forked from OSchip/llvm-project
[AMDGPU] Add some image tests with enable-prt-strict-null disabled. NFC.
This commit is contained in:
parent
a991ee330b
commit
b138cf115e
|
@ -2,6 +2,7 @@
|
|||
; RUN: llc -global-isel -mtriple=amdgcn-mesa-mesa3d -mcpu=tahiti -verify-machineinstrs < %s | FileCheck -check-prefix=GFX68 %s
|
||||
; RUN: llc -global-isel -mtriple=amdgcn-mesa-mesa3d -mcpu=fiji -verify-machineinstrs < %s | FileCheck -check-prefix=GFX68 %s
|
||||
; RUN: llc -global-isel -mtriple=amdgcn-mesa-mesa3d -mcpu=gfx1010 -verify-machineinstrs < %s | FileCheck -check-prefix=GFX10 %s
|
||||
; RUN: llc -global-isel -mtriple=amdgcn-mesa-mesa3d -mcpu=gfx1010 -mattr=-enable-prt-strict-null -verify-machineinstrs < %s | FileCheck -check-prefix=NOPRT %s
|
||||
|
||||
define amdgpu_ps float @load_1d_f32_x(<8 x i32> inreg %rsrc, i32 %s) {
|
||||
; GFX68-LABEL: load_1d_f32_x:
|
||||
|
@ -31,6 +32,20 @@ define amdgpu_ps float @load_1d_f32_x(<8 x i32> inreg %rsrc, i32 %s) {
|
|||
; GFX10-NEXT: image_load v0, v0, s[0:7] dmask:0x1 dim:SQ_RSRC_IMG_1D unorm
|
||||
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
||||
; GFX10-NEXT: ; return to shader part epilog
|
||||
;
|
||||
; NOPRT-LABEL: load_1d_f32_x:
|
||||
; NOPRT: ; %bb.0:
|
||||
; NOPRT-NEXT: s_mov_b32 s0, s2
|
||||
; NOPRT-NEXT: s_mov_b32 s1, s3
|
||||
; NOPRT-NEXT: s_mov_b32 s2, s4
|
||||
; NOPRT-NEXT: s_mov_b32 s3, s5
|
||||
; NOPRT-NEXT: s_mov_b32 s4, s6
|
||||
; NOPRT-NEXT: s_mov_b32 s5, s7
|
||||
; NOPRT-NEXT: s_mov_b32 s6, s8
|
||||
; NOPRT-NEXT: s_mov_b32 s7, s9
|
||||
; NOPRT-NEXT: image_load v0, v0, s[0:7] dmask:0x1 dim:SQ_RSRC_IMG_1D unorm
|
||||
; NOPRT-NEXT: s_waitcnt vmcnt(0)
|
||||
; NOPRT-NEXT: ; return to shader part epilog
|
||||
%v = call float @llvm.amdgcn.image.load.1d.f32.i32(i32 1, i32 %s, <8 x i32> %rsrc, i32 0, i32 0)
|
||||
ret float %v
|
||||
}
|
||||
|
@ -63,6 +78,20 @@ define amdgpu_ps float @load_1d_f32_y(<8 x i32> inreg %rsrc, i32 %s) {
|
|||
; GFX10-NEXT: image_load v0, v0, s[0:7] dmask:0x2 dim:SQ_RSRC_IMG_1D unorm
|
||||
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
||||
; GFX10-NEXT: ; return to shader part epilog
|
||||
;
|
||||
; NOPRT-LABEL: load_1d_f32_y:
|
||||
; NOPRT: ; %bb.0:
|
||||
; NOPRT-NEXT: s_mov_b32 s0, s2
|
||||
; NOPRT-NEXT: s_mov_b32 s1, s3
|
||||
