i32 15, i32 %s, <8 x i32> %rsrc, 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 <4 x float> @load_1d_lwe(<8 x i32> inreg %rsrc, i32 addrspace(1)* inreg %out, i32 %s) {
|
|
; VERDE-LABEL: load_1d_lwe:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: v_mov_b32_e32 v5, 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: v_mov_b32_e32 v4, v0
|
|
; VERDE-NEXT: image_load v[0:4], v5, s[0:7] dmask:0xf unorm lwe
|
|
; VERDE-NEXT: s_mov_b32 s11, 0xf000
|
|
; VERDE-NEXT: s_mov_b32 s10, -1
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: buffer_store_dword v4, off, s[8:11], 0
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0) expcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; FIJI-LABEL: load_1d_lwe:
|
|
; FIJI: ; %bb.0: ; %main_body
|
|
; FIJI-NEXT: v_mov_b32_e32 v5, v0
|
|
; FIJI-NEXT: v_mov_b32_e32 v0, 0
|
|
; FIJI-NEXT: v_mov_b32_e32 v1, v0
|
|
; FIJI-NEXT: v_mov_b32_e32 v2, v0
|
|
; FIJI-NEXT: v_mov_b32_e32 v3, v0
|
|
; FIJI-NEXT: v_mov_b32_e32 v4, v0
|
|
; FIJI-NEXT: image_load v[0:4], v5, s[0:7] dmask:0xf unorm lwe
|
|
; FIJI-NEXT: s_mov_b32 s11, 0xf000
|
|
; FIJI-NEXT: s_mov_b32 s10, -1
|
|
; FIJI-NEXT: s_waitcnt vmcnt(0)
|
|
; FIJI-NEXT: buffer_store_dword v4, off, s[8:11], 0
|
|
; FIJI-NEXT: s_waitcnt vmcnt(0)
|
|
; FIJI-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: load_1d_lwe:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: v_mov_b32_e32 v6, 0
|
|
; GFX6789-NEXT: v_mov_b32_e32 v5, v0
|
|
; GFX6789-NEXT: v_mov_b32_e32 v7, v6
|
|
; GFX6789-NEXT: v_mov_b32_e32 v8, v6
|
|
; GFX6789-NEXT: v_mov_b32_e32 v9, v6
|
|
; GFX6789-NEXT: v_mov_b32_e32 v10, v6
|
|
; GFX6789-NEXT: v_mov_b32_e32 v0, v6
|
|
; GFX6789-NEXT: v_mov_b32_e32 v1, v7
|
|
; GFX6789-NEXT: v_mov_b32_e32 v2, v8
|
|
; GFX6789-NEXT: v_mov_b32_e32 v3, v9
|
|
; GFX6789-NEXT: v_mov_b32_e32 v4, v10
|
|
; GFX6789-NEXT: image_load v[0:4], v5, s[0:7] dmask:0xf unorm lwe
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: global_store_dword v6, v4, s[8:9]
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; NOPRT-LABEL: load_1d_lwe:
|
|
; NOPRT: ; %bb.0: ; %main_body
|
|
; NOPRT-NEXT: v_mov_b32_e32 v4, 0
|
|
; NOPRT-NEXT: image_load v[0:4], v0, s[0:7] dmask:0xf unorm lwe
|
|
; NOPRT-NEXT: v_mov_b32_e32 v5, 0
|
|
; NOPRT-NEXT: s_waitcnt vmcnt(0)
|
|
; NOPRT-NEXT: global_store_dword v5, v4, s[8:9]
|
|
; NOPRT-NEXT: s_waitcnt vmcnt(0)
|
|
; NOPRT-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: load_1d_lwe:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: v_mov_b32_e32 v6, 0 ; encoding: [0x80,0x02,0x0c,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v5, v0 ; encoding: [0x00,0x03,0x0a,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v7, v6 ; encoding: [0x06,0x03,0x0e,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v8, v6 ; encoding: [0x06,0x03,0x10,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v9, v6 ; encoding: [0x06,0x03,0x12,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v10, v6 ; encoding: [0x06,0x03,0x14,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v0, v6 ; encoding: [0x06,0x03,0x00,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v1, v7 ; encoding: [0x07,0x03,0x02,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v2, v8 ; encoding: [0x08,0x03,0x04,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v3, v9 ; encoding: [0x09,0x03,0x06,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v4, v10 ; encoding: [0x0a,0x03,0x08,0x7e]
|
|
; GFX10-NEXT: image_load v[0:4], v5, s[0:7] dmask:0xf dim:SQ_RSRC_IMG_1D unorm lwe ; encoding: [0x00,0x1f,0x02,0xf0,0x05,0x00,0x00,0x00]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: global_store_dword v6, v4, s[8:9] ; encoding: [0x00,0x80,0x70,0xdc,0x06,0x04,0x08,0x00]
|
|
; 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.load.1d.v4f32i32.i32(i32 15, i32 %s, <8 x i32> %rsrc, 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> @load_2d(<8 x i32> inreg %rsrc, i32 %s, i32 %t) {
|
|
; VERDE-LABEL: load_2d:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: image_load v[0:3], v[0:1], s[0:7] dmask:0xf unorm
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; FIJI-LABEL: load_2d:
|
|
; FIJI: ; %bb.0: ; %main_body
|
|
; FIJI-NEXT: image_load v[0:3], v[0:1], s[0:7] dmask:0xf unorm
|
|
; FIJI-NEXT: s_waitcnt vmcnt(0)
|
|
; FIJI-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: load_2d:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: image_load v[0:3], v[0:1], s[0:7] dmask:0xf unorm
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; NOPRT-LABEL: load_2d:
|
|
; NOPRT: ; %bb.0: ; %main_body
|
|
; NOPRT-NEXT: image_load v[0:3], v[0:1], s[0:7] dmask:0xf unorm
|
|
; NOPRT-NEXT: s_waitcnt vmcnt(0)
|
|
; NOPRT-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: load_2d:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: image_load v[0:3], v[0:1], s[0:7] dmask:0xf dim:SQ_RSRC_IMG_2D unorm ; encoding: [0x08,0x1f,0x00,0xf0,0x00,0x00,0x00,0x00]
|
|
; 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.load.2d.v4f32.i32(i32 15, i32 %s, i32 %t, <8 x i32> %rsrc, i32 0, i32 0)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @load_2d_tfe(<8 x i32> inreg %rsrc, i32 addrspace(1)* inreg %out, i32 %s, i32 %t) {
|
|
; VERDE-LABEL: load_2d_tfe:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: v_mov_b32_e32 v5, v0
|
|
; VERDE-NEXT: v_mov_b32_e32 v0, 0
|
|
; VERDE-NEXT: v_mov_b32_e32 v6, v1
|
|
; 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: image_load v[0:4], v[5:6], s[0:7] dmask:0xf unorm tfe
|
|
; VERDE-NEXT: s_mov_b32 s11, 0xf000
|
|
; VERDE-NEXT: s_mov_b32 s10, -1
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: buffer_store_dword v4, off, s[8:11], 0
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0) expcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; FIJI-LABEL: load_2d_tfe:
|
|
; FIJI: ; %bb.0: ; %main_body
|
|
; FIJI-NEXT: v_mov_b32_e32 v5, v0
|
|
; FIJI-NEXT: v_mov_b32_e32 v0, 0
|
|
; FIJI-NEXT: v_mov_b32_e32 v6, v1
|
|
; FIJI-NEXT: v_mov_b32_e32 v1, v0
|
|
; FIJI-NEXT: v_mov_b32_e32 v2, v0
|
|
; FIJI-NEXT: v_mov_b32_e32 v3, v0
|
|
; FIJI-NEXT: v_mov_b32_e32 v4, v0
|
|
; FIJI-NEXT: image_load v[0:4], v[5:6], s[0:7] dmask:0xf unorm tfe
|
|
; FIJI-NEXT: s_mov_b32 s11, 0xf000
|
|
; FIJI-NEXT: s_mov_b32 s10, -1
|
|
; FIJI-NEXT: s_waitcnt vmcnt(0)
|
|
; FIJI-NEXT: buffer_store_dword v4, off, s[8:11], 0
|
|
; FIJI-NEXT: s_waitcnt vmcnt(0)
|
|
; FIJI-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: load_2d_tfe:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: v_mov_b32_e32 v7, 0
|
|
; GFX6789-NEXT: v_mov_b32_e32 v6, v1
|
|
; GFX6789-NEXT: v_mov_b32_e32 v5, v0
|
|
; GFX6789-NEXT: v_mov_b32_e32 v8, v7
|
|
; GFX6789-NEXT: v_mov_b32_e32 v9, v7
|
|
; GFX6789-NEXT: v_mov_b32_e32 v10, v7
|
|
; GFX6789-NEXT: v_mov_b32_e32 v11, v7
|
|
; GFX6789-NEXT: v_mov_b32_e32 v0, v7
|
|
; GFX6789-NEXT: v_mov_b32_e32 v1, v8
|
|
; GFX6789-NEXT: v_mov_b32_e32 v2, v9
|
|
; GFX6789-NEXT: v_mov_b32_e32 v3, v10
|
|
; GFX6789-NEXT: v_mov_b32_e32 v4, v11
|
|
; GFX6789-NEXT: image_load v[0:4], v[5:6], s[0:7] dmask:0xf unorm tfe
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: global_store_dword v7, v4, s[8:9]
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; NOPRT-LABEL: load_2d_tfe:
|
|
; NOPRT: ; %bb.0: ; %main_body
|
|
; NOPRT-NEXT: v_mov_b32_e32 v4, 0
|
|
; NOPRT-NEXT: image_load v[0:4], v[0:1], s[0:7] dmask:0xf unorm tfe
|
|
; NOPRT-NEXT: v_mov_b32_e32 v5, 0
|
|
; NOPRT-NEXT: s_waitcnt vmcnt(0)
|
|
; NOPRT-NEXT: global_store_dword v5, v4, s[8:9]
|
|
; NOPRT-NEXT: s_waitcnt vmcnt(0)
|
|
; NOPRT-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: load_2d_tfe:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: v_mov_b32_e32 v7, 0 ; encoding: [0x80,0x02,0x0e,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v6, v1 ; encoding: [0x01,0x03,0x0c,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v5, v0 ; encoding: [0x00,0x03,0x0a,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v8, v7 ; encoding: [0x07,0x03,0x10,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v9, v7 ; encoding: [0x07,0x03,0x12,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v10, v7 ; encoding: [0x07,0x03,0x14,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v11, v7 ; encoding: [0x07,0x03,0x16,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v0, v7 ; encoding: [0x07,0x03,0x00,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v1, v8 ; encoding: [0x08,0x03,0x02,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v2, v9 ; encoding: [0x09,0x03,0x04,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v3, v10 ; encoding: [0x0a,0x03,0x06,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v4, v11 ; encoding: [0x0b,0x03,0x08,0x7e]
|
|
; GFX10-NEXT: image_load v[0:4], v[5:6], s[0:7] dmask:0xf dim:SQ_RSRC_IMG_2D unorm tfe ; encoding: [0x08,0x1f,0x01,0xf0,0x05,0x00,0x00,0x00]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: global_store_dword v7, v4, s[8:9] ; encoding: [0x00,0x80,0x70,0xdc,0x07,0x04,0x08,0x00]
|
|
; 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.load.2d.v4f32i32.i32(i32 15, i32 %s, i32 %t, <8 x i32> %rsrc, 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 <4 x float> @load_3d(<8 x i32> inreg %rsrc, i32 %s, i32 %t, i32 %r) {
|
|
; VERDE-LABEL: load_3d:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: image_load v[0:3], v[0:2], s[0:7] dmask:0xf unorm
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; FIJI-LABEL: load_3d:
|
|
; FIJI: ; %bb.0: ; %main_body
|
|
; FIJI-NEXT: image_load v[0:3], v[0:2], s[0:7] dmask:0xf unorm
|
|
; FIJI-NEXT: s_waitcnt vmcnt(0)
|
|
; FIJI-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: load_3d:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: image_load v[0:3], v[0:2], s[0:7] dmask:0xf unorm
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; NOPRT-LABEL: load_3d:
|
|
; NOPRT: ; %bb.0: ; %main_body
|
|
; NOPRT-NEXT: image_load v[0:3], v[0:2], s[0:7] dmask:0xf unorm
|
|
; NOPRT-NEXT: s_waitcnt vmcnt(0)
|
|
; NOPRT-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: load_3d:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: image_load v[0:3], v[0:2], s[0:7] dmask:0xf dim:SQ_RSRC_IMG_3D unorm ; encoding: [0x10,0x1f,0x00,0xf0,0x00,0x00,0x00,0x00]
|
|
; 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.load.3d.v4f32.i32(i32 15, i32 %s, i32 %t, i32 %r, <8 x i32> %rsrc, i32 0, i32 0)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @load_3d_tfe_lwe(<8 x i32> inreg %rsrc, i32 addrspace(1)* inreg %out, i32 %s, i32 %t, i32 %r) {
|
|
; VERDE-LABEL: load_3d_tfe_lwe:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: v_mov_b32_e32 v5, v0
|
|
; VERDE-NEXT: v_mov_b32_e32 v0, 0
|
|
; VERDE-NEXT: v_mov_b32_e32 v7, v2
|
|
; VERDE-NEXT: v_mov_b32_e32 v6, v1
|
|
; 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: image_load v[0:4], v[5:7], s[0:7] dmask:0xf unorm tfe lwe
|
|
; VERDE-NEXT: s_mov_b32 s11, 0xf000
|
|
; VERDE-NEXT: s_mov_b32 s10, -1
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: buffer_store_dword v4, off, s[8:11], 0
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0) expcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; FIJI-LABEL: load_3d_tfe_lwe:
|
|
; FIJI: ; %bb.0: ; %main_body
|
|
; FIJI-NEXT: v_mov_b32_e32 v5, v0
|
|
; FIJI-NEXT: v_mov_b32_e32 v0, 0
|
|
; FIJI-NEXT: v_mov_b32_e32 v7, v2
|
|
; FIJI-NEXT: v_mov_b32_e32 v6, v1
|
|
; FIJI-NEXT: v_mov_b32_e32 v1, v0
|
|
; FIJI-NEXT: v_mov_b32_e32 v2, v0
|
|
; FIJI-NEXT: v_mov_b32_e32 v3, v0
|
|
; FIJI-NEXT: v_mov_b32_e32 v4, v0
|
|
; FIJI-NEXT: image_load v[0:4], v[5:7], s[0:7] dmask:0xf unorm tfe lwe
|
|
; FIJI-NEXT: s_mov_b32 s11, 0xf000
|
|
; FIJI-NEXT: s_mov_b32 s10, -1
|
|
; FIJI-NEXT: s_waitcnt vmcnt(0)
|
|
; FIJI-NEXT: buffer_store_dword v4, off, s[8:11], 0
|
|
; FIJI-NEXT: s_waitcnt vmcnt(0)
|
|
; FIJI-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: load_3d_tfe_lwe:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: v_mov_b32_e32 v8, 0
|
|
; GFX6789-NEXT: v_mov_b32_e32 v7, v2
|
|
; GFX6789-NEXT: v_mov_b32_e32 v6, v1
|
|
; GFX6789-NEXT: v_mov_b32_e32 v5, v0
|
|
; GFX6789-NEXT: v_mov_b32_e32 v9, v8
|
|
; GFX6789-NEXT: v_mov_b32_e32 v10, v8
|
|
; GFX6789-NEXT: v_mov_b32_e32 v11, v8
|
|
; GFX6789-NEXT: v_mov_b32_e32 v12, v8
|
|
; GFX6789-NEXT: v_mov_b32_e32 v0, v8
|
|
; GFX6789-NEXT: v_mov_b32_e32 v1, v9
|
|
; GFX6789-NEXT: v_mov_b32_e32 v2, v10
|
|
; GFX6789-NEXT: v_mov_b32_e32 v3, v11
|
|
; GFX6789-NEXT: v_mov_b32_e32 v4, v12
|
|
; GFX6789-NEXT: image_load v[0:4], v[5:7], s[0:7] dmask:0xf unorm tfe lwe
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: global_store_dword v8, v4, s[8:9]
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; NOPRT-LABEL: load_3d_tfe_lwe:
|
|
; NOPRT: ; %bb.0: ; %main_body
|
|
; NOPRT-NEXT: v_mov_b32_e32 v4, 0
|
|
; NOPRT-NEXT: image_load v[0:4], v[0:2], s[0:7] dmask:0xf unorm tfe lwe
|
|
; NOPRT-NEXT: v_mov_b32_e32 v5, 0
|
|
; NOPRT-NEXT: s_waitcnt vmcnt(0)
|
|
; NOPRT-NEXT: global_store_dword v5, v4, s[8:9]
|
|
; NOPRT-NEXT: s_waitcnt vmcnt(0)
|
|
; NOPRT-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: load_3d_tfe_lwe:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: v_mov_b32_e32 v11, 0 ; encoding: [0x80,0x02,0x16,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v7, v2 ; encoding: [0x02,0x03,0x0e,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v6, v1 ; encoding: [0x01,0x03,0x0c,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v5, v0 ; encoding: [0x00,0x03,0x0a,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v12, v11 ; encoding: [0x0b,0x03,0x18,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v13, v11 ; encoding: [0x0b,0x03,0x1a,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v14, v11 ; encoding: [0x0b,0x03,0x1c,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v15, v11 ; encoding: [0x0b,0x03,0x1e,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v0, v11 ; encoding: [0x0b,0x03,0x00,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v1, v12 ; encoding: [0x0c,0x03,0x02,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v2, v13 ; encoding: [0x0d,0x03,0x04,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v3, v14 ; encoding: [0x0e,0x03,0x06,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v4, v15 ; encoding: [0x0f,0x03,0x08,0x7e]
|
|
; GFX10-NEXT: image_load v[0:4], v[5:7], s[0:7] dmask:0xf dim:SQ_RSRC_IMG_3D unorm tfe lwe ; encoding: [0x10,0x1f,0x03,0xf0,0x05,0x00,0x00,0x00]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: global_store_dword v11, v4, s[8:9] ; encoding: [0x00,0x80,0x70,0xdc,0x0b,0x04,0x08,0x00]
|
|
; 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.load.3d.v4f32i32.i32(i32 15, i32 %s, i32 %t, i32 %r, <8 x i32> %rsrc, i32 3, 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> @load_cube(<8 x i32> inreg %rsrc, i32 %s, i32 %t, i32 %slice) {
|
|
; VERDE-LABEL: load_cube:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: image_load v[0:3], v[0:2], s[0:7] dmask:0xf unorm da
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; FIJI-LABEL: load_cube:
|
|
; FIJI: ; %bb.0: ; %main_body
|
|
; FIJI-NEXT: image_load v[0:3], v[0:2], s[0:7] dmask:0xf unorm da
|
|
; FIJI-NEXT: s_waitcnt vmcnt(0)
|
|
; FIJI-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: load_cube:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: image_load v[0:3], v[0:2], s[0:7] dmask:0xf unorm da
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; NOPRT-LABEL: load_cube:
|
|
; NOPRT: ; %bb.0: ; %main_body
|
|
; NOPRT-NEXT: image_load v[0:3], v[0:2], s[0:7] dmask:0xf unorm da
|
|
; NOPRT-NEXT: s_waitcnt vmcnt(0)
|
|
; NOPRT-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: load_cube:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: image_load v[0:3], v[0:2], s[0:7] dmask:0xf dim:SQ_RSRC_IMG_CUBE unorm ; encoding: [0x18,0x1f,0x00,0xf0,0x00,0x00,0x00,0x00]
|
|
; 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.load.cube.v4f32.i32(i32 15, i32 %s, i32 %t, i32 %slice, <8 x i32> %rsrc, i32 0, i32 0)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @load_cube_lwe(<8 x i32> inreg %rsrc, i32 addrspace(1)* inreg %out, i32 %s, i32 %t, i32 %slice) {
|
|
; VERDE-LABEL: load_cube_lwe:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: v_mov_b32_e32 v5, v0
|
|
; VERDE-NEXT: v_mov_b32_e32 v0, 0
|
|
; VERDE-NEXT: v_mov_b32_e32 v7, v2
|
|
; VERDE-NEXT: v_mov_b32_e32 v6, v1
|
|
; 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: image_load v[0:4], v[5:7], s[0:7] dmask:0xf unorm lwe da
|
|
; VERDE-NEXT: s_mov_b32 s11, 0xf000
|
|
; VERDE-NEXT: s_mov_b32 s10, -1
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: buffer_store_dword v4, off, s[8:11], 0
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0) expcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; FIJI-LABEL: load_cube_lwe:
|
|
; FIJI: ; %bb.0: ; %main_body
|
|
; FIJI-NEXT: v_mov_b32_e32 v5, v0
|
|
; FIJI-NEXT: v_mov_b32_e32 v0, 0
|
|
; FIJI-NEXT: v_mov_b32_e32 v7, v2
|
|
; FIJI-NEXT: v_mov_b32_e32 v6, v1
|
|
; FIJI-NEXT: v_mov_b32_e32 v1, v0
|
|
; FIJI-NEXT: v_mov_b32_e32 v2, v0
|
|
; FIJI-NEXT: v_mov_b32_e32 v3, v0
|
|
; FIJI-NEXT: v_mov_b32_e32 v4, v0
|
|
; FIJI-NEXT: image_load v[0:4], v[5:7], s[0:7] dmask:0xf unorm lwe da
|
|
; FIJI-NEXT: s_mov_b32 s11, 0xf000
|
|
; FIJI-NEXT: s_mov_b32 s10, -1
|
|
; FIJI-NEXT: s_waitcnt vmcnt(0)
|
|
; FIJI-NEXT: buffer_store_dword v4, off, s[8:11], 0
|
|
; FIJI-NEXT: s_waitcnt vmcnt(0)
|
|
; FIJI-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: load_cube_lwe:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: v_mov_b32_e32 v8, 0
|
|
; GFX6789-NEXT: v_mov_b32_e32 v7, v2
|
|
; GFX6789-NEXT: v_mov_b32_e32 v6, v1
|
|
; GFX6789-NEXT: v_mov_b32_e32 v5, v0
|
|
; GFX6789-NEXT: v_mov_b32_e32 v9, v8
|
|
; GFX6789-NEXT: v_mov_b32_e32 v10, v8
|
|
; GFX6789-NEXT: v_mov_b32_e32 v11, v8
|
|
; GFX6789-NEXT: v_mov_b32_e32 v12, v8
|
|
; GFX6789-NEXT: v_mov_b32_e32 v0, v8
|
|
; GFX6789-NEXT: v_mov_b32_e32 v1, v9
|
|
; GFX6789-NEXT: v_mov_b32_e32 v2, v10
|
|
; GFX6789-NEXT: v_mov_b32_e32 v3, v11
|
|
; GFX6789-NEXT: v_mov_b32_e32 v4, v12
|
|
; GFX6789-NEXT: image_load v[0:4], v[5:7], s[0:7] dmask:0xf unorm lwe da
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: global_store_dword v8, v4, s[8:9]
