maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

AMDGPU/GlobalISel: Allow selecting s128 load/stores

This commit is contained in:
Matt Arsenault 2020-02-01 11:02:04 -05:00
parent 726446a009
commit 2758ae41ae
5 changed files with 59 additions and 55 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
llvm/lib/Target/AMDGPU/SIRegisterInfo.td
View File

@ -612,7 +612,7 @@ def VReg_96 : RegisterClass<"AMDGPU", [v3i32, v3f32], 32, (add VGPR_96)> {
let AllocationPriority = 3;
}
def VReg_128 : RegisterClass<"AMDGPU", [v4i32, v4f32, v2i64, v2f64], 32,
def VReg_128 : RegisterClass<"AMDGPU", [v4i32, v4f32, v2i64, v2f64, i128], 32,
(add VGPR_128)> {
let Size = 128;

25
llvm/test/CodeGen/AMDGPU/GlobalISel/inst-select-load-flat.mir
View File

@ -392,24 +392,25 @@ body: |
; GFX7-LABEL: name: load_flat_s128
; GFX7: liveins: $vgpr0_vgpr1
; GFX7: [[COPY:%[0-9]+]]:vgpr(p1) = COPY $vgpr0_vgpr1
; GFX7: [[LOAD:%[0-9]+]]:vreg_128(s128) = G_LOAD [[COPY]](p1) :: (load 16, align 4)
; GFX7: $vgpr0_vgpr1_vgpr2_vgpr3 = COPY [[LOAD]](s128)
; GFX7: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
; GFX7: [[FLAT_LOAD_DWORDX4_:%[0-9]+]]:vreg_128 = FLAT_LOAD_DWORDX4 [[COPY]], 0, 0, 0, 0, implicit $exec, implicit $flat_scr :: (load 16, align 4)
; GFX7: $vgpr0_vgpr1_vgpr2_vgpr3 = COPY [[FLAT_LOAD_DWORDX4_]]
; GFX8-LABEL: name: load_flat_s128
; GFX8: liveins: $vgpr0_vgpr1
; GFX8: [[COPY:%[0-9]+]]:vgpr(p1) = COPY $vgpr0_vgpr1
; GFX8: [[LOAD:%[0-9]+]]:vreg_128(s128) = G_LOAD [[COPY]](p1) :: (load 16, align 4)
; GFX8: $vgpr0_vgpr1_vgpr2_vgpr3 = COPY [[LOAD]](s128)
; GFX8: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
; GFX8: [[FLAT_LOAD_DWORDX4_:%[0-9]+]]:vreg_128 = FLAT_LOAD_DWORDX4 [[COPY]], 0, 0, 0, 0, implicit $exec, implicit $flat_scr :: (load 16, align 4)
; GFX8: $vgpr0_vgpr1_vgpr2_vgpr3 = COPY [[FLAT_LOAD_DWORDX4_]]
; GFX9-LABEL: name: load_flat_s128
; GFX9: liveins: $vgpr0_vgpr1
; GFX9: [[COPY:%[0-9]+]]:vgpr(p1) = COPY $vgpr0_vgpr1
; GFX9: [[LOAD:%[0-9]+]]:vreg_128(s128) = G_LOAD [[COPY]](p1) :: (load 16, align 4)
; GFX9: $vgpr0_vgpr1_vgpr2_vgpr3 = COPY [[LOAD]](s128)
; GFX9: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
; GFX9: [[FLAT_LOAD_DWORDX4_:%[0-9]+]]:vreg_128 = FLAT_LOAD_DWORDX4 [[COPY]], 0, 0, 0, 0, implicit $exec, implicit $flat_scr :: (load 16, align 4)
; GFX9: $vgpr0_vgpr1_vgpr2_vgpr3 = COPY [[FLAT_LOAD_DWORDX4_]]
; GFX10-LABEL: name: load_flat_s128
; GFX10: liveins: $vgpr0_vgpr1
; GFX10: [[COPY:%[0-9]+]]:vgpr(p1) = COPY $vgpr0_vgpr1
; GFX10: [[LOAD:%[0-9]+]]:vreg_128(s128) = G_LOAD [[COPY]](p1) :: (load 16, align 4)
; GFX10: $vgpr0_vgpr1_vgpr2_vgpr3 = COPY [[LOAD]](s128)
; GFX10: $vcc_hi = IMPLICIT_DEF
; GFX10: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
; GFX10: [[FLAT_LOAD_DWORDX4_:%[0-9]+]]:vreg_128 = FLAT_LOAD_DWORDX4 [[COPY]], 0, 0, 0, 0, implicit $exec, implicit $flat_scr :: (load 16, align 4)
; GFX10: $vgpr0_vgpr1_vgpr2_vgpr3 = COPY [[FLAT_LOAD_DWORDX4_]]
%0:vgpr(p1) = COPY $vgpr0_vgpr1
%1:vgpr(s128) = G_LOAD %0 :: (load 16, align 4, addrspace 0)
$vgpr0_vgpr1_vgpr2_vgpr3 = COPY %1

