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.raw.buffer.load...

88 lines
4.0 KiB
LLVM
Raw Normal View History

[AMDGPU] New buffer intrinsics Summary: This commit adds new intrinsics llvm.amdgcn.raw.buffer.load llvm.amdgcn.raw.buffer.load.format llvm.amdgcn.raw.buffer.load.format.d16 llvm.amdgcn.struct.buffer.load llvm.amdgcn.struct.buffer.load.format llvm.amdgcn.struct.buffer.load.format.d16 llvm.amdgcn.raw.buffer.store llvm.amdgcn.raw.buffer.store.format llvm.amdgcn.raw.buffer.store.format.d16 llvm.amdgcn.struct.buffer.store llvm.amdgcn.struct.buffer.store.format llvm.amdgcn.struct.buffer.store.format.d16 llvm.amdgcn.raw.buffer.atomic.* llvm.amdgcn.struct.buffer.atomic.* with the following changes from the llvm.amdgcn.buffer.* 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 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::BUFFER_* SD nodes always have an index operand, all three offset operands, combined cachepolicy operand, and an extra idxen operand. The obsolescent llvm.amdgcn.buffer.* intrinsics continue to work. Subscribers: arsenm, kzhuravl, wdng, nhaehnle, yaxunl, dstuttard, t-tye, jfb, llvm-commits Differential Revision: https://reviews.llvm.org/D50306 Change-Id: If897ea7dc34fcbf4d5496e98cc99a934f62fc205 llvm-svn: 340269
2018-08-21 19:07:10 +08:00
;RUN: llc < %s -march=amdgcn -mcpu=verde -verify-machineinstrs | FileCheck %s -check-prefix=CHECK -check-prefix=SICI
;RUN: llc < %s -march=amdgcn -mcpu=tonga -verify-machineinstrs | FileCheck %s -check-prefix=CHECK -check-prefix=VI
;CHECK-LABEL: {{^}}buffer_load:
;CHECK: buffer_load_format_xyzw v[0:3], off, s[0:3], 0
;CHECK: buffer_load_format_xyzw v[4:7], off, s[0:3], 0 glc
;CHECK: buffer_load_format_xyzw v[8:11], off, s[0:3], 0 slc
;CHECK: s_waitcnt
define amdgpu_ps {<4 x float>, <4 x float>, <4 x float>} @buffer_load(<4 x i32> inreg) {
main_body:
%data = call <4 x float> @llvm.amdgcn.raw.buffer.load.format.v4f32(<4 x i32> %0, i32 0, i32 0, i32 0)
%data_glc = call <4 x float> @llvm.amdgcn.raw.buffer.load.format.v4f32(<4 x i32> %0, i32 0, i32 0, i32 1)
%data_slc = call <4 x float> @llvm.amdgcn.raw.buffer.load.format.v4f32(<4 x i32> %0, i32 0, i32 0, i32 2)
%r0 = insertvalue {<4 x float>, <4 x float>, <4 x float>} undef, <4 x float> %data, 0
%r1 = insertvalue {<4 x float>, <4 x float>, <4 x float>} %r0, <4 x float> %data_glc, 1
%r2 = insertvalue {<4 x float>, <4 x float>, <4 x float>} %r1, <4 x float> %data_slc, 2
ret {<4 x float>, <4 x float>, <4 x float>} %r2
}
;CHECK-LABEL: {{^}}buffer_load_immoffs:
;CHECK: buffer_load_format_xyzw v[0:3], off, s[0:3], 0 offset:42
;CHECK: s_waitcnt
define amdgpu_ps <4 x float> @buffer_load_immoffs(<4 x i32> inreg) {