; NOPRT-NEXT: s_mov_b32 s2, s4
|
||||
; NOPRT-NEXT: s_mov_b32 s3, s5
|
||||
; NOPRT-NEXT: s_mov_b32 s4, s6
|
||||
; NOPRT-NEXT: s_mov_b32 s5, s7
|
||||
; NOPRT-NEXT: s_mov_b32 s6, s8
|
||||
; NOPRT-NEXT: s_mov_b32 s7, s9
|
||||
; NOPRT-NEXT: image_load v0, v0, s[0:7] dmask:0x2 dim:SQ_RSRC_IMG_1D unorm
|
||||
; NOPRT-NEXT: s_waitcnt vmcnt(0)
|
||||
; NOPRT-NEXT: ; return to shader part epilog
|
||||
%v = call float @llvm.amdgcn.image.load.1d.f32.i32(i32 2, i32 %s, <8 x i32> %rsrc, i32 0, i32 0)
|
||||
ret float %v
|
||||
}
|
||||
|
@ -95,6 +124,20 @@ define amdgpu_ps float @load_1d_f32_z(<8 x i32> inreg %rsrc, i32 %s) {
|
|||
; GFX10-NEXT: image_load v0, v0, s[0:7] dmask:0x4 dim:SQ_RSRC_IMG_1D unorm
|
||||
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
||||
; GFX10-NEXT: ; return to shader part epilog
|
||||
;
|
||||
; NOPRT-LABEL: load_1d_f32_z:
|
||||
; NOPRT: ; %bb.0:
|
||||
; NOPRT-NEXT: s_mov_b32 s0, s2
|
||||
; NOPRT-NEXT: s_mov_b32 s1, s3
|
||||
; NOPRT-NEXT: s_mov_b32 s2, s4
|
||||
; NOPRT-NEXT: s_mov_b32 s3, s5
|
||||
; NOPRT-NEXT: s_mov_b32 s4, s6
|
||||
; NOPRT-NEXT: s_mov_b32 s5, s7
|
||||
; NOPRT-NEXT: s_mov_b32 s6, s8
|
||||
; NOPRT-NEXT: s_mov_b32 s7, s9
|
||||
; NOPRT-NEXT: image_load v0, v0, s[0:7] dmask:0x4 dim:SQ_RSRC_IMG_1D unorm
|
||||
; NOPRT-NEXT: s_waitcnt vmcnt(0)
|
||||
; NOPRT-NEXT: ; return to shader part epilog
|
||||
%v = call float @llvm.amdgcn.image.load.1d.f32.i32(i32 4, i32 %s, <8 x i32> %rsrc, i32 0, i32 0)
|
||||
ret float %v
|
||||
}
|
||||
|
@ -127,6 +170,20 @@ define amdgpu_ps float @load_1d_f32_w(<8 x i32> inreg %rsrc, i32 %s) {
|
|||
; GFX10-NEXT: image_load v0, v0, s[0:7] dmask:0x8 dim:SQ_RSRC_IMG_1D unorm
|
||||
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
||||
; GFX10-NEXT: ; return to shader part epilog
|
||||
;
|
||||
; NOPRT-LABEL: load_1d_f32_w:
|
||||
; NOPRT: ; %bb.0:
|
||||
; NOPRT-NEXT: s_mov_b32 s0, s2
|
||||
; NOPRT-NEXT: s_mov_b32 s1, s3
|
||||
; NOPRT-NEXT: s_mov_b32 s2, s4
|
||||
; NOPRT-NEXT: s_mov_b32 s3, s5
|
||||
; NOPRT-NEXT: s_mov_b32 s4, s6
|
||||
; NOPRT-NEXT: s_mov_b32 s5, s7
|
||||
; NOPRT-NEXT: s_mov_b32 s6, s8
|
||||
; NOPRT-NEXT: s_mov_b32 s7, s9
|
||||
; NOPRT-NEXT: image_load v0, v0, s[0:7] dmask:0x8 dim:SQ_RSRC_IMG_1D unorm
|
||||
; NOPRT-NEXT: s_waitcnt vmcnt(0)
|
||||