31
llvm/test/CodeGen/AMDGPU/GlobalISel/inst-select-load-global.mir
View File

@ -459,29 +459,30 @@ body: |
; GFX6: $vgpr0_vgpr1_vgpr2_vgpr3 = COPY [[LOAD]](s128)
; GFX7-LABEL: name: load_global_s128
; GFX7: liveins: $vgpr0_vgpr1
; GFX7: [[COPY:%[0-9]+]]:vgpr(p1) = COPY $vgpr0_vgpr1
; GFX7: [[LOAD:%[0-9]+]]:vreg_128(s128) = G_LOAD [[COPY]](p1) :: (load 16, align 4, addrspace 1)
; GFX7: $vgpr0_vgpr1_vgpr2_vgpr3 = COPY [[LOAD]](s128)
; GFX7: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
; GFX7: [[FLAT_LOAD_DWORDX4_:%[0-9]+]]:vreg_128 = FLAT_LOAD_DWORDX4 [[COPY]], 0, 0, 0, 0, implicit $exec, implicit $flat_scr :: (load 16, align 4, addrspace 1)
; GFX7: $vgpr0_vgpr1_vgpr2_vgpr3 = COPY [[FLAT_LOAD_DWORDX4_]]
; GFX7-FLAT-LABEL: name: load_global_s128
; GFX7-FLAT: liveins: $vgpr0_vgpr1
; GFX7-FLAT: [[COPY:%[0-9]+]]:vgpr(p1) = COPY $vgpr0_vgpr1
; GFX7-FLAT: [[LOAD:%[0-9]+]]:vreg_128(s128) = G_LOAD [[COPY]](p1) :: (load 16, align 4, addrspace 1)
; GFX7-FLAT: $vgpr0_vgpr1_vgpr2_vgpr3 = COPY [[LOAD]](s128)
; GFX7-FLAT: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
; GFX7-FLAT: [[FLAT_LOAD_DWORDX4_:%[0-9]+]]:vreg_128 = FLAT_LOAD_DWORDX4 [[COPY]], 0, 0, 0, 0, implicit $exec, implicit $flat_scr :: (load 16, align 4, addrspace 1)
; GFX7-FLAT: $vgpr0_vgpr1_vgpr2_vgpr3 = COPY [[FLAT_LOAD_DWORDX4_]]
; GFX8-LABEL: name: load_global_s128
; GFX8: liveins: $vgpr0_vgpr1
; GFX8: [[COPY:%[0-9]+]]:vgpr(p1) = COPY $vgpr0_vgpr1
; GFX8: [[LOAD:%[0-9]+]]:vreg_128(s128) = G_LOAD [[COPY]](p1) :: (load 16, align 4, addrspace 1)
; GFX8: $vgpr0_vgpr1_vgpr2_vgpr3 = COPY [[LOAD]](s128)
