1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-22 18:54:02 +01:00
llvm-mirror/test/CodeGen/AMDGPU/llvm.amdgcn.struct.buffer.load.format.d16.ll
Tim Renouf 524551cd05 [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 11:07:10 +00:00

42 lines
2.3 KiB
LLVM

; RUN: llc < %s -march=amdgcn -mcpu=tonga -verify-machineinstrs -show-mc-encoding | FileCheck -enable-var-scope -check-prefix=GCN -check-prefix=UNPACKED %s
; RUN: llc < %s -march=amdgcn -mcpu=gfx810 -verify-machineinstrs | FileCheck -enable-var-scope -check-prefix=GCN -check-prefix=PACKED %s
; RUN: llc < %s -march=amdgcn -mcpu=gfx900 -verify-machineinstrs | FileCheck -enable-var-scope -check-prefix=GCN -check-prefix=PACKED %s
; GCN-LABEL: {{^}}buffer_load_format_d16_x:
; GCN: buffer_load_format_d16_x v{{[0-9]+}}, {{v[0-9]+}}, s[{{[0-9]+:[0-9]+}}], 0 idxen
define amdgpu_ps half @buffer_load_format_d16_x(<4 x i32> inreg %rsrc) {
main_body:
%data = call half @llvm.amdgcn.struct.buffer.load.format.f16(<4 x i32> %rsrc, i32 0, i32 0, i32 0, i32 0)
ret half %data
}
; GCN-LABEL: {{^}}buffer_load_format_d16_xy:
; UNPACKED: buffer_load_format_d16_xy v{{\[}}{{[0-9]+}}:[[HI:[0-9]+]]{{\]}}, {{v[0-9]+}}, s[{{[0-9]+:[0-9]+}}], 0 idxen
; UNPACKED: v_mov_b32_e32 v{{[0-9]+}}, v[[HI]]
; PACKED: buffer_load_format_d16_xy v[[FULL:[0-9]+]], {{v[0-9]+}}, s[{{[0-9]+:[0-9]+}}], 0 idxen
; PACKED: v_lshrrev_b32_e32 v{{[0-9]+}}, 16, v[[FULL]]
define amdgpu_ps half @buffer_load_format_d16_xy(<4 x i32> inreg %rsrc) {
main_body:
%data = call <2 x half> @llvm.amdgcn.struct.buffer.load.format.v2f16(<4 x i32> %rsrc, i32 0, i32 0, i32 0, i32 0)
%elt = extractelement <2 x half> %data, i32 1
ret half %elt
}
; GCN-LABEL: {{^}}buffer_load_format_d16_xyzw:
; UNPACKED: buffer_load_format_d16_xyzw v{{\[}}{{[0-9]+}}:[[HI:[0-9]+]]{{\]}}, {{v[0-9]+}}, s[{{[0-9]+:[0-9]+}}], 0 idxen
; UNPACKED: v_mov_b32_e32 v{{[0-9]+}}, v[[HI]]
; PACKED: buffer_load_format_d16_xyzw v{{\[}}{{[0-9]+}}:[[HI:[0-9]+]]{{\]}}, {{v[0-9]+}}, s[{{[0-9]+:[0-9]+}}], 0 idxen
; PACKED: v_lshrrev_b32_e32 v{{[0-9]+}}, 16, v[[HI]]
define amdgpu_ps half @buffer_load_format_d16_xyzw(<4 x i32> inreg %rsrc) {
main_body:
%data = call <4 x half> @llvm.amdgcn.struct.buffer.load.format.v4f16(<4 x i32> %rsrc, i32 0, i32 0, i32 0, i32 0)
%elt = extractelement <4 x half> %data, i32 3
ret half %elt
}
declare half @llvm.amdgcn.struct.buffer.load.format.f16(<4 x i32>, i32, i32, i32, i32)
declare <2 x half> @llvm.amdgcn.struct.buffer.load.format.v2f16(<4 x i32>, i32, i32, i32, i32)
declare <4 x half> @llvm.amdgcn.struct.buffer.load.format.v4f16(<4 x i32>, i32, i32, i32, i32)