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/s_code_end.ll

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

50 lines
2.0 KiB
LLVM
Raw Normal View History

AMDGPU/GFX10: Don't generate s_code_end padding in the asm-printer Summary: The purpose of the padding is to guard against stale code being fetched into the instruction cache by the lowest level prefetching. We're generating relocatable ELF here, and so the padding should arguably be added by the linker. This is in fact what Mesa does. This also fixes multi-part shaders for Mesa. Change-Id: I6bfede58f20e9f337762ccf39ef9e0e263e69e82 Reviewers: arsenm, rampitec, t-tye Subscribers: kzhuravl, jvesely, wdng, yaxunl, dstuttard, tpr, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D63427 llvm-svn: 363602
2019-06-18 03:28:43 +08:00
; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1010 -asm-verbose=0 < %s | FileCheck -check-prefixes=GCN,GCN-ASM,GFX10END,GFX10END-ASM %s
; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1010 -filetype=obj < %s | llvm-objdump -arch=amdgcn -mcpu=gfx1010 -disassemble - | FileCheck -check-prefixes=GCN,GCN-OBJ,GFX10END,GFX10END-OBJ %s
; RUN: llc -mtriple=amdgcn-amd-amdpal -mcpu=gfx1010 -asm-verbose=0 < %s | FileCheck -check-prefixes=GCN,GCN-ASM,GFX10END,GFX10END-ASM %s
; RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=gfx1010 -asm-verbose=0 < %s | FileCheck -check-prefixes=GCN,GCN-ASM,GFX10NOEND,GFX10NOEND-ASM %s
; RUN