; NOPRT-NEXT: ; return to shader part epilog
|
||||
%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
|
||||
}
|
||||
|
@ -159,6 +216,20 @@ define amdgpu_ps <2 x float> @load_1d_v2f32_xy(<8 x i32> inreg %rsrc, i32 %s) {
|
|||
; GFX10-NEXT: image_load v[0:1], v0, s[0:7] dmask:0x3 dim:SQ_RSRC_IMG_1D unorm
|
||||
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
||||
; GFX10-NEXT: ; return to shader part epilog
|
||||
;
|
||||
; NOPRT-LABEL: load_1d_v2f32_xy:
|
||||
; NOPRT: ; %bb.0:
|
||||
; NOPRT-NEXT: s_mov_b32 s0, s2
|
||||
; NOPRT-NEXT: s_mov_b32 s1, s3
|
||||
; NOPRT-NEXT: s_mov_b32 s2, s4
|
||||
; NOPRT-NEXT: s_mov_b32 s3, s5
|
||||
; NOPRT-NEXT: s_mov_b32 s4, s6
|
||||
; NOPRT-NEXT: s_mov_b32 s5, s7
|
||||
; NOPRT-NEXT: s_mov_b32 s6, s8
|
||||
; NOPRT-NEXT: s_mov_b32 s7, s9
|
||||
; NOPRT-NEXT: image_load v[0:1], v0, s[0:7] dmask:0x3 dim:SQ_RSRC_IMG_1D unorm
|
||||
; NOPRT-NEXT: s_waitcnt vmcnt(0)
|
||||
; NOPRT-NEXT: ; return to shader part epilog
|
||||
%v = call <2 x float> @llvm.amdgcn.image.load.1d.v2f32.i32(i32 3, i32 %s, <8 x i32> %rsrc, i32 0, i32 0)
|
||||
ret <2 x float> %v
|
||||
}
|
||||
|
@ -191,6 +262,20 @@ define amdgpu_ps <2 x float> @load_1d_v2f32_xz(<8 x i32> inreg %rsrc, i32 %s) {
|
|||
; GFX10-NEXT: image_load v[0:1], v0, s[0:7] dmask:0x5 dim:SQ_RSRC_IMG_1D unorm
|
||||
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
||||
; GFX10-NEXT: ; return to shader part epilog
|
||||
;
|
||||
; NOPRT-LABEL: load_1d_v2f32_xz:
|
||||
; NOPRT: ; %bb.0:
|
||||
; NOPRT-NEXT: s_mov_b32 s0, s2
|
||||
; NOPRT-NEXT: s_mov_b32 s1, s3
|
||||
; NOPRT-NEXT: s_mov_b32 s2, s4
|
||||
; NOPRT-NEXT: s_mov_b32 s3, s5
|
||||
; NOPRT-NEXT: s_mov_b32 s4, s6
|
||||
; NOPRT-NEXT: s_mov_b32 s5, s7
|
||||
; NOPRT-NEXT: s_mov_b32 s6, s8
|
||||
; NOPRT-NEXT: s_mov_b32 s7, s9
|
||||
; NOPRT-NEXT: image_load v[0:1], v0, s[0:7] dmask:0x5 dim:SQ_RSRC_IMG_1D unorm
|
||||
; NOPRT-NEXT: s_waitcnt vmcnt(0)
|
||||
; NOPRT-NEXT: ; return to shader part epilog
|
||||
%v = call <2 x float> @llvm.amdgcn.image.load.1d.v2f32.i32(i32 5, i32 %s, <8 x i32> %rsrc, i32 0, i32 0)
|
||||
ret <2 x float> %v
|
||||
}
|
||||
|
@ -223,6 +308,20 @@ define amdgpu_ps <2 x float> @load_1d_v2f32_xw(<8 x i32> inreg %rsrc, i32 %s) {
|
|||
; GFX10-NEXT: image_load v[0:1], v0, s[0:7] dmask:0x9 dim:SQ_RSRC_IMG_1D unorm
