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/nsa-vmem-hazard.mir

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

62 lines
3.2 KiB
Plaintext
Raw Normal View History

AMDGPU] gfx1010 hazard recognizer Differential Revision: https://reviews.llvm.org/D61536 llvm-svn: 359961
2019-05-04 12:30:57 +08:00
# RUN: llc -march=amdgcn -mcpu=gfx1010 -verify-machineinstrs -run-pass post-RA-hazard-rec -o - %s | FileCheck -check-prefix=GCN %s
# GCN-LABEL: name: hazard_image_sample_d_buf_off6
# GCN: IMAGE_SAMPLE
# GCN-NEXT: S_NOP 0
# GCN-NEXT: BUFFER_LOAD_DWORD_OFFSET
---
name: hazard_image_sample_d_buf_off6
body: |
bb.0:
[AMDGPU] Add a16 feature to gfx10 Based on D72931 This adds a new feature called A16 which is enabled for gfx10. gfx9 keeps the R128A16 feature so it can share all the instruction encodings with gfx7/8. Differential Revision: https://reviews.llvm.org/D73956
2020-01-29 17:04:36 +08:00
$vgpr0_vgpr1_vgpr2_vgpr3 = IMAGE_SAMPLE_D_V4_V9_nsa_gfx10 undef $vgpr3, undef $vgpr8, undef $vgpr7, undef $vgpr5, undef $vgpr4, undef $vgpr6, undef $vgpr0, undef $vgpr2, undef $vgpr2, undef $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7, undef $sgpr8_sgpr9_sgpr10_sgpr11, 15, 2, 0, 0, 0, 0, 0, 0, 0, 0, 0, implicit $exec
[AMDGPU] Extend buffer intrinsics with swizzling Summary: Extend cachepolicy operand in the new VMEM buffer intrinsics to supply information whether the buffer data is swizzled. Also, propagate this information to MIR. Intrinsics updated: int_amdgcn_raw_buffer_load int_amdgcn_raw_buffer_load_format int_amdgcn_raw_buffer_store int_amdgcn_raw_buffer_store_format int_amdgcn_raw_tbuffer_load int_amdgcn_raw_tbuffer_store int_amdgcn_struct_buffer_load int_amdgcn_struct_buffer_load_format int_amdgcn_struct_buffer_store int_amdgcn_struct_buffer_store_format int_amdgcn_struct_tbuffer_load int_amdgcn_struct_tbuffer_store Furthermore, disable merging of VMEM buffer instructions in SI Load/Store optimizer, if the "swizzled" bit on the instruction is on. The default value of the bit is 0, meaning that data in buffer is linear and buffer instructions can be merged. There is no difference in the generated code with this commit. However, in the future it will be expected that front-ends use buffer intrinsics with correct "swizzled" bit set. Reviewers: arsenm, nhaehnle, tpr Reviewed By: nhaehnle Subscribers: arsenm, kzhuravl, jvesely, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye, arphaman, jfb, Petar.Avramovic, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D68200 llvm-svn: 373491
2019-10-03 01:22:36 +08:00
$vgpr1 = BUFFER_LOAD_DWORD_OFFSET undef $sgpr0_sgpr1_sgpr2_sgpr3, undef $sgpr4, 6, 0, 0, 0, 0, 0, implicit $exec
AMDGPU] gfx1010 hazard recognizer Differential Revision: https://reviews.llvm.org/D61536 llvm-svn: 359961
2019-05-04 12:30:57 +08:00
...
# GCN-LABEL: name: no_hazard_image_sample_d_buf_off1
# GCN: IMAGE_SAMPLE
# GCN-NEXT: BUFFER_LOAD_DWORD_OFFSET
---
name: no_hazard_image_sample_d_buf_off1
body: |
bb.0:
[AMDGPU] Add a16 feature to gfx10 Based on D72931 This adds a new feature called A16 which is enabled for gfx10. gfx9 keeps the R128A16 feature so it can share all the instruction encodings with gfx7/8. Differential Revision: https://reviews.llvm.org/D73956
2020-01-29 17:04:36 +08:00
$vgpr0_vgpr1_vgpr2_vgpr3 = IMAGE_SAMPLE_D_V4_V9_nsa_gfx10 undef $vgpr3, undef $vgpr8, undef $vgpr7, undef $vgpr5, undef $vgpr4, undef $vgpr6, undef $vgpr0, undef $vgpr2, undef $vgpr2, undef $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7, undef $sgpr8_sgpr9_sgpr10_sgpr11, 15, 2, 0, 0, 0, 0, 0, 0, 0, 0, 0, implicit $exec
[AMDGPU] Extend buffer intrinsics with swizzling Summary: Extend cachepolicy operand in the new VMEM buffer intrinsics to supply information whether the buffer data is swizzled. Also, propagate this information to MIR. Intrinsics updated: int_amdgcn_raw_buffer_load int_amdgcn_raw_buffer_load_format int_amdgcn_raw_buffer_store int_amdgcn_raw_buffer_store_format int_amdgcn_raw_tbuffer_load int_amdgcn_raw_tbuffer_store int_amdgcn_struct_buffer_load int_amdgcn_struct_buffer_load_format int_amdgcn_struct_buffer_store int_amdgcn_struct_buffer_store_format int_amdgcn_struct_tbuffer_load int_amdgcn_struct_tbuffer_store Furthermore, disable merging of VMEM buffer instructions in SI Load/Store optimizer, if the "swizzled" bit on the instruction is on. The default value of the bit is 0, meaning that data in buffer is linear and buffer instructions can be merged. There is no difference in the generated code with this commit. However, in the future it will be expected that front-ends use buffer intrinsics with correct "swizzled" bit set. Reviewers: arsenm, nhaehnle, tpr Reviewed By: nhaehnle Subscribers: arsenm, kzhuravl, jvesely, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye, arphaman, jfb, Petar.Avramovic, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D68200 llvm-svn: 373491
2019-10-03 01:22:36 +08:00
$vgpr1 = BUFFER_LOAD_DWORD_OFFSET undef $sgpr0_sgpr1_sgpr2_sgpr3, undef $sgpr4, 1, 0, 0, 0, 0, 0, implicit $exec
AMDGPU] gfx1010 hazard recognizer Differential Revision: https://reviews.llvm.org/D61536 llvm-svn: 359961
2019-05-04 12:30:57 +08:00
...