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; NOPRT-LABEL: load_cube_lwe:
|
|
; NOPRT: ; %bb.0: ; %main_body
|
|
; NOPRT-NEXT: v_mov_b32_e32 v4, 0
|
|
; NOPRT-NEXT: image_load v[0:4], v[0:2], s[0:7] dmask:0xf unorm lwe da
|
|
; NOPRT-NEXT: v_mov_b32_e32 v5, 0
|
|
; NOPRT-NEXT: s_waitcnt vmcnt(0)
|
|
; NOPRT-NEXT: global_store_dword v5, v4, s[8:9]
|
|
; NOPRT-NEXT: s_waitcnt vmcnt(0)
|
|
; NOPRT-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: load_cube_lwe:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: v_mov_b32_e32 v11, 0 ; encoding: [0x80,0x02,0x16,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v7, v2 ; encoding: [0x02,0x03,0x0e,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v6, v1 ; encoding: [0x01,0x03,0x0c,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v5, v0 ; encoding: [0x00,0x03,0x0a,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v12, v11 ; encoding: [0x0b,0x03,0x18,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v13, v11 ; encoding: [0x0b,0x03,0x1a,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v14, v11 ; encoding: [0x0b,0x03,0x1c,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v15, v11 ; encoding: [0x0b,0x03,0x1e,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v0, v11 ; encoding: [0x0b,0x03,0x00,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v1, v12 ; encoding: [0x0c,0x03,0x02,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v2, v13 ; encoding: [0x0d,0x03,0x04,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v3, v14 ; encoding: [0x0e,0x03,0x06,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v4, v15 ; encoding: [0x0f,0x03,0x08,0x7e]
|
|
; GFX10-NEXT: image_load v[0:4], v[5:7], s[0:7] dmask:0xf dim:SQ_RSRC_IMG_CUBE unorm lwe ; encoding: [0x18,0x1f,0x02,0xf0,0x05,0x00,0x00,0x00]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: global_store_dword v11, v4, s[8:9] ; encoding: [0x00,0x80,0x70,0xdc,0x0b,0x04,0x08,0x00]
|
|
; 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.load.cube.v4f32i32.i32(i32 15, i32 %s, i32 %t, i32 %slice, <8 x i32> %rsrc, 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> @load_1darray(<8 x i32> inreg %rsrc, i32 %s, i32 %slice) {
|
|
; VERDE-LABEL: load_1darray:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: image_load v[0:3], v[0:1], s[0:7] dmask:0xf unorm da
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; FIJI-LABEL: load_1darray:
|
|
; FIJI: ; %bb.0: ; %main_body
|
|
; FIJI-NEXT: image_load v[0:3], v[0:1], s[0:7] dmask:0xf unorm da
|
|
; FIJI-NEXT: s_waitcnt vmcnt(0)
|
|
; FIJI-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: load_1darray:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: image_load v[0:3], v[0:1], s[0:7] dmask:0xf unorm da
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; NOPRT-LABEL: load_1darray:
|
|
; NOPRT: ; %bb.0: ; %main_body
|
|
; NOPRT-NEXT: image_load v[0:3], v[0:1], s[0:7] dmask:0xf unorm da
|
|
; NOPRT-NEXT: s_waitcnt vmcnt(0)
|
|
; NOPRT-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: load_1darray:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: image_load v[0:3], v[0:1], s[0:7] dmask:0xf dim:SQ_RSRC_IMG_1D_ARRAY unorm ; encoding: [0x20,0x1f,0x00,0xf0,0x00,0x00,0x00,0x00]
|
|
; 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.load.1darray.v4f32.i32(i32 15, i32 %s, i32 %slice, <8 x i32> %rsrc, i32 0, i32 0)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @load_1darray_tfe(<8 x i32> inreg %rsrc, i32 addrspace(1)* inreg %out, i32 %s, i32 %slice) {
|
|
; VERDE-LABEL: load_1darray_tfe:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: v_mov_b32_e32 v5, v0
|
|
; VERDE-NEXT: v_mov_b32_e32 v0, 0
|
|
; VERDE-NEXT: v_mov_b32_e32 v6, v1
|
|
; 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: image_load v[0:4], v[5:6], s[0:7] dmask:0xf unorm tfe da
|
|
; VERDE-NEXT: s_mov_b32 s11, 0xf000
|
|
; VERDE-NEXT: s_mov_b32 s10, -1
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: buffer_store_dword v4, off, s[8:11], 0
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0) expcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; FIJI-LABEL: load_1darray_tfe:
|
|
; FIJI: ; %bb.0: ; %main_body
|
|
; FIJI-NEXT: v_mov_b32_e32 v5, v0
|
|
; FIJI-NEXT: v_mov_b32_e32 v0, 0
|
|
; FIJI-NEXT: v_mov_b32_e32 v6, v1
|
|
; FIJI-NEXT: v_mov_b32_e32 v1, v0
|
|
; FIJI-NEXT: v_mov_b32_e32 v2, v0
|
|
; FIJI-NEXT: v_mov_b32_e32 v3, v0
|
|
; FIJI-NEXT: v_mov_b32_e32 v4, v0
|
|
; FIJI-NEXT: image_load v[0:4], v[5:6], s[0:7] dmask:0xf unorm tfe da
|
|
; FIJI-NEXT: s_mov_b32 s11, 0xf000
|
|
; FIJI-NEXT: s_mov_b32 s10, -1
|
|
; FIJI-NEXT: s_waitcnt vmcnt(0)
|
|
; FIJI-NEXT: buffer_store_dword v4, off, s[8:11], 0
|
|
; FIJI-NEXT: s_waitcnt vmcnt(0)
|
|
; FIJI-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: load_1darray_tfe:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: v_mov_b32_e32 v7, 0
|
|
; GFX6789-NEXT: v_mov_b32_e32 v6, v1
|
|
; GFX6789-NEXT: v_mov_b32_e32 v5, v0
|
|
; GFX6789-NEXT: v_mov_b32_e32 v8, v7
|
|
; GFX6789-NEXT: v_mov_b32_e32 v9, v7
|
|
; GFX6789-NEXT: v_mov_b32_e32 v10, v7
|
|
; GFX6789-NEXT: v_mov_b32_e32 v11, v7
|
|
; GFX6789-NEXT: v_mov_b32_e32 v0, v7
|
|
; GFX6789-NEXT: v_mov_b32_e32 v1, v8
|
|
; GFX6789-NEXT: v_mov_b32_e32 v2, v9
|
|
; GFX6789-NEXT: v_mov_b32_e32 v3, v10
|
|
; GFX6789-NEXT: v_mov_b32_e32 v4, v11
|
|
; GFX6789-NEXT: image_load v[0:4], v[5:6], s[0:7] dmask:0xf unorm tfe da
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: global_store_dword v7, v4, s[8:9]
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; NOPRT-LABEL: load_1darray_tfe:
|
|
; NOPRT: ; %bb.0: ; %main_body
|
|
; NOPRT-NEXT: v_mov_b32_e32 v4, 0
|
|
; NOPRT-NEXT: image_load v[0:4], v[0:1], s[0:7] dmask:0xf unorm tfe da
|
|
; NOPRT-NEXT: v_mov_b32_e32 v5, 0
|
|
; NOPRT-NEXT: s_waitcnt vmcnt(0)
|
|
; NOPRT-NEXT: global_store_dword v5, v4, s[8:9]
|
|
; NOPRT-NEXT: s_waitcnt vmcnt(0)
|
|
; NOPRT-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: load_1darray_tfe:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: v_mov_b32_e32 v7, 0 ; encoding: [0x80,0x02,0x0e,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v6, v1 ; encoding: [0x01,0x03,0x0c,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v5, v0 ; encoding: [0x00,0x03,0x0a,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v8, v7 ; encoding: [0x07,0x03,0x10,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v9, v7 ; encoding: [0x07,0x03,0x12,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v10, v7 ; encoding: [0x07,0x03,0x14,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v11, v7 ; encoding: [0x07,0x03,0x16,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v0, v7 ; encoding: [0x07,0x03,0x00,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v1, v8 ; encoding: [0x08,0x03,0x02,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v2, v9 ; encoding: [0x09,0x03,0x04,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v3, v10 ; encoding: [0x0a,0x03,0x06,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v4, v11 ; encoding: [0x0b,0x03,0x08,0x7e]
|
|
; GFX10-NEXT: image_load v[0:4], v[5:6], s[0:7] dmask:0xf dim:SQ_RSRC_IMG_1D_ARRAY unorm tfe ; encoding: [0x20,0x1f,0x01,0xf0,0x05,0x00,0x00,0x00]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: global_store_dword v7, v4, s[8:9] ; encoding: [0x00,0x80,0x70,0xdc,0x07,0x04,0x08,0x00]
|
|
; 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.load.1darray.v4f32i32.i32(i32 15, i32 %s, i32 %slice, <8 x i32> %rsrc, 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 <4 x float> @load_2darray(<8 x i32> inreg %rsrc, i32 %s, i32 %t, i32 %slice) {
|
|
; VERDE-LABEL: load_2darray:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: image_load v[0:3], v[0:2], s[0:7] dmask:0xf unorm da
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; FIJI-LABEL: load_2darray:
|
|
; FIJI: ; %bb.0: ; %main_body
|
|
; FIJI-NEXT: image_load v[0:3], v[0:2], s[0:7] dmask:0xf unorm da
|
|
; FIJI-NEXT: s_waitcnt vmcnt(0)
|
|
; FIJI-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: load_2darray:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: image_load v[0:3], v[0:2], s[0:7] dmask:0xf unorm da
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; NOPRT-LABEL: load_2darray:
|
|
; NOPRT: ; %bb.0: ; %main_body
|
|
; NOPRT-NEXT: image_load v[0:3], v[0:2], s[0:7] dmask:0xf unorm da
|
|
; NOPRT-NEXT: s_waitcnt vmcnt(0)
|
|
; NOPRT-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: load_2darray:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: image_load v[0:3], v[0:2], s[0:7] dmask:0xf dim:SQ_RSRC_IMG_2D_ARRAY unorm ; encoding: [0x28,0x1f,0x00,0xf0,0x00,0x00,0x00,0x00]
|
|
; 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.load.2darray.v4f32.i32(i32 15, i32 %s, i32 %t, i32 %slice, <8 x i32> %rsrc, i32 0, i32 0)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @load_2darray_lwe(<8 x i32> inreg %rsrc, i32 addrspace(1)* inreg %out, i32 %s, i32 %t, i32 %slice) {
|
|
; VERDE-LABEL: load_2darray_lwe:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: v_mov_b32_e32 v5, v0
|
|
; VERDE-NEXT: v_mov_b32_e32 v0, 0
|
|
; VERDE-NEXT: v_mov_b32_e32 v7, v2
|
|
; VERDE-NEXT: v_mov_b32_e32 v6, v1
|
|
; 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: image_load v[0:4], v[5:7], s[0:7] dmask:0xf unorm lwe da
|
|
; VERDE-NEXT: s_mov_b32 s11, 0xf000
|
|
; VERDE-NEXT: s_mov_b32 s10, -1
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: buffer_store_dword v4, off, s[8:11], 0
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0) expcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; FIJI-LABEL: load_2darray_lwe:
|
|
; FIJI: ; %bb.0: ; %main_body
|
|
; FIJI-NEXT: v_mov_b32_e32 v5, v0
|
|
; FIJI-NEXT: v_mov_b32_e32 v0, 0
|
|
; FIJI-NEXT: v_mov_b32_e32 v7, v2
|
|
; FIJI-NEXT: v_mov_b32_e32 v6, v1
|
|
; FIJI-NEXT: v_mov_b32_e32 v1, v0
|
|
; FIJI-NEXT: v_mov_b32_e32 v2, v0
|
|
; FIJI-NEXT: v_mov_b32_e32 v3, v0
|
|
; FIJI-NEXT: v_mov_b32_e32 v4, v0
|
|
; FIJI-NEXT: image_load v[0:4], v[5:7], s[0:7] dmask:0xf unorm lwe da
|
|
; FIJI-NEXT: s_mov_b32 s11, 0xf000
|
|
; FIJI-NEXT: s_mov_b32 s10, -1
|
|
; FIJI-NEXT: s_waitcnt vmcnt(0)
|
|
; FIJI-NEXT: buffer_store_dword v4, off, s[8:11], 0
|
|
; FIJI-NEXT: s_waitcnt vmcnt(0)
|
|
; FIJI-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: load_2darray_lwe:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: v_mov_b32_e32 v8, 0
|
|
; GFX6789-NEXT: v_mov_b32_e32 v7, v2
|
|
; GFX6789-NEXT: v_mov_b32_e32 v6, v1
|
|
; GFX6789-NEXT: v_mov_b32_e32 v5, v0
|
|
; GFX6789-NEXT: v_mov_b32_e32 v9, v8
|
|
; GFX6789-NEXT: v_mov_b32_e32 v10, v8
|
|
; GFX6789-NEXT: v_mov_b32_e32 v11, v8
|
|
; GFX6789-NEXT: v_mov_b32_e32 v12, v8
|
|
; GFX6789-NEXT: v_mov_b32_e32 v0, v8
|
|
; GFX6789-NEXT: v_mov_b32_e32 v1, v9
|
|
; GFX6789-NEXT: v_mov_b32_e32 v2, v10
|
|
; GFX6789-NEXT: v_mov_b32_e32 v3, v11
|
|
; GFX6789-NEXT: v_mov_b32_e32 v4, v12
|
|
; GFX6789-NEXT: image_load v[0:4], v[5:7], s[0:7] dmask:0xf unorm lwe da
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: global_store_dword v8, v4, s[8:9]
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; NOPRT-LABEL: load_2darray_lwe:
|
|
; NOPRT: ; %bb.0: ; %main_body
|
|
; NOPRT-NEXT: v_mov_b32_e32 v4, 0
|
|
; NOPRT-NEXT: image_load v[0:4], v[0:2], s[0:7] dmask:0xf unorm lwe da
|
|
; NOPRT-NEXT: v_mov_b32_e32 v5, 0
|
|
; NOPRT-NEXT: s_waitcnt vmcnt(0)
|
|
; NOPRT-NEXT: global_store_dword v5, v4, s[8:9]
|
|
; NOPRT-NEXT: s_waitcnt vmcnt(0)
|
|
; NOPRT-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: load_2darray_lwe:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: v_mov_b32_e32 v11, 0 ; encoding: [0x80,0x02,0x16,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v7, v2 ; encoding: [0x02,0x03,0x0e,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v6, v1 ; encoding: [0x01,0x03,0x0c,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v5, v0 ; encoding: [0x00,0x03,0x0a,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v12, v11 ; encoding: [0x0b,0x03,0x18,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v13, v11 ; encoding: [0x0b,0x03,0x1a,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v14, v11 ; encoding: [0x0b,0x03,0x1c,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v15, v11 ; encoding: [0x0b,0x03,0x1e,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v0, v11 ; encoding: [0x0b,0x03,0x00,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v1, v12 ; encoding: [0x0c,0x03,0x02,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v2, v13 ; encoding: [0x0d,0x03,0x04,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v3, v14 ; encoding: [0x0e,0x03,0x06,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v4, v15 ; encoding: [0x0f,0x03,0x08,0x7e]
|
|
; GFX10-NEXT: image_load v[0:4], v[5:7], s[0:7] dmask:0xf dim:SQ_RSRC_IMG_2D_ARRAY unorm lwe ; encoding: [0x28,0x1f,0x02,0xf0,0x05,0x00,0x00,0x00]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: global_store_dword v11, v4, s[8:9] ; encoding: [0x00,0x80,0x70,0xdc,0x0b,0x04,0x08,0x00]
|
|
; 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.load.2darray.v4f32i32.i32(i32 15, i32 %s, i32 %t, i32 %slice, <8 x i32> %rsrc, 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> @load_2dmsaa(<8 x i32> inreg %rsrc, i32 %s, i32 %t, i32 %fragid) {
|
|
; VERDE-LABEL: load_2dmsaa:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: image_load v[0:3], v[0:2], s[0:7] dmask:0xf unorm
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; FIJI-LABEL: load_2dmsaa:
|
|
; FIJI: ; %bb.0: ; %main_body
|
|
; FIJI-NEXT: image_load v[0:3], v[0:2], s[0:7] dmask:0xf unorm
|
|
; FIJI-NEXT: s_waitcnt vmcnt(0)
|
|
; FIJI-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: load_2dmsaa:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: image_load v[0:3], v[0:2], s[0:7] dmask:0xf unorm
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; NOPRT-LABEL: load_2dmsaa:
|
|
; NOPRT: ; %bb.0: ; %main_body
|
|
; NOPRT-NEXT: image_load v[0:3], v[0:2], s[0:7] dmask:0xf unorm
|
|
; NOPRT-NEXT: s_waitcnt vmcnt(0)
|
|
; NOPRT-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: load_2dmsaa:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: image_load v[0:3], v[0:2], s[0:7] dmask:0xf dim:SQ_RSRC_IMG_2D_MSAA unorm ; encoding: [0x30,0x1f,0x00,0xf0,0x00,0x00,0x00,0x00]
|
|
; 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.load.2dmsaa.v4f32.i32(i32 15, i32 %s, i32 %t, i32 %fragid, <8 x i32> %rsrc, i32 0, i32 0)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @load_2dmsaa_both(<8 x i32> inreg %rsrc, i32 addrspace(1)* inreg %out, i32 %s, i32 %t, i32 %fragid) {
|
|
; VERDE-LABEL: load_2dmsaa_both:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: v_mov_b32_e32 v5, v0
|
|
; VERDE-NEXT: v_mov_b32_e32 v0, 0
|
|
; VERDE-NEXT: v_mov_b32_e32 v7, v2
|
|
; VERDE-NEXT: v_mov_b32_e32 v6, v1
|
|
; 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: image_load v[0:4], v[5:7], s[0:7] dmask:0xf unorm tfe lwe
|
|
; VERDE-NEXT: s_mov_b32 s11, 0xf000
|
|
; VERDE-NEXT: s_mov_b32 s10, -1
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: buffer_store_dword v4, off, s[8:11], 0
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0) expcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; FIJI-LABEL: load_2dmsaa_both:
|
|
; FIJI: ; %bb.0: ; %main_body
|
|
; FIJI-NEXT: v_mov_b32_e32 v5, v0
|
|
; FIJI-NEXT: v_mov_b32_e32 v0, 0
|
|
; FIJI-NEXT: v_mov_b32_e32 v7, v2
|
|
; FIJI-NEXT: v_mov_b32_e32 v6, v1
|
|
; FIJI-NEXT: v_mov_b32_e32 v1, v0
|
|
; FIJI-NEXT: v_mov_b32_e32 v2, v0
|
|
; FIJI-NEXT: v_mov_b32_e32 v3, v0
|
|
; FIJI-NEXT: v_mov_b32_e32 v4, v0
|
|
; FIJI-NEXT: image_load v[0:4], v[5:7], s[0:7] dmask:0xf unorm tfe lwe
|
|
; FIJI-NEXT: s_mov_b32 s11, 0xf000
|
|
; FIJI-NEXT: s_mov_b32 s10, -1
|
|
; FIJI-NEXT: s_waitcnt vmcnt(0)
|
|
; FIJI-NEXT: buffer_store_dword v4, off, s[8:11], 0
|
|
; FIJI-NEXT: s_waitcnt vmcnt(0)
|
|
; FIJI-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: load_2dmsaa_both:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: v_mov_b32_e32 v8, 0
|
|
; GFX6789-NEXT: v_mov_b32_e32 v7, v2
|
|
; GFX6789-NEXT: v_mov_b32_e32 v6, v1
|
|
; GFX6789-NEXT: v_mov_b32_e32 v5, v0
|
|
; GFX6789-NEXT: v_mov_b32_e32 v9, v8
|
|
; GFX6789-NEXT: v_mov_b32_e32 v10, v8
|
|
; GFX6789-NEXT: v_mov_b32_e32 v11, v8
|
|
; GFX6789-NEXT: v_mov_b32_e32 v12, v8
|
|
; GFX6789-NEXT: v_mov_b32_e32 v0, v8
|
|
; GFX6789-NEXT: v_mov_b32_e32 v1, v9
|
|
; GFX6789-NEXT: v_mov_b32_e32 v2, v10
|
|
; GFX6789-NEXT: v_mov_b32_e32 v3, v11
|
|
; GFX6789-NEXT: v_mov_b32_e32 v4, v12
|
|
; GFX6789-NEXT: image_load v[0:4], v[5:7], s[0:7] dmask:0xf unorm tfe lwe
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: global_store_dword v8, v4, s[8:9]
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; NOPRT-LABEL: load_2dmsaa_both:
|
|
; NOPRT: ; %bb.0: ; %main_body
|
|
; NOPRT-NEXT: v_mov_b32_e32 v4, 0
|
|
; NOPRT-NEXT: image_load v[0:4], v[0:2], s[0:7] dmask:0xf unorm tfe lwe
|
|
; NOPRT-NEXT: v_mov_b32_e32 v5, 0
|
|
; NOPRT-NEXT: s_waitcnt vmcnt(0)
|
|
; NOPRT-NEXT: global_store_dword v5, v4, s[8:9]
|
|
; NOPRT-NEXT: s_waitcnt vmcnt(0)
|
|
; NOPRT-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: load_2dmsaa_both:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: v_mov_b32_e32 v11, 0 ; encoding: [0x80,0x02,0x16,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v7, v2 ; encoding: [0x02,0x03,0x0e,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v6, v1 ; encoding: [0x01,0x03,0x0c,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v5, v0 ; encoding: [0x00,0x03,0x0a,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v12, v11 ; encoding: [0x0b,0x03,0x18,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v13, v11 ; encoding: [0x0b,0x03,0x1a,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v14, v11 ; encoding: [0x0b,0x03,0x1c,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v15, v11 ; encoding: [0x0b,0x03,0x1e,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v0, v11 ; encoding: [0x0b,0x03,0x00,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v1, v12 ; encoding: [0x0c,0x03,0x02,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v2, v13 ; encoding: [0x0d,0x03,0x04,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v3, v14 ; encoding: [0x0e,0x03,0x06,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v4, v15 ; encoding: [0x0f,0x03,0x08,0x7e]
