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.buffer.store.ll

180 lines
8.5 KiB
LLVM
Raw Normal View History

AMDGPU: add llvm.amdgcn.buffer.load/store intrinsics Summary: They correspond to BUFFER_LOAD/STORE_DWORD[_X2,X3,X4] and mostly behave like llvm.amdgcn.buffer.load/store.format. They will be used by Mesa for SSBO and atomic counters at least when robust buffer access behavior is desired. (These instructions perform no format conversion and do buffer range checking per component.) As a side effect of sharing patterns with llvm.amdgcn.buffer.store.format, it has become trivial to add support for the f32 and v2f32 variants of that intrinsic, so the patch does so. Also DAG-ify (and fix) some tests that I noticed intermittent failures in while developing this patch. Some tests were (temporarily) adjusted for the required mayLoad/hasSideEffects changes to the BUFFER_STORE_DWORD* instructions. See also http://reviews.llvm.org/D18291. Reviewers: arsenm, tstellarAMD, mareko Subscribers: arsenm, llvm-commits Differential Revision: http://reviews.llvm.org/D18292 llvm-svn: 266126
2016-04-13 05:18:10 +08:00
;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:
AMDGPU: Lower buffer store and atomic intrinsics manually Summary: Without this, SIMemoryLegalizer inserts s_waitcnt vmcnt(0) before every buffer store and atomic instruction. Reviewers: arsenm, nhaehnle Subscribers: kzhuravl, wdng, yaxunl, dstuttard, tpr, llvm-commits, t-tye Differential Revision: https://reviews.llvm.org/D39060 llvm-svn: 317754
2017-11-09 09:52:48 +08:00
;CHECK-NOT: s_waitcnt
AMDGPU/SI: Assembler: Unify parsing/printing of operands. Summary: The goal is for each operand type to have its own parse function and at the same time share common code for tracking state as different instruction types share operand types (e.g. glc/glc_flat, etc). Introduce parseAMDGPUOperand which can parse any optional operand. DPP and Clamp/OMod have custom handling for now. Sam also suggested to have class hierarchy for operand types instead of table. This can be done in separate change. Remove parseVOP3OptionalOps, parseDS*OptionalOps, parseFlatOptionalOps, parseMubufOptionalOps, parseDPPOptionalOps. Reduce number of definitions of AsmOperand's and MatchClasses' by using common base class. Rename AsmMatcher/InstPrinter methods accordingly. Print immediate type when printing parsed immediate operand. Use 'off' if offset/index register is unused instead of skipping it to make it more readable (also agreed with SP3). Update tests. Reviewers: tstellarAMD, SamWot, artem.tamazov Subscribers: qcolombet, arsenm, llvm-commits Differential Revision: http://reviews.llvm.org/D19584 llvm-svn: 268015
2016-04-29 17:02:30 +08:00
;CHECK: buffer_store_dwordx4 v[0:3], off, s[0:3], 0
;CHECK: buffer_store_dwordx4 v[4:7], off, s[0:3], 0 glc
;CHECK: buffer_store_dwordx4 v[8:11], off, s[0:3], 0 slc
AMDGPU: add llvm.amdgcn.buffer.load/store intrinsics Summary: They correspond to BUFFER_LOAD/STORE_DWORD[_X2,X3,X4] and mostly behave like llvm.amdgcn.buffer.load/store.format. They will be used by Mesa for SSBO and atomic counters at least when robust buffer access behavior is desired. (These instructions perform no format conversion and do buffer range checking per component.) As a side effect of sharing patterns with llvm.amdgcn.buffer.store.format, it has become trivial to add support for the f32 and v2f32 variants of that intrinsic, so the patch does so. Also DAG-ify (and fix) some tests that I noticed intermittent failures in while developing this patch. Some tests were (temporarily) adjusted for the required mayLoad/hasSideEffects changes to the BUFFER_STORE_DWORD* instructions. See also http://reviews.llvm.org/D18291. Reviewers: arsenm, tstellarAMD, mareko Subscribers: arsenm, llvm-commits Differential Revision: http://reviews.llvm.org/D18292 llvm-svn: 266126