|
||||
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
||||
; GFX10-NEXT: ; return to shader part epilog
|
||||
;
|
||||
; NOPRT-LABEL: load_1d_v2f32_xw:
|
||||
; NOPRT: ; %bb.0:
|
||||
; NOPRT-NEXT: s_mov_b32 s0, s2
|
||||
; NOPRT-NEXT: s_mov_b32 s1, s3
|
||||
; NOPRT-NEXT: s_mov_b32 s2, s4
|
||||
; NOPRT-NEXT: s_mov_b32 s3, s5
|
||||
; NOPRT-NEXT: s_mov_b32 s4, s6
|
||||
; NOPRT-NEXT: s_mov_b32 s5, s7
|
||||
; NOPRT-NEXT: s_mov_b32 s6, s8
|
||||
; NOPRT-NEXT: s_mov_b32 s7, s9
|
||||
; NOPRT-NEXT: image_load v[0:1], v0, s[0:7] dmask:0x9 dim:SQ_RSRC_IMG_1D unorm
|
||||
; NOPRT-NEXT: s_waitcnt vmcnt(0)
|
||||
; NOPRT-NEXT: ; return to shader part epilog
|
||||
%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
|
||||
}
|
||||
|
@ -255,6 +354,20 @@ define amdgpu_ps <2 x float> @load_1d_v2f32_yz(<8 x i32> inreg %rsrc, i32 %s) {
|
|||
; GFX10-NEXT: image_load v[0:1], v0, s[0:7] dmask:0x6 dim:SQ_RSRC_IMG_1D unorm
|
||||
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
||||
; GFX10-NEXT: ; return to shader part epilog
|
||||
;
|
||||
; NOPRT-LABEL: load_1d_v2f32_yz:
|
||||
; NOPRT: ; %bb.0:
|
||||
; NOPRT-NEXT: s_mov_b32 s0, s2
|
||||
; NOPRT-NEXT: s_mov_b32 s1, s3
|
||||
; NOPRT-NEXT: s_mov_b32 s2, s4
|
||||
; NOPRT-NEXT: s_mov_b32 s3, s5
|
||||
; NOPRT-NEXT: s_mov_b32 s4, s6
|
||||
; NOPRT-NEXT: s_mov_b32 s5, s7
|
||||
; NOPRT-NEXT: s_mov_b32 s6, s8
|
||||
; NOPRT-NEXT: s_mov_b32 s7, s9
|
||||
; NOPRT-NEXT: image_load v[0:1], v0, s[0:7] dmask:0x6 dim:SQ_RSRC_IMG_1D unorm
|
||||
; NOPRT-NEXT: s_waitcnt vmcnt(0)
|
||||
; NOPRT-NEXT: ; return to shader part epilog
|
||||
%v = call <2 x float> @llvm.amdgcn.image.load.1d.v2f32.i32(i32 6, i32 %s, <8 x i32> %rsrc, i32 0, i32 0)
|
||||
ret <2 x float> %v
|
||||
}
|
||||
|
@ -287,6 +400,20 @@ define amdgpu_ps <3 x float> @load_1d_v3f32_xyz(<8 x i32> inreg %rsrc, i32 %s) {
|
|||
; GFX10-NEXT: image_load v[0:2], v0, s[0:7] dmask:0x7 dim:SQ_RSRC_IMG_1D unorm
|
||||
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
||||
; GFX10-NEXT: ; return to shader part epilog
|
||||
;
|
||||
; NOPRT-LABEL: load_1d_v3f32_xyz:
|
||||
; NOPRT: ; %bb.0:
|
||||
; NOPRT-NEXT: s_mov_b32 s0, s2
|
||||
; NOPRT-NEXT: s_mov_b32 s1, s3
|
||||
; NOPRT-NEXT: s_mov_b32 s2, s4
|
||||
; NOPRT-NEXT: s_mov_b32 s3, s5
|
||||
; NOPRT-NEXT: s_mov_b32 s4, s6