|
|
; GFX10-NEXT: image_load v[0:4], v[5:7], s[0:7] dmask:0xf dim:SQ_RSRC_IMG_2D_MSAA unorm tfe lwe ; encoding: [0x30,0x1f,0x03,0xf0,0x05,0x00,0x00,0x00]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: global_store_dword v11, v4, s[8:9] ; encoding: [0x00,0x80,0x70,0xdc,0x0b,0x04,0x08,0x00]
|
|
; 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.load.2dmsaa.v4f32i32.i32(i32 15, i32 %s, i32 %t, i32 %fragid, <8 x i32> %rsrc, i32 3, 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> @load_2darraymsaa(<8 x i32> inreg %rsrc, i32 %s, i32 %t, i32 %slice, i32 %fragid) {
|
|
; VERDE-LABEL: load_2darraymsaa:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: image_load v[0:3], v[0:3], s[0:7] dmask:0xf unorm da
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; FIJI-LABEL: load_2darraymsaa:
|
|
; FIJI: ; %bb.0: ; %main_body
|
|
; FIJI-NEXT: image_load v[0:3], v[0:3], s[0:7] dmask:0xf unorm da
|
|
; FIJI-NEXT: s_waitcnt vmcnt(0)
|
|
; FIJI-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: load_2darraymsaa:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: image_load v[0:3], v[0:3], s[0:7] dmask:0xf unorm da
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; NOPRT-LABEL: load_2darraymsaa:
|
|
; NOPRT: ; %bb.0: ; %main_body
|
|
; NOPRT-NEXT: image_load v[0:3], v[0:3], s[0:7] dmask:0xf unorm da
|
|
; NOPRT-NEXT: s_waitcnt vmcnt(0)
|
|
; NOPRT-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: load_2darraymsaa:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: image_load v[0:3], v[0:3], s[0:7] dmask:0xf dim:SQ_RSRC_IMG_2D_MSAA_ARRAY unorm ; encoding: [0x38,0x1f,0x00,0xf0,0x00,0x00,0x00,0x00]
|
|
; 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.load.2darraymsaa.v4f32.i32(i32 15, i32 %s, i32 %t, i32 %slice, i32 %fragid, <8 x i32> %rsrc, i32 0, i32 0)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @load_2darraymsaa_tfe(<8 x i32> inreg %rsrc, i32 addrspace(1)* inreg %out, i32 %s, i32 %t, i32 %slice, i32 %fragid) {
|
|
; VERDE-LABEL: load_2darraymsaa_tfe:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: v_mov_b32_e32 v5, v0
|
|
; VERDE-NEXT: v_mov_b32_e32 v0, 0
|
|
; VERDE-NEXT: v_mov_b32_e32 v8, v3
|
|
; VERDE-NEXT: v_mov_b32_e32 v7, v2
|
|
; VERDE-NEXT: v_mov_b32_e32 v6, v1
|
|
; 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: image_load v[0:4], v[5:8], s[0:7] dmask:0xf unorm tfe da
|
|
; VERDE-NEXT: s_mov_b32 s11, 0xf000
|
|
; VERDE-NEXT: s_mov_b32 s10, -1
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: buffer_store_dword v4, off, s[8:11], 0
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0) expcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; FIJI-LABEL: load_2darraymsaa_tfe:
|
|
; FIJI: ; %bb.0: ; %main_body
|
|
; FIJI-NEXT: v_mov_b32_e32 v5, v0
|
|
; FIJI-NEXT: v_mov_b32_e32 v0, 0
|
|
; FIJI-NEXT: v_mov_b32_e32 v8, v3
|
|
; FIJI-NEXT: v_mov_b32_e32 v7, v2
|
|
; FIJI-NEXT: v_mov_b32_e32 v6, v1
|
|
; FIJI-NEXT: v_mov_b32_e32 v1, v0
|
|
; FIJI-NEXT: v_mov_b32_e32 v2, v0
|
|
; FIJI-NEXT: v_mov_b32_e32 v3, v0
|
|
; FIJI-NEXT: v_mov_b32_e32 v4, v0
|
|
; FIJI-NEXT: image_load v[0:4], v[5:8], s[0:7] dmask:0xf unorm tfe da
|
|
; FIJI-NEXT: s_mov_b32 s11, 0xf000
|
|
; FIJI-NEXT: s_mov_b32 s10, -1
|
|
; FIJI-NEXT: s_waitcnt vmcnt(0)
|
|
; FIJI-NEXT: buffer_store_dword v4, off, s[8:11], 0
|
|
; FIJI-NEXT: s_waitcnt vmcnt(0)
|
|
; FIJI-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: load_2darraymsaa_tfe:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: v_mov_b32_e32 v9, 0
|
|
; GFX6789-NEXT: v_mov_b32_e32 v8, v3
|
|
; GFX6789-NEXT: v_mov_b32_e32 v7, v2
|
|
; GFX6789-NEXT: v_mov_b32_e32 v6, v1
|
|
; GFX6789-NEXT: v_mov_b32_e32 v5, v0
|
|
; GFX6789-NEXT: v_mov_b32_e32 v10, v9
|
|
; GFX6789-NEXT: v_mov_b32_e32 v11, v9
|
|
; GFX6789-NEXT: v_mov_b32_e32 v12, v9
|
|
; GFX6789-NEXT: v_mov_b32_e32 v13, v9
|
|
; 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: v_mov_b32_e32 v3, v12
|
|
; GFX6789-NEXT: v_mov_b32_e32 v4, v13
|
|
; GFX6789-NEXT: image_load v[0:4], v[5:8], s[0:7] dmask:0xf unorm tfe da
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: global_store_dword v9, v4, s[8:9]
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; NOPRT-LABEL: load_2darraymsaa_tfe:
|
|
; NOPRT: ; %bb.0: ; %main_body
|
|
; NOPRT-NEXT: v_mov_b32_e32 v4, 0
|
|
; NOPRT-NEXT: image_load v[0:4], v[0:3], s[0:7] dmask:0xf unorm tfe da
|
|
; NOPRT-NEXT: v_mov_b32_e32 v5, 0
|
|
; NOPRT-NEXT: s_waitcnt vmcnt(0)
|
|
; NOPRT-NEXT: global_store_dword v5, v4, s[8:9]
|
|
; NOPRT-NEXT: s_waitcnt vmcnt(0)
|
|
; NOPRT-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: load_2darraymsaa_tfe:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: v_mov_b32_e32 v9, 0 ; encoding: [0x80,0x02,0x12,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v8, v3 ; encoding: [0x03,0x03,0x10,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v7, v2 ; encoding: [0x02,0x03,0x0e,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v6, v1 ; encoding: [0x01,0x03,0x0c,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v5, v0 ; encoding: [0x00,0x03,0x0a,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v10, v9 ; encoding: [0x09,0x03,0x14,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v11, v9 ; encoding: [0x09,0x03,0x16,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v12, v9 ; encoding: [0x09,0x03,0x18,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v13, v9 ; encoding: [0x09,0x03,0x1a,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v0, v9 ; encoding: [0x09,0x03,0x00,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v1, v10 ; encoding: [0x0a,0x03,0x02,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v2, v11 ; encoding: [0x0b,0x03,0x04,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v3, v12 ; encoding: [0x0c,0x03,0x06,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v4, v13 ; encoding: [0x0d,0x03,0x08,0x7e]
|
|
; GFX10-NEXT: image_load v[0:4], v[5:8], s[0:7] dmask:0xf dim:SQ_RSRC_IMG_2D_MSAA_ARRAY unorm tfe ; encoding: [0x38,0x1f,0x01,0xf0,0x05,0x00,0x00,0x00]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: global_store_dword v9, v4, s[8:9] ; encoding: [0x00,0x80,0x70,0xdc,0x09,0x04,0x08,0x00]
|
|
; 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.load.2darraymsaa.v4f32i32.i32(i32 15, i32 %s, i32 %t, i32 %slice, i32 %fragid, <8 x i32> %rsrc, 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 <4 x float> @load_mip_1d(<8 x i32> inreg %rsrc, i32 %s, i32 %mip) {
|
|
; VERDE-LABEL: load_mip_1d:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: image_load_mip v[0:3], v[0:1], s[0:7] dmask:0xf unorm
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; FIJI-LABEL: load_mip_1d:
|
|
; FIJI: ; %bb.0: ; %main_body
|
|
; FIJI-NEXT: image_load_mip v[0:3], v[0:1], s[0:7] dmask:0xf unorm
|
|
; FIJI-NEXT: s_waitcnt vmcnt(0)
|
|
; FIJI-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: load_mip_1d:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: image_load_mip v[0:3], v[0:1], s[0:7] dmask:0xf unorm
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; NOPRT-LABEL: load_mip_1d:
|
|
; NOPRT: ; %bb.0: ; %main_body
|
|
; NOPRT-NEXT: image_load_mip v[0:3], v[0:1], s[0:7] dmask:0xf unorm
|
|
; NOPRT-NEXT: s_waitcnt vmcnt(0)
|
|
; NOPRT-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: load_mip_1d:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: image_load_mip v[0:3], v[0:1], s[0:7] dmask:0xf dim:SQ_RSRC_IMG_1D unorm ; encoding: [0x00,0x1f,0x04,0xf0,0x00,0x00,0x00,0x00]
|
|
; 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.load.mip.1d.v4f32.i32(i32 15, i32 %s, i32 %mip, <8 x i32> %rsrc, i32 0, i32 0)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @load_mip_1d_lwe(<8 x i32> inreg %rsrc, i32 addrspace(1)* inreg %out, i32 %s, i32 %mip) {
|
|
; VERDE-LABEL: load_mip_1d_lwe:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: v_mov_b32_e32 v5, v0
|
|
; VERDE-NEXT: v_mov_b32_e32 v0, 0
|
|
; VERDE-NEXT: v_mov_b32_e32 v6, v1
|
|
; 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: image_load_mip v[0:4], v[5:6], s[0:7] dmask:0xf unorm lwe
|
|
; VERDE-NEXT: s_mov_b32 s11, 0xf000
|
|
; VERDE-NEXT: s_mov_b32 s10, -1
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: buffer_store_dword v4, off, s[8:11], 0
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0) expcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; FIJI-LABEL: load_mip_1d_lwe:
|
|
; FIJI: ; %bb.0: ; %main_body
|
|
; FIJI-NEXT: v_mov_b32_e32 v5, v0
|
|
; FIJI-NEXT: v_mov_b32_e32 v0, 0
|
|
; FIJI-NEXT: v_mov_b32_e32 v6, v1
|
|
; FIJI-NEXT: v_mov_b32_e32 v1, v0
|
|
; FIJI-NEXT: v_mov_b32_e32 v2, v0
|
|
; FIJI-NEXT: v_mov_b32_e32 v3, v0
|
|
; FIJI-NEXT: v_mov_b32_e32 v4, v0
|
|
; FIJI-NEXT: image_load_mip v[0:4], v[5:6], s[0:7] dmask:0xf unorm lwe
|
|
; FIJI-NEXT: s_mov_b32 s11, 0xf000
|
|
; FIJI-NEXT: s_mov_b32 s10, -1
|
|
; FIJI-NEXT: s_waitcnt vmcnt(0)
|
|
; FIJI-NEXT: buffer_store_dword v4, off, s[8:11], 0
|
|
; FIJI-NEXT: s_waitcnt vmcnt(0)
|
|
; FIJI-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: load_mip_1d_lwe:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: v_mov_b32_e32 v7, 0
|
|
; GFX6789-NEXT: v_mov_b32_e32 v6, v1
|
|
; GFX6789-NEXT: v_mov_b32_e32 v5, v0
|
|
; GFX6789-NEXT: v_mov_b32_e32 v8, v7
|
|
; GFX6789-NEXT: v_mov_b32_e32 v9, v7
|
|
; GFX6789-NEXT: v_mov_b32_e32 v10, v7
|
|
; GFX6789-NEXT: v_mov_b32_e32 v11, v7
|
|
; GFX6789-NEXT: v_mov_b32_e32 v0, v7
|
|
; GFX6789-NEXT: v_mov_b32_e32 v1, v8
|
|
; GFX6789-NEXT: v_mov_b32_e32 v2, v9
|
|
; GFX6789-NEXT: v_mov_b32_e32 v3, v10
|
|
; GFX6789-NEXT: v_mov_b32_e32 v4, v11
|
|
; GFX6789-NEXT: image_load_mip v[0:4], v[5:6], s[0:7] dmask:0xf unorm lwe
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: global_store_dword v7, v4, s[8:9]
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; NOPRT-LABEL: load_mip_1d_lwe:
|
|
; NOPRT: ; %bb.0: ; %main_body
|
|
; NOPRT-NEXT: v_mov_b32_e32 v4, 0
|
|
; NOPRT-NEXT: image_load_mip v[0:4], v[0:1], s[0:7] dmask:0xf unorm lwe
|
|
; NOPRT-NEXT: v_mov_b32_e32 v5, 0
|
|
; NOPRT-NEXT: s_waitcnt vmcnt(0)
|
|
; NOPRT-NEXT: global_store_dword v5, v4, s[8:9]
|
|
; NOPRT-NEXT: s_waitcnt vmcnt(0)
|
|
; NOPRT-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: load_mip_1d_lwe:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: v_mov_b32_e32 v7, 0 ; encoding: [0x80,0x02,0x0e,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v6, v1 ; encoding: [0x01,0x03,0x0c,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v5, v0 ; encoding: [0x00,0x03,0x0a,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v8, v7 ; encoding: [0x07,0x03,0x10,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v9, v7 ; encoding: [0x07,0x03,0x12,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v10, v7 ; encoding: [0x07,0x03,0x14,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v11, v7 ; encoding: [0x07,0x03,0x16,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v0, v7 ; encoding: [0x07,0x03,0x00,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v1, v8 ; encoding: [0x08,0x03,0x02,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v2, v9 ; encoding: [0x09,0x03,0x04,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v3, v10 ; encoding: [0x0a,0x03,0x06,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v4, v11 ; encoding: [0x0b,0x03,0x08,0x7e]
|
|
; GFX10-NEXT: image_load_mip v[0:4], v[5:6], s[0:7] dmask:0xf dim:SQ_RSRC_IMG_1D unorm lwe ; encoding: [0x00,0x1f,0x06,0xf0,0x05,0x00,0x00,0x00]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: global_store_dword v7, v4, s[8:9] ; encoding: [0x00,0x80,0x70,0xdc,0x07,0x04,0x08,0x00]
|
|
; 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.load.mip.1d.v4f32i32.i32(i32 15, i32 %s, i32 %mip, <8 x i32> %rsrc, 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> @load_mip_2d(<8 x i32> inreg %rsrc, i32 %s, i32 %t, i32 %mip) {
|
|
; VERDE-LABEL: load_mip_2d:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: image_load_mip v[0:3], v[0:2], s[0:7] dmask:0xf unorm
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; FIJI-LABEL: load_mip_2d:
|
|
; FIJI: ; %bb.0: ; %main_body
|
|
; FIJI-NEXT: image_load_mip v[0:3], v[0:2], s[0:7] dmask:0xf unorm
|
|
; FIJI-NEXT: s_waitcnt vmcnt(0)
|
|
; FIJI-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: load_mip_2d:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: image_load_mip v[0:3], v[0:2], s[0:7] dmask:0xf unorm
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; NOPRT-LABEL: load_mip_2d:
|
|
; NOPRT: ; %bb.0: ; %main_body
|
|
; NOPRT-NEXT: image_load_mip v[0:3], v[0:2], s[0:7] dmask:0xf unorm
|
|
; NOPRT-NEXT: s_waitcnt vmcnt(0)
|
|
; NOPRT-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: load_mip_2d:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: image_load_mip v[0:3], v[0:2], s[0:7] dmask:0xf dim:SQ_RSRC_IMG_2D unorm ; encoding: [0x08,0x1f,0x04,0xf0,0x00,0x00,0x00,0x00]
|
|
; 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.load.mip.2d.v4f32.i32(i32 15, i32 %s, i32 %t, i32 %mip, <8 x i32> %rsrc, i32 0, i32 0)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @load_mip_2d_tfe(<8 x i32> inreg %rsrc, i32 addrspace(1)* inreg %out, i32 %s, i32 %t, i32 %mip) {
|
|
; VERDE-LABEL: load_mip_2d_tfe:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: v_mov_b32_e32 v5, v0
|
|
; VERDE-NEXT: v_mov_b32_e32 v0, 0
|
|
; VERDE-NEXT: v_mov_b32_e32 v7, v2
|
|
; VERDE-NEXT: v_mov_b32_e32 v6, v1
|
|
; 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: image_load_mip v[0:4], v[5:7], s[0:7] dmask:0xf unorm tfe
|
|
; VERDE-NEXT: s_mov_b32 s11, 0xf000
|
|
; VERDE-NEXT: s_mov_b32 s10, -1
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: buffer_store_dword v4, off, s[8:11], 0
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0) expcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; FIJI-LABEL: load_mip_2d_tfe:
|
|
; FIJI: ; %bb.0: ; %main_body
|
|
; FIJI-NEXT: v_mov_b32_e32 v5, v0
|
|
; FIJI-NEXT: v_mov_b32_e32 v0, 0
|
|
; FIJI-NEXT: v_mov_b32_e32 v7, v2
|
|
; FIJI-NEXT: v_mov_b32_e32 v6, v1
|
|
; FIJI-NEXT: v_mov_b32_e32 v1, v0
|
|
; FIJI-NEXT: v_mov_b32_e32 v2, v0
|
|
; FIJI-NEXT: v_mov_b32_e32 v3, v0
|
|
; FIJI-NEXT: v_mov_b32_e32 v4, v0
|
|
; FIJI-NEXT: image_load_mip v[0:4], v[5:7], s[0:7] dmask:0xf unorm tfe
|
|
; FIJI-NEXT: s_mov_b32 s11, 0xf000
|
|
; FIJI-NEXT: s_mov_b32 s10, -1
|
|
; FIJI-NEXT: s_waitcnt vmcnt(0)
|
|
; FIJI-NEXT: buffer_store_dword v4, off, s[8:11], 0
|
|
; FIJI-NEXT: s_waitcnt vmcnt(0)
|
|
; FIJI-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: load_mip_2d_tfe:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: v_mov_b32_e32 v8, 0
|
|
; GFX6789-NEXT: v_mov_b32_e32 v7, v2
|
|
; GFX6789-NEXT: v_mov_b32_e32 v6, v1
|
|
; GFX6789-NEXT: v_mov_b32_e32 v5, v0
|
|
; GFX6789-NEXT: v_mov_b32_e32 v9, v8
|
|
; GFX6789-NEXT: v_mov_b32_e32 v10, v8
|
|
; GFX6789-NEXT: v_mov_b32_e32 v11, v8
|
|
; GFX6789-NEXT: v_mov_b32_e32 v12, v8
|
|
; GFX6789-NEXT: v_mov_b32_e32 v0, v8
|
|
; GFX6789-NEXT: v_mov_b32_e32 v1, v9
|
|
; GFX6789-NEXT: v_mov_b32_e32 v2, v10
|
|
; GFX6789-NEXT: v_mov_b32_e32 v3, v11
|
|
; GFX6789-NEXT: v_mov_b32_e32 v4, v12
|
|
; GFX6789-NEXT: image_load_mip v[0:4], v[5:7], s[0:7] dmask:0xf unorm tfe
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: global_store_dword v8, v4, s[8:9]
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; NOPRT-LABEL: load_mip_2d_tfe:
|
|
; NOPRT: ; %bb.0: ; %main_body
|
|
; NOPRT-NEXT: v_mov_b32_e32 v4, 0
|
|
; NOPRT-NEXT: image_load_mip v[0:4], v[0:2], s[0:7] dmask:0xf unorm tfe
|
|
; NOPRT-NEXT: v_mov_b32_e32 v5, 0
|
|
; NOPRT-NEXT: s_waitcnt vmcnt(0)
|
|
; NOPRT-NEXT: global_store_dword v5, v4, s[8:9]
|
|
; NOPRT-NEXT: s_waitcnt vmcnt(0)
|
|
; NOPRT-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: load_mip_2d_tfe:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: v_mov_b32_e32 v11, 0 ; encoding: [0x80,0x02,0x16,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v7, v2 ; encoding: [0x02,0x03,0x0e,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v6, v1 ; encoding: [0x01,0x03,0x0c,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v5, v0 ; encoding: [0x00,0x03,0x0a,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v12, v11 ; encoding: [0x0b,0x03,0x18,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v13, v11 ; encoding: [0x0b,0x03,0x1a,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v14, v11 ; encoding: [0x0b,0x03,0x1c,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v15, v11 ; encoding: [0x0b,0x03,0x1e,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v0, v11 ; encoding: [0x0b,0x03,0x00,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v1, v12 ; encoding: [0x0c,0x03,0x02,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v2, v13 ; encoding: [0x0d,0x03,0x04,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v3, v14 ; encoding: [0x0e,0x03,0x06,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v4, v15 ; encoding: [0x0f,0x03,0x08,0x7e]
|
|
; GFX10-NEXT: image_load_mip v[0:4], v[5:7], s[0:7] dmask:0xf dim:SQ_RSRC_IMG_2D unorm tfe ; encoding: [0x08,0x1f,0x05,0xf0,0x05,0x00,0x00,0x00]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: global_store_dword v11, v4, s[8:9] ; encoding: [0x00,0x80,0x70,0xdc,0x0b,0x04,0x08,0x00]
|
|
; 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.load.mip.2d.v4f32i32.i32(i32 15, i32 %s, i32 %t, i32 %mip, <8 x i32> %rsrc, 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 float @load_1d_V2_tfe_dmask0(<8 x i32> inreg %rsrc, i32 %s) {
|
|
; VERDE-LABEL: load_1d_V2_tfe_dmask0:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: v_mov_b32_e32 v1, 0
|
|
; VERDE-NEXT: v_mov_b32_e32 v2, v1
|
|
; VERDE-NEXT: image_load v[1:2], v0, s[0:7] dmask:0x1 unorm tfe
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: v_mov_b32_e32 v0, v2
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; FIJI-LABEL: load_1d_V2_tfe_dmask0:
|
|
; FIJI: ; %bb.0: ; %main_body
|
|
; FIJI-NEXT: v_mov_b32_e32 v1, 0
|
|
; FIJI-NEXT: v_mov_b32_e32 v2, v1
|
|
; FIJI-NEXT: image_load v[1:2], v0, s[0:7] dmask:0x1 unorm tfe
|
|
; FIJI-NEXT: s_waitcnt vmcnt(0)
|
|
; FIJI-NEXT: v_mov_b32_e32 v0, v2
|
|