2016-04-13 05:18:10 +08:00
define amdgpu_ps void @buffer_store(<4 x i32> inreg, <4 x float>, <4 x float>, <4 x float>) {
main_body:
call void @llvm.amdgcn.buffer.store.v4f32(<4 x float> %1, <4 x i32> %0, i32 0, i32 0, i1 0, i1 0)
call void @llvm.amdgcn.buffer.store.v4f32(<4 x float> %2, <4 x i32> %0, i32 0, i32 0, i1 1, i1 0)
call void @llvm.amdgcn.buffer.store.v4f32(<4 x float> %3, <4 x i32> %0, i32 0, i32 0, i1 0, i1 1)
ret void
}
;CHECK-LABEL: {{^}}buffer_store_immoffs:
AMDGPU: Lower buffer store and atomic intrinsics manually Summary: Without this, SIMemoryLegalizer inserts s_waitcnt vmcnt(0) before every buffer store and atomic instruction. Reviewers: arsenm, nhaehnle Subscribers: kzhuravl, wdng, yaxunl, dstuttard, tpr, llvm-commits, t-tye Differential Revision: https://reviews.llvm.org/D39060 llvm-svn: 317754
2017-11-09 09:52:48 +08:00
;CHECK-NOT: s_waitcnt
AMDGPU/SI: Assembler: Unify parsing/printing of operands. Summary: The goal is for each operand type to have its own parse function and at the same time share common code for tracking state as different instruction types share operand types (e.g. glc/glc_flat, etc). Introduce parseAMDGPUOperand which can parse any optional operand. DPP and Clamp/OMod have custom handling for now. Sam also suggested to have class hierarchy for operand types instead of table. This can be done in separate change. Remove parseVOP3OptionalOps, parseDS*OptionalOps, parseFlatOptionalOps, parseMubufOptionalOps, parseDPPOptionalOps. Reduce number of definitions of AsmOperand's and MatchClasses' by using common base class. Rename AsmMatcher/InstPrinter methods accordingly. Print immediate type when printing parsed immediate operand. Use 'off' if offset/index register is unused instead of skipping it to make it more readable (also agreed with SP3). Update tests. Reviewers: tstellarAMD, SamWot, artem.tamazov Subscribers: qcolombet, arsenm, llvm-commits Differential Revision: http://reviews.llvm.org/D19584 llvm-svn: 268015
2016-04-29 17:02:30 +08:00
;CHECK: buffer_store_dwordx4 v[0:3], off, s[0:3], 0 offset:42
AMDGPU: add llvm.amdgcn.buffer.load/store intrinsics Summary: They correspond to BUFFER_LOAD/STORE_DWORD[_X2,X3,X4] and mostly behave like llvm.amdgcn.buffer.load/store.format. They will be used by Mesa for SSBO and atomic counters at least when robust buffer access behavior is desired. (These instructions perform no format conversion and do buffer range checking per component.) As a side effect of sharing patterns with llvm.amdgcn.buffer.store.format, it has become trivial to add support for the f32 and v2f32 variants of that intrinsic, so the patch does so. Also DAG-ify (and fix) some tests that I noticed intermittent failures in while developing this patch. Some tests were (temporarily) adjusted for the required mayLoad/hasSideEffects changes to the BUFFER_STORE_DWORD* instructions. See also http://reviews.llvm.org/D18291. Reviewers: arsenm, tstellarAMD, mareko Subscribers: arsenm, llvm-commits Differential Revision: http://reviews.llvm.org/D18292 llvm-svn: 266126