|
||||
; NOPRT-NEXT: s_mov_b32 s5, s7
|
||||
; NOPRT-NEXT: s_mov_b32 s6, s8
|
||||
; NOPRT-NEXT: s_mov_b32 s7, s9
|
||||
; NOPRT-NEXT: image_load v[0:2], v0, s[0:7] dmask:0x7 dim:SQ_RSRC_IMG_1D unorm
|
||||
; NOPRT-NEXT: s_waitcnt vmcnt(0)
|
||||
; NOPRT-NEXT: ; return to shader part epilog
|
||||
%v = call <3 x float> @llvm.amdgcn.image.load.1d.v3f32.i32(i32 7, i32 %s, <8 x i32> %rsrc, i32 0, i32 0)
|
||||
ret <3 x float> %v
|
||||
}
|
||||
|
@ -319,6 +446,20 @@ define amdgpu_ps <4 x float> @load_1d_v4f32_xyzw(<8 x i32> inreg %rsrc, i32 %s)
|
|||
; GFX10-NEXT: image_load v[0:3], v0, s[0:7] dmask:0xf dim:SQ_RSRC_IMG_1D unorm
|
||||
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
||||
; GFX10-NEXT: ; return to shader part epilog
|
||||
;
|
||||
; NOPRT-LABEL: load_1d_v4f32_xyzw:
|
||||
; NOPRT: ; %bb.0:
|
||||
; NOPRT-NEXT: s_mov_b32 s0, s2
|
||||
; NOPRT-NEXT: s_mov_b32 s1, s3
|
||||
; NOPRT-NEXT: s_mov_b32 s2, s4
|
||||
; NOPRT-NEXT: s_mov_b32 s3, s5
|
||||
; NOPRT-NEXT: s_mov_b32 s4, s6
|
||||
; NOPRT-NEXT: s_mov_b32 s5, s7
|
||||
; NOPRT-NEXT: s_mov_b32 s6, s8
|
||||
; NOPRT-NEXT: s_mov_b32 s7, s9
|
||||
; NOPRT-NEXT: image_load v[0:3], v0, s[0:7] dmask:0xf dim:SQ_RSRC_IMG_1D unorm
|
||||
; NOPRT-NEXT: s_waitcnt vmcnt(0)
|
||||
; NOPRT-NEXT: ; return to shader part epilog
|
||||
%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
|
||||
}
|
||||
|
@ -357,6 +498,22 @@ define amdgpu_ps float @load_1d_f32_tfe_dmask_x(<8 x i32> inreg %rsrc, i32 %s) {
|
|||
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
||||
; GFX10-NEXT: v_mov_b32_e32 v0, v2
|
||||
; GFX10-NEXT: ; return to shader part epilog
|
||||
;
|
||||
; NOPRT-LABEL: load_1d_f32_tfe_dmask_x:
|
||||
; NOPRT: ; %bb.0:
|
||||
; NOPRT-NEXT: s_mov_b32 s0, s2
|
||||
; NOPRT-NEXT: s_mov_b32 s1, s3
|
||||
; NOPRT-NEXT: s_mov_b32 s2, s4
|
||||
; NOPRT-NEXT: s_mov_b32 s3, s5
|
||||
; NOPRT-NEXT: s_mov_b32 s4, s6
|
||||
; NOPRT-NEXT: s_mov_b32 s5, s7
|
||||
; NOPRT-NEXT: s_mov_b32 s6, s8
|
||||
; NOPRT-NEXT: s_mov_b32 s7, s9
|
||||
; NOPRT-NEXT: v_mov_b32_e32 v1, 0
|
||||
; NOPRT-NEXT: image_load v[0:1], v0, s[0:7] dmask:0x1 dim:SQ_RSRC_IMG_1D unorm tfe
|
||||
; NOPRT-NEXT: s_waitcnt vmcnt(0)
|
||||
; NOPRT-NEXT: v_mov_b32_e32 v0, v1
|
||||
; NOPRT-NEXT: ; return to shader part epilog
|
