maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.struct.tbuffer....

115 lines
5.8 KiB
LLVM
Raw Normal View History

[AMDGPU] New tbuffer intrinsics Summary: This commit adds new intrinsics llvm.amdgcn.raw.tbuffer.load llvm.amdgcn.struct.tbuffer.load llvm.amdgcn.raw.tbuffer.store llvm.amdgcn.struct.tbuffer.store with the following changes from the llvm.amdgcn.tbuffer.* intrinsics: * there are separate raw and struct versions: raw does not have an index arg and sets idxen=0 in the instruction, and struct always sets idxen=1 in the instruction even if the index is 0, to allow for the fact that gfx9 does bounds checking differently depending on whether idxen is set; * there is a combined format arg (dfmt+nfmt) * there is a combined cachepolicy arg (glc+slc) * there are now only two offset args: one for the offset that is included in bounds checking and swizzling, to be split between the instruction's voffset and immoffset fields, and one for the offset that is excluded from bounds checking and swizzling, to go into the instruction's soffset field. The AMDISD::TBUFFER_* SD nodes always have an index operand, all three offset operands, combined format operand, combined cachepolicy operand, and an extra idxen operand. The tbuffer pseudo- and real instructions now also have a combined format operand. The obsolescent llvm.amdgcn.tbuffer.* and llvm.SI.tbuffer.store intrinsics continue to work. V2: Separate raw and struct intrinsics. V3: Moved extract_glc and extract_slc defs to a more sensible place. V4: Rebased on D49995. V5: Only two separate offset args instead of three. V6: Pseudo- and real instructions have joint format operand. V7: Restored optionality of dfmt and nfmt in assembler. V8: Addressed minor review comments. Subscribers: arsenm, kzhuravl, wdng, nhaehnle, yaxunl, dstuttard, t-tye, llvm-commits Differential Revision: https://reviews.llvm.org/D49026 Change-Id: If22ad77e349fac3a5d2f72dda53c010377d470d4 llvm-svn: 340268
2018-08-21 19:06:05 +08:00
;RUN: llc < %s -march=amdgcn -mcpu=verde -verify-machineinstrs | FileCheck -check-prefixes=GCN,VERDE %s
;RUN: llc < %s -march=amdgcn -mcpu=tonga -verify-machineinstrs | FileCheck -check-prefix=GCN %s
; GCN-LABEL: {{^}}tbuffer_store:
; GCN: v_mov_b32_e32 [[ZEROREG:v[0-9]+]], 0
; GCN: tbuffer_store_format_xyzw v[0:3], [[ZEROREG]], s[0:3], dfmt:12, nfmt:2, 0 idxen
; GCN: tbuffer_store_format_xyzw v[4:7], [[ZEROREG]], s[0:3], dfmt:13, nfmt:3, 0 idxen glc
; GCN: tbuffer_store_format_xyzw v[8:11], [[ZEROREG]], s[0:3], dfmt:14, nfmt:4, 0 idxen slc
; GCN: tbuffer_store_format_xyzw v[8:11], [[ZEROREG]], s[0:3], dfmt:14, nfmt:4, 0 idxen
define amdgpu_ps void @tbuffer_store(<4 x i32> inreg, <4 x float>, <4 x float>, <4 x float>) {
main_body:
%in1 = bitcast <4 x float> %1 to <4 x i32>
%in2 = bitcast <4 x float> %2 to <4 x i32>
%in3 = bitcast <4 x float> %3 to <4 x i32>
call void @llvm.amdgcn.struct.tbuffer.store.v4i32(<4 x i32> %in1, <4 x i32> %0, i32 0, i32 0, i32 0, i32 44, i32 0)
call void @llvm.amdgcn.struct.tbuffer.store.v4i32(<4 x i32> %in2, <4 x i32> %0, i32 0, i32 0, i32 0, i32 61, i32 1)
call void @llvm.amdgcn.struct.tbuffer.store.v4i32(<4 x i32> %in3, <4 x i32> %0, i32 0, i32 0, i32 0, i32 78, i32 2)
call void @llvm.amdgcn.struct.tbuffer.store.v4f32(<4 x float> %3, <4 x i32> %0, i32 0, i32 0, i32 0, i32 78, i32 0)
ret void
}
; GCN-LABEL: {{^}}tbuffer_store_immoffs:
; GCN: v_mov_b32_e32 [[ZEROREG:v[0-9]+]], 0
; GCN: tbuffer_store_format_xyzw v[0:3], [[ZEROREG]], s[0:3], dfmt:5, nfmt:7, 0 idxen offset:42
define amdgpu_ps void @tbuffer_store_immoffs(<4 x i32> inreg, <4 x float>) {
main_body:
%in1 = bitcast <4 x float> %1 to <4 x i32>
call void @llvm.amdgcn.struct.tbuffer.store.v4i32(<4 x i32> %in1, <4 x i32> %0, i32 0, i32 42, i32 0, i32 117, i32 0)
ret void
}
; GCN-LABEL: {{^}}tbuffer_store_scalar_and_imm_offs:
; GCN: v_mov_b32_e32 [[ZEROREG:v[0-9]+]], 0
; GCN: tbuffer_store_format_xyzw v[0:3], [[ZEROREG]], s[0:3], dfmt:5, nfmt:7, {{s[0-9]+}} idxen offset:42