main_body:
%data = call <4 x float> @llvm.amdgcn.raw.buffer.load.format.v4f32(<4 x i32> %0, i32 42, i32 0, i32 0)
ret <4 x float> %data
}
;CHECK-LABEL: {{^}}buffer_load_immoffs_large:
;CHECK-DAG: buffer_load_format_xyzw {{v\[[0-9]+:[0-9]+\]}}, off, s[0:3], 60 offset:4092
;CHECK-DAG: s_movk_i32 [[OFS1:s[0-9]+]], 0x7ffc
;CHECK-DAG: buffer_load_format_xyzw {{v\[[0-9]+:[0-9]+\]}}, off, s[0:3], [[OFS1]] offset:4092
;CHECK-DAG: s_mov_b32 [[OFS2:s[0-9]+]], 0x8ffc
;CHECK-DAG: buffer_load_format_xyzw {{v\[[0-9]+:[0-9]+\]}}, off, s[0:3], [[OFS2]] offset:4
;CHECK: s_waitcnt
define amdgpu_ps <4 x float> @buffer_load_immoffs_large(<4 x i32> inreg) {
main_body:
%d.0 = call <4 x float> @llvm.amdgcn.raw.buffer.load.format.v4f32(<4 x i32> %0, i32 4092, i32 60, i32 0)
%d.1 = call <4 x float> @llvm.amdgcn.raw.buffer.load.format.v4f32(<4 x i32> %0, i32 4092, i32 32764, i32 0)
%d.2 = call <4 x float> @llvm.amdgcn.raw.buffer.load.format.v4f32(<4 x i32> %0, i32 4, i32 36860, i32 0)
%d.3 = fadd <4 x float> %d.0, %d.1
%data = fadd <4 x float> %d.2, %d.3
ret <4 x float> %data
}
;CHECK-LABEL: {{^}}buffer_load_ofs:
;CHECK: buffer_load_format_xyzw v[0:3], v0, s[0:3], 0 offen
;CHECK: s_waitcnt
define amdgpu_ps <4 x float> @buffer_load_ofs(<4 x i32> inreg, i32) {
main_body:
%data = call <4 x float> @llvm.amdgcn.raw.buffer.load.format.v4f32(<4 x i32> %0, i32 %1, i32 0, i32 0)
ret <4 x float> %data
}
;CHECK-LABEL: {{^}}buffer_load_ofs_imm:
;CHECK: buffer_load_format_xyzw v[0:3], v0, s[0:3], 0 offen offset:60
;CHECK: s_waitcnt
define amdgpu_ps <4 x float> @buffer_load_ofs_imm(<4 x i32> inreg, i32) {
main_body:
%ofs = add i32 %1, 60
%data = call <4 x float> @llvm.amdgcn.raw.buffer.load.format.v4f32(<4 x i32> %0, i32 %ofs, i32 0, i32 0)
ret <4 x float> %data
}
;CHECK-LABEL: {{^}}buffer_load_x:
;CHECK: buffer_load_format_x v0, off, s[0:3], 0
;CHECK: s_waitcnt
define amdgpu_ps float @buffer_load_x(<4 x i32> inreg %rsrc) {
main_body:
%data = call float @llvm.amdgcn.raw.buffer.load.format.f32(<4 x i32> %rsrc, i32 0, i32 0, i32 0)
ret float %data
}
;CHECK-LABEL: {{^}}buffer_load_xy:
;CHECK: buffer_load_format_xy v[0:1], off, s[0:3], 0
;CHECK: s_waitcnt
define amdgpu_ps <2 x float> @buffer_load_xy(<4 x i32> inreg %rsrc) {
main_body:
%data = call <2 x float> @llvm.amdgcn.raw.buffer.load.format.v2f32(<4 x i32> %rsrc, i32 0, i32 0, i32 0)
ret <2 x float> %data
}
declare float @llvm.amdgcn.raw.buffer.load.format.f32(<4 x i32>, i32, i32, i32) #0
declare <2 x float> @llvm.amdgcn.raw.buffer.load.format.v2f32(<4 x i32>, i32, i32, i32) #0
declare <4 x float> @llvm.amdgcn.raw.buffer.load.format.v4f32(<4 x i32>, i32, i32, i32) #0
attributes #0 = { nounwind readonly }