||||
%v = call { float, i32 } @llvm.amdgcn.image.load.1d.sl_f32i32s.i32(i32 1, i32 %s, <8 x i32> %rsrc, i32 1, i32 0)
|
||||
%v.err = extractvalue { float, i32 } %v, 1
|
||||
%vv = bitcast i32 %v.err to float
|
||||
|
@ -399,6 +556,22 @@ define amdgpu_ps float @load_1d_v2f32_tfe_dmask_xy(<8 x i32> inreg %rsrc, i32 %s
|
|||
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
||||
; GFX10-NEXT: v_mov_b32_e32 v0, v3
|
||||
; GFX10-NEXT: ; return to shader part epilog
|
||||
;
|
||||
; NOPRT-LABEL: load_1d_v2f32_tfe_dmask_xy:
|
||||
; NOPRT: ; %bb.0:
|
||||
; NOPRT-NEXT: s_mov_b32 s0, s2
|
||||
; NOPRT-NEXT: s_mov_b32 s1, s3
|
||||
; NOPRT-NEXT: s_mov_b32 s2, s4
|
||||
; NOPRT-NEXT: s_mov_b32 s3, s5
|
||||
; NOPRT-NEXT: s_mov_b32 s4, s6
|
||||
; NOPRT-NEXT: s_mov_b32 s5, s7
|
||||
; NOPRT-NEXT: s_mov_b32 s6, s8
|
||||
; NOPRT-NEXT: s_mov_b32 s7, s9
|
||||
; NOPRT-NEXT: v_mov_b32_e32 v2, 0
|
||||
; NOPRT-NEXT: image_load v[0:2], v0, s[0:7] dmask:0x3 dim:SQ_RSRC_IMG_1D unorm tfe
|
||||
; NOPRT-NEXT: s_waitcnt vmcnt(0)
|
||||
; NOPRT-NEXT: v_mov_b32_e32 v0, v2
|
||||
; NOPRT-NEXT: ; return to shader part epilog
|
||||
%v = call { <2 x float>, i32 } @llvm.amdgcn.image.load.1d.sl_v2f32i32s.i32(i32 3, 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
|
||||
|
@ -443,6 +616,22 @@ define amdgpu_ps float @load_1d_v3f32_tfe_dmask_xyz(<8 x i32> inreg %rsrc, i32 %
|
|||
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
||||
; GFX10-NEXT: v_mov_b32_e32 v0, v4
|
||||
; GFX10-NEXT: ; return to shader part epilog
|
||||
;
|
||||
; NOPRT-LABEL: load_1d_v3f32_tfe_dmask_xyz:
|
||||
; NOPRT: ; %bb.0:
|
||||
; NOPRT-NEXT: s_mov_b32 s0, s2
|
||||
; NOPRT-NEXT: s_mov_b32 s1, s3
|
||||
; NOPRT-NEXT: s_mov_b32 s2, s4
|
||||
; NOPRT-NEXT: s_mov_b32 s3, s5
|
||||
; NOPRT-NEXT: s_mov_b32 s4, s6
|
||||
; NOPRT-NEXT: s_mov_b32 s5, s7
|
||||
; NOPRT-NEXT: s_mov_b32 s6, s8
|
||||
; NOPRT-NEXT: s_mov_b32 s7, s9
|
||||
; NOPRT-NEXT: v_mov_b32_e32 v3, 0
|
||||
; NOPRT-NEXT: image_load v[0:3], v0, s[0:7] dmask:0x7 dim:SQ_RSRC_IMG_1D unorm tfe
|
||||
; NOPRT-NEXT: s_waitcnt vmcnt(0)
|
||||
; NOPRT-NEXT: v_mov_b32_e32 v0, v3
|
||||
; NOPRT-NEXT: ; return to shader part epilog
|
||||
%v = call { <3 x float>, i32 } @llvm.amdgcn.image.load.1d.sl_v3f32i32s.i32(i32 7, i32 %s, <8 x i32> %rsrc, i32 1, i32 0)