define amdgpu_ps void @tbuffer_store_scalar_and_imm_offs(<4 x i32> inreg, <4 x float> %vdata, i32 inreg %soffset) {
main_body:
%in1 = bitcast <4 x float> %vdata to <4 x i32>
call void @llvm.amdgcn.struct.tbuffer.store.v4i32(<4 x i32> %in1, <4 x i32> %0, i32 0, i32 42, i32 %soffset, i32 117, i32 0)
ret void
}
; GCN-LABEL: {{^}}buffer_store_idx:
; GCN: tbuffer_store_format_xyzw v[0:3], v4, s[0:3], dfmt:15, nfmt:2, 0 idxen
define amdgpu_ps void @buffer_store_idx(<4 x i32> inreg, <4 x float> %vdata, i32 %vindex) {
main_body:
%in1 = bitcast <4 x float> %vdata to <4 x i32>
call void @llvm.amdgcn.struct.tbuffer.store.v4i32(<4 x i32> %in1, <4 x i32> %0, i32 %vindex, i32 0, i32 0, i32 47, i32 0)
ret void
}
; GCN-LABEL: {{^}}buffer_store_ofs:
; GCN: tbuffer_store_format_xyzw v[0:3], {{v\[[0-9]+:[0-9]+\]}}, s[0:3], dfmt:3, nfmt:7, 0 idxen offen
define amdgpu_ps void @buffer_store_ofs(<4 x i32> inreg, <4 x float> %vdata, i32 %voffset) {
main_body:
%in1 = bitcast <4 x float> %vdata to <4 x i32>
call void @llvm.amdgcn.struct.tbuffer.store.v4i32(<4 x i32> %in1, <4 x i32> %0, i32 0, i32 %voffset, i32 0, i32 115, i32 0)
ret void
}
; GCN-LABEL: {{^}}buffer_store_both:
; GCN: tbuffer_store_format_xyzw v[0:3], v[4:5], s[0:3], dfmt:6, nfmt:4, 0 idxen offen
define amdgpu_ps void @buffer_store_both(<4 x i32> inreg, <4 x float> %vdata, i32 %vindex, i32 %voffset) {
main_body:
%in1 = bitcast <4 x float> %vdata to <4 x i32>
call void @llvm.amdgcn.struct.tbuffer.store.v4i32(<4 x i32> %in1, <4 x i32> %0, i32 %vindex, i32 %voffset, i32 0, i32 70, i32 0)
ret void
}
; Ideally, the register allocator would avoid the wait here
;
; GCN-LABEL: {{^}}buffer_store_wait:
; GCN: tbuffer_store_format_xyzw v[0:3], v4, s[0:3], dfmt:15, nfmt:3, 0 idxen
; VERDE: s_waitcnt expcnt(0)
; GCN: buffer_load_format_xyzw v[0:3], v5, s[0:3], 0 idxen
; GCN: s_waitcnt vmcnt(0)
; GCN: tbuffer_store_format_xyzw v[0:3], v6, s[0:3], dfmt:14, nfmt:2, 0 idxen
define amdgpu_ps void @buffer_store_wait(<4 x i32> inreg, <4 x float> %vdata, i32 %vindex.1, i32 %vindex.2, i32 %vindex.3) {
main_body:
%in1 = bitcast <4 x float> %vdata to <4 x i32>
call void @llvm.amdgcn.struct.tbuffer.store.v4i32(<4 x i32> %in1, <4 x i32> %0, i32 %vindex.1, i32 0, i32 0, i32 63, i32 0)
%data = call <4 x float> @llvm.amdgcn.buffer.load.format.v4f32(<4 x i32> %0, i32 %vindex.2, i32 0, i1 0, i1 0)
%data.i = bitcast <4 x float> %data to <4 x i32>
call void @llvm.amdgcn.struct.tbuffer.store.v4i32(<4 x i32> %data.i, <4 x i32> %0, i32 %vindex.3, i32 0, i32 0, i32 46, i32 0)
ret void
}
; GCN-LABEL: {{^}}buffer_store_x1:
; GCN: tbuffer_store_format_x v0, v1, s[0:3], dfmt:13, nfmt:7, 0 idxen
define amdgpu_ps void @buffer_store_x1(<4 x i32> inreg %rsrc, float %data, i32 %vindex) {
main_body:
%data.i = bitcast float %data to i32
call void @llvm.amdgcn.struct.tbuffer.store.i32(i32 %data.i, <4 x i32> %rsrc, i32 %vindex, i32 0, i32 0, i32 125, i32 0)
ret void
}
; GCN-LABEL: {{^}}buffer_store_x2:
; GCN: tbuffer_store_format_xy v[0:1], v2, s[0:3], dfmt:1, nfmt:2, 0 idxen
define amdgpu_ps void @buffer_store_x2(<4 x i32> inreg %rsrc, <2 x float> %data, i32 %vindex) {
main_body:
%data.i = bitcast <2 x float> %data to <2 x i32>
call void @llvm.amdgcn.struct.tbuffer.store.v2i32(<2 x i32> %data.i, <4 x i32> %rsrc, i32 %vindex, i32 0, i32 0, i32 33, i32 0)
ret void
}
declare void @llvm.amdgcn.struct.tbuffer.store.i32(i32, <4 x i32>, i32, i32, i32, i32, i32) #0
declare void @llvm.amdgcn.struct.tbuffer.store.v2i32(<2 x i32>, <4 x i32>, i32, i32, i32, i32, i32) #0
declare void @llvm.amdgcn.struct.tbuffer.store.v4i32(<4 x i32>, <4 x i32>, i32, i32, i32, i32, i32) #0
declare void @llvm.amdgcn.struct.tbuffer.store.v4f32(<4 x float>, <4 x i32>, i32, i32, i32, i32, i32) #0
declare <4 x float> @llvm.amdgcn.buffer.load.format.v4f32(<4 x i32>, i32, i32, i1, i1) #1
attributes #0 = { nounwind }
attributes #1 = { nounwind readonly }