; FIJI-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: load_1d_V2_tfe_dmask0:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: v_mov_b32_e32 v1, 0
|
|
; GFX6789-NEXT: v_mov_b32_e32 v2, v1
|
|
; GFX6789-NEXT: image_load v[1:2], v0, s[0:7] dmask:0x1 unorm tfe
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: v_mov_b32_e32 v0, v2
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; NOPRT-LABEL: load_1d_V2_tfe_dmask0:
|
|
; NOPRT: ; %bb.0: ; %main_body
|
|
; NOPRT-NEXT: v_mov_b32_e32 v1, 0
|
|
; NOPRT-NEXT: image_load v[0:1], v0, s[0:7] dmask:0x1 unorm tfe
|
|
; NOPRT-NEXT: s_waitcnt vmcnt(0)
|
|
; NOPRT-NEXT: v_mov_b32_e32 v0, v1
|
|
; NOPRT-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: load_1d_V2_tfe_dmask0:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: v_mov_b32_e32 v1, 0 ; encoding: [0x80,0x02,0x02,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v2, v1 ; encoding: [0x01,0x03,0x04,0x7e]
|
|
; GFX10-NEXT: image_load v[1:2], v0, s[0:7] dmask:0x1 dim:SQ_RSRC_IMG_1D unorm tfe ; encoding: [0x00,0x11,0x01,0xf0,0x00,0x01,0x00,0x00]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: v_mov_b32_e32 v0, v2 ; encoding: [0x02,0x03,0x00,0x7e]
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call {<2 x float>,i32} @llvm.amdgcn.image.load.1d.v2f32i32.i32(i32 0, i32 %s, <8 x i32> %rsrc, i32 1, i32 0)
|
|
%v.err = extractvalue {<2 x float>, i32} %v, 1
|
|
%vv = bitcast i32 %v.err to float
|
|
ret float %vv
|
|
}
|
|
|
|
define amdgpu_ps float @load_1d_V1_tfe_dmask0(<8 x i32> inreg %rsrc, i32 %s) {
|
|
; VERDE-LABEL: load_1d_V1_tfe_dmask0:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: v_mov_b32_e32 v1, 0
|
|
; VERDE-NEXT: v_mov_b32_e32 v2, v1
|
|
; VERDE-NEXT: image_load v[1:2], v0, s[0:7] dmask:0x1 unorm tfe
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: v_mov_b32_e32 v0, v2
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; FIJI-LABEL: load_1d_V1_tfe_dmask0:
|
|
; FIJI: ; %bb.0: ; %main_body
|
|
; FIJI-NEXT: v_mov_b32_e32 v1, 0
|
|
; FIJI-NEXT: v_mov_b32_e32 v2, v1
|
|
; FIJI-NEXT: image_load v[1:2], v0, s[0:7] dmask:0x1 unorm tfe
|
|
; FIJI-NEXT: s_waitcnt vmcnt(0)
|
|
; FIJI-NEXT: v_mov_b32_e32 v0, v2
|
|
; FIJI-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: load_1d_V1_tfe_dmask0:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: v_mov_b32_e32 v1, 0
|
|
; GFX6789-NEXT: v_mov_b32_e32 v2, v1
|
|
; GFX6789-NEXT: image_load v[1:2], v0, s[0:7] dmask:0x1 unorm tfe
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: v_mov_b32_e32 v0, v2
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; NOPRT-LABEL: load_1d_V1_tfe_dmask0:
|
|
; NOPRT: ; %bb.0: ; %main_body
|
|
; NOPRT-NEXT: v_mov_b32_e32 v1, 0
|
|
; NOPRT-NEXT: image_load v[0:1], v0, s[0:7] dmask:0x1 unorm tfe
|
|
; NOPRT-NEXT: s_waitcnt vmcnt(0)
|
|
; NOPRT-NEXT: v_mov_b32_e32 v0, v1
|
|
; NOPRT-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: load_1d_V1_tfe_dmask0:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: v_mov_b32_e32 v1, 0 ; encoding: [0x80,0x02,0x02,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v2, v1 ; encoding: [0x01,0x03,0x04,0x7e]
|
|
; GFX10-NEXT: image_load v[1:2], v0, s[0:7] dmask:0x1 dim:SQ_RSRC_IMG_1D unorm tfe ; encoding: [0x00,0x11,0x01,0xf0,0x00,0x01,0x00,0x00]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: v_mov_b32_e32 v0, v2 ; encoding: [0x02,0x03,0x00,0x7e]
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call {float,i32} @llvm.amdgcn.image.load.1d.f32i32.i32(i32 0, i32 %s, <8 x i32> %rsrc, i32 1, i32 0)
|
|
%v.err = extractvalue {float, i32} %v, 1
|
|
%vv = bitcast i32 %v.err to float
|
|
ret float %vv
|
|
}
|
|
|
|
define amdgpu_ps float @load_mip_2d_tfe_dmask0(<8 x i32> inreg %rsrc, i32 %s, i32 %t, i32 %mip) {
|
|
; VERDE-LABEL: load_mip_2d_tfe_dmask0:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: v_mov_b32_e32 v3, 0
|
|
; VERDE-NEXT: v_mov_b32_e32 v4, v3
|
|
; VERDE-NEXT: image_load_mip v[3:4], v[0:2], s[0:7] dmask:0x1 unorm tfe
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: v_mov_b32_e32 v0, v4
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; FIJI-LABEL: load_mip_2d_tfe_dmask0:
|
|
; FIJI: ; %bb.0: ; %main_body
|
|
; FIJI-NEXT: v_mov_b32_e32 v3, 0
|
|
; FIJI-NEXT: v_mov_b32_e32 v4, v3
|
|
; FIJI-NEXT: image_load_mip v[3:4], v[0:2], s[0:7] dmask:0x1 unorm tfe
|
|
; FIJI-NEXT: s_waitcnt vmcnt(0)
|
|
; FIJI-NEXT: v_mov_b32_e32 v0, v4
|
|
; FIJI-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: load_mip_2d_tfe_dmask0:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: v_mov_b32_e32 v3, 0
|
|
; GFX6789-NEXT: v_mov_b32_e32 v4, v3
|
|
; GFX6789-NEXT: image_load_mip v[3:4], v[0:2], s[0:7] dmask:0x1 unorm tfe
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: v_mov_b32_e32 v0, v4
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; NOPRT-LABEL: load_mip_2d_tfe_dmask0:
|
|
; NOPRT: ; %bb.0: ; %main_body
|
|
; NOPRT-NEXT: v_mov_b32_e32 v3, 0
|
|
; NOPRT-NEXT: image_load_mip v[2:3], v[0:2], s[0:7] dmask:0x1 unorm tfe
|
|
; NOPRT-NEXT: s_waitcnt vmcnt(0)
|
|
; NOPRT-NEXT: v_mov_b32_e32 v0, v3
|
|
; NOPRT-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: load_mip_2d_tfe_dmask0:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: v_mov_b32_e32 v3, 0 ; encoding: [0x80,0x02,0x06,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v4, v3 ; encoding: [0x03,0x03,0x08,0x7e]
|
|
; GFX10-NEXT: image_load_mip v[3:4], v[0:2], s[0:7] dmask:0x1 dim:SQ_RSRC_IMG_2D unorm tfe ; encoding: [0x08,0x11,0x05,0xf0,0x00,0x03,0x00,0x00]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: v_mov_b32_e32 v0, v4 ; encoding: [0x04,0x03,0x00,0x7e]
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call {<4 x float>,i32} @llvm.amdgcn.image.load.mip.2d.v4f32i32.i32(i32 0, i32 %s, i32 %t, i32 %mip, <8 x i32> %rsrc, i32 1, i32 0)
|
|
%v.err = extractvalue {<4 x float>, i32} %v, 1
|
|
%vv = bitcast i32 %v.err to float
|
|
ret float %vv
|
|
}
|
|
|
|
define amdgpu_ps float @load_mip_2d_tfe_nouse(<8 x i32> inreg %rsrc, i32 %s, i32 %t, i32 %mip) {
|
|
; VERDE-LABEL: load_mip_2d_tfe_nouse:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: v_mov_b32_e32 v3, 0
|
|
; VERDE-NEXT: v_mov_b32_e32 v4, v3
|
|
; VERDE-NEXT: image_load_mip v[3:4], v[0:2], s[0:7] dmask:0x1 unorm tfe
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: v_mov_b32_e32 v0, v4
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; FIJI-LABEL: load_mip_2d_tfe_nouse:
|
|
; FIJI: ; %bb.0: ; %main_body
|
|
; FIJI-NEXT: v_mov_b32_e32 v3, 0
|
|
; FIJI-NEXT: v_mov_b32_e32 v4, v3
|
|
; FIJI-NEXT: image_load_mip v[3:4], v[0:2], s[0:7] dmask:0x1 unorm tfe
|
|
; FIJI-NEXT: s_waitcnt vmcnt(0)
|
|
; FIJI-NEXT: v_mov_b32_e32 v0, v4
|
|
; FIJI-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: load_mip_2d_tfe_nouse:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: v_mov_b32_e32 v3, 0
|
|
; GFX6789-NEXT: v_mov_b32_e32 v4, v3
|
|
; GFX6789-NEXT: image_load_mip v[3:4], v[0:2], s[0:7] dmask:0x1 unorm tfe
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: v_mov_b32_e32 v0, v4
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; NOPRT-LABEL: load_mip_2d_tfe_nouse:
|
|
; NOPRT: ; %bb.0: ; %main_body
|
|
; NOPRT-NEXT: v_mov_b32_e32 v3, 0
|
|
; NOPRT-NEXT: image_load_mip v[2:3], v[0:2], s[0:7] dmask:0x1 unorm tfe
|
|
; NOPRT-NEXT: s_waitcnt vmcnt(0)
|
|
; NOPRT-NEXT: v_mov_b32_e32 v0, v3
|
|
; NOPRT-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: load_mip_2d_tfe_nouse:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: v_mov_b32_e32 v3, 0 ; encoding: [0x80,0x02,0x06,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v4, v3 ; encoding: [0x03,0x03,0x08,0x7e]
|
|
; GFX10-NEXT: image_load_mip v[3:4], v[0:2], s[0:7] dmask:0x1 dim:SQ_RSRC_IMG_2D unorm tfe ; encoding: [0x08,0x11,0x05,0xf0,0x00,0x03,0x00,0x00]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: v_mov_b32_e32 v0, v4 ; encoding: [0x04,0x03,0x00,0x7e]
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call {<4 x float>,i32} @llvm.amdgcn.image.load.mip.2d.v4f32i32.i32(i32 15, i32 %s, i32 %t, i32 %mip, <8 x i32> %rsrc, i32 1, i32 0)
|
|
%v.err = extractvalue {<4 x float>, i32} %v, 1
|
|
%vv = bitcast i32 %v.err to float
|
|
ret float %vv
|
|
}
|
|
|
|
define amdgpu_ps float @load_mip_2d_tfe_nouse_V2(<8 x i32> inreg %rsrc, i32 %s, i32 %t, i32 %mip) {
|
|
; VERDE-LABEL: load_mip_2d_tfe_nouse_V2:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: v_mov_b32_e32 v3, 0
|
|
; VERDE-NEXT: v_mov_b32_e32 v4, v3
|
|
; VERDE-NEXT: image_load_mip v[3:4], v[0:2], s[0:7] dmask:0x1 unorm tfe
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: v_mov_b32_e32 v0, v4
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; FIJI-LABEL: load_mip_2d_tfe_nouse_V2:
|
|
; FIJI: ; %bb.0: ; %main_body
|
|
; FIJI-NEXT: v_mov_b32_e32 v3, 0
|
|
; FIJI-NEXT: v_mov_b32_e32 v4, v3
|
|
; FIJI-NEXT: image_load_mip v[3:4], v[0:2], s[0:7] dmask:0x1 unorm tfe
|
|
; FIJI-NEXT: s_waitcnt vmcnt(0)
|
|
; FIJI-NEXT: v_mov_b32_e32 v0, v4
|
|
; FIJI-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: load_mip_2d_tfe_nouse_V2:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: v_mov_b32_e32 v3, 0
|
|
; GFX6789-NEXT: v_mov_b32_e32 v4, v3
|
|
; GFX6789-NEXT: image_load_mip v[3:4], v[0:2], s[0:7] dmask:0x1 unorm tfe
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: v_mov_b32_e32 v0, v4
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; NOPRT-LABEL: load_mip_2d_tfe_nouse_V2:
|
|
; NOPRT: ; %bb.0: ; %main_body
|
|
; NOPRT-NEXT: v_mov_b32_e32 v3, 0
|
|
; NOPRT-NEXT: image_load_mip v[2:3], v[0:2], s[0:7] dmask:0x1 unorm tfe
|
|
; NOPRT-NEXT: s_waitcnt vmcnt(0)
|
|
; NOPRT-NEXT: v_mov_b32_e32 v0, v3
|
|
; NOPRT-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: load_mip_2d_tfe_nouse_V2:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: v_mov_b32_e32 v3, 0 ; encoding: [0x80,0x02,0x06,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v4, v3 ; encoding: [0x03,0x03,0x08,0x7e]
|
|
; GFX10-NEXT: image_load_mip v[3:4], v[0:2], s[0:7] dmask:0x1 dim:SQ_RSRC_IMG_2D unorm tfe ; encoding: [0x08,0x11,0x05,0xf0,0x00,0x03,0x00,0x00]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: v_mov_b32_e32 v0, v4 ; encoding: [0x04,0x03,0x00,0x7e]
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call {<2 x float>,i32} @llvm.amdgcn.image.load.mip.2d.v2f32i32.i32(i32 6, i32 %s, i32 %t, i32 %mip, <8 x i32> %rsrc, i32 1, i32 0)
|
|
%v.err = extractvalue {<2 x float>, i32} %v, 1
|
|
%vv = bitcast i32 %v.err to float
|
|
ret float %vv
|
|
}
|
|
|
|
define amdgpu_ps float @load_mip_2d_tfe_nouse_V1(<8 x i32> inreg %rsrc, i32 %s, i32 %t, i32 %mip) {
|
|
; VERDE-LABEL: load_mip_2d_tfe_nouse_V1:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: v_mov_b32_e32 v3, 0
|
|
; VERDE-NEXT: v_mov_b32_e32 v4, v3
|
|
; VERDE-NEXT: image_load_mip v[3:4], v[0:2], s[0:7] dmask:0x2 unorm tfe
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: v_mov_b32_e32 v0, v4
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; FIJI-LABEL: load_mip_2d_tfe_nouse_V1:
|
|
; FIJI: ; %bb.0: ; %main_body
|
|
; FIJI-NEXT: v_mov_b32_e32 v3, 0
|
|
; FIJI-NEXT: v_mov_b32_e32 v4, v3
|
|
; FIJI-NEXT: image_load_mip v[3:4], v[0:2], s[0:7] dmask:0x2 unorm tfe
|
|
; FIJI-NEXT: s_waitcnt vmcnt(0)
|
|
; FIJI-NEXT: v_mov_b32_e32 v0, v4
|
|
; FIJI-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: load_mip_2d_tfe_nouse_V1:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: v_mov_b32_e32 v3, 0
|
|
; GFX6789-NEXT: v_mov_b32_e32 v4, v3
|
|
; GFX6789-NEXT: image_load_mip v[3:4], v[0:2], s[0:7] dmask:0x2 unorm tfe
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: v_mov_b32_e32 v0, v4
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; NOPRT-LABEL: load_mip_2d_tfe_nouse_V1:
|
|
; NOPRT: ; %bb.0: ; %main_body
|
|
; NOPRT-NEXT: v_mov_b32_e32 v3, 0
|
|
; NOPRT-NEXT: image_load_mip v[2:3], v[0:2], s[0:7] dmask:0x2 unorm tfe
|
|
; NOPRT-NEXT: s_waitcnt vmcnt(0)
|
|
; NOPRT-NEXT: v_mov_b32_e32 v0, v3
|
|
; NOPRT-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: load_mip_2d_tfe_nouse_V1:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: v_mov_b32_e32 v3, 0 ; encoding: [0x80,0x02,0x06,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v4, v3 ; encoding: [0x03,0x03,0x08,0x7e]
|
|
; GFX10-NEXT: image_load_mip v[3:4], v[0:2], s[0:7] dmask:0x2 dim:SQ_RSRC_IMG_2D unorm tfe ; encoding: [0x08,0x12,0x05,0xf0,0x00,0x03,0x00,0x00]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: v_mov_b32_e32 v0, v4 ; encoding: [0x04,0x03,0x00,0x7e]
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call {float, i32} @llvm.amdgcn.image.load.mip.2d.f32i32.i32(i32 2, i32 %s, i32 %t, i32 %mip, <8 x i32> %rsrc, i32 1, i32 0)
|
|
%v.err = extractvalue {float, i32} %v, 1
|
|
%vv = bitcast i32 %v.err to float
|
|
ret float %vv
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @load_1d_tfe_V4_dmask3(<8 x i32> inreg %rsrc, i32 addrspace(1)* inreg %out, i32 %s) {
|
|
; VERDE-LABEL: load_1d_tfe_V4_dmask3:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; 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: image_load v[0:3], v4, s[0:7] dmask:0x7 unorm tfe
|
|
; VERDE-NEXT: s_mov_b32 s11, 0xf000
|
|
; VERDE-NEXT: s_mov_b32 s10, -1
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: buffer_store_dword v3, off, s[8:11], 0
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0) expcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; FIJI-LABEL: load_1d_tfe_V4_dmask3:
|
|
; FIJI: ; %bb.0: ; %main_body
|
|
; FIJI-NEXT: v_mov_b32_e32 v4, v0
|
|
; FIJI-NEXT: v_mov_b32_e32 v0, 0
|
|
; FIJI-NEXT: v_mov_b32_e32 v1, v0
|
|
; FIJI-NEXT: v_mov_b32_e32 v2, v0
|
|
; FIJI-NEXT: v_mov_b32_e32 v3, v0
|
|
; FIJI-NEXT: image_load v[0:3], v4, s[0:7] dmask:0x7 unorm tfe
|
|
; FIJI-NEXT: s_mov_b32 s11, 0xf000
|
|
; FIJI-NEXT: s_mov_b32 s10, -1
|
|
; FIJI-NEXT: s_waitcnt vmcnt(0)
|
|
; FIJI-NEXT: buffer_store_dword v3, off, s[8:11], 0
|
|
; FIJI-NEXT: s_waitcnt vmcnt(0)
|
|
; FIJI-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: load_1d_tfe_V4_dmask3:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: v_mov_b32_e32 v5, 0
|
|
; GFX6789-NEXT: v_mov_b32_e32 v4, v0
|
|
; GFX6789-NEXT: v_mov_b32_e32 v6, v5
|
|
; GFX6789-NEXT: v_mov_b32_e32 v7, v5
|
|
; GFX6789-NEXT: v_mov_b32_e32 v8, v5
|
|
; GFX6789-NEXT: v_mov_b32_e32 v0, v5
|
|
; GFX6789-NEXT: v_mov_b32_e32 v1, v6
|
|
; GFX6789-NEXT: v_mov_b32_e32 v2, v7
|
|
; GFX6789-NEXT: v_mov_b32_e32 v3, v8
|
|
; GFX6789-NEXT: image_load v[0:3], v4, s[0:7] dmask:0x7 unorm tfe
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: global_store_dword v5, v3, s[8:9]
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; NOPRT-LABEL: load_1d_tfe_V4_dmask3:
|
|
; NOPRT: ; %bb.0: ; %main_body
|
|
; NOPRT-NEXT: v_mov_b32_e32 v3, 0
|
|
; NOPRT-NEXT: image_load v[0:3], v0, s[0:7] dmask:0x7 unorm tfe
|
|
; NOPRT-NEXT: v_mov_b32_e32 v4, 0
|
|
; NOPRT-NEXT: s_waitcnt vmcnt(0)
|
|
; NOPRT-NEXT: global_store_dword v4, v3, s[8:9]
|
|
; NOPRT-NEXT: s_waitcnt vmcnt(0)
|
|
; NOPRT-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: load_1d_tfe_V4_dmask3:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: v_mov_b32_e32 v5, 0 ; encoding: [0x80,0x02,0x0a,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v4, v0 ; encoding: [0x00,0x03,0x08,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v6, v5 ; encoding: [0x05,0x03,0x0c,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v7, v5 ; encoding: [0x05,0x03,0x0e,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v8, v5 ; encoding: [0x05,0x03,0x10,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v0, v5 ; encoding: [0x05,0x03,0x00,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v1, v6 ; encoding: [0x06,0x03,0x02,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v2, v7 ; encoding: [0x07,0x03,0x04,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v3, v8 ; encoding: [0x08,0x03,0x06,0x7e]
|
|
; GFX10-NEXT: image_load v[0:3], v4, s[0:7] dmask:0x7 dim:SQ_RSRC_IMG_1D unorm tfe ; encoding: [0x00,0x17,0x01,0xf0,0x04,0x00,0x00,0x00]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: global_store_dword v5, v3, s[8:9] ; encoding: [0x00,0x80,0x70,0xdc,0x05,0x03,0x08,0x00]
|
|
; 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.load.1d.v4f32i32.i32(i32 7, i32 %s, <8 x i32> %rsrc, 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 <4 x float> @load_1d_tfe_V4_dmask2(<8 x i32> inreg %rsrc, i32 addrspace(1)* inreg %out, i32 %s) {
|
|
; VERDE-LABEL: load_1d_tfe_V4_dmask2:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; 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: image_load v[0:2], v3, s[0:7] dmask:0x6 unorm tfe
|
|
; VERDE-NEXT: s_mov_b32 s11, 0xf000
|
|
; VERDE-NEXT: s_mov_b32 s10, -1
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: buffer_store_dword v2, off, s[8:11], 0
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0) expcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; FIJI-LABEL: load_1d_tfe_V4_dmask2:
|
|
; FIJI: ; %bb.0: ; %main_body
|
|
; FIJI-NEXT: v_mov_b32_e32 v3, v0
|
|
; FIJI-NEXT: v_mov_b32_e32 v0, 0
|
|
; FIJI-NEXT: v_mov_b32_e32 v1, v0
|
|
; FIJI-NEXT: v_mov_b32_e32 v2, v0
|
|
; FIJI-NEXT: image_load v[0:2], v3, s[0:7] dmask:0x6 unorm tfe
|
|
; FIJI-NEXT: s_mov_b32 s11, 0xf000
|
|
; FIJI-NEXT: s_mov_b32 s10, -1
|
|
; FIJI-NEXT: s_waitcnt vmcnt(0)
|
|
; FIJI-NEXT: buffer_store_dword v2, off, s[8:11], 0
|
|
; FIJI-NEXT: s_waitcnt vmcnt(0)
|
|
; FIJI-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: load_1d_tfe_V4_dmask2:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: v_mov_b32_e32 v4, 0
|
|
; GFX6789-NEXT: v_mov_b32_e32 v3, v0
|
|
; GFX6789-NEXT: v_mov_b32_e32 v5, v4
|
|
; GFX6789-NEXT: v_mov_b32_e32 v6, v4
|
|
; GFX6789-NEXT: v_mov_b32_e32 v0, v4
|
|
; GFX6789-NEXT: v_mov_b32_e32 v1, v5
|
|
; GFX6789-NEXT: v_mov_b32_e32 v2, v6
|
|
; GFX6789-NEXT: image_load v[0:2], v3, s[0:7] dmask:0x6 unorm tfe
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: global_store_dword v4, v2, s[8:9]
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; NOPRT-LABEL: load_1d_tfe_V4_dmask2:
|
|
; NOPRT: ; %bb.0: ; %main_body
|
|
; NOPRT-NEXT: v_mov_b32_e32 v2, 0
|
|
; NOPRT-NEXT: image_load v[0:2], v0, s[0:7] dmask:0x6 unorm tfe
|
|
; NOPRT-NEXT: v_mov_b32_e32 v3, 0
|
|
; NOPRT-NEXT: s_waitcnt vmcnt(0)
|
|
