Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
AMDGPU/SI: add llvm.amdgcn.buffer.load/store.format intrinsics
Summary: They correspond to BUFFER_LOAD/STORE_FORMAT_XYZW and will be used by Mesa to implement the GL_ARB_shader_image_load_store extension. The intention is that for llvm.amdgcn.buffer.load.format, LLVM will decide whether one of the _X/_XY/_XYZ opcodes can be used (similar to image sampling and loads). However, this is not currently implemented. For llvm.amdgcn.buffer.store, LLVM cannot decide to use one of the "smaller" opcodes and therefore the intrinsic is overloaded. Currently, only the v4f32 is actually implemented since GLSL also only has a vec4 variant of the store instructions, although it's conceivable that Mesa will want to be smarter about this in the future. BUFFER_LOAD_FORMAT_XYZW is already exposed via llvm.SI.vs.load.input, which has a legacy name, pretends not to access memory, and does not capture the full flexibility of the instruction. Reviewers: arsenm, tstellarAMD, mareko Subscribers: arsenm, llvm-commits Differential Revision: http://reviews.llvm.org/D17277 llvm-svn: 263140
- Loading branch information
Showing
5 changed files
with
257 additions
and
15 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
69 changes: 69 additions & 0 deletions
69
llvm/test/CodeGen/AMDGPU/llvm.amdgcn.buffer.load.format.ll
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,69 @@ | ||
;RUN: llc < %s -march=amdgcn -mcpu=verde -verify-machineinstrs | FileCheck %s | ||
;RUN: llc < %s -march=amdgcn -mcpu=tonga -verify-machineinstrs | FileCheck %s | ||
|
||
;CHECK-LABEL: {{^}}buffer_load: | ||
;CHECK: buffer_load_format_xyzw v[0:3], s[0:3], s4 | ||
;CHECK: buffer_load_format_xyzw v[4:7], s[0:3], s4 glc | ||
;CHECK: buffer_load_format_xyzw v[8:11], s[0:3], s4 slc | ||
;CHECK: s_waitcnt | ||
define {<4 x float>, <4 x float>, <4 x float>} @buffer_load(<4 x i32> inreg, i32 inreg) #0 { | ||
main_body: | ||
%data = call <4 x float> @llvm.amdgcn.buffer.load.format(<4 x i32> %0, i32 %1, i32 0, i32 0, i32 0, i1 0, i1 0) | ||
%data_glc = call <4 x float> @llvm.amdgcn.buffer.load.format(<4 x i32> %0, i32 %1, i32 0, i32 0, i32 0, i1 1, i1 0) | ||
%data_slc = call <4 x float> @llvm.amdgcn.buffer.load.format(<4 x i32> %0, i32 %1, i32 0, i32 0, i32 0, i1 0, i1 1) | ||
%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], s[0:3], s4 offset:42 | ||
;CHECK: s_waitcnt | ||
define <4 x float> @buffer_load_immoffs(<4 x i32> inreg, i32 inreg) #0 { | ||
main_body: | ||
%data = call <4 x float> @llvm.amdgcn.buffer.load.format(<4 x i32> %0, i32 %1, i32 42, i32 0, i32 0, i1 0, i1 0) | ||
ret <4 x float> %data | ||
} | ||
|
||
;CHECK-LABEL: {{^}}buffer_load_idx: | ||
;CHECK: buffer_load_format_xyzw v[0:3], v0, s[0:3], 0 idxen | ||
;CHECK: s_waitcnt | ||
define <4 x float> @buffer_load_idx(<4 x i32> inreg, i32) #0 { | ||
main_body: | ||
%data = call <4 x float> @llvm.amdgcn.buffer.load.format(<4 x i32> %0, i32 0, i32 0, i32 %1, i32 0, i1 0, i1 0) | ||
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 <4 x float> @buffer_load_ofs(<4 x i32> inreg, i32) #0 { | ||
main_body: | ||
%data = call <4 x float> @llvm.amdgcn.buffer.load.format(<4 x i32> %0, i32 0, i32 0, i32 0, i32 %1, i1 0, i1 0) | ||
ret <4 x float> %data | ||
} | ||
|
||
;CHECK-LABEL: {{^}}buffer_load_both: | ||
;CHECK: buffer_load_format_xyzw v[0:3], v[0:1], s[0:3], 0 idxen offen | ||
;CHECK: s_waitcnt | ||
define <4 x float> @buffer_load_both(<4 x i32> inreg, i32, i32) #0 { | ||
main_body: | ||
%data = call <4 x float> @llvm.amdgcn.buffer.load.format(<4 x i32> %0, i32 0, i32 0, i32 %1, i32 %2, i1 0, i1 0) | ||
ret <4 x float> %data | ||
} | ||
|
||
;CHECK-LABEL: {{^}}buffer_load_both_reversed: | ||
;CHECK: v_mov_b32_e32 v2, v0 | ||
;CHECK: buffer_load_format_xyzw v[0:3], v[1:2], s[0:3], 0 idxen offen | ||
;CHECK: s_waitcnt | ||
define <4 x float> @buffer_load_both_reversed(<4 x i32> inreg, i32, i32) #0 { | ||
main_body: | ||
%data = call <4 x float> @llvm.amdgcn.buffer.load.format(<4 x i32> %0, i32 0, i32 0, i32 %2, i32 %1, i1 0, i1 0) | ||
ret <4 x float> %data | ||
} | ||
|
||
declare <4 x float> @llvm.amdgcn.buffer.load.format(<4 x i32>, i32, i32, i32, i32, i1, i1) #1 | ||
|
||
attributes #0 = { "ShaderType"="0" } | ||
attributes #1 = { nounwind readonly } |
78 changes: 78 additions & 0 deletions
78
llvm/test/CodeGen/AMDGPU/llvm.amdgcn.buffer.store.format.ll
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,78 @@ | ||
;RUN: llc < %s -march=amdgcn -mcpu=verde -verify-machineinstrs | FileCheck %s | ||
;RUN: llc < %s -march=amdgcn -mcpu=tonga -verify-machineinstrs | FileCheck %s | ||
|
||
;CHECK-LABEL: {{^}}buffer_store: | ||
;CHECK: buffer_store_format_xyzw v[0:3], s[0:3], s4 | ||
;CHECK: buffer_store_format_xyzw v[4:7], s[0:3], s4 glc | ||
;CHECK: buffer_store_format_xyzw v[8:11], s[0:3], s4 slc | ||
define void @buffer_store(<4 x i32> inreg, i32 inreg, <4 x float>, <4 x float>, <4 x float>) #0 { | ||
main_body: | ||
call void @llvm.amdgcn.buffer.store.format.v4f32(<4 x float> %2, <4 x i32> %0, i32 %1, i32 0, i32 0, i32 0, i1 0, i1 0) | ||
call void @llvm.amdgcn.buffer.store.format.v4f32(<4 x float> %3, <4 x i32> %0, i32 %1, i32 0, i32 0, i32 0, i1 1, i1 0) | ||
call void @llvm.amdgcn.buffer.store.format.v4f32(<4 x float> %4, <4 x i32> %0, i32 %1, i32 0, i32 0, i32 0, i1 0, i1 1) | ||
ret void | ||
} | ||
|
||
;CHECK-LABEL: {{^}}buffer_store_immoffs: | ||
;CHECK: buffer_store_format_xyzw v[0:3], s[0:3], s4 offset:42 | ||
define void @buffer_store_immoffs(<4 x i32> inreg, i32 inreg, <4 x float>) #0 { | ||
main_body: | ||
call void @llvm.amdgcn.buffer.store.format.v4f32(<4 x float> %2, <4 x i32> %0, i32 %1, i32 42, i32 0, i32 0, i1 0, i1 0) | ||
ret void | ||
} | ||
|
||
;CHECK-LABEL: {{^}}buffer_store_idx: | ||
;CHECK: buffer_store_format_xyzw v[0:3], v4, s[0:3], 0 idxen | ||
define void @buffer_store_idx(<4 x i32> inreg, i32 inreg, <4 x float>, i32) #0 { | ||
main_body: | ||
call void @llvm.amdgcn.buffer.store.format.v4f32(<4 x float> %2, <4 x i32> %0, i32 0, i32 0, i32 %3, i32 0, i1 0, i1 0) | ||
ret void | ||
} | ||
|
||
;CHECK-LABEL: {{^}}buffer_store_ofs: | ||
;CHECK: buffer_store_format_xyzw v[0:3], v4, s[0:3], 0 offen | ||
define void @buffer_store_ofs(<4 x i32> inreg, i32 inreg, <4 x float>, i32) #0 { | ||
main_body: | ||
call void @llvm.amdgcn.buffer.store.format.v4f32(<4 x float> %2, <4 x i32> %0, i32 0, i32 0, i32 0, i32 %3, i1 0, i1 0) | ||
ret void | ||
} | ||
|
||
;CHECK-LABEL: {{^}}buffer_store_both: | ||
;CHECK: buffer_store_format_xyzw v[0:3], v[4:5], s[0:3], 0 idxen offen | ||
define void @buffer_store_both(<4 x i32> inreg, i32 inreg, <4 x float>, i32, i32) #0 { | ||
main_body: | ||
call void @llvm.amdgcn.buffer.store.format.v4f32(<4 x float> %2, <4 x i32> %0, i32 0, i32 0, i32 %3, i32 %4, i1 0, i1 0) | ||
ret void | ||
} | ||
|
||
;CHECK-LABEL: {{^}}buffer_store_both_reversed: | ||
;CHECK: v_mov_b32_e32 v6, v4 | ||
;CHECK: buffer_store_format_xyzw v[0:3], v[5:6], s[0:3], 0 idxen offen | ||
define void @buffer_store_both_reversed(<4 x i32> inreg, i32 inreg, <4 x float>, i32, i32) #0 { | ||
main_body: | ||
call void @llvm.amdgcn.buffer.store.format.v4f32(<4 x float> %2, <4 x i32> %0, i32 0, i32 0, i32 %4, i32 %3, i1 0, i1 0) | ||
ret void | ||
} | ||
|
||
; Ideally, the register allocator would avoid the wait here | ||
; | ||
;CHECK-LABEL: {{^}}buffer_store_wait: | ||
;CHECK: buffer_store_format_xyzw v[0:3], v4, s[0:3], 0 idxen | ||
;CHECK: s_waitcnt vmcnt(0) expcnt(0) | ||
;CHECK: buffer_load_format_xyzw v[0:3], v5, s[0:3], 0 idxen | ||
;CHECK: s_waitcnt vmcnt(0) | ||
;CHECK: buffer_store_format_xyzw v[0:3], v6, s[0:3], 0 idxen | ||
define void @buffer_store_wait(<4 x i32> inreg, i32 inreg, <4 x float>, i32, i32, i32) #0 { | ||
main_body: | ||
call void @llvm.amdgcn.buffer.store.format.v4f32(<4 x float> %2, <4 x i32> %0, i32 0, i32 0, i32 %3, i32 0, i1 0, i1 0) | ||
%data = call <4 x float> @llvm.amdgcn.buffer.load.format(<4 x i32> %0, i32 0, i32 0, i32 %4, i32 0, i1 0, i1 0) | ||
call void @llvm.amdgcn.buffer.store.format.v4f32(<4 x float> %data, <4 x i32> %0, i32 0, i32 0, i32 %5, i32 0, i1 0, i1 0) | ||
ret void | ||
} | ||
|
||
declare void @llvm.amdgcn.buffer.store.format.v4f32(<4 x float>, <4 x i32>, i32, i32, i32, i32, i1, i1) #1 | ||
declare <4 x float> @llvm.amdgcn.buffer.load.format(<4 x i32>, i32, i32, i32, i32, i1, i1) #2 | ||
|
||
attributes #0 = { "ShaderType"="0" } | ||
attributes #1 = { nounwind } | ||
attributes #2 = { nounwind readonly } |