2016-04-13 05:18:10 +08:00
define amdgpu_ps void @buffer_store_immoffs(<4 x i32> inreg, <4 x float>) {
main_body:
call void @llvm.amdgcn.buffer.store.v4f32(<4 x float> %1, <4 x i32> %0, i32 0, i32 42, i1 0, i1 0)
ret void
}
;CHECK-LABEL: {{^}}buffer_store_idx:
AMDGPU: Lower buffer store and atomic intrinsics manually Summary: Without this, SIMemoryLegalizer inserts s_waitcnt vmcnt(0) before every buffer store and atomic instruction. Reviewers: arsenm, nhaehnle Subscribers: kzhuravl, wdng, yaxunl, dstuttard, tpr, llvm-commits, t-tye Differential Revision: https://reviews.llvm.org/D39060 llvm-svn: 317754
2017-11-09 09:52:48 +08:00
;CHECK-NOT: s_waitcnt
AMDGPU: add llvm.amdgcn.buffer.load/store intrinsics Summary: They correspond to BUFFER_LOAD/STORE_DWORD[_X2,X3,X4] and mostly behave like llvm.amdgcn.buffer.load/store.format. They will be used by Mesa for SSBO and atomic counters at least when robust buffer access behavior is desired. (These instructions perform no format conversion and do buffer range checking per component.) As a side effect of sharing patterns with llvm.amdgcn.buffer.store.format, it has become trivial to add support for the f32 and v2f32 variants of that intrinsic, so the patch does so. Also DAG-ify (and fix) some tests that I noticed intermittent failures in while developing this patch. Some tests were (temporarily) adjusted for the required mayLoad/hasSideEffects changes to the BUFFER_STORE_DWORD* instructions. See also http://reviews.llvm.org/D18291. Reviewers: arsenm, tstellarAMD, mareko Subscribers: arsenm, llvm-commits Differential Revision: http://reviews.llvm.org/D18292 llvm-svn: 266126
2016-04-13 05:18:10 +08:00
;CHECK: buffer_store_dwordx4 v[0:3], v4, s[0:3], 0 idxen
define amdgpu_ps void @buffer_store_idx(<4 x i32> inreg, <4 x float>, i32) {
main_body:
call void @llvm.amdgcn.buffer.store.v4f32(<4 x float> %1, <4 x i32> %0, i32 %2, i32 0, i1 0, i1 0)
ret void
}
;CHECK-LABEL: {{^}}buffer_store_ofs:
AMDGPU: Lower buffer store and atomic intrinsics manually Summary: Without this, SIMemoryLegalizer inserts s_waitcnt vmcnt(0) before every buffer store and atomic instruction. Reviewers: arsenm, nhaehnle Subscribers: kzhuravl, wdng, yaxunl, dstuttard, tpr, llvm-commits, t-tye Differential Revision: https://reviews.llvm.org/D39060 llvm-svn: 317754
2017-11-09 09:52:48 +08:00
;CHECK-NOT: s_waitcnt
AMDGPU: add llvm.amdgcn.buffer.load/store intrinsics Summary: They correspond to BUFFER_LOAD/STORE_DWORD[_X2,X3,X4] and mostly behave like llvm.amdgcn.buffer.load/store.format. They will be used by Mesa for SSBO and atomic counters at least when robust buffer access behavior is desired. (These instructions perform no format conversion and do buffer range checking per component.) As a side effect of sharing patterns with llvm.amdgcn.buffer.store.format, it has become trivial to add support for the f32 and v2f32 variants of that intrinsic, so the patch does so. Also DAG-ify (and fix) some tests that I noticed intermittent failures in while developing this patch. Some tests were (temporarily) adjusted for the required mayLoad/hasSideEffects changes to the BUFFER_STORE_DWORD* instructions. See also http://reviews.llvm.org/D18291. Reviewers: arsenm, tstellarAMD, mareko Subscribers: arsenm, llvm-commits Differential Revision: http://reviews.llvm.org/D18292 llvm-svn: 266126
2016-04-13 05:18:10 +08:00
;CHECK: buffer_store_dwordx4 v[0:3], v4, s[0:3], 0 offen
define amdgpu_ps void @buffer_store_ofs(<4 x i32> inreg, <4 x float>, i32) {
main_body:
call void @llvm.amdgcn.buffer.store.v4f32(<4 x float> %1, <4 x i32> %0, i32 0, i32 %2, i1 0, i1 0)
ret void
}
;CHECK-LABEL: {{^}}buffer_store_both:
AMDGPU: Lower buffer store and atomic intrinsics manually Summary: Without this, SIMemoryLegalizer inserts s_waitcnt vmcnt(0) before every buffer store and atomic instruction. Reviewers: arsenm, nhaehnle Subscribers: kzhuravl, wdng, yaxunl, dstuttard, tpr, llvm-commits, t-tye Differential Revision: https://reviews.llvm.org/D39060 llvm-svn: 317754
2017-11-09 09:52:48 +08:00
;CHECK-NOT: s_waitcnt
AMDGPU: add llvm.amdgcn.buffer.load/store intrinsics Summary: They correspond to BUFFER_LOAD/STORE_DWORD[_X2,X3,X4] and mostly behave like llvm.amdgcn.buffer.load/store.format. They will be used by Mesa for SSBO and atomic counters at least when robust buffer access behavior is desired. (These instructions perform no format conversion and do buffer range checking per component.) As a side effect of sharing patterns with llvm.amdgcn.buffer.store.format, it has become trivial to add support for the f32 and v2f32 variants of that intrinsic, so the patch does so. Also DAG-ify (and fix) some tests that I noticed intermittent failures in while developing this patch. Some tests were (temporarily) adjusted for the required mayLoad/hasSideEffects changes to the BUFFER_STORE_DWORD* instructions. See also http://reviews.llvm.org/D18291. Reviewers: arsenm, tstellarAMD, mareko Subscribers: arsenm, llvm-commits Differential Revision: http://reviews.llvm.org/D18292 llvm-svn: 266126
2016-04-13 05:18:10 +08:00
;CHECK: buffer_store_dwordx4 v[0:3], v[4:5], s[0:3], 0 idxen offen
define amdgpu_ps void @buffer_store_both(<4 x i32> inreg, <4 x float>, i32, i32) {
main_body:
call void @llvm.amdgcn.buffer.store.v4f32(<4 x float> %1, <4 x i32> %0, i32 %2, i32 %3, i1 0, i1 0)
ret void
}
;CHECK-LABEL: {{^}}buffer_store_both_reversed:
;CHECK: v_mov_b32_e32 v6, v4
AMDGPU: Lower buffer store and atomic intrinsics manually Summary: Without this, SIMemoryLegalizer inserts s_waitcnt vmcnt(0) before every buffer store and atomic instruction. Reviewers: arsenm, nhaehnle Subscribers: kzhuravl, wdng, yaxunl, dstuttard, tpr, llvm-commits, t-tye Differential Revision: https://reviews.llvm.org/D39060 llvm-svn: 317754
2017-11-09 09:52:48 +08:00
;CHECK-NOT: s_waitcnt
AMDGPU: add llvm.amdgcn.buffer.load/store intrinsics Summary: They correspond to BUFFER_LOAD/STORE_DWORD[_X2,X3,X4] and mostly behave like llvm.amdgcn.buffer.load/store.format. They will be used by Mesa for SSBO and atomic counters at least when robust buffer access behavior is desired. (These instructions perform no format conversion and do buffer range checking per component.) As a side effect of sharing patterns with llvm.amdgcn.buffer.store.format, it has become trivial to add support for the f32 and v2f32 variants of that intrinsic, so the patch does so. Also DAG-ify (and fix) some tests that I noticed intermittent failures in while developing this patch. Some tests were (temporarily) adjusted for the required mayLoad/hasSideEffects changes to the BUFFER_STORE_DWORD* instructions. See also http://reviews.llvm.org/D18291. Reviewers: arsenm, tstellarAMD, mareko Subscribers: arsenm, llvm-commits Differential Revision: http://reviews.llvm.org/D18292 llvm-svn: 266126