; NOPRT-NEXT: global_store_dword v3, v2, s[8:9]
|
|
; NOPRT-NEXT: s_waitcnt vmcnt(0)
|
|
; NOPRT-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: load_1d_tfe_V4_dmask2:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: v_mov_b32_e32 v4, 0 ; encoding: [0x80,0x02,0x08,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v3, v0 ; encoding: [0x00,0x03,0x06,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v5, v4 ; encoding: [0x04,0x03,0x0a,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v6, v4 ; encoding: [0x04,0x03,0x0c,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v0, v4 ; encoding: [0x04,0x03,0x00,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v1, v5 ; encoding: [0x05,0x03,0x02,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v2, v6 ; encoding: [0x06,0x03,0x04,0x7e]
|
|
; GFX10-NEXT: image_load v[0:2], v3, s[0:7] dmask:0x6 dim:SQ_RSRC_IMG_1D unorm tfe ; encoding: [0x00,0x16,0x01,0xf0,0x03,0x00,0x00,0x00]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: global_store_dword v4, v2, s[8:9] ; encoding: [0x00,0x80,0x70,0xdc,0x04,0x02,0x08,0x00]
|
|
; 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.load.1d.v4f32i32.i32(i32 6, i32 %s, <8 x i32> %rsrc, 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 <4 x float> @load_1d_tfe_V4_dmask1(<8 x i32> inreg %rsrc, i32 addrspace(1)* inreg %out, i32 %s) {
|
|
; VERDE-LABEL: load_1d_tfe_V4_dmask1:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; 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: image_load v[0:1], v2, s[0:7] dmask:0x8 unorm tfe
|
|
; VERDE-NEXT: s_mov_b32 s11, 0xf000
|
|
; VERDE-NEXT: s_mov_b32 s10, -1
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: buffer_store_dword v1, off, s[8:11], 0
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0) expcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; FIJI-LABEL: load_1d_tfe_V4_dmask1:
|
|
; FIJI: ; %bb.0: ; %main_body
|
|
; FIJI-NEXT: v_mov_b32_e32 v2, v0
|
|
; FIJI-NEXT: v_mov_b32_e32 v0, 0
|
|
; FIJI-NEXT: v_mov_b32_e32 v1, v0
|
|
; FIJI-NEXT: image_load v[0:1], v2, s[0:7] dmask:0x8 unorm tfe
|
|
; FIJI-NEXT: s_mov_b32 s11, 0xf000
|
|
; FIJI-NEXT: s_mov_b32 s10, -1
|
|
; FIJI-NEXT: s_waitcnt vmcnt(0)
|
|
; FIJI-NEXT: buffer_store_dword v1, off, s[8:11], 0
|
|
; FIJI-NEXT: s_waitcnt vmcnt(0)
|
|
; FIJI-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: load_1d_tfe_V4_dmask1:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: v_mov_b32_e32 v3, 0
|
|
; GFX6789-NEXT: v_mov_b32_e32 v2, v0
|
|
; GFX6789-NEXT: v_mov_b32_e32 v4, v3
|
|
; GFX6789-NEXT: v_mov_b32_e32 v0, v3
|
|
; GFX6789-NEXT: v_mov_b32_e32 v1, v4
|
|
; GFX6789-NEXT: image_load v[0:1], v2, s[0:7] dmask:0x8 unorm tfe
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: global_store_dword v3, v1, s[8:9]
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; NOPRT-LABEL: load_1d_tfe_V4_dmask1:
|
|
; NOPRT: ; %bb.0: ; %main_body
|
|
; NOPRT-NEXT: v_mov_b32_e32 v1, 0
|
|
; NOPRT-NEXT: image_load v[0:1], v0, s[0:7] dmask:0x8 unorm tfe
|
|
; NOPRT-NEXT: v_mov_b32_e32 v2, 0
|
|
; NOPRT-NEXT: s_waitcnt vmcnt(0)
|
|
; NOPRT-NEXT: global_store_dword v2, v1, s[8:9]
|
|
; NOPRT-NEXT: s_waitcnt vmcnt(0)
|
|
; NOPRT-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: load_1d_tfe_V4_dmask1:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: v_mov_b32_e32 v3, 0 ; encoding: [0x80,0x02,0x06,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v2, v0 ; encoding: [0x00,0x03,0x04,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v4, v3 ; encoding: [0x03,0x03,0x08,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v0, v3 ; encoding: [0x03,0x03,0x00,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v1, v4 ; encoding: [0x04,0x03,0x02,0x7e]
|
|
; GFX10-NEXT: image_load v[0:1], v2, s[0:7] dmask:0x8 dim:SQ_RSRC_IMG_1D unorm tfe ; encoding: [0x00,0x18,0x01,0xf0,0x02,0x00,0x00,0x00]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: global_store_dword v3, v1, s[8:9] ; encoding: [0x00,0x80,0x70,0xdc,0x03,0x01,0x08,0x00]
|
|
; 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.load.1d.v4f32i32.i32(i32 8, i32 %s, <8 x i32> %rsrc, 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> @load_1d_tfe_V2_dmask1(<8 x i32> inreg %rsrc, i32 addrspace(1)* inreg %out, i32 %s) {
|
|
; VERDE-LABEL: load_1d_tfe_V2_dmask1:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; 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: image_load v[0:1], v2, s[0:7] dmask:0x8 unorm tfe
|
|
; VERDE-NEXT: s_mov_b32 s11, 0xf000
|
|
; VERDE-NEXT: s_mov_b32 s10, -1
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: buffer_store_dword v1, off, s[8:11], 0
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0) expcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; FIJI-LABEL: load_1d_tfe_V2_dmask1:
|
|
; FIJI: ; %bb.0: ; %main_body
|
|
; FIJI-NEXT: v_mov_b32_e32 v2, v0
|
|
; FIJI-NEXT: v_mov_b32_e32 v0, 0
|
|
; FIJI-NEXT: v_mov_b32_e32 v1, v0
|
|
; FIJI-NEXT: image_load v[0:1], v2, s[0:7] dmask:0x8 unorm tfe
|
|
; FIJI-NEXT: s_mov_b32 s11, 0xf000
|
|
; FIJI-NEXT: s_mov_b32 s10, -1
|
|
; FIJI-NEXT: s_waitcnt vmcnt(0)
|
|
; FIJI-NEXT: buffer_store_dword v1, off, s[8:11], 0
|
|
; FIJI-NEXT: s_waitcnt vmcnt(0)
|
|
; FIJI-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: load_1d_tfe_V2_dmask1:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: v_mov_b32_e32 v3, 0
|
|
; GFX6789-NEXT: v_mov_b32_e32 v2, v0
|
|
; GFX6789-NEXT: v_mov_b32_e32 v4, v3
|
|
; GFX6789-NEXT: v_mov_b32_e32 v0, v3
|
|
; GFX6789-NEXT: v_mov_b32_e32 v1, v4
|
|
; GFX6789-NEXT: image_load v[0:1], v2, s[0:7] dmask:0x8 unorm tfe
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: global_store_dword v3, v1, s[8:9]
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; NOPRT-LABEL: load_1d_tfe_V2_dmask1:
|
|
; NOPRT: ; %bb.0: ; %main_body
|
|
; NOPRT-NEXT: v_mov_b32_e32 v1, 0
|
|
; NOPRT-NEXT: image_load v[0:1], v0, s[0:7] dmask:0x8 unorm tfe
|
|
; NOPRT-NEXT: v_mov_b32_e32 v2, 0
|
|
; NOPRT-NEXT: s_waitcnt vmcnt(0)
|
|
; NOPRT-NEXT: global_store_dword v2, v1, s[8:9]
|
|
; NOPRT-NEXT: s_waitcnt vmcnt(0)
|
|
; NOPRT-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: load_1d_tfe_V2_dmask1:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: v_mov_b32_e32 v3, 0 ; encoding: [0x80,0x02,0x06,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v2, v0 ; encoding: [0x00,0x03,0x04,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v4, v3 ; encoding: [0x03,0x03,0x08,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v0, v3 ; encoding: [0x03,0x03,0x00,0x7e]
|
|
; GFX10-NEXT: v_mov_b32_e32 v1, v4 ; encoding: [0x04,0x03,0x02,0x7e]
|
|
; GFX10-NEXT: image_load v[0:1], v2, s[0:7] dmask:0x8 dim:SQ_RSRC_IMG_1D unorm tfe ; encoding: [0x00,0x18,0x01,0xf0,0x02,0x00,0x00,0x00]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: global_store_dword v3, v1, s[8:9] ; encoding: [0x00,0x80,0x70,0xdc,0x03,0x01,0x08,0x00]
|
|
; GFX10-NEXT: s_waitcnt_vscnt null, 0x0 ; encoding: [0x00,0x00,0xfd,0xbb]
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%v = call {<2 x float>,i32} @llvm.amdgcn.image.load.1d.v2f32i32.i32(i32 8, i32 %s, <8 x i32> %rsrc, i32 1, i32 0)
|
|
%v.vec = extractvalue {<2 x float>, i32} %v, 0
|
|
%v.err = extractvalue {<2 x float>, i32} %v, 1
|
|
store i32 %v.err, i32 addrspace(1)* %out, align 4
|
|
ret <2 x float> %v.vec
|
|
}
|
|
|
|
|
|
define amdgpu_ps <4 x float> @load_mip_3d(<8 x i32> inreg %rsrc, i32 %s, i32 %t, i32 %r, i32 %mip) {
|
|
; VERDE-LABEL: load_mip_3d:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: image_load_mip v[0:3], v[0:3], s[0:7] dmask:0xf unorm
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; FIJI-LABEL: load_mip_3d:
|
|
; FIJI: ; %bb.0: ; %main_body
|
|
; FIJI-NEXT: image_load_mip v[0:3], v[0:3], s[0:7] dmask:0xf unorm
|
|
; FIJI-NEXT: s_waitcnt vmcnt(0)
|
|
; FIJI-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: load_mip_3d:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: image_load_mip v[0:3], v[0:3], s[0:7] dmask:0xf unorm
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; NOPRT-LABEL: load_mip_3d:
|
|
; NOPRT: ; %bb.0: ; %main_body
|
|
; NOPRT-NEXT: image_load_mip v[0:3], v[0:3], s[0:7] dmask:0xf unorm
|
|
; NOPRT-NEXT: s_waitcnt vmcnt(0)
|
|
; NOPRT-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: load_mip_3d:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: image_load_mip v[0:3], v[0:3], s[0:7] dmask:0xf dim:SQ_RSRC_IMG_3D unorm ; encoding: [0x10,0x1f,0x04,0xf0,0x00,0x00,0x00,0x00]
|
|
; 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.load.mip.3d.v4f32.i32(i32 15, i32 %s, i32 %t, i32 %r, i32 %mip, <8 x i32> %rsrc, i32 0, i32 0)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @load_mip_cube(<8 x i32> inreg %rsrc, i32 %s, i32 %t, i32 %slice, i32 %mip) {
|
|
; VERDE-LABEL: load_mip_cube:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: image_load_mip v[0:3], v[0:3], s[0:7] dmask:0xf unorm da
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; FIJI-LABEL: load_mip_cube:
|
|
; FIJI: ; %bb.0: ; %main_body
|
|
; FIJI-NEXT: image_load_mip v[0:3], v[0:3], s[0:7] dmask:0xf unorm da
|
|
; FIJI-NEXT: s_waitcnt vmcnt(0)
|
|
; FIJI-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: load_mip_cube:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: image_load_mip v[0:3], v[0:3], s[0:7] dmask:0xf unorm da
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; NOPRT-LABEL: load_mip_cube:
|
|
; NOPRT: ; %bb.0: ; %main_body
|
|
; NOPRT-NEXT: image_load_mip v[0:3], v[0:3], s[0:7] dmask:0xf unorm da
|
|
; NOPRT-NEXT: s_waitcnt vmcnt(0)
|
|
; NOPRT-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: load_mip_cube:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: image_load_mip v[0:3], v[0:3], s[0:7] dmask:0xf dim:SQ_RSRC_IMG_CUBE unorm ; encoding: [0x18,0x1f,0x04,0xf0,0x00,0x00,0x00,0x00]
|
|
; 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.load.mip.cube.v4f32.i32(i32 15, i32 %s, i32 %t, i32 %slice, i32 %mip, <8 x i32> %rsrc, i32 0, i32 0)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @load_mip_1darray(<8 x i32> inreg %rsrc, i32 %s, i32 %slice, i32 %mip) {
|
|
; VERDE-LABEL: load_mip_1darray:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: image_load_mip v[0:3], v[0:2], s[0:7] dmask:0xf unorm da
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; FIJI-LABEL: load_mip_1darray:
|
|
; FIJI: ; %bb.0: ; %main_body
|
|
; FIJI-NEXT: image_load_mip v[0:3], v[0:2], s[0:7] dmask:0xf unorm da
|
|
; FIJI-NEXT: s_waitcnt vmcnt(0)
|
|
; FIJI-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: load_mip_1darray:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: image_load_mip v[0:3], v[0:2], s[0:7] dmask:0xf unorm da
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; NOPRT-LABEL: load_mip_1darray:
|
|
; NOPRT: ; %bb.0: ; %main_body
|
|
; NOPRT-NEXT: image_load_mip v[0:3], v[0:2], s[0:7] dmask:0xf unorm da
|
|
; NOPRT-NEXT: s_waitcnt vmcnt(0)
|
|
; NOPRT-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: load_mip_1darray:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: image_load_mip v[0:3], v[0:2], s[0:7] dmask:0xf dim:SQ_RSRC_IMG_1D_ARRAY unorm ; encoding: [0x20,0x1f,0x04,0xf0,0x00,0x00,0x00,0x00]
|
|
; 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.load.mip.1darray.v4f32.i32(i32 15, i32 %s, i32 %slice, i32 %mip, <8 x i32> %rsrc, i32 0, i32 0)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @load_mip_2darray(<8 x i32> inreg %rsrc, i32 %s, i32 %t, i32 %slice, i32 %mip) {
|
|
; VERDE-LABEL: load_mip_2darray:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: image_load_mip v[0:3], v[0:3], s[0:7] dmask:0xf unorm da
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; FIJI-LABEL: load_mip_2darray:
|
|
; FIJI: ; %bb.0: ; %main_body
|
|
; FIJI-NEXT: image_load_mip v[0:3], v[0:3], s[0:7] dmask:0xf unorm da
|
|
; FIJI-NEXT: s_waitcnt vmcnt(0)
|
|
; FIJI-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: load_mip_2darray:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: image_load_mip v[0:3], v[0:3], s[0:7] dmask:0xf unorm da
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; NOPRT-LABEL: load_mip_2darray:
|
|
; NOPRT: ; %bb.0: ; %main_body
|
|
; NOPRT-NEXT: image_load_mip v[0:3], v[0:3], s[0:7] dmask:0xf unorm da
|
|
; NOPRT-NEXT: s_waitcnt vmcnt(0)
|
|
; NOPRT-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: load_mip_2darray:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: image_load_mip v[0:3], v[0:3], s[0:7] dmask:0xf dim:SQ_RSRC_IMG_2D_ARRAY unorm ; encoding: [0x28,0x1f,0x04,0xf0,0x00,0x00,0x00,0x00]
|
|
; 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.load.mip.2darray.v4f32.i32(i32 15, i32 %s, i32 %t, i32 %slice, i32 %mip, <8 x i32> %rsrc, i32 0, i32 0)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps void @store_1d(<8 x i32> inreg %rsrc, <4 x float> %vdata, i32 %s) {
|
|
; VERDE-LABEL: store_1d:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: image_store v[0:3], v4, s[0:7] dmask:0xf unorm
|
|
; VERDE-NEXT: s_endpgm
|
|
;
|
|
; FIJI-LABEL: store_1d:
|
|
; FIJI: ; %bb.0: ; %main_body
|
|
; FIJI-NEXT: image_store v[0:3], v4, s[0:7] dmask:0xf unorm
|
|
; FIJI-NEXT: s_endpgm
|
|
;
|
|
; GFX6789-LABEL: store_1d:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: image_store v[0:3], v4, s[0:7] dmask:0xf unorm
|
|
; GFX6789-NEXT: s_endpgm
|
|
;
|
|
; NOPRT-LABEL: store_1d:
|
|
; NOPRT: ; %bb.0: ; %main_body
|
|
; NOPRT-NEXT: image_store v[0:3], v4, s[0:7] dmask:0xf unorm
|
|
; NOPRT-NEXT: s_endpgm
|
|
;
|
|
; GFX10-LABEL: store_1d:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: image_store v[0:3], v4, s[0:7] dmask:0xf dim:SQ_RSRC_IMG_1D unorm ; encoding: [0x00,0x1f,0x20,0xf0,0x04,0x00,0x00,0x00]
|
|
; GFX10-NEXT: s_endpgm ; encoding: [0x00,0x00,0x81,0xbf]
|
|
main_body:
|
|
call void @llvm.amdgcn.image.store.1d.v4f32.i32(<4 x float> %vdata, i32 15, i32 %s, <8 x i32> %rsrc, i32 0, i32 0)
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_ps void @store_2d(<8 x i32> inreg %rsrc, <4 x float> %vdata, i32 %s, i32 %t) {
|
|
; VERDE-LABEL: store_2d:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: image_store v[0:3], v[4:5], s[0:7] dmask:0xf unorm
|
|
; VERDE-NEXT: s_endpgm
|
|
;
|
|
; FIJI-LABEL: store_2d:
|
|
; FIJI: ; %bb.0: ; %main_body
|
|
; FIJI-NEXT: image_store v[0:3], v[4:5], s[0:7] dmask:0xf unorm
|
|
; FIJI-NEXT: s_endpgm
|
|
;
|
|
; GFX6789-LABEL: store_2d:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: image_store v[0:3], v[4:5], s[0:7] dmask:0xf unorm
|
|
; GFX6789-NEXT: s_endpgm
|
|
;
|
|
; NOPRT-LABEL: store_2d:
|
|
; NOPRT: ; %bb.0: ; %main_body
|
|
; NOPRT-NEXT: image_store v[0:3], v[4:5], s[0:7] dmask:0xf unorm
|
|
; NOPRT-NEXT: s_endpgm
|
|
;
|
|
; GFX10-LABEL: store_2d:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: image_store v[0:3], v[4:5], s[0:7] dmask:0xf dim:SQ_RSRC_IMG_2D unorm ; encoding: [0x08,0x1f,0x20,0xf0,0x04,0x00,0x00,0x00]
|
|
; GFX10-NEXT: s_endpgm ; encoding: [0x00,0x00,0x81,0xbf]
|
|
main_body:
|
|
call void @llvm.amdgcn.image.store.2d.v4f32.i32(<4 x float> %vdata, i32 15, i32 %s, i32 %t, <8 x i32> %rsrc, i32 0, i32 0)
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_ps void @store_3d(<8 x i32> inreg %rsrc, <4 x float> %vdata, i32 %s, i32 %t, i32 %r) {
|
|
; VERDE-LABEL: store_3d:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: image_store v[0:3], v[4:6], s[0:7] dmask:0xf unorm
|
|
; VERDE-NEXT: s_endpgm
|
|
;
|
|
; FIJI-LABEL: store_3d:
|
|
; FIJI: ; %bb.0: ; %main_body
|
|
; FIJI-NEXT: image_store v[0:3], v[4:6], s[0:7] dmask:0xf unorm
|
|
; FIJI-NEXT: s_endpgm
|
|
;
|
|
; GFX6789-LABEL: store_3d:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: image_store v[0:3], v[4:6], s[0:7] dmask:0xf unorm
|
|
; GFX6789-NEXT: s_endpgm
|
|
;
|
|
; NOPRT-LABEL: store_3d:
|
|
; NOPRT: ; %bb.0: ; %main_body
|
|
; NOPRT-NEXT: image_store v[0:3], v[4:6], s[0:7] dmask:0xf unorm
|
|
; NOPRT-NEXT: s_endpgm
|
|
;
|
|
; GFX10-LABEL: store_3d:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: image_store v[0:3], v[4:6], s[0:7] dmask:0xf dim:SQ_RSRC_IMG_3D unorm ; encoding: [0x10,0x1f,0x20,0xf0,0x04,0x00,0x00,0x00]
|
|
; GFX10-NEXT: s_endpgm ; encoding: [0x00,0x00,0x81,0xbf]
|
|
main_body:
|
|
call void @llvm.amdgcn.image.store.3d.v4f32.i32(<4 x float> %vdata, i32 15, i32 %s, i32 %t, i32 %r, <8 x i32> %rsrc, i32 0, i32 0)
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_ps void @store_cube(<8 x i32> inreg %rsrc, <4 x float> %vdata, i32 %s, i32 %t, i32 %slice) {
|
|
; VERDE-LABEL: store_cube:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: image_store v[0:3], v[4:6], s[0:7] dmask:0xf unorm da
|
|
; VERDE-NEXT: s_endpgm
|
|
;
|
|
; FIJI-LABEL: store_cube:
|
|
; FIJI: ; %bb.0: ; %main_body
|
|
; FIJI-NEXT: image_store v[0:3], v[4:6], s[0:7] dmask:0xf unorm da
|
|
; FIJI-NEXT: s_endpgm
|
|
;
|
|
; GFX6789-LABEL: store_cube:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: image_store v[0:3], v[4:6], s[0:7] dmask:0xf unorm da
|
|
; GFX6789-NEXT: s_endpgm
|
|
;
|
|
; NOPRT-LABEL: store_cube:
|
|
; NOPRT: ; %bb.0: ; %main_body
|
|
; NOPRT-NEXT: image_store v[0:3], v[4:6], s[0:7] dmask:0xf unorm da
|
|
; NOPRT-NEXT: s_endpgm
|
|
;
|
|
; GFX10-LABEL: store_cube:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: image_store v[0:3], v[4:6], s[0:7] dmask:0xf dim:SQ_RSRC_IMG_CUBE unorm ; encoding: [0x18,0x1f,0x20,0xf0,0x04,0x00,0x00,0x00]
|
|
; GFX10-NEXT: s_endpgm ; encoding: [0x00,0x00,0x81,0xbf]
|
|
main_body:
|
|
call void @llvm.amdgcn.image.store.cube.v4f32.i32(<4 x float> %vdata, i32 15, i32 %s, i32 %t, i32 %slice, <8 x i32> %rsrc, i32 0, i32 0)
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_ps void @store_1darray(<8 x i32> inreg %rsrc, <4 x float> %vdata, i32 %s, i32 %slice) {
|
|
; VERDE-LABEL: store_1darray:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: image_store v[0:3], v[4:5], s[0:7] dmask:0xf unorm da
|
|
; VERDE-NEXT: s_endpgm
|
|
;
|
|
; FIJI-LABEL: store_1darray:
|
|
; FIJI: ; %bb.0: ; %main_body
|
|
; FIJI-NEXT: image_store v[0:3], v[4:5], s[0:7] dmask:0xf unorm da
|
|
; FIJI-NEXT: s_endpgm
|
|
;
|
|
; GFX6789-LABEL: store_1darray:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: image_store v[0:3], v[4:5], s[0:7] dmask:0xf unorm da
|
|
; GFX6789-NEXT: s_endpgm
|
|