; GFX8: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
; GFX8: [[FLAT_LOAD_DWORDX4_:%[0-9]+]]:vreg_128 = FLAT_LOAD_DWORDX4 [[COPY]], 0, 0, 0, 0, implicit $exec, implicit $flat_scr :: (load 16, align 4, addrspace 1)
; GFX8: $vgpr0_vgpr1_vgpr2_vgpr3 = COPY [[FLAT_LOAD_DWORDX4_]]
; GFX9-LABEL: name: load_global_s128
; GFX9: liveins: $vgpr0_vgpr1
; GFX9: [[COPY:%[0-9]+]]:vgpr(p1) = COPY $vgpr0_vgpr1
; GFX9: [[LOAD:%[0-9]+]]:vreg_128(s128) = G_LOAD [[COPY]](p1) :: (load 16, align 4, addrspace 1)
; GFX9: $vgpr0_vgpr1_vgpr2_vgpr3 = COPY [[LOAD]](s128)
; GFX9: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
; GFX9: [[GLOBAL_LOAD_DWORDX4_:%[0-9]+]]:vreg_128 = GLOBAL_LOAD_DWORDX4 [[COPY]], 0, 0, 0, 0, implicit $exec :: (load 16, align 4, addrspace 1)
; GFX9: $vgpr0_vgpr1_vgpr2_vgpr3 = COPY [[GLOBAL_LOAD_DWORDX4_]]
; GFX10-LABEL: name: load_global_s128
; GFX10: liveins: $vgpr0_vgpr1
; GFX10: [[COPY:%[0-9]+]]:vgpr(p1) = COPY $vgpr0_vgpr1
; GFX10: [[LOAD:%[0-9]+]]:vreg_128(s128) = G_LOAD [[COPY]](p1) :: (load 16, align 4, addrspace 1)
; GFX10: $vgpr0_vgpr1_vgpr2_vgpr3 = COPY [[LOAD]](s128)
; GFX10: $vcc_hi = IMPLICIT_DEF
; GFX10: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
; GFX10: [[GLOBAL_LOAD_DWORDX4_:%[0-9]+]]:vreg_128 = GLOBAL_LOAD_DWORDX4 [[COPY]], 0, 0, 0, 0, implicit $exec :: (load 16, align 4, addrspace 1)
; GFX10: $vgpr0_vgpr1_vgpr2_vgpr3 = COPY [[GLOBAL_LOAD_DWORDX4_]]
%0:vgpr(p1) = COPY $vgpr0_vgpr1
%1:vgpr(s128) = G_LOAD %0 :: (load 16, align 4, addrspace 1)
$vgpr0_vgpr1_vgpr2_vgpr3 = COPY %1