# GCN-LABEL: name: no_hazard_image_sample_d_buf_far
# GCN: IMAGE_SAMPLE
# GCN-NEXT: V_NOP_e32
# GCN-NEXT: BUFFER_LOAD_DWORD_OFFSET
---
name: no_hazard_image_sample_d_buf_far
body: |
bb.0:
[AMDGPU] Add a16 feature to gfx10 Based on D72931 This adds a new feature called A16 which is enabled for gfx10. gfx9 keeps the R128A16 feature so it can share all the instruction encodings with gfx7/8. Differential Revision: https://reviews.llvm.org/D73956
2020-01-29 17:04:36 +08:00
$vgpr0_vgpr1_vgpr2_vgpr3 = IMAGE_SAMPLE_D_V4_V9_nsa_gfx10 undef $vgpr3, undef $vgpr8, undef $vgpr7, undef $vgpr5, undef $vgpr4, undef $vgpr6, undef $vgpr0, undef $vgpr2, undef $vgpr2, undef $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7, undef $sgpr8_sgpr9_sgpr10_sgpr11, 15, 2, 0, 0, 0, 0, 0, 0, 0, 0, 0, implicit $exec
AMDGPU] gfx1010 hazard recognizer Differential Revision: https://reviews.llvm.org/D61536 llvm-svn: 359961
2019-05-04 12:30:57 +08:00
V_NOP_e32 implicit $exec
[AMDGPU] Extend buffer intrinsics with swizzling Summary: Extend cachepolicy operand in the new VMEM buffer intrinsics to supply information whether the buffer data is swizzled. Also, propagate this information to MIR. Intrinsics updated: int_amdgcn_raw_buffer_load int_amdgcn_raw_buffer_load_format int_amdgcn_raw_buffer_store int_amdgcn_raw_buffer_store_format int_amdgcn_raw_tbuffer_load int_amdgcn_raw_tbuffer_store int_amdgcn_struct_buffer_load int_amdgcn_struct_buffer_load_format int_amdgcn_struct_buffer_store int_amdgcn_struct_buffer_store_format int_amdgcn_struct_tbuffer_load int_amdgcn_struct_tbuffer_store Furthermore, disable merging of VMEM buffer instructions in SI Load/Store optimizer, if the "swizzled" bit on the instruction is on. The default value of the bit is 0, meaning that data in buffer is linear and buffer instructions can be merged. There is no difference in the generated code with this commit. However, in the future it will be expected that front-ends use buffer intrinsics with correct "swizzled" bit set. Reviewers: arsenm, nhaehnle, tpr Reviewed By: nhaehnle Subscribers: arsenm, kzhuravl, jvesely, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye, arphaman, jfb, Petar.Avramovic, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D68200 llvm-svn: 373491
2019-10-03 01:22:36 +08:00
$vgpr1 = BUFFER_LOAD_DWORD_OFFSET undef $sgpr0_sgpr1_sgpr2_sgpr3, undef $sgpr4, 6, 0, 0, 0, 0, 0, implicit $exec
AMDGPU] gfx1010 hazard recognizer Differential Revision: https://reviews.llvm.org/D61536 llvm-svn: 359961
2019-05-04 12:30:57 +08:00
...