2016-04-13 05:18:10 +08:00
;CHECK: buffer_store_dwordx4 v[0:3], v[5:6], s[0:3], 0 idxen offen
define amdgpu_ps void @buffer_store_both_reversed(<4 x i32> inreg, <4 x float>, i32, i32) {
main_body:
call void @llvm.amdgcn.buffer.store.v4f32(<4 x float> %1, <4 x i32> %0, i32 %3, i32 %2, i1 0, i1 0)
ret void
}
; Ideally, the register allocator would avoid the wait here
;
;CHECK-LABEL: {{^}}buffer_store_wait:
AMDGPU: Lower buffer store and atomic intrinsics manually Summary: Without this, SIMemoryLegalizer inserts s_waitcnt vmcnt(0) before every buffer store and atomic instruction. Reviewers: arsenm, nhaehnle Subscribers: kzhuravl, wdng, yaxunl, dstuttard, tpr, llvm-commits, t-tye Differential Revision: https://reviews.llvm.org/D39060 llvm-svn: 317754
2017-11-09 09:52:48 +08:00
;CHECK-NOT: s_waitcnt
AMDGPU: add llvm.amdgcn.buffer.load/store intrinsics Summary: They correspond to BUFFER_LOAD/STORE_DWORD[_X2,X3,X4] and mostly behave like llvm.amdgcn.buffer.load/store.format. They will be used by Mesa for SSBO and atomic counters at least when robust buffer access behavior is desired. (These instructions perform no format conversion and do buffer range checking per component.) As a side effect of sharing patterns with llvm.amdgcn.buffer.store.format, it has become trivial to add support for the f32 and v2f32 variants of that intrinsic, so the patch does so. Also DAG-ify (and fix) some tests that I noticed intermittent failures in while developing this patch. Some tests were (temporarily) adjusted for the required mayLoad/hasSideEffects changes to the BUFFER_STORE_DWORD* instructions. See also http://reviews.llvm.org/D18291. Reviewers: arsenm, tstellarAMD, mareko Subscribers: arsenm, llvm-commits Differential Revision: http://reviews.llvm.org/D18292 llvm-svn: 266126
2016-04-13 05:18:10 +08:00
;CHECK: buffer_store_dwordx4 v[0:3], v4, s[0:3], 0 idxen
[AMDGPU] Turn on the new waitcnt insertion pass. Adjust tests. -enable-si-insert-waitcnts=1 becomes the default -enable-si-insert-waitcnts=0 to use old pass Differential Revision: https://reviews.llvm.org/D33730 llvm-svn: 304551
2017-06-02 22:19:25 +08:00
;CHECK: s_waitcnt expcnt(0)
AMDGPU: add llvm.amdgcn.buffer.load/store intrinsics Summary: They correspond to BUFFER_LOAD/STORE_DWORD[_X2,X3,X4] and mostly behave like llvm.amdgcn.buffer.load/store.format. They will be used by Mesa for SSBO and atomic counters at least when robust buffer access behavior is desired. (These instructions perform no format conversion and do buffer range checking per component.) As a side effect of sharing patterns with llvm.amdgcn.buffer.store.format, it has become trivial to add support for the f32 and v2f32 variants of that intrinsic, so the patch does so. Also DAG-ify (and fix) some tests that I noticed intermittent failures in while developing this patch. Some tests were (temporarily) adjusted for the required mayLoad/hasSideEffects changes to the BUFFER_STORE_DWORD* instructions. See also http://reviews.llvm.org/D18291. Reviewers: arsenm, tstellarAMD, mareko Subscribers: arsenm, llvm-commits Differential Revision: http://reviews.llvm.org/D18292 llvm-svn: 266126
2016-04-13 05:18:10 +08:00
;CHECK: buffer_load_dwordx4 v[0:3], v5, s[0:3], 0 idxen
;CHECK: s_waitcnt vmcnt(0)
;CHECK: buffer_store_dwordx4 v[0:3], v6, s[0:3], 0 idxen
define amdgpu_ps void @buffer_store_wait(<4 x i32> inreg, <4 x float>, i32, i32, i32) {
main_body:
call void @llvm.amdgcn.buffer.store.v4f32(<4 x float> %1, <4 x i32> %0, i32 %2, i32 0, i1 0, i1 0)
%data = call <4 x float> @llvm.amdgcn.buffer.load.v4f32(<4 x i32> %0, i32 %3, i32 0, i1 0, i1 0)
call void @llvm.amdgcn.buffer.store.v4f32(<4 x float> %data, <4 x i32> %0, i32 %4, i32 0, i1 0, i1 0)
ret void
}
;CHECK-LABEL: {{^}}buffer_store_x1:
AMDGPU: Lower buffer store and atomic intrinsics manually Summary: Without this, SIMemoryLegalizer inserts s_waitcnt vmcnt(0) before every buffer store and atomic instruction. Reviewers: arsenm, nhaehnle Subscribers: kzhuravl, wdng, yaxunl, dstuttard, tpr, llvm-commits, t-tye Differential Revision: https://reviews.llvm.org/D39060 llvm-svn: 317754
2017-11-09 09:52:48 +08:00
;CHECK-NOT: s_waitcnt
AMDGPU: add llvm.amdgcn.buffer.load/store intrinsics Summary: They correspond to BUFFER_LOAD/STORE_DWORD[_X2,X3,X4] and mostly behave like llvm.amdgcn.buffer.load/store.format. They will be used by Mesa for SSBO and atomic counters at least when robust buffer access behavior is desired. (These instructions perform no format conversion and do buffer range checking per component.) As a side effect of sharing patterns with llvm.amdgcn.buffer.store.format, it has become trivial to add support for the f32 and v2f32 variants of that intrinsic, so the patch does so. Also DAG-ify (and fix) some tests that I noticed intermittent failures in while developing this patch. Some tests were (temporarily) adjusted for the required mayLoad/hasSideEffects changes to the BUFFER_STORE_DWORD* instructions. See also http://reviews.llvm.org/D18291. Reviewers: arsenm, tstellarAMD, mareko Subscribers: arsenm, llvm-commits Differential Revision: http://reviews.llvm.org/D18292 llvm-svn: 266126
2016-04-13 05:18:10 +08:00
;CHECK: buffer_store_dword v0, v1, s[0:3], 0 idxen
define amdgpu_ps void @buffer_store_x1(<4 x i32> inreg %rsrc, float %data, i32 %index) {
main_body:
call void @llvm.amdgcn.buffer.store.f32(float %data, <4 x i32> %rsrc, i32 %index, i32 0, i1 0, i1 0)
ret void
}
;CHECK-LABEL: {{^}}buffer_store_x2:
AMDGPU: Lower buffer store and atomic intrinsics manually Summary: Without this, SIMemoryLegalizer inserts s_waitcnt vmcnt(0) before every buffer store and atomic instruction. Reviewers: arsenm, nhaehnle Subscribers: kzhuravl, wdng, yaxunl, dstuttard, tpr, llvm-commits, t-tye Differential Revision: https://reviews.llvm.org/D39060 llvm-svn: 317754
2017-11-09 09:52:48 +08:00
;CHECK-NOT: s_waitcnt
AMDGPU: add llvm.amdgcn.buffer.load/store intrinsics Summary: They correspond to BUFFER_LOAD/STORE_DWORD[_X2,X3,X4] and mostly behave like llvm.amdgcn.buffer.load/store.format. They will be used by Mesa for SSBO and atomic counters at least when robust buffer access behavior is desired. (These instructions perform no format conversion and do buffer range checking per component.) As a side effect of sharing patterns with llvm.amdgcn.buffer.store.format, it has become trivial to add support for the f32 and v2f32 variants of that intrinsic, so the patch does so. Also DAG-ify (and fix) some tests that I noticed intermittent failures in while developing this patch. Some tests were (temporarily) adjusted for the required mayLoad/hasSideEffects changes to the BUFFER_STORE_DWORD* instructions. See also http://reviews.llvm.org/D18291. Reviewers: arsenm, tstellarAMD, mareko Subscribers: arsenm, llvm-commits Differential Revision: http://reviews.llvm.org/D18292 llvm-svn: 266126
2016-04-13 05:18:10 +08:00
;CHECK: buffer_store_dwordx2 v[0:1], v2, s[0:3], 0 idxen
define amdgpu_ps void @buffer_store_x2(<4 x i32> inreg %rsrc, <2 x float> %data, i32 %index) #0 {
main_body:
call void @llvm.amdgcn.buffer.store.v2f32(<2 x float> %data, <4 x i32> %rsrc, i32 %index, i32 0, i1 0, i1 0)
ret void
}
AMDGPU: Merge BUFFER_STORE_DWORD_OFFEN/OFFSET into x2, x4 Summary: Only 56 shaders (out of 48486) are affected. Totals from affected shaders (changed stats only): SGPRS: 2420 -> 2460 (1.65 %) Spilled VGPRs: 94 -> 112 (19.15 %) Scratch size: 524 -> 528 (0.76 %) dwords per thread Code Size: 187400 -> 184992 (-1.28 %) bytes One DiRT Showdown shader spills 6 more VGPRs. One Grid Autosport shader spills 12 more VGPRs. The other 54 shaders only have a decrease in code size. (I'm ignoring the SGPR noise) Reviewers: arsenm, nhaehnle Subscribers: kzhuravl, wdng, yaxunl, dstuttard, tpr, llvm-commits, t-tye Differential Revision: https://reviews.llvm.org/D39012 llvm-svn: 317755
2017-11-09 09:52:55 +08:00
;CHECK-LABEL: {{^}}buffer_store_x1_offen_merged:
;CHECK-NOT: s_waitcnt
;CHECK-DAG: buffer_store_dwordx4 v[{{[0-9]}}:{{[0-9]}}], v0, s[0:3], 0 offen offset:4
;CHECK-DAG: buffer_store_dwordx2 v[{{[0-9]}}:{{[0-9]}}], v0, s[0:3], 0 offen offset:28
define amdgpu_ps void @buffer_store_x1_offen_merged(<4 x i32> inreg %rsrc, i32 %a, float %v1, float %v2, float %v3, float %v4, float %v5, float %v6) {
%a1 = add i32 %a, 4
%a2 = add i32 %a, 8
%a3 = add i32 %a, 12
%a4 = add i32 %a, 16
%a5 = add i32 %a, 28
%a6 = add i32 %a, 32
call void @llvm.amdgcn.buffer.store.f32(float %v1, <4 x i32> %rsrc, i32 0, i32 %a1, i1 0, i1 0)
call void @llvm.amdgcn.buffer.store.f32(float %v2, <4 x i32> %rsrc, i32 0, i32 %a2, i1 0, i1 0)
call void @llvm.amdgcn.buffer.store.f32(float %v3, <4 x i32> %rsrc, i32 0, i32 %a3, i1 0, i1 0)
call void @llvm.amdgcn.buffer.store.f32(float %v4, <4 x i32> %rsrc, i32 0, i32 %a4, i1 0, i1 0)
call void @llvm.amdgcn.buffer.store.f32(float %v5, <4 x i32> %rsrc, i32 0, i32 %a5, i1 0, i1 0)
call void @llvm.amdgcn.buffer.store.f32(float %v6, <4 x i32> %rsrc, i32 0, i32 %a6, i1 0, i1 0)
ret void
}
;CHECK-LABEL: {{^}}buffer_store_x1_offen_merged_glc_slc:
;CHECK-NOT: s_waitcnt
;CHECK-DAG: buffer_store_dwordx2 v[{{[0-9]}}:{{[0-9]}}], v0, s[0:3], 0 offen offset:4{{$}}
;CHECK-DAG: buffer_store_dwordx2 v[{{[0-9]}}:{{[0-9]}}], v0, s[0:3], 0 offen offset:12 glc{{$}}
;CHECK-DAG: buffer_store_dwordx2 v[{{[0-9]}}:{{[0-9]}}], v0, s[0:3], 0 offen offset:28 glc slc{{$}}
define amdgpu_ps void @buffer_store_x1_offen_merged_glc_slc(<4 x i32> inreg %rsrc, i32 %a, float %v1, float %v2, float %v3, float %v4, float %v5, float %v6) {
%a1 = add i32 %a, 4
%a2 = add i32 %a, 8
%a3 = add i32 %a, 12
%a4 = add i32 %a, 16
%a5 = add i32 %a, 28
%a6 = add i32 %a, 32
call void @llvm.amdgcn.buffer.store.f32(float %v1, <4 x i32> %rsrc, i32 0, i32 %a1, i1 0, i1 0)
call void @llvm.amdgcn.buffer.store.f32(float %v2, <4 x i32> %rsrc, i32 0, i32 %a2, i1 0, i1 0)
call void @llvm.amdgcn.buffer.store.f32(float %v3, <4 x i32> %rsrc, i32 0, i32 %a3, i1 1, i1 0)
call void @llvm.amdgcn.buffer.store.f32(float %v4, <4 x i32> %rsrc, i32 0, i32 %a4, i1 1, i1 0)
call void @llvm.amdgcn.buffer.store.f32(float %v5, <4 x i32> %rsrc, i32 0, i32 %a5, i1 1, i1 1)
call void @llvm.amdgcn.buffer.store.f32(float %v6, <4 x i32> %rsrc, i32 0, i32 %a6, i1 1, i1 1)
ret void
}
;CHECK-LABEL: {{^}}buffer_store_x2_offen_merged:
;CHECK-NOT: s_waitcnt
;CHECK: buffer_store_dwordx4 v[{{[0-9]}}:{{[0-9]}}], v0, s[0:3], 0 offen offset:4
define amdgpu_ps void @buffer_store_x2_offen_merged(<4 x i32> inreg %rsrc, i32 %a, <2 x float> %v1, <2 x float> %v2) {
%a1 = add i32 %a, 4
%a2 = add i32 %a, 12
call void @llvm.amdgcn.buffer.store.v2f32(<2 x float> %v1, <4 x i32> %rsrc, i32 0, i32 %a1, i1 0, i1 0)
call void @llvm.amdgcn.buffer.store.v2f32(<2 x float> %v2, <4 x i32> %rsrc, i32 0, i32 %a2, i1 0, i1 0)
ret void
}
;CHECK-LABEL: {{^}}buffer_store_x1_offset_merged:
;CHECK-NOT: s_waitcnt
;CHECK-DAG: buffer_store_dwordx4 v[{{[0-9]}}:{{[0-9]}}], off, s[0:3], 0 offset:4
;CHECK-DAG: buffer_store_dwordx2 v[{{[0-9]}}:{{[0-9]}}], off, s[0:3], 0 offset:28
define amdgpu_ps void @buffer_store_x1_offset_merged(<4 x i32> inreg %rsrc, float %v1, float %v2, float %v3, float %v4, float %v5, float %v6) {
call void @llvm.amdgcn.buffer.store.f32(float %v1, <4 x i32> %rsrc, i32 0, i32 4, i1 0, i1 0)
call void @llvm.amdgcn.buffer.store.f32(float %v2, <4 x i32> %rsrc, i32 0, i32 8, i1 0, i1 0)
call void @llvm.amdgcn.buffer.store.f32(float %v3, <4 x i32> %rsrc, i32 0, i32 12, i1 0, i1 0)
call void @llvm.amdgcn.buffer.store.f32(float %v4, <4 x i32> %rsrc, i32 0, i32 16, i1 0, i1 0)
call void @llvm.amdgcn.buffer.store.f32(float %v5, <4 x i32> %rsrc, i32 0, i32 28, i1 0, i1 0)
call void @llvm.amdgcn.buffer.store.f32(float %v6, <4 x i32> %rsrc, i32 0, i32 32, i1 0, i1 0)
ret void
}
;CHECK-LABEL: {{^}}buffer_store_x2_offset_merged:
;CHECK-NOT: s_waitcnt
;CHECK: buffer_store_dwordx4 v[{{[0-9]}}:{{[0-9]}}], off, s[0:3], 0 offset:4
define amdgpu_ps void @buffer_store_x2_offset_merged(<4 x i32> inreg %rsrc, <2 x float> %v1,<2 x float> %v2) {
call void @llvm.amdgcn.buffer.store.v2f32(<2 x float> %v1, <4 x i32> %rsrc, i32 0, i32 4, i1 0, i1 0)
call void @llvm.amdgcn.buffer.store.v2f32(<2 x float> %v2, <4 x i32> %rsrc, i32 0, i32 12, i1 0, i1 0)
ret void
}
AMDGPU: add llvm.amdgcn.buffer.load/store intrinsics Summary: They correspond to BUFFER_LOAD/STORE_DWORD[_X2,X3,X4] and mostly behave like llvm.amdgcn.buffer.load/store.format. They will be used by Mesa for SSBO and atomic counters at least when robust buffer access behavior is desired. (These instructions perform no format conversion and do buffer range checking per component.) As a side effect of sharing patterns with llvm.amdgcn.buffer.store.format, it has become trivial to add support for the f32 and v2f32 variants of that intrinsic, so the patch does so. Also DAG-ify (and fix) some tests that I noticed intermittent failures in while developing this patch. Some tests were (temporarily) adjusted for the required mayLoad/hasSideEffects changes to the BUFFER_STORE_DWORD* instructions. See also http://reviews.llvm.org/D18291. Reviewers: arsenm, tstellarAMD, mareko Subscribers: arsenm, llvm-commits Differential Revision: http://reviews.llvm.org/D18292 llvm-svn: 266126
2016-04-13 05:18:10 +08:00
declare void @llvm.amdgcn.buffer.store.f32(float, <4 x i32>, i32, i32, i1, i1) #0
declare void @llvm.amdgcn.buffer.store.v2f32(<2 x float>, <4 x i32>, i32, i32, i1, i1) #0
declare void @llvm.amdgcn.buffer.store.v4f32(<4 x float>, <4 x i32>, i32, i32, i1, i1) #0
declare <4 x float> @llvm.amdgcn.buffer.load.v4f32(<4 x i32>, i32, i32, i1, i1) #1
attributes #0 = { nounwind }
attributes #1 = { nounwind readonly }