|
||||
%v.err = extractvalue { <3 x float>, i32 } %v, 1
|
||||
%vv = bitcast i32 %v.err to float
|
||||
|
@ -483,6 +672,22 @@ define amdgpu_ps float @load_1d_v4f32_tfe_dmask_xyzw(<8 x i32> inreg %rsrc, i32
|
|||
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
||||
; GFX10-NEXT: v_mov_b32_e32 v0, v2
|
||||
; GFX10-NEXT: ; return to shader part epilog
|
||||
;
|
||||
; NOPRT-LABEL: load_1d_v4f32_tfe_dmask_xyzw:
|
||||
; NOPRT: ; %bb.0:
|
||||
; NOPRT-NEXT: s_mov_b32 s0, s2
|
||||
; NOPRT-NEXT: s_mov_b32 s1, s3
|
||||
; NOPRT-NEXT: s_mov_b32 s2, s4
|
||||
; NOPRT-NEXT: s_mov_b32 s3, s5
|
||||
; NOPRT-NEXT: s_mov_b32 s4, s6
|
||||
; NOPRT-NEXT: s_mov_b32 s5, s7
|
||||
; NOPRT-NEXT: s_mov_b32 s6, s8
|
||||
; NOPRT-NEXT: s_mov_b32 s7, s9
|
||||
; NOPRT-NEXT: v_mov_b32_e32 v1, 0
|
||||
; NOPRT-NEXT: image_load v[0:1], v0, s[0:7] dmask:0x10 dim:SQ_RSRC_IMG_1D unorm tfe
|
||||
; NOPRT-NEXT: s_waitcnt vmcnt(0)
|
||||
; NOPRT-NEXT: v_mov_b32_e32 v0, v1
|
||||
; NOPRT-NEXT: ; return to shader part epilog
|
||||
%v = call { <4 x float>, i32 } @llvm.amdgcn.image.load.1d.sl_v4f32i32s.i32(i32 16, i32 %s, <8 x i32> %rsrc, i32 1, i32 0)
|
||||
%v.err = extractvalue { <4 x float>, i32 } %v, 1
|
||||
%vv = bitcast i32 %v.err to float
|
||||
|
@ -523,6 +728,22 @@ define amdgpu_ps float @load_1d_f32_tfe_dmask_0(<8 x i32> inreg %rsrc, i32 %s) {
|
|||
; GFX10-NEXT: s_waitcnt vmcnt(0)
|
||||
; GFX10-NEXT: v_mov_b32_e32 v0, v2
|
||||
; GFX10-NEXT: ; return to shader part epilog
|
||||
;
|
||||
; NOPRT-LABEL: load_1d_f32_tfe_dmask_0:
|
||||
; NOPRT: ; %bb.0:
|
||||
; NOPRT-NEXT: s_mov_b32 s0, s2
|
||||
; NOPRT-NEXT: s_mov_b32 s1, s3
|
||||
; NOPRT-NEXT: s_mov_b32 s2, s4
|
||||
; NOPRT-NEXT: s_mov_b32 s3, s5
|
||||
; NOPRT-NEXT: s_mov_b32 s4, s6
|
||||
; NOPRT-NEXT: s_mov_b32 s5, s7
|
||||
; NOPRT-NEXT: s_mov_b32 s6, s8
|
||||
; NOPRT-NEXT: s_mov_b32 s7, s9
|
||||
; NOPRT-NEXT: v_mov_b32_e32 v1, 0
|
||||
; NOPRT-NEXT: image_load v[0:1], v0, s[0:7] dmask:0x1 dim:SQ_RSRC_IMG_1D unorm tfe
|
||||
; NOPRT-NEXT: s_waitcnt vmcnt(0)
|
||||
; NOPRT-NEXT: v_mov_b32_e32 v0, v1
|
||||
; NOPRT-NEXT: ; return to shader part epilog
|
||||
%v = call { float, i32 } @llvm.amdgcn.image.load.1d.sl_f32i32s.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
|
||||
|
|
Loading…
Reference in New Issue