# Non-NSA
# GCN-LABEL: name: no_hazard_image_sample_v4_v2_buf_off6
# GCN: IMAGE_SAMPLE
# GCN-NEXT: BUFFER_LOAD_DWORD_OFFSET
---
name: no_hazard_image_sample_v4_v2_buf_off6
body: |
bb.0:
[AMDGPU] Add a16 feature to gfx10 Based on D72931 This adds a new feature called A16 which is enabled for gfx10. gfx9 keeps the R128A16 feature so it can share all the instruction encodings with gfx7/8. Differential Revision: https://reviews.llvm.org/D73956
2020-01-29 17:04:36 +08:00
$vgpr0_vgpr1_vgpr2_vgpr3 = IMAGE_SAMPLE_V4_V2_gfx10 undef $vgpr1_vgpr2, undef $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7, undef $sgpr8_sgpr9_sgpr10_sgpr11, 15, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, implicit $exec
[AMDGPU] Extend buffer intrinsics with swizzling Summary: Extend cachepolicy operand in the new VMEM buffer intrinsics to supply information whether the buffer data is swizzled. Also, propagate this information to MIR. Intrinsics updated: int_amdgcn_raw_buffer_load int_amdgcn_raw_buffer_load_format int_amdgcn_raw_buffer_store int_amdgcn_raw_buffer_store_format int_amdgcn_raw_tbuffer_load int_amdgcn_raw_tbuffer_store int_amdgcn_struct_buffer_load int_amdgcn_struct_buffer_load_format int_amdgcn_struct_buffer_store int_amdgcn_struct_buffer_store_format int_amdgcn_struct_tbuffer_load int_amdgcn_struct_tbuffer_store Furthermore, disable merging of VMEM buffer instructions in SI Load/Store optimizer, if the "swizzled" bit on the instruction is on. The default value of the bit is 0, meaning that data in buffer is linear and buffer instructions can be merged. There is no difference in the generated code with this commit. However, in the future it will be expected that front-ends use buffer intrinsics with correct "swizzled" bit set. Reviewers: arsenm, nhaehnle, tpr Reviewed By: nhaehnle Subscribers: arsenm, kzhuravl, jvesely, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye, arphaman, jfb, Petar.Avramovic, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D68200 llvm-svn: 373491
2019-10-03 01:22:36 +08:00
$vgpr1 = BUFFER_LOAD_DWORD_OFFSET undef $sgpr0_sgpr1_sgpr2_sgpr3, undef $sgpr4, 6, 0, 0, 0, 0, 0, implicit $exec
AMDGPU] gfx1010 hazard recognizer Differential Revision: https://reviews.llvm.org/D61536 llvm-svn: 359961
2019-05-04 12:30:57 +08:00
...
# Less than 4 dwords
# GCN-LABEL: name: no_hazard_image_sample_v4_v3_buf_off6
# GCN: IMAGE_SAMPLE
# GCN-NEXT: BUFFER_LOAD_DWORD_OFFSET
---
name: no_hazard_image_sample_v4_v3_buf_off6
body: |
bb.0:
[AMDGPU] Add a16 feature to gfx10 Based on D72931 This adds a new feature called A16 which is enabled for gfx10. gfx9 keeps the R128A16 feature so it can share all the instruction encodings with gfx7/8. Differential Revision: https://reviews.llvm.org/D73956
2020-01-29 17:04:36 +08:00
$vgpr0_vgpr1_vgpr2_vgpr3 = IMAGE_SAMPLE_V4_V3_nsa_gfx10 undef $vgpr1, undef $vgpr2, undef $vgpr0, undef $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7, undef $sgpr8_sgpr9_sgpr10_sgpr11, 15, 2, 0, 0, 0, 0, 0, 0, 0, 0, 0, implicit $exec
[AMDGPU] Extend buffer intrinsics with swizzling Summary: Extend cachepolicy operand in the new VMEM buffer intrinsics to supply information whether the buffer data is swizzled. Also, propagate this information to MIR. Intrinsics updated: int_amdgcn_raw_buffer_load int_amdgcn_raw_buffer_load_format int_amdgcn_raw_buffer_store int_amdgcn_raw_buffer_store_format int_amdgcn_raw_tbuffer_load int_amdgcn_raw_tbuffer_store int_amdgcn_struct_buffer_load int_amdgcn_struct_buffer_load_format int_amdgcn_struct_buffer_store int_amdgcn_struct_buffer_store_format int_amdgcn_struct_tbuffer_load int_amdgcn_struct_tbuffer_store Furthermore, disable merging of VMEM buffer instructions in SI Load/Store optimizer, if the "swizzled" bit on the instruction is on. The default value of the bit is 0, meaning that data in buffer is linear and buffer instructions can be merged. There is no difference in the generated code with this commit. However, in the future it will be expected that front-ends use buffer intrinsics with correct "swizzled" bit set. Reviewers: arsenm, nhaehnle, tpr Reviewed By: nhaehnle Subscribers: arsenm, kzhuravl, jvesely, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye, arphaman, jfb, Petar.Avramovic, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D68200 llvm-svn: 373491
2019-10-03 01:22:36 +08:00
$vgpr1 = BUFFER_LOAD_DWORD_OFFSET undef $sgpr0_sgpr1_sgpr2_sgpr3, undef $sgpr4, 6, 0, 0, 0, 0, 0, implicit $exec
AMDGPU] gfx1010 hazard recognizer Differential Revision: https://reviews.llvm.org/D61536 llvm-svn: 359961
2019-05-04 12:30:57 +08:00
...