25
llvm/test/CodeGen/AMDGPU/GlobalISel/inst-select-store-flat.mir
View File

@ -202,24 +202,25 @@ body: |
; GFX7-LABEL: name: store_flat_s128
; GFX7: liveins: $vgpr0_vgpr1, $vgpr2_vgpr3_vgpr4_vgpr5
; GFX7: [[COPY:%[0-9]+]]:vgpr(p1) = COPY $vgpr0_vgpr1
; GFX7: [[COPY1:%[0-9]+]]:vgpr(s128) = COPY $vgpr2_vgpr3_vgpr4_vgpr5
; GFX7: G_STORE [[COPY1]](s128), [[COPY]](p1) :: (store 16)
; GFX7: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
; GFX7: [[COPY1:%[0-9]+]]:vreg_128 = COPY $vgpr2_vgpr3_vgpr4_vgpr5
; GFX7: FLAT_STORE_DWORDX4 [[COPY]], [[COPY1]], 0, 0, 0, 0, implicit $exec, implicit $flat_scr :: (store 16)
; GFX8-LABEL: name: store_flat_s128
; GFX8: liveins: $vgpr0_vgpr1, $vgpr2_vgpr3_vgpr4_vgpr5
; GFX8: [[COPY:%[0-9]+]]:vgpr(p1) = COPY $vgpr0_vgpr1
; GFX8: [[COPY1:%[0-9]+]]:vgpr(s128) = COPY $vgpr2_vgpr3_vgpr4_vgpr5
; GFX8: G_STORE [[COPY1]](s128), [[COPY]](p1) :: (store 16)
; GFX8: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
; GFX8: [[COPY1:%[0-9]+]]:vreg_128 = COPY $vgpr2_vgpr3_vgpr4_vgpr5
; GFX8: FLAT_STORE_DWORDX4 [[COPY]], [[COPY1]], 0, 0, 0, 0, implicit $exec, implicit $flat_scr :: (store 16)
; GFX9-LABEL: name: store_flat_s128
; GFX9: liveins: $vgpr0_vgpr1, $vgpr2_vgpr3_vgpr4_vgpr5
; GFX9: [[COPY:%[0-9]+]]:vgpr(p1) = COPY $vgpr0_vgpr1
; GFX9: [[COPY1:%[0-9]+]]:vgpr(s128) = COPY $vgpr2_vgpr3_vgpr4_vgpr5
; GFX9: G_STORE [[COPY1]](s128), [[COPY]](p1) :: (store 16)
; GFX9: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
; GFX9: [[COPY1:%[0-9]+]]:vreg_128 = COPY $vgpr2_vgpr3_vgpr4_vgpr5
; GFX9: FLAT_STORE_DWORDX4 [[COPY]], [[COPY1]], 0, 0, 0, 0, implicit $exec, implicit $flat_scr :: (store 16)
; GFX10-LABEL: name: store_flat_s128
; GFX10: liveins: $vgpr0_vgpr1, $vgpr2_vgpr3_vgpr4_vgpr5
; GFX10: [[COPY:%[0-9]+]]:vgpr(p1) = COPY $vgpr0_vgpr1
; GFX10: [[COPY1:%[0-9]+]]:vgpr(s128) = COPY $vgpr2_vgpr3_vgpr4_vgpr5
; GFX10: G_STORE [[COPY1]](s128), [[COPY]](p1) :: (store 16)
; GFX10: $vcc_hi = IMPLICIT_DEF
; GFX10: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
; GFX10: [[COPY1:%[0-9]+]]:vreg_128 = COPY $vgpr2_vgpr3_vgpr4_vgpr5
; GFX10: FLAT_STORE_DWORDX4 [[COPY]], [[COPY1]], 0, 0, 0, 0, implicit $exec, implicit $flat_scr :: (store 16)
%0:vgpr(p1) = COPY $vgpr0_vgpr1
%1:vgpr(s128) = COPY $vgpr2_vgpr3_vgpr4_vgpr5
G_STORE %1, %0 :: (store 16, align 16, addrspace 0)