;
|
|
; NOPRT-LABEL: store_1darray:
|
|
; NOPRT: ; %bb.0: ; %main_body
|
|
; NOPRT-NEXT: image_store v[0:3], v[4:5], s[0:7] dmask:0xf unorm da
|
|
; NOPRT-NEXT: s_endpgm
|
|
;
|
|
; GFX10-LABEL: store_1darray:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: image_store v[0:3], v[4:5], s[0:7] dmask:0xf dim:SQ_RSRC_IMG_1D_ARRAY unorm ; encoding: [0x20,0x1f,0x20,0xf0,0x04,0x00,0x00,0x00]
|
|
; GFX10-NEXT: s_endpgm ; encoding: [0x00,0x00,0x81,0xbf]
|
|
main_body:
|
|
call void @llvm.amdgcn.image.store.1darray.v4f32.i32(<4 x float> %vdata, i32 15, i32 %s, i32 %slice, <8 x i32> %rsrc, i32 0, i32 0)
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_ps void @store_2darray(<8 x i32> inreg %rsrc, <4 x float> %vdata, i32 %s, i32 %t, i32 %slice) {
|
|
; VERDE-LABEL: store_2darray:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: image_store v[0:3], v[4:6], s[0:7] dmask:0xf unorm da
|
|
; VERDE-NEXT: s_endpgm
|
|
;
|
|
; FIJI-LABEL: store_2darray:
|
|
; FIJI: ; %bb.0: ; %main_body
|
|
; FIJI-NEXT: image_store v[0:3], v[4:6], s[0:7] dmask:0xf unorm da
|
|
; FIJI-NEXT: s_endpgm
|
|
;
|
|
; GFX6789-LABEL: store_2darray:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: image_store v[0:3], v[4:6], s[0:7] dmask:0xf unorm da
|
|
; GFX6789-NEXT: s_endpgm
|
|
;
|
|
; NOPRT-LABEL: store_2darray:
|
|
; NOPRT: ; %bb.0: ; %main_body
|
|
; NOPRT-NEXT: image_store v[0:3], v[4:6], s[0:7] dmask:0xf unorm da
|
|
; NOPRT-NEXT: s_endpgm
|
|
;
|
|
; GFX10-LABEL: store_2darray:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: image_store v[0:3], v[4:6], s[0:7] dmask:0xf dim:SQ_RSRC_IMG_2D_ARRAY unorm ; encoding: [0x28,0x1f,0x20,0xf0,0x04,0x00,0x00,0x00]
|
|
; GFX10-NEXT: s_endpgm ; encoding: [0x00,0x00,0x81,0xbf]
|
|
main_body:
|
|
call void @llvm.amdgcn.image.store.2darray.v4f32.i32(<4 x float> %vdata, i32 15, i32 %s, i32 %t, i32 %slice, <8 x i32> %rsrc, i32 0, i32 0)
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_ps void @store_2dmsaa(<8 x i32> inreg %rsrc, <4 x float> %vdata, i32 %s, i32 %t, i32 %fragid) {
|
|
; VERDE-LABEL: store_2dmsaa:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: image_store v[0:3], v[4:6], s[0:7] dmask:0xf unorm
|
|
; VERDE-NEXT: s_endpgm
|
|
;
|
|
; FIJI-LABEL: store_2dmsaa:
|
|
; FIJI: ; %bb.0: ; %main_body
|
|
; FIJI-NEXT: image_store v[0:3], v[4:6], s[0:7] dmask:0xf unorm
|
|
; FIJI-NEXT: s_endpgm
|
|
;
|
|
; GFX6789-LABEL: store_2dmsaa:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: image_store v[0:3], v[4:6], s[0:7] dmask:0xf unorm
|
|
; GFX6789-NEXT: s_endpgm
|
|
;
|
|
; NOPRT-LABEL: store_2dmsaa:
|
|
; NOPRT: ; %bb.0: ; %main_body
|
|
; NOPRT-NEXT: image_store v[0:3], v[4:6], s[0:7] dmask:0xf unorm
|
|
; NOPRT-NEXT: s_endpgm
|
|
;
|
|
; GFX10-LABEL: store_2dmsaa:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: image_store v[0:3], v[4:6], s[0:7] dmask:0xf dim:SQ_RSRC_IMG_2D_MSAA unorm ; encoding: [0x30,0x1f,0x20,0xf0,0x04,0x00,0x00,0x00]
|
|
; GFX10-NEXT: s_endpgm ; encoding: [0x00,0x00,0x81,0xbf]
|
|
main_body:
|
|
call void @llvm.amdgcn.image.store.2dmsaa.v4f32.i32(<4 x float> %vdata, i32 15, i32 %s, i32 %t, i32 %fragid, <8 x i32> %rsrc, i32 0, i32 0)
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_ps void @store_2darraymsaa(<8 x i32> inreg %rsrc, <4 x float> %vdata, i32 %s, i32 %t, i32 %slice, i32 %fragid) {
|
|
; VERDE-LABEL: store_2darraymsaa:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: image_store v[0:3], v[4:7], s[0:7] dmask:0xf unorm da
|
|
; VERDE-NEXT: s_endpgm
|
|
;
|
|
; FIJI-LABEL: store_2darraymsaa:
|
|
; FIJI: ; %bb.0: ; %main_body
|
|
; FIJI-NEXT: image_store v[0:3], v[4:7], s[0:7] dmask:0xf unorm da
|
|
; FIJI-NEXT: s_endpgm
|
|
;
|
|
; GFX6789-LABEL: store_2darraymsaa:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: image_store v[0:3], v[4:7], s[0:7] dmask:0xf unorm da
|
|
; GFX6789-NEXT: s_endpgm
|
|
;
|
|
; NOPRT-LABEL: store_2darraymsaa:
|
|
; NOPRT: ; %bb.0: ; %main_body
|
|
; NOPRT-NEXT: image_store v[0:3], v[4:7], s[0:7] dmask:0xf unorm da
|
|
; NOPRT-NEXT: s_endpgm
|
|
;
|
|
; GFX10-LABEL: store_2darraymsaa:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: image_store v[0:3], v[4:7], s[0:7] dmask:0xf dim:SQ_RSRC_IMG_2D_MSAA_ARRAY unorm ; encoding: [0x38,0x1f,0x20,0xf0,0x04,0x00,0x00,0x00]
|
|
; GFX10-NEXT: s_endpgm ; encoding: [0x00,0x00,0x81,0xbf]
|
|
main_body:
|
|
call void @llvm.amdgcn.image.store.2darraymsaa.v4f32.i32(<4 x float> %vdata, i32 15, i32 %s, i32 %t, i32 %slice, i32 %fragid, <8 x i32> %rsrc, i32 0, i32 0)
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_ps void @store_mip_1d(<8 x i32> inreg %rsrc, <4 x float> %vdata, i32 %s, i32 %mip) {
|
|
; VERDE-LABEL: store_mip_1d:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: image_store_mip v[0:3], v[4:5], s[0:7] dmask:0xf unorm
|
|
; VERDE-NEXT: s_endpgm
|
|
;
|
|
; FIJI-LABEL: store_mip_1d:
|
|
; FIJI: ; %bb.0: ; %main_body
|
|
; FIJI-NEXT: image_store_mip v[0:3], v[4:5], s[0:7] dmask:0xf unorm
|
|
; FIJI-NEXT: s_endpgm
|
|
;
|
|
; GFX6789-LABEL: store_mip_1d:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: image_store_mip v[0:3], v[4:5], s[0:7] dmask:0xf unorm
|
|
; GFX6789-NEXT: s_endpgm
|
|
;
|
|
; NOPRT-LABEL: store_mip_1d:
|
|
; NOPRT: ; %bb.0: ; %main_body
|
|
; NOPRT-NEXT: image_store_mip v[0:3], v[4:5], s[0:7] dmask:0xf unorm
|
|
; NOPRT-NEXT: s_endpgm
|
|
;
|
|
; GFX10-LABEL: store_mip_1d:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: image_store_mip v[0:3], v[4:5], s[0:7] dmask:0xf dim:SQ_RSRC_IMG_1D unorm ; encoding: [0x00,0x1f,0x24,0xf0,0x04,0x00,0x00,0x00]
|
|
; GFX10-NEXT: s_endpgm ; encoding: [0x00,0x00,0x81,0xbf]
|
|
main_body:
|
|
call void @llvm.amdgcn.image.store.mip.1d.v4f32.i32(<4 x float> %vdata, i32 15, i32 %s, i32 %mip, <8 x i32> %rsrc, i32 0, i32 0)
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_ps void @store_mip_2d(<8 x i32> inreg %rsrc, <4 x float> %vdata, i32 %s, i32 %t, i32 %mip) {
|
|
; VERDE-LABEL: store_mip_2d:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: image_store_mip v[0:3], v[4:6], s[0:7] dmask:0xf unorm
|
|
; VERDE-NEXT: s_endpgm
|
|
;
|
|
; FIJI-LABEL: store_mip_2d:
|
|
; FIJI: ; %bb.0: ; %main_body
|
|
; FIJI-NEXT: image_store_mip v[0:3], v[4:6], s[0:7] dmask:0xf unorm
|
|
; FIJI-NEXT: s_endpgm
|
|
;
|
|
; GFX6789-LABEL: store_mip_2d:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: image_store_mip v[0:3], v[4:6], s[0:7] dmask:0xf unorm
|
|
; GFX6789-NEXT: s_endpgm
|
|
;
|
|
; NOPRT-LABEL: store_mip_2d:
|
|
; NOPRT: ; %bb.0: ; %main_body
|
|
; NOPRT-NEXT: image_store_mip v[0:3], v[4:6], s[0:7] dmask:0xf unorm
|
|
; NOPRT-NEXT: s_endpgm
|
|
;
|
|
; GFX10-LABEL: store_mip_2d:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: image_store_mip v[0:3], v[4:6], s[0:7] dmask:0xf dim:SQ_RSRC_IMG_2D unorm ; encoding: [0x08,0x1f,0x24,0xf0,0x04,0x00,0x00,0x00]
|
|
; GFX10-NEXT: s_endpgm ; encoding: [0x00,0x00,0x81,0xbf]
|
|
main_body:
|
|
call void @llvm.amdgcn.image.store.mip.2d.v4f32.i32(<4 x float> %vdata, i32 15, i32 %s, i32 %t, i32 %mip, <8 x i32> %rsrc, i32 0, i32 0)
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_ps void @store_mip_3d(<8 x i32> inreg %rsrc, <4 x float> %vdata, i32 %s, i32 %t, i32 %r, i32 %mip) {
|
|
; VERDE-LABEL: store_mip_3d:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: image_store_mip v[0:3], v[4:7], s[0:7] dmask:0xf unorm
|
|
; VERDE-NEXT: s_endpgm
|
|
;
|
|
; FIJI-LABEL: store_mip_3d:
|
|
; FIJI: ; %bb.0: ; %main_body
|
|
; FIJI-NEXT: image_store_mip v[0:3], v[4:7], s[0:7] dmask:0xf unorm
|
|
; FIJI-NEXT: s_endpgm
|
|
;
|
|
; GFX6789-LABEL: store_mip_3d:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: image_store_mip v[0:3], v[4:7], s[0:7] dmask:0xf unorm
|
|
; GFX6789-NEXT: s_endpgm
|
|
;
|
|
; NOPRT-LABEL: store_mip_3d:
|
|
; NOPRT: ; %bb.0: ; %main_body
|
|
; NOPRT-NEXT: image_store_mip v[0:3], v[4:7], s[0:7] dmask:0xf unorm
|
|
; NOPRT-NEXT: s_endpgm
|
|
;
|
|
; GFX10-LABEL: store_mip_3d:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: image_store_mip v[0:3], v[4:7], s[0:7] dmask:0xf dim:SQ_RSRC_IMG_3D unorm ; encoding: [0x10,0x1f,0x24,0xf0,0x04,0x00,0x00,0x00]
|
|
; GFX10-NEXT: s_endpgm ; encoding: [0x00,0x00,0x81,0xbf]
|
|
main_body:
|
|
call void @llvm.amdgcn.image.store.mip.3d.v4f32.i32(<4 x float> %vdata, i32 15, i32 %s, i32 %t, i32 %r, i32 %mip, <8 x i32> %rsrc, i32 0, i32 0)
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_ps void @store_mip_cube(<8 x i32> inreg %rsrc, <4 x float> %vdata, i32 %s, i32 %t, i32 %slice, i32 %mip) {
|
|
; VERDE-LABEL: store_mip_cube:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: image_store_mip v[0:3], v[4:7], s[0:7] dmask:0xf unorm da
|
|
; VERDE-NEXT: s_endpgm
|
|
;
|
|
; FIJI-LABEL: store_mip_cube:
|
|
; FIJI: ; %bb.0: ; %main_body
|
|
; FIJI-NEXT: image_store_mip v[0:3], v[4:7], s[0:7] dmask:0xf unorm da
|
|
; FIJI-NEXT: s_endpgm
|
|
;
|
|
; GFX6789-LABEL: store_mip_cube:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: image_store_mip v[0:3], v[4:7], s[0:7] dmask:0xf unorm da
|
|
; GFX6789-NEXT: s_endpgm
|
|
;
|
|
; NOPRT-LABEL: store_mip_cube:
|
|
; NOPRT: ; %bb.0: ; %main_body
|
|
; NOPRT-NEXT: image_store_mip v[0:3], v[4:7], s[0:7] dmask:0xf unorm da
|
|
; NOPRT-NEXT: s_endpgm
|
|
;
|
|
; GFX10-LABEL: store_mip_cube:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: image_store_mip v[0:3], v[4:7], s[0:7] dmask:0xf dim:SQ_RSRC_IMG_CUBE unorm ; encoding: [0x18,0x1f,0x24,0xf0,0x04,0x00,0x00,0x00]
|
|
; GFX10-NEXT: s_endpgm ; encoding: [0x00,0x00,0x81,0xbf]
|
|
main_body:
|
|
call void @llvm.amdgcn.image.store.mip.cube.v4f32.i32(<4 x float> %vdata, i32 15, i32 %s, i32 %t, i32 %slice, i32 %mip, <8 x i32> %rsrc, i32 0, i32 0)
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_ps void @store_mip_1darray(<8 x i32> inreg %rsrc, <4 x float> %vdata, i32 %s, i32 %slice, i32 %mip) {
|
|
; VERDE-LABEL: store_mip_1darray:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: image_store_mip v[0:3], v[4:6], s[0:7] dmask:0xf unorm da
|
|
; VERDE-NEXT: s_endpgm
|
|
;
|
|
; FIJI-LABEL: store_mip_1darray:
|
|
; FIJI: ; %bb.0: ; %main_body
|
|
; FIJI-NEXT: image_store_mip v[0:3], v[4:6], s[0:7] dmask:0xf unorm da
|
|
; FIJI-NEXT: s_endpgm
|
|
;
|
|
; GFX6789-LABEL: store_mip_1darray:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: image_store_mip v[0:3], v[4:6], s[0:7] dmask:0xf unorm da
|
|
; GFX6789-NEXT: s_endpgm
|
|
;
|
|
; NOPRT-LABEL: store_mip_1darray:
|
|
; NOPRT: ; %bb.0: ; %main_body
|
|
; NOPRT-NEXT: image_store_mip v[0:3], v[4:6], s[0:7] dmask:0xf unorm da
|
|
; NOPRT-NEXT: s_endpgm
|
|
;
|
|
; GFX10-LABEL: store_mip_1darray:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: image_store_mip v[0:3], v[4:6], s[0:7] dmask:0xf dim:SQ_RSRC_IMG_1D_ARRAY unorm ; encoding: [0x20,0x1f,0x24,0xf0,0x04,0x00,0x00,0x00]
|
|
; GFX10-NEXT: s_endpgm ; encoding: [0x00,0x00,0x81,0xbf]
|
|
main_body:
|
|
call void @llvm.amdgcn.image.store.mip.1darray.v4f32.i32(<4 x float> %vdata, i32 15, i32 %s, i32 %slice, i32 %mip, <8 x i32> %rsrc, i32 0, i32 0)
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_ps void @store_mip_2darray(<8 x i32> inreg %rsrc, <4 x float> %vdata, i32 %s, i32 %t, i32 %slice, i32 %mip) {
|
|
; VERDE-LABEL: store_mip_2darray:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: image_store_mip v[0:3], v[4:7], s[0:7] dmask:0xf unorm da
|
|
; VERDE-NEXT: s_endpgm
|
|
;
|
|
; FIJI-LABEL: store_mip_2darray:
|
|
; FIJI: ; %bb.0: ; %main_body
|
|
; FIJI-NEXT: image_store_mip v[0:3], v[4:7], s[0:7] dmask:0xf unorm da
|
|
; FIJI-NEXT: s_endpgm
|
|
;
|
|
; GFX6789-LABEL: store_mip_2darray:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: image_store_mip v[0:3], v[4:7], s[0:7] dmask:0xf unorm da
|
|
; GFX6789-NEXT: s_endpgm
|
|
;
|
|
; NOPRT-LABEL: store_mip_2darray:
|
|
; NOPRT: ; %bb.0: ; %main_body
|
|
; NOPRT-NEXT: image_store_mip v[0:3], v[4:7], s[0:7] dmask:0xf unorm da
|
|
; NOPRT-NEXT: s_endpgm
|
|
;
|
|
; GFX10-LABEL: store_mip_2darray:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: image_store_mip v[0:3], v[4:7], s[0:7] dmask:0xf dim:SQ_RSRC_IMG_2D_ARRAY unorm ; encoding: [0x28,0x1f,0x24,0xf0,0x04,0x00,0x00,0x00]
|
|
; GFX10-NEXT: s_endpgm ; encoding: [0x00,0x00,0x81,0xbf]
|
|
main_body:
|
|
call void @llvm.amdgcn.image.store.mip.2darray.v4f32.i32(<4 x float> %vdata, i32 15, i32 %s, i32 %t, i32 %slice, i32 %mip, <8 x i32> %rsrc, i32 0, i32 0)
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @getresinfo_1d(<8 x i32> inreg %rsrc, i32 %mip) {
|
|
; VERDE-LABEL: getresinfo_1d:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: image_get_resinfo v[0:3], v0, s[0:7] dmask:0xf unorm
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; FIJI-LABEL: getresinfo_1d:
|
|
; FIJI: ; %bb.0: ; %main_body
|
|
; FIJI-NEXT: image_get_resinfo v[0:3], v0, s[0:7] dmask:0xf unorm
|
|
; FIJI-NEXT: s_waitcnt vmcnt(0)
|
|
; FIJI-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: getresinfo_1d:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: image_get_resinfo v[0:3], v0, s[0:7] dmask:0xf unorm
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; NOPRT-LABEL: getresinfo_1d:
|
|
; NOPRT: ; %bb.0: ; %main_body
|
|
; NOPRT-NEXT: image_get_resinfo v[0:3], v0, s[0:7] dmask:0xf unorm
|
|
; NOPRT-NEXT: s_waitcnt vmcnt(0)
|
|
; NOPRT-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: getresinfo_1d:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: image_get_resinfo v[0:3], v0, s[0:7] dmask:0xf dim:SQ_RSRC_IMG_1D unorm ; encoding: [0x00,0x1f,0x38,0xf0,0x00,0x00,0x00,0x00]
|
|
; 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.getresinfo.1d.v4f32.i32(i32 15, i32 %mip, <8 x i32> %rsrc, i32 0, i32 0)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @getresinfo_2d(<8 x i32> inreg %rsrc, i32 %mip) {
|
|
; VERDE-LABEL: getresinfo_2d:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: image_get_resinfo v[0:3], v0, s[0:7] dmask:0xf unorm
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; FIJI-LABEL: getresinfo_2d:
|
|
; FIJI: ; %bb.0: ; %main_body
|
|
; FIJI-NEXT: image_get_resinfo v[0:3], v0, s[0:7] dmask:0xf unorm
|
|
; FIJI-NEXT: s_waitcnt vmcnt(0)
|
|
; FIJI-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: getresinfo_2d:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: image_get_resinfo v[0:3], v0, s[0:7] dmask:0xf unorm
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; NOPRT-LABEL: getresinfo_2d:
|
|
; NOPRT: ; %bb.0: ; %main_body
|
|
; NOPRT-NEXT: image_get_resinfo v[0:3], v0, s[0:7] dmask:0xf unorm
|
|
; NOPRT-NEXT: s_waitcnt vmcnt(0)
|
|
; NOPRT-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: getresinfo_2d:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: image_get_resinfo v[0:3], v0, s[0:7] dmask:0xf dim:SQ_RSRC_IMG_2D unorm ; encoding: [0x08,0x1f,0x38,0xf0,0x00,0x00,0x00,0x00]
|
|
; 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.getresinfo.2d.v4f32.i32(i32 15, i32 %mip, <8 x i32> %rsrc, i32 0, i32 0)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @getresinfo_3d(<8 x i32> inreg %rsrc, i32 %mip) {
|
|
; VERDE-LABEL: getresinfo_3d:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: image_get_resinfo v[0:3], v0, s[0:7] dmask:0xf unorm
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; FIJI-LABEL: getresinfo_3d:
|
|
; FIJI: ; %bb.0: ; %main_body
|
|
; FIJI-NEXT: image_get_resinfo v[0:3], v0, s[0:7] dmask:0xf unorm
|
|
; FIJI-NEXT: s_waitcnt vmcnt(0)
|
|
; FIJI-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: getresinfo_3d:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: image_get_resinfo v[0:3], v0, s[0:7] dmask:0xf unorm
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; NOPRT-LABEL: getresinfo_3d:
|
|
; NOPRT: ; %bb.0: ; %main_body
|
|
; NOPRT-NEXT: image_get_resinfo v[0:3], v0, s[0:7] dmask:0xf unorm
|
|
; NOPRT-NEXT: s_waitcnt vmcnt(0)
|
|
; NOPRT-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: getresinfo_3d:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: image_get_resinfo v[0:3], v0, s[0:7] dmask:0xf dim:SQ_RSRC_IMG_3D unorm ; encoding: [0x10,0x1f,0x38,0xf0,0x00,0x00,0x00,0x00]
|
|
; 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.getresinfo.3d.v4f32.i32(i32 15, i32 %mip, <8 x i32> %rsrc, i32 0, i32 0)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @getresinfo_cube(<8 x i32> inreg %rsrc, i32 %mip) {
|
|
; VERDE-LABEL: getresinfo_cube:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: image_get_resinfo v[0:3], v0, s[0:7] dmask:0xf unorm da
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; FIJI-LABEL: getresinfo_cube:
|
|
; FIJI: ; %bb.0: ; %main_body
|
|
; FIJI-NEXT: image_get_resinfo v[0:3], v0, s[0:7] dmask:0xf unorm da
|
|
; FIJI-NEXT: s_waitcnt vmcnt(0)
|
|
; FIJI-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: getresinfo_cube:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: image_get_resinfo v[0:3], v0, s[0:7] dmask:0xf unorm da
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; NOPRT-LABEL: getresinfo_cube:
|
|
; NOPRT: ; %bb.0: ; %main_body
|
|
; NOPRT-NEXT: image_get_resinfo v[0:3], v0, s[0:7] dmask:0xf unorm da
|
|
; NOPRT-NEXT: s_waitcnt vmcnt(0)
|
|
; NOPRT-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: getresinfo_cube:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: image_get_resinfo v[0:3], v0, s[0:7] dmask:0xf dim:SQ_RSRC_IMG_CUBE unorm ; encoding: [0x18,0x1f,0x38,0xf0,0x00,0x00,0x00,0x00]
|
|
; 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.getresinfo.cube.v4f32.i32(i32 15, i32 %mip, <8 x i32> %rsrc, i32 0, i32 0)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @getresinfo_1darray(<8 x i32> inreg %rsrc, i32 %mip) {
|
|
; VERDE-LABEL: getresinfo_1darray:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: image_get_resinfo v[0:3], v0, s[0:7] dmask:0xf unorm da
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; FIJI-LABEL: getresinfo_1darray:
|
|
; FIJI: ; %bb.0: ; %main_body
|
|
; FIJI-NEXT: image_get_resinfo v[0:3], v0, s[0:7] dmask:0xf unorm da
|
|
; FIJI-NEXT: s_waitcnt vmcnt(0)
|
|
; FIJI-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: getresinfo_1darray:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: image_get_resinfo v[0:3], v0, s[0:7] dmask:0xf unorm da
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; NOPRT-LABEL: getresinfo_1darray:
|
|
; NOPRT: ; %bb.0: ; %main_body
|
|
; NOPRT-NEXT: image_get_resinfo v[0:3], v0, s[0:7] dmask:0xf unorm da
|
|
; NOPRT-NEXT: s_waitcnt vmcnt(0)
|
|
; NOPRT-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: getresinfo_1darray:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: image_get_resinfo v[0:3], v0, s[0:7] dmask:0xf dim:SQ_RSRC_IMG_1D_ARRAY unorm ; encoding: [0x20,0x1f,0x38,0xf0,0x00,0x00,0x00,0x00]
|
|
; 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.getresinfo.1darray.v4f32.i32(i32 15, i32 %mip, <8 x i32> %rsrc, i32 0, i32 0)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @getresinfo_2darray(<8 x i32> inreg %rsrc, i32 %mip) {
|
|
; VERDE-LABEL: getresinfo_2darray:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: image_get_resinfo v[0:3], v0, s[0:7] dmask:0xf unorm da
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; FIJI-LABEL: getresinfo_2darray:
|
|
; FIJI: ; %bb.0: ; %main_body
|
|
; FIJI-NEXT: image_get_resinfo v[0:3], v0, s[0:7] dmask:0xf unorm da
|
|
; FIJI-NEXT: s_waitcnt vmcnt(0)
|
|
; FIJI-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: getresinfo_2darray:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: image_get_resinfo v[0:3], v0, s[0:7] dmask:0xf unorm da
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; NOPRT-LABEL: getresinfo_2darray:
|
|
; NOPRT: ; %bb.0: ; %main_body
|
|
; NOPRT-NEXT: image_get_resinfo v[0:3], v0, s[0:7] dmask:0xf unorm da
|
|
; NOPRT-NEXT: s_waitcnt vmcnt(0)
|
|
; NOPRT-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: getresinfo_2darray:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: image_get_resinfo v[0:3], v0, s[0:7] dmask:0xf dim:SQ_RSRC_IMG_2D_ARRAY unorm ; encoding: [0x28,0x1f,0x38,0xf0,0x00,0x00,0x00,0x00]
|
|
; 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.getresinfo.2darray.v4f32.i32(i32 15, i32 %mip, <8 x i32> %rsrc, i32 0, i32 0)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @getresinfo_2dmsaa(<8 x i32> inreg %rsrc, i32 %mip) {
|
|
; VERDE-LABEL: getresinfo_2dmsaa:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: image_get_resinfo v[0:3], v0, s[0:7] dmask:0xf unorm
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; FIJI-LABEL: getresinfo_2dmsaa:
|
|
; FIJI: ; %bb.0: ; %main_body
|
|
; FIJI-NEXT: image_get_resinfo v[0:3], v0, s[0:7] dmask:0xf unorm
|
|
; FIJI-NEXT: s_waitcnt vmcnt(0)
|
|
; FIJI-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: getresinfo_2dmsaa:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: image_get_resinfo v[0:3], v0, s[0:7] dmask:0xf unorm
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; NOPRT-LABEL: getresinfo_2dmsaa:
|
|
; NOPRT: ; %bb.0: ; %main_body
|
|
; NOPRT-NEXT: image_get_resinfo v[0:3], v0, s[0:7] dmask:0xf unorm
|
|
; NOPRT-NEXT: s_waitcnt vmcnt(0)
|
|
; NOPRT-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: getresinfo_2dmsaa:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: image_get_resinfo v[0:3], v0, s[0:7] dmask:0xf dim:SQ_RSRC_IMG_2D_MSAA unorm ; encoding: [0x30,0x1f,0x38,0xf0,0x00,0x00,0x00,0x00]
|
|
; 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.getresinfo.2dmsaa.v4f32.i32(i32 15, i32 %mip, <8 x i32> %rsrc, i32 0, i32 0)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @getresinfo_2darraymsaa(<8 x i32> inreg %rsrc, i32 %mip) {
|
|
; VERDE-LABEL: getresinfo_2darraymsaa:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: image_get_resinfo v[0:3], v0, s[0:7] dmask:0xf unorm da
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; FIJI-LABEL: getresinfo_2darraymsaa:
|
|
; FIJI: ; %bb.0: ; %main_body
|
|
; FIJI-NEXT: image_get_resinfo v[0:3], v0, s[0:7] dmask:0xf unorm da
|
|
; FIJI-NEXT: s_waitcnt vmcnt(0)
|
|
; FIJI-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: getresinfo_2darraymsaa:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: image_get_resinfo v[0:3], v0, s[0:7] dmask:0xf unorm da
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; NOPRT-LABEL: getresinfo_2darraymsaa:
|
|
; NOPRT: ; %bb.0: ; %main_body
|
|
; NOPRT-NEXT: image_get_resinfo v[0:3], v0, s[0:7] dmask:0xf unorm da
|
|
; NOPRT-NEXT: s_waitcnt vmcnt(0)
|
|
; NOPRT-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: getresinfo_2darraymsaa:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: image_get_resinfo v[0:3], v0, s[0:7] dmask:0xf dim:SQ_RSRC_IMG_2D_MSAA_ARRAY unorm ; encoding: [0x38,0x1f,0x38,0xf0,0x00,0x00,0x00,0x00]
|
|
; 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.getresinfo.2darraymsaa.v4f32.i32(i32 15, i32 %mip, <8 x i32> %rsrc, i32 0, i32 0)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps float @load_1d_V1(<8 x i32> inreg %rsrc, i32 %s) {
|
|
; VERDE-LABEL: load_1d_V1:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: image_load v0, v0, s[0:7] dmask:0x8 unorm
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; FIJI-LABEL: load_1d_V1:
|
|
; FIJI: ; %bb.0: ; %main_body
|
|
; FIJI-NEXT: image_load v0, v0, s[0:7] dmask:0x8 unorm
|
|
; FIJI-NEXT: s_waitcnt vmcnt(0)
|
|
; FIJI-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: load_1d_V1:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: image_load v0, v0, s[0:7] dmask:0x8 unorm
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; NOPRT-LABEL: load_1d_V1:
|
|
; NOPRT: ; %bb.0: ; %main_body
|
|
; NOPRT-NEXT: image_load v0, v0, s[0:7] dmask:0x8 unorm
|
|
; NOPRT-NEXT: s_waitcnt vmcnt(0)
|
|
; NOPRT-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: load_1d_V1:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: image_load v0, v0, s[0:7] dmask:0x8 dim:SQ_RSRC_IMG_1D unorm ; encoding: [0x00,0x18,0x00,0xf0,0x00,0x00,0x00,0x00]
|
|
; 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.load.1d.f32.i32(i32 8, i32 %s, <8 x i32> %rsrc, i32 0, i32 0)
|
|
ret float %v
|
|
}
|
|
|
|
define amdgpu_ps <2 x float> @load_1d_V2(<8 x i32> inreg %rsrc, i32 %s) {
|
|
; VERDE-LABEL: load_1d_V2:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: image_load v[0:1], v0, s[0:7] dmask:0x9 unorm
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; FIJI-LABEL: load_1d_V2:
|
|
; FIJI: ; %bb.0: ; %main_body
|
|
; FIJI-NEXT: image_load v[0:1], v0, s[0:7] dmask:0x9 unorm
|
|
; FIJI-NEXT: s_waitcnt vmcnt(0)
|
|
; FIJI-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: load_1d_V2:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: image_load v[0:1], v0, s[0:7] dmask:0x9 unorm
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; NOPRT-LABEL: load_1d_V2:
|
|
; NOPRT: ; %bb.0: ; %main_body
|
|
; NOPRT-NEXT: image_load v[0:1], v0, s[0:7] dmask:0x9 unorm
|
|
; NOPRT-NEXT: s_waitcnt vmcnt(0)
|
|
; NOPRT-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: load_1d_V2:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: image_load v[0:1], v0, s[0:7] dmask:0x9 dim:SQ_RSRC_IMG_1D unorm ; encoding: [0x00,0x19,0x00,0xf0,0x00,0x00,0x00,0x00]
|
|
; 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.load.1d.v2f32.i32(i32 9, i32 %s, <8 x i32> %rsrc, i32 0, i32 0)
|
|
ret <2 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps void @store_1d_V1(<8 x i32> inreg %rsrc, float %vdata, i32 %s) {
|
|
; VERDE-LABEL: store_1d_V1:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: image_store v0, v1, s[0:7] dmask:0x2 unorm
|
|
; VERDE-NEXT: s_endpgm
|
|
;
|
|
; FIJI-LABEL: store_1d_V1:
|
|
; FIJI: ; %bb.0: ; %main_body
|
|
; FIJI-NEXT: image_store v0, v1, s[0:7] dmask:0x2 unorm
|
|
; FIJI-NEXT: s_endpgm
|
|
;
|
|
; GFX6789-LABEL: store_1d_V1:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: image_store v0, v1, s[0:7] dmask:0x2 unorm
|
|
; GFX6789-NEXT: s_endpgm
|
|
;
|
|
; NOPRT-LABEL: store_1d_V1:
|
|
; NOPRT: ; %bb.0: ; %main_body
|
|
; NOPRT-NEXT: image_store v0, v1, s[0:7] dmask:0x2 unorm
|
|
; NOPRT-NEXT: s_endpgm
|
|
;
|
|
; GFX10-LABEL: store_1d_V1:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: image_store v0, v1, s[0:7] dmask:0x2 dim:SQ_RSRC_IMG_1D unorm ; encoding: [0x00,0x12,0x20,0xf0,0x01,0x00,0x00,0x00]
|
|
; GFX10-NEXT: s_endpgm ; encoding: [0x00,0x00,0x81,0xbf]
|
|
main_body:
|
|
call void @llvm.amdgcn.image.store.1d.f32.i32(float %vdata, i32 2, i32 %s, <8 x i32> %rsrc, i32 0, i32 0)
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_ps void @store_1d_V2(<8 x i32> inreg %rsrc, <2 x float> %vdata, i32 %s) {
|
|
; VERDE-LABEL: store_1d_V2:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: image_store v[0:1], v2, s[0:7] dmask:0xc unorm
|
|
; VERDE-NEXT: s_endpgm
|
|
;
|
|
; FIJI-LABEL: store_1d_V2:
|
|
; FIJI: ; %bb.0: ; %main_body
|
|
; FIJI-NEXT: image_store v[0:1], v2, s[0:7] dmask:0xc unorm
|
|
; FIJI-NEXT: s_endpgm
|
|
;
|
|
; GFX6789-LABEL: store_1d_V2:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: image_store v[0:1], v2, s[0:7] dmask:0xc unorm
|
|
; GFX6789-NEXT: s_endpgm
|
|
;
|
|
; NOPRT-LABEL: store_1d_V2:
|
|
; NOPRT: ; %bb.0: ; %main_body
|
|
; NOPRT-NEXT: image_store v[0:1], v2, s[0:7] dmask:0xc unorm
|
|
; NOPRT-NEXT: s_endpgm
|
|
;
|
|
; GFX10-LABEL: store_1d_V2:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: image_store v[0:1], v2, s[0:7] dmask:0xc dim:SQ_RSRC_IMG_1D unorm ; encoding: [0x00,0x1c,0x20,0xf0,0x02,0x00,0x00,0x00]
|
|
; GFX10-NEXT: s_endpgm ; encoding: [0x00,0x00,0x81,0xbf]
|
|
main_body:
|
|
call void @llvm.amdgcn.image.store.1d.v2f32.i32(<2 x float> %vdata, i32 12, i32 %s, <8 x i32> %rsrc, i32 0, i32 0)
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @load_1d_glc(<8 x i32> inreg %rsrc, i32 %s) {
|
|
; VERDE-LABEL: load_1d_glc:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: image_load v[0:3], v0, s[0:7] dmask:0xf unorm glc
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; FIJI-LABEL: load_1d_glc:
|
|
; FIJI: ; %bb.0: ; %main_body
|
|
; FIJI-NEXT: image_load v[0:3], v0, s[0:7] dmask:0xf unorm glc
|
|
; FIJI-NEXT: s_waitcnt vmcnt(0)
|
|
; FIJI-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: load_1d_glc:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: image_load v[0:3], v0, s[0:7] dmask:0xf unorm glc
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; NOPRT-LABEL: load_1d_glc:
|
|
; NOPRT: ; %bb.0: ; %main_body
|
|
; NOPRT-NEXT: image_load v[0:3], v0, s[0:7] dmask:0xf unorm glc
|
|
; NOPRT-NEXT: s_waitcnt vmcnt(0)
|
|
; NOPRT-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: load_1d_glc:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: image_load v[0:3], v0, s[0:7] dmask:0xf dim:SQ_RSRC_IMG_1D unorm glc ; encoding: [0x00,0x3f,0x00,0xf0,0x00,0x00,0x00,0x00]
|
|
; 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.load.1d.v4f32.i32(i32 15, i32 %s, <8 x i32> %rsrc, i32 0, i32 1)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @load_1d_slc(<8 x i32> inreg %rsrc, i32 %s) {
|
|
; VERDE-LABEL: load_1d_slc:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: image_load v[0:3], v0, s[0:7] dmask:0xf unorm slc
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; FIJI-LABEL: load_1d_slc:
|
|
; FIJI: ; %bb.0: ; %main_body
|
|
; FIJI-NEXT: image_load v[0:3], v0, s[0:7] dmask:0xf unorm slc
|
|
; FIJI-NEXT: s_waitcnt vmcnt(0)
|
|
; FIJI-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: load_1d_slc:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: image_load v[0:3], v0, s[0:7] dmask:0xf unorm slc
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; NOPRT-LABEL: load_1d_slc:
|
|
; NOPRT: ; %bb.0: ; %main_body
|
|
; NOPRT-NEXT: image_load v[0:3], v0, s[0:7] dmask:0xf unorm slc
|
|
; NOPRT-NEXT: s_waitcnt vmcnt(0)
|
|
; NOPRT-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: load_1d_slc:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: image_load v[0:3], v0, s[0:7] dmask:0xf dim:SQ_RSRC_IMG_1D unorm slc ; encoding: [0x00,0x1f,0x00,0xf2,0x00,0x00,0x00,0x00]
|
|
; 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.load.1d.v4f32.i32(i32 15, i32 %s, <8 x i32> %rsrc, i32 0, i32 2)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @load_1d_glc_slc(<8 x i32> inreg %rsrc, i32 %s) {
|
|
; VERDE-LABEL: load_1d_glc_slc:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: image_load v[0:3], v0, s[0:7] dmask:0xf unorm glc slc
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; FIJI-LABEL: load_1d_glc_slc:
|
|
; FIJI: ; %bb.0: ; %main_body
|
|
; FIJI-NEXT: image_load v[0:3], v0, s[0:7] dmask:0xf unorm glc slc
|
|
; FIJI-NEXT: s_waitcnt vmcnt(0)
|
|
; FIJI-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: load_1d_glc_slc:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: image_load v[0:3], v0, s[0:7] dmask:0xf unorm glc slc
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; NOPRT-LABEL: load_1d_glc_slc:
|
|
; NOPRT: ; %bb.0: ; %main_body
|
|
; NOPRT-NEXT: image_load v[0:3], v0, s[0:7] dmask:0xf unorm glc slc
|
|
; NOPRT-NEXT: s_waitcnt vmcnt(0)
|
|
; NOPRT-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: load_1d_glc_slc:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: image_load v[0:3], v0, s[0:7] dmask:0xf dim:SQ_RSRC_IMG_1D unorm glc slc ; encoding: [0x00,0x3f,0x00,0xf2,0x00,0x00,0x00,0x00]
|
|
; 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.load.1d.v4f32.i32(i32 15, i32 %s, <8 x i32> %rsrc, i32 0, i32 3)
|
|
ret <4 x float> %v
|
|
}
|
|
|
|
define amdgpu_ps void @store_1d_glc(<8 x i32> inreg %rsrc, <4 x float> %vdata, i32 %s) {
|
|
; VERDE-LABEL: store_1d_glc:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: image_store v[0:3], v4, s[0:7] dmask:0xf unorm glc
|
|
; VERDE-NEXT: s_endpgm
|
|
;
|
|
; FIJI-LABEL: store_1d_glc:
|
|
; FIJI: ; %bb.0: ; %main_body
|
|
; FIJI-NEXT: image_store v[0:3], v4, s[0:7] dmask:0xf unorm glc
|
|
; FIJI-NEXT: s_endpgm
|
|
;
|
|
; GFX6789-LABEL: store_1d_glc:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: image_store v[0:3], v4, s[0:7] dmask:0xf unorm glc
|
|
; GFX6789-NEXT: s_endpgm
|
|
;
|
|
; NOPRT-LABEL: store_1d_glc:
|
|
; NOPRT: ; %bb.0: ; %main_body
|
|
; NOPRT-NEXT: image_store v[0:3], v4, s[0:7] dmask:0xf unorm glc
|
|
; NOPRT-NEXT: s_endpgm
|
|
;
|
|
; GFX10-LABEL: store_1d_glc:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: image_store v[0:3], v4, s[0:7] dmask:0xf dim:SQ_RSRC_IMG_1D unorm glc ; encoding: [0x00,0x3f,0x20,0xf0,0x04,0x00,0x00,0x00]
|
|
; GFX10-NEXT: s_endpgm ; encoding: [0x00,0x00,0x81,0xbf]
|
|
main_body:
|
|
call void @llvm.amdgcn.image.store.1d.v4f32.i32(<4 x float> %vdata, i32 15, i32 %s, <8 x i32> %rsrc, i32 0, i32 1)
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_ps void @store_1d_slc(<8 x i32> inreg %rsrc, <4 x float> %vdata, i32 %s) {
|
|
; VERDE-LABEL: store_1d_slc:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: image_store v[0:3], v4, s[0:7] dmask:0xf unorm slc
|
|
; VERDE-NEXT: s_endpgm
|
|
;
|
|
; FIJI-LABEL: store_1d_slc:
|
|
; FIJI: ; %bb.0: ; %main_body
|
|
; FIJI-NEXT: image_store v[0:3], v4, s[0:7] dmask:0xf unorm slc
|
|
; FIJI-NEXT: s_endpgm
|
|
;
|
|
; GFX6789-LABEL: store_1d_slc:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: image_store v[0:3], v4, s[0:7] dmask:0xf unorm slc
|
|
; GFX6789-NEXT: s_endpgm
|
|
;
|
|
; NOPRT-LABEL: store_1d_slc:
|
|
; NOPRT: ; %bb.0: ; %main_body
|
|
; NOPRT-NEXT: image_store v[0:3], v4, s[0:7] dmask:0xf unorm slc
|
|
; NOPRT-NEXT: s_endpgm
|
|
;
|
|
; GFX10-LABEL: store_1d_slc:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: image_store v[0:3], v4, s[0:7] dmask:0xf dim:SQ_RSRC_IMG_1D unorm slc ; encoding: [0x00,0x1f,0x20,0xf2,0x04,0x00,0x00,0x00]
|
|
; GFX10-NEXT: s_endpgm ; encoding: [0x00,0x00,0x81,0xbf]
|
|
main_body:
|
|
call void @llvm.amdgcn.image.store.1d.v4f32.i32(<4 x float> %vdata, i32 15, i32 %s, <8 x i32> %rsrc, i32 0, i32 2)
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_ps void @store_1d_glc_slc(<8 x i32> inreg %rsrc, <4 x float> %vdata, i32 %s) {
|
|
; VERDE-LABEL: store_1d_glc_slc:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: image_store v[0:3], v4, s[0:7] dmask:0xf unorm glc slc
|
|
; VERDE-NEXT: s_endpgm
|
|
;
|
|
; FIJI-LABEL: store_1d_glc_slc:
|
|
; FIJI: ; %bb.0: ; %main_body
|
|
; FIJI-NEXT: image_store v[0:3], v4, s[0:7] dmask:0xf unorm glc slc
|
|
; FIJI-NEXT: s_endpgm
|
|
;
|
|
; GFX6789-LABEL: store_1d_glc_slc:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: image_store v[0:3], v4, s[0:7] dmask:0xf unorm glc slc
|
|
; GFX6789-NEXT: s_endpgm
|
|
;
|
|
; NOPRT-LABEL: store_1d_glc_slc:
|
|
; NOPRT: ; %bb.0: ; %main_body
|
|
; NOPRT-NEXT: image_store v[0:3], v4, s[0:7] dmask:0xf unorm glc slc
|
|
; NOPRT-NEXT: s_endpgm
|
|
;
|
|
; GFX10-LABEL: store_1d_glc_slc:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: image_store v[0:3], v4, s[0:7] dmask:0xf dim:SQ_RSRC_IMG_1D unorm glc slc ; encoding: [0x00,0x3f,0x20,0xf2,0x04,0x00,0x00,0x00]
|
|
; GFX10-NEXT: s_endpgm ; encoding: [0x00,0x00,0x81,0xbf]
|
|
main_body:
|
|
call void @llvm.amdgcn.image.store.1d.v4f32.i32(<4 x float> %vdata, i32 15, i32 %s, <8 x i32> %rsrc, i32 0, i32 3)
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_ps <3 x float> @getresinfo_dmask7(<8 x i32> inreg %rsrc, <4 x float> %vdata, i32 %mip) {
|
|
; GFX6-LABEL: getresinfo_dmask7:
|
|
; GFX6: ; %bb.0: ; %main_body
|
|
; GFX6-NEXT: s_mov_b32 s0, s2
|
|
; GFX6-NEXT: s_mov_b32 s1, s3
|
|
; GFX6-NEXT: s_mov_b32 s2, s4
|
|
; GFX6-NEXT: s_mov_b32 s3, s5
|
|
; GFX6-NEXT: s_mov_b32 s4, s6
|
|
; GFX6-NEXT: s_mov_b32 s5, s7
|
|
; GFX6-NEXT: s_mov_b32 s6, s8
|
|
; GFX6-NEXT: s_mov_b32 s7, s9
|
|
; GFX6-NEXT: image_get_resinfo v[0:2], v0, s[0:7] dmask:0x7 unorm
|
|
; GFX6-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX8-LABEL: getresinfo_dmask7:
|
|
; GFX8: ; %bb.0: ; %main_body
|
|
; GFX8-NEXT: s_mov_b32 s0, s2
|
|
; GFX8-NEXT: s_mov_b32 s1, s3
|
|
; GFX8-NEXT: s_mov_b32 s2, s4
|
|
; GFX8-NEXT: s_mov_b32 s3, s5
|
|
; GFX8-NEXT: s_mov_b32 s4, s6
|
|
; GFX8-NEXT: s_mov_b32 s5, s7
|
|
; GFX8-NEXT: s_mov_b32 s6, s8
|
|
; GFX8-NEXT: s_mov_b32 s7, s9
|
|
; GFX8-NEXT: image_get_resinfo v[0:2], v0, s[0:7] dmask:0x7 unorm
|
|
; GFX8-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX8-NEXT: ; return to shader part epilog
|
|
;
|
|
; VERDE-LABEL: getresinfo_dmask7:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: image_get_resinfo v[0:2], v0, s[0:7] dmask:0x7 unorm
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; FIJI-LABEL: getresinfo_dmask7:
|
|
; FIJI: ; %bb.0: ; %main_body
|
|
; FIJI-NEXT: image_get_resinfo v[0:2], v0, s[0:7] dmask:0x7 unorm
|
|
; FIJI-NEXT: s_waitcnt vmcnt(0)
|
|
; FIJI-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: getresinfo_dmask7:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: image_get_resinfo v[0:2], v0, s[0:7] dmask:0x7 unorm
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; NOPRT-LABEL: getresinfo_dmask7:
|
|
; NOPRT: ; %bb.0: ; %main_body
|
|
; NOPRT-NEXT: image_get_resinfo v[0:2], v0, s[0:7] dmask:0x7 unorm
|
|
; NOPRT-NEXT: s_waitcnt vmcnt(0)
|
|
; NOPRT-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: getresinfo_dmask7:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: image_get_resinfo v[0:2], v0, s[0:7] dmask:0x7 dim:SQ_RSRC_IMG_1D unorm ; encoding: [0x00,0x17,0x38,0xf0,0x00,0x00,0x00,0x00]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%r = call <3 x float> @llvm.amdgcn.image.getresinfo.1d.v3f32.i32(i32 7, i32 %mip, <8 x i32> %rsrc, i32 0, i32 0)
|
|
ret <3 x float> %r
|
|
}
|
|
|
|
define amdgpu_ps <2 x float> @getresinfo_dmask3(<8 x i32> inreg %rsrc, <4 x float> %vdata, i32 %mip) {
|
|
; GFX6-LABEL: getresinfo_dmask3:
|
|
; GFX6: ; %bb.0: ; %main_body
|
|
; GFX6-NEXT: s_mov_b32 s0, s2
|
|
; GFX6-NEXT: s_mov_b32 s1, s3
|
|
; GFX6-NEXT: s_mov_b32 s2, s4
|
|
; GFX6-NEXT: s_mov_b32 s3, s5
|
|
; GFX6-NEXT: s_mov_b32 s4, s6
|
|
; GFX6-NEXT: s_mov_b32 s5, s7
|
|
; GFX6-NEXT: s_mov_b32 s6, s8
|
|
; GFX6-NEXT: s_mov_b32 s7, s9
|
|
; GFX6-NEXT: image_get_resinfo v[0:1], v0, s[0:7] dmask:0x3 unorm
|
|
; GFX6-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX8-LABEL: getresinfo_dmask3:
|
|
; GFX8: ; %bb.0: ; %main_body
|
|
; GFX8-NEXT: s_mov_b32 s0, s2
|
|
; GFX8-NEXT: s_mov_b32 s1, s3
|
|
; GFX8-NEXT: s_mov_b32 s2, s4
|
|
; GFX8-NEXT: s_mov_b32 s3, s5
|
|
; GFX8-NEXT: s_mov_b32 s4, s6
|
|
; GFX8-NEXT: s_mov_b32 s5, s7
|
|
; GFX8-NEXT: s_mov_b32 s6, s8
|
|
; GFX8-NEXT: s_mov_b32 s7, s9
|
|
; GFX8-NEXT: image_get_resinfo v[0:1], v0, s[0:7] dmask:0x3 unorm
|
|
; GFX8-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX8-NEXT: ; return to shader part epilog
|
|
;
|
|
; VERDE-LABEL: getresinfo_dmask3:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: image_get_resinfo v[0:1], v0, s[0:7] dmask:0x3 unorm
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; FIJI-LABEL: getresinfo_dmask3:
|
|
; FIJI: ; %bb.0: ; %main_body
|
|
; FIJI-NEXT: image_get_resinfo v[0:1], v0, s[0:7] dmask:0x3 unorm
|
|
; FIJI-NEXT: s_waitcnt vmcnt(0)
|
|
; FIJI-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: getresinfo_dmask3:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: image_get_resinfo v[0:1], v0, s[0:7] dmask:0x3 unorm
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; NOPRT-LABEL: getresinfo_dmask3:
|
|
; NOPRT: ; %bb.0: ; %main_body
|
|
; NOPRT-NEXT: image_get_resinfo v[0:1], v0, s[0:7] dmask:0x3 unorm
|
|
; NOPRT-NEXT: s_waitcnt vmcnt(0)
|
|
; NOPRT-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: getresinfo_dmask3:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: image_get_resinfo v[0:1], v0, s[0:7] dmask:0x3 dim:SQ_RSRC_IMG_1D unorm ; encoding: [0x00,0x13,0x38,0xf0,0x00,0x00,0x00,0x00]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%r = call <2 x float> @llvm.amdgcn.image.getresinfo.1d.v2f32.i32(i32 3, i32 %mip, <8 x i32> %rsrc, i32 0, i32 0)
|
|
ret <2 x float> %r
|
|
}
|
|
|
|
define amdgpu_ps float @getresinfo_dmask1(<8 x i32> inreg %rsrc, <4 x float> %vdata, i32 %mip) {
|
|
; GFX6-LABEL: getresinfo_dmask1:
|
|
; GFX6: ; %bb.0: ; %main_body
|
|
; GFX6-NEXT: s_mov_b32 s0, s2
|
|
; GFX6-NEXT: s_mov_b32 s1, s3
|
|
; GFX6-NEXT: s_mov_b32 s2, s4
|
|
; GFX6-NEXT: s_mov_b32 s3, s5
|
|
; GFX6-NEXT: s_mov_b32 s4, s6
|
|
; GFX6-NEXT: s_mov_b32 s5, s7
|
|
; GFX6-NEXT: s_mov_b32 s6, s8
|
|
; GFX6-NEXT: s_mov_b32 s7, s9
|
|
; GFX6-NEXT: image_get_resinfo v0, v0, s[0:7] dmask:0x1 unorm
|
|
; GFX6-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX8-LABEL: getresinfo_dmask1:
|
|
; GFX8: ; %bb.0: ; %main_body
|
|
; GFX8-NEXT: s_mov_b32 s0, s2
|
|
; GFX8-NEXT: s_mov_b32 s1, s3
|
|
; GFX8-NEXT: s_mov_b32 s2, s4
|
|
; GFX8-NEXT: s_mov_b32 s3, s5
|
|
; GFX8-NEXT: s_mov_b32 s4, s6
|
|
; GFX8-NEXT: s_mov_b32 s5, s7
|
|
; GFX8-NEXT: s_mov_b32 s6, s8
|
|
; GFX8-NEXT: s_mov_b32 s7, s9
|
|
; GFX8-NEXT: image_get_resinfo v0, v0, s[0:7] dmask:0x1 unorm
|
|
; GFX8-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX8-NEXT: ; return to shader part epilog
|
|
;
|
|
; VERDE-LABEL: getresinfo_dmask1:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: image_get_resinfo v0, v0, s[0:7] dmask:0x1 unorm
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; FIJI-LABEL: getresinfo_dmask1:
|
|
; FIJI: ; %bb.0: ; %main_body
|
|
; FIJI-NEXT: image_get_resinfo v0, v0, s[0:7] dmask:0x1 unorm
|
|
; FIJI-NEXT: s_waitcnt vmcnt(0)
|
|
; FIJI-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: getresinfo_dmask1:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: image_get_resinfo v0, v0, s[0:7] dmask:0x1 unorm
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; NOPRT-LABEL: getresinfo_dmask1:
|
|
; NOPRT: ; %bb.0: ; %main_body
|
|
; NOPRT-NEXT: image_get_resinfo v0, v0, s[0:7] dmask:0x1 unorm
|
|
; NOPRT-NEXT: s_waitcnt vmcnt(0)
|
|
; NOPRT-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: getresinfo_dmask1:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: image_get_resinfo v0, v0, s[0:7] dmask:0x1 dim:SQ_RSRC_IMG_1D unorm ; encoding: [0x00,0x11,0x38,0xf0,0x00,0x00,0x00,0x00]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%r = call float @llvm.amdgcn.image.getresinfo.1d.f32.i32(i32 1, i32 %mip, <8 x i32> %rsrc, i32 0, i32 0)
|
|
ret float %r
|
|
}
|
|
|
|
define amdgpu_ps <4 x float> @getresinfo_dmask0(<8 x i32> inreg %rsrc, <4 x float> %vdata, i32 %mip) #0 {
|
|
; VERDE-LABEL: getresinfo_dmask0:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; FIJI-LABEL: getresinfo_dmask0:
|
|
; FIJI: ; %bb.0: ; %main_body
|
|
; FIJI-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: getresinfo_dmask0:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; NOPRT-LABEL: getresinfo_dmask0:
|
|
; NOPRT: ; %bb.0: ; %main_body
|
|
; NOPRT-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: getresinfo_dmask0:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
main_body:
|
|
%r = call <4 x float> @llvm.amdgcn.image.getresinfo.1d.v4f32.i32(i32 0, i32 %mip, <8 x i32> %rsrc, i32 0, i32 0)
|
|
ret <4 x float> %r
|
|
}
|
|
|
|
;
|
|
define amdgpu_ps void @image_store_wait(<8 x i32> inreg %arg, <8 x i32> inreg %arg1, <8 x i32> inreg %arg2, <4 x float> %arg3, i32 %arg4) #0 {
|
|
; VERDE-LABEL: image_store_wait:
|
|
; VERDE: ; %bb.0: ; %main_body
|
|
; VERDE-NEXT: image_store v[0:3], v4, s[0:7] dmask:0xf unorm
|
|
; VERDE-NEXT: s_waitcnt expcnt(0)
|
|
; VERDE-NEXT: image_load v[0:3], v4, s[8:15] dmask:0xf unorm
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: image_store v[0:3], v4, s[16:23] dmask:0xf unorm
|
|
; VERDE-NEXT: s_endpgm
|
|
;
|
|
; FIJI-LABEL: image_store_wait:
|
|
; FIJI: ; %bb.0: ; %main_body
|
|
; FIJI-NEXT: image_store v[0:3], v4, s[0:7] dmask:0xf unorm
|
|
; FIJI-NEXT: image_load v[0:3], v4, s[8:15] dmask:0xf unorm
|
|
; FIJI-NEXT: s_waitcnt vmcnt(0)
|
|
; FIJI-NEXT: image_store v[0:3], v4, s[16:23] dmask:0xf unorm
|
|
; FIJI-NEXT: s_endpgm
|
|
;
|
|
; GFX6789-LABEL: image_store_wait:
|
|
; GFX6789: ; %bb.0: ; %main_body
|
|
; GFX6789-NEXT: image_store v[0:3], v4, s[0:7] dmask:0xf unorm
|
|
; GFX6789-NEXT: image_load v[0:3], v4, s[8:15] dmask:0xf unorm
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: image_store v[0:3], v4, s[16:23] dmask:0xf unorm
|
|
; GFX6789-NEXT: s_endpgm
|
|
;
|
|
; NOPRT-LABEL: image_store_wait:
|
|
; NOPRT: ; %bb.0: ; %main_body
|
|
; NOPRT-NEXT: image_store v[0:3], v4, s[0:7] dmask:0xf unorm
|
|
; NOPRT-NEXT: image_load v[0:3], v4, s[8:15] dmask:0xf unorm
|
|
; NOPRT-NEXT: s_waitcnt vmcnt(0)
|
|
; NOPRT-NEXT: image_store v[0:3], v4, s[16:23] dmask:0xf unorm
|
|
; NOPRT-NEXT: s_endpgm
|
|
;
|
|
; GFX10-LABEL: image_store_wait:
|
|
; GFX10: ; %bb.0: ; %main_body
|
|
; GFX10-NEXT: image_store v[0:3], v4, s[0:7] dmask:0xf dim:SQ_RSRC_IMG_1D unorm ; encoding: [0x00,0x1f,0x20,0xf0,0x04,0x00,0x00,0x00]
|
|
; GFX10-NEXT: image_load v[0:3], v4, s[8:15] dmask:0xf dim:SQ_RSRC_IMG_1D unorm ; encoding: [0x00,0x1f,0x00,0xf0,0x04,0x00,0x02,0x00]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: image_store v[0:3], v4, s[16:23] dmask:0xf dim:SQ_RSRC_IMG_1D unorm ; encoding: [0x00,0x1f,0x20,0xf0,0x04,0x00,0x04,0x00]
|
|
; GFX10-NEXT: s_endpgm ; encoding: [0x00,0x00,0x81,0xbf]
|
|
main_body:
|
|
call void @llvm.amdgcn.image.store.1d.v4f32.i32(<4 x float> %arg3, i32 15, i32 %arg4, <8 x i32> %arg, i32 0, i32 0)
|
|
%data = call <4 x float> @llvm.amdgcn.image.load.1d.v4f32.i32(i32 15, i32 %arg4, <8 x i32> %arg1, i32 0, i32 0)
|
|
call void @llvm.amdgcn.image.store.1d.v4f32.i32(<4 x float> %data, i32 15, i32 %arg4, <8 x i32> %arg2, i32 0, i32 0)
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_ps float @image_load_mmo(<8 x i32> inreg %rsrc, float addrspace(3)* %lds, <2 x i32> %c) #0 {
|
|
; VERDE-LABEL: image_load_mmo:
|
|
; VERDE: ; %bb.0:
|
|
; VERDE-NEXT: image_load v1, v[1:2], s[0:7] dmask:0x1 unorm
|
|
; VERDE-NEXT: v_mov_b32_e32 v3, 0
|
|
; VERDE-NEXT: s_mov_b32 m0, -1
|
|
; VERDE-NEXT: ds_write_b32 v0, v3
|
|
; VERDE-NEXT: v_add_i32_e32 v0, vcc, 16, v0
|
|
; VERDE-NEXT: ds_write_b32 v0, v3
|
|
; VERDE-NEXT: s_waitcnt vmcnt(0)
|
|
; VERDE-NEXT: v_mov_b32_e32 v0, v1
|
|
; VERDE-NEXT: s_waitcnt lgkmcnt(0)
|
|
; VERDE-NEXT: ; return to shader part epilog
|
|
;
|
|
; FIJI-LABEL: image_load_mmo:
|
|
; FIJI: ; %bb.0:
|
|
; FIJI-NEXT: image_load v1, v[1:2], s[0:7] dmask:0x1 unorm
|
|
; FIJI-NEXT: v_mov_b32_e32 v3, 0
|
|
; FIJI-NEXT: s_mov_b32 m0, -1
|
|
; FIJI-NEXT: ds_write2_b32 v0, v3, v3 offset1:4
|
|
; FIJI-NEXT: s_waitcnt vmcnt(0)
|
|
; FIJI-NEXT: v_mov_b32_e32 v0, v1
|
|
; FIJI-NEXT: s_waitcnt lgkmcnt(0)
|
|
; FIJI-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX6789-LABEL: image_load_mmo:
|
|
; GFX6789: ; %bb.0:
|
|
; GFX6789-NEXT: image_load v1, v[1:2], s[0:7] dmask:0x1 unorm
|
|
; GFX6789-NEXT: v_mov_b32_e32 v3, 0
|
|
; GFX6789-NEXT: ds_write2_b32 v0, v3, v3 offset1:4
|
|
; GFX6789-NEXT: s_waitcnt vmcnt(0)
|
|
; GFX6789-NEXT: v_mov_b32_e32 v0, v1
|
|
; GFX6789-NEXT: s_waitcnt lgkmcnt(0)
|
|
; GFX6789-NEXT: ; return to shader part epilog
|
|
;
|
|
; NOPRT-LABEL: image_load_mmo:
|
|
; NOPRT: ; %bb.0:
|
|
; NOPRT-NEXT: image_load v1, v[1:2], s[0:7] dmask:0x1 unorm
|
|
; NOPRT-NEXT: v_mov_b32_e32 v3, 0
|
|
; NOPRT-NEXT: ds_write2_b32 v0, v3, v3 offset1:4
|
|
; NOPRT-NEXT: s_waitcnt vmcnt(0)
|
|
; NOPRT-NEXT: v_mov_b32_e32 v0, v1
|
|
; NOPRT-NEXT: s_waitcnt lgkmcnt(0)
|
|
; NOPRT-NEXT: ; return to shader part epilog
|
|
;
|
|
; GFX10-LABEL: image_load_mmo:
|
|
; GFX10: ; %bb.0:
|
|
; GFX10-NEXT: image_load v1, v[1:2], s[0:7] dmask:0x1 dim:SQ_RSRC_IMG_2D unorm ; encoding: [0x08,0x11,0x00,0xf0,0x01,0x01,0x00,0x00]
|
|
; GFX10-NEXT: v_mov_b32_e32 v2, 0 ; encoding: [0x80,0x02,0x04,0x7e]
|
|
; GFX10-NEXT: ds_write2_b32 v0, v2, v2 offset1:4 ; encoding: [0x00,0x04,0x38,0xd8,0x00,0x02,0x02,0x00]
|
|
; GFX10-NEXT: s_waitcnt vmcnt(0) ; encoding: [0x70,0x3f,0x8c,0xbf]
|
|
; GFX10-NEXT: v_mov_b32_e32 v0, v1 ; encoding: [0x01,0x03,0x00,0x7e]
|
|
; GFX10-NEXT: s_waitcnt lgkmcnt(0) ; encoding: [0x7f,0xc0,0x8c,0xbf]
|
|
; GFX10-NEXT: ; return to shader part epilog
|
|
store float 0.000000e+00, float addrspace(3)* %lds
|
|
%c0 = extractelement <2 x i32> %c, i32 0
|
|
%c1 = extractelement <2 x i32> %c, i32 1
|
|
%tex = call float @llvm.amdgcn.image.load.2d.f32.i32(i32 1, i32 %c0, i32 %c1, <8 x i32> %rsrc, i32 0, i32 0)
|
|
%tmp2 = getelementptr float, float addrspace(3)* %lds, i32 4
|
|
store float 0.000000e+00, float addrspace(3)* %tmp2
|
|
ret float %tex
|
|
}
|
|
|
|
declare <4 x float> @llvm.amdgcn.image.load.1d.v4f32.i32(i32, i32, <8 x i32>, i32, i32) #1
|
|
declare {float,i32} @llvm.amdgcn.image.load.1d.f32i32.i32(i32, i32, <8 x i32>, i32, i32) #1
|
|
declare {<2 x float>,i32} @llvm.amdgcn.image.load.1d.v2f32i32.i32(i32, i32, <8 x i32>, i32, i32) #1
|
|
declare {<4 x float>,i32} @llvm.amdgcn.image.load.1d.v4f32i32.i32(i32, i32, <8 x i32>, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.load.2d.v4f32.i32(i32, i32, i32, <8 x i32>, i32, i32) #1
|
|
declare {<4 x float>,i32} @llvm.amdgcn.image.load.2d.v4f32i32.i32(i32, i32, i32, <8 x i32>, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.load.3d.v4f32.i32(i32, i32, i32, i32, <8 x i32>, i32, i32) #1
|
|
declare {<4 x float>,i32} @llvm.amdgcn.image.load.3d.v4f32i32.i32(i32, i32, i32, i32, <8 x i32>, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.load.cube.v4f32.i32(i32, i32, i32, i32, <8 x i32>, i32, i32) #1
|
|
declare {<4 x float>,i32} @llvm.amdgcn.image.load.cube.v4f32i32.i32(i32, i32, i32, i32, <8 x i32>, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.load.1darray.v4f32.i32(i32, i32, i32, <8 x i32>, i32, i32) #1
|
|
declare {<4 x float>,i32} @llvm.amdgcn.image.load.1darray.v4f32i32.i32(i32, i32, i32, <8 x i32>, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.load.2darray.v4f32.i32(i32, i32, i32, i32, <8 x i32>, i32, i32) #1
|
|
declare {<4 x float>,i32} @llvm.amdgcn.image.load.2darray.v4f32i32.i32(i32, i32, i32, i32, <8 x i32>, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.load.2dmsaa.v4f32.i32(i32, i32, i32, i32, <8 x i32>, i32, i32) #1
|
|
declare {<4 x float>,i32} @llvm.amdgcn.image.load.2dmsaa.v4f32i32.i32(i32, i32, i32, i32, <8 x i32>, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.load.2darraymsaa.v4f32.i32(i32, i32, i32, i32, i32, <8 x i32>, i32, i32) #1
|
|
declare {<4 x float>,i32} @llvm.amdgcn.image.load.2darraymsaa.v4f32i32.i32(i32, i32, i32, i32, i32, <8 x i32>, i32, i32) #1
|
|
|
|
declare <4 x float> @llvm.amdgcn.image.load.mip.1d.v4f32.i32(i32, i32, i32, <8 x i32>, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.load.mip.2d.v4f32.i32(i32, i32, i32, i32, <8 x i32>, i32, i32) #1
|
|
declare {<4 x float>,i32} @llvm.amdgcn.image.load.mip.1d.v4f32i32.i32(i32, i32, i32, <8 x i32>, i32, i32) #1
|
|
declare {<4 x float>,i32} @llvm.amdgcn.image.load.mip.2d.v4f32i32.i32(i32, i32, i32, i32, <8 x i32>, i32, i32) #1
|
|
declare {<2 x float>,i32} @llvm.amdgcn.image.load.mip.2d.v2f32i32.i32(i32, i32, i32, i32, <8 x i32>, i32, i32) #1
|
|
declare {float,i32} @llvm.amdgcn.image.load.mip.2d.f32i32.i32(i32, i32, i32, i32, <8 x i32>, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.load.mip.3d.v4f32.i32(i32, i32, i32, i32, i32, <8 x i32>, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.load.mip.cube.v4f32.i32(i32, i32, i32, i32, i32, <8 x i32>, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.load.mip.1darray.v4f32.i32(i32, i32, i32, i32, <8 x i32>, i32, i32) #1
|
|
declare <4 x float> @llvm.amdgcn.image.load.mip.2darray.v4f32.i32(i32, i32, i32, i32, i32, <8 x i32>, i32, i32) #1
|
|
|
|
declare void @llvm.amdgcn.image.store.1d.v4f32.i32(<4 x float>, i32, i32, <8 x i32>, i32, i32) #0
|
|
declare void @llvm.amdgcn.image.store.2d.v4f32.i32(<4 x float>, i32, i32, i32, <8 x i32>, i32, i32) #0
|
|
declare void @llvm.amdgcn.image.store.3d.v4f32.i32(<4 x float>, i32, i32, i32, i32, <8 x i32>, i32, i32) #0
|
|
declare void @llvm.amdgcn.image.store.cube.v4f32.i32(<4 x float>, i32, i32, i32, i32, <8 x i32>, i32, i32) #0
|
|
declare void @llvm.amdgcn.image.store.1darray.v4f32.i32(<4 x float>, i32, i32, i32, <8 x i32>, i32, i32) #0
|
|
declare void @llvm.amdgcn.image.store.2darray.v4f32.i32(<4 x float>, i32, i32, i32, i32, <8 x i32>, i32, i32) #0
|
|
declare void @llvm.amdgcn.image.store.2dmsaa.v4f32.i32(<4 x float>, i32, i32, i32, i32, <8 x i32>, i32, i32) #0
|
|
declare void @llvm.amdgcn.image.store.2darraymsaa.v4f32.i32(<4 x float>, i32, i32, i32, i32, i32, <8 x i32>, i32, i32) #0
|
|
|
|
declare void @llvm.amdgcn.image.store.mip.1d.v4f32.i32(<4 x float>, i32, i32, i32, <8 x i32>, i32, i32) #0
|
|
declare void @llvm.amdgcn.image.store.mip.2d.v4f32.i32(<4 x float>, i32, i32, i32, i32, <8 x i32>, i32, i32) #0
|
|
declare void @llvm.amdgcn.image.store.mip.3d.v4f32.i32(<4 x float>, i32, i32, i32, i32, i32, <8 x i32>, i32, i32) #0
|
|
declare void @llvm.amdgcn.image.store.mip.cube.v4f32.i32(<4 x float>, i32, i32, i32, i32, i32, <8 x i32>, i32, i32) #0
|
|
declare void @llvm.amdgcn.image.store.mip.1darray.v4f32.i32(<4 x float>, i32, i32, i32, i32, <8 x i32>, i32, i32) #0
|
|
declare void @llvm.amdgcn.image.store.mip.2darray.v4f32.i32(<4 x float>, i32, i32, i32, i32, i32, <8 x i32>, i32, i32) #0
|
|
|
|
declare <4 x float> @llvm.amdgcn.image.getresinfo.1d.v4f32.i32(i32, i32, <8 x i32>, i32, i32) #2
|
|
declare <3 x float> @llvm.amdgcn.image.getresinfo.1d.v3f32.i32(i32 immarg, i32, <8 x i32>, i32 immarg, i32 immarg) #1
|
|
declare <2 x float> @llvm.amdgcn.image.getresinfo.1d.v2f32.i32(i32 immarg, i32, <8 x i32>, i32 immarg, i32 immarg) #1
|
|
declare float @llvm.amdgcn.image.getresinfo.1d.f32.i32(i32 immarg, i32, <8 x i32>, i32 immarg, i32 immarg) #1
|
|
declare <4 x float> @llvm.amdgcn.image.getresinfo.2d.v4f32.i32(i32, i32, <8 x i32>, i32, i32) #2
|
|
declare <4 x float> @llvm.amdgcn.image.getresinfo.3d.v4f32.i32(i32, i32, <8 x i32>, i32, i32) #2
|
|
declare <4 x float> @llvm.amdgcn.image.getresinfo.cube.v4f32.i32(i32, i32, <8 x i32>, i32, i32) #2
|
|
declare <4 x float> @llvm.amdgcn.image.getresinfo.1darray.v4f32.i32(i32, i32, <8 x i32>, i32, i32) #2
|
|
declare <4 x float> @llvm.amdgcn.image.getresinfo.2darray.v4f32.i32(i32, i32, <8 x i32>, i32, i32) #2
|
|
declare <4 x float> @llvm.amdgcn.image.getresinfo.2dmsaa.v4f32.i32(i32, i32, <8 x i32>, i32, i32) #2
|
|
declare <4 x float> @llvm.amdgcn.image.getresinfo.2darraymsaa.v4f32.i32(i32, i32, <8 x i32>, i32, i32) #2
|
|
|
|
declare float @llvm.amdgcn.image.load.1d.f32.i32(i32, i32, <8 x i32>, i32, i32) #1
|
|
declare float @llvm.amdgcn.image.load.2d.f32.i32(i32, i32, i32, <8 x i32>, i32, i32) #1
|
|
declare <2 x float> @llvm.amdgcn.image.load.1d.v2f32.i32(i32, i32, <8 x i32>, i32, i32) #1
|
|
declare void @llvm.amdgcn.image.store.1d.f32.i32(float, i32, i32, <8 x i32>, i32, i32) #0
|
|
declare void @llvm.amdgcn.image.store.1d.v2f32.i32(<2 x float>, i32, i32, <8 x i32>, i32, i32) #0
|
|
|
|
attributes #0 = { nounwind }
|
|
attributes #1 = { nounwind readonly }
|
|
attributes #2 = { nounwind readnone }
|