31
llvm/test/CodeGen/AMDGPU/GlobalISel/inst-select-store-global.mir
View File

@ -289,29 +289,30 @@ body: |
; GFX6: G_STORE [[COPY1]](s128), [[COPY]](p1) :: (store 16, addrspace 1)
; GFX7-LABEL: name: store_global_s128
; GFX7: liveins: $vgpr0_vgpr1, $vgpr2_vgpr3_vgpr4_vgpr5
; GFX7: [[COPY:%[0-9]+]]:vgpr(p1) = COPY $vgpr0_vgpr1
; GFX7: [[COPY1:%[0-9]+]]:vgpr(s128) = COPY $vgpr2_vgpr3_vgpr4_vgpr5
; GFX7: G_STORE [[COPY1]](s128), [[COPY]](p1) :: (store 16, addrspace 1)
; GFX7: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
; GFX7: [[COPY1:%[0-9]+]]:vreg_128 = COPY $vgpr2_vgpr3_vgpr4_vgpr5
; GFX7: FLAT_STORE_DWORDX4 [[COPY]], [[COPY1]], 0, 0, 0, 0, implicit $exec, implicit $flat_scr :: (store 16, addrspace 1)
; GFX7-FLAT-LABEL: name: store_global_s128
; GFX7-FLAT: liveins: $vgpr0_vgpr1, $vgpr2_vgpr3_vgpr4_vgpr5
; GFX7-FLAT: [[COPY:%[0-9]+]]:vgpr(p1) = COPY $vgpr0_vgpr1
; GFX7-FLAT: [[COPY1:%[0-9]+]]:vgpr(s128) = COPY $vgpr2_vgpr3_vgpr4_vgpr5
; GFX7-FLAT: G_STORE [[COPY1]](s128), [[COPY]](p1) :: (store 16, addrspace 1)
; GFX7-FLAT: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
; GFX7-FLAT: [[COPY1:%[0-9]+]]:vreg_128 = COPY $vgpr2_vgpr3_vgpr4_vgpr5
; GFX7-FLAT: FLAT_STORE_DWORDX4 [[COPY]], [[COPY1]], 0, 0, 0, 0, implicit $exec, implicit $flat_scr :: (store 16, addrspace 1)
; GFX8-LABEL: name: store_global_s128
; GFX8: liveins: $vgpr0_vgpr1, $vgpr2_vgpr3_vgpr4_vgpr5
; GFX8: [[COPY:%[0-9]+]]:vgpr(p1) = COPY $vgpr0_vgpr1
; GFX8: [[COPY1:%[0-9]+]]:vgpr(s128) = COPY $vgpr2_vgpr3_vgpr4_vgpr5
; GFX8: G_STORE [[COPY1]](s128), [[COPY]](p1) :: (store 16, addrspace 1)
; GFX8: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
; GFX8: [[COPY1:%[0-9]+]]:vreg_128 = COPY $vgpr2_vgpr3_vgpr4_vgpr5
; GFX8: FLAT_STORE_DWORDX4 [[COPY]], [[COPY1]], 0, 0, 0, 0, implicit $exec, implicit $flat_scr :: (store 16, addrspace 1)
; GFX9-LABEL: name: store_global_s128
; GFX9: liveins: $vgpr0_vgpr1, $vgpr2_vgpr3_vgpr4_vgpr5
; GFX9: [[COPY:%[0-9]+]]:vgpr(p1) = COPY $vgpr0_vgpr1
; GFX9: [[COPY1:%[0-9]+]]:vgpr(s128) = COPY $vgpr2_vgpr3_vgpr4_vgpr5
; GFX9: G_STORE [[COPY1]](s128), [[COPY]](p1) :: (store 16, addrspace 1)
; GFX9: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
; GFX9: [[COPY1:%[0-9]+]]:vreg_128 = COPY $vgpr2_vgpr3_vgpr4_vgpr5
; GFX9: GLOBAL_STORE_DWORDX4 [[COPY]], [[COPY1]], 0, 0, 0, 0, implicit $exec :: (store 16, addrspace 1)
; GFX10-LABEL: name: store_global_s128
; GFX10: liveins: $vgpr0_vgpr1, $vgpr2_vgpr3_vgpr4_vgpr5
; GFX10: [[COPY:%[0-9]+]]:vgpr(p1) = COPY $vgpr0_vgpr1
; GFX10: [[COPY1:%[0-9]+]]:vgpr(s128) = COPY $vgpr2_vgpr3_vgpr4_vgpr5
; GFX10: G_STORE [[COPY1]](s128), [[COPY]](p1) :: (store 16, addrspace 1)
; GFX10: $vcc_hi = IMPLICIT_DEF
; GFX10: [[COPY:%[0-9]+]]:vreg_64 = COPY $vgpr0_vgpr1
; GFX10: [[COPY1:%[0-9]+]]:vreg_128 = COPY $vgpr2_vgpr3_vgpr4_vgpr5
; GFX10: GLOBAL_STORE_DWORDX4 [[COPY]], [[COPY1]], 0, 0, 0, 0, implicit $exec :: (store 16, addrspace 1)
%0:vgpr(p1) = COPY $vgpr0_vgpr1
%1:vgpr(s128) = COPY $vgpr2_vgpr3_vgpr4_vgpr5
G_STORE %1, %0 :: (store 16, align 16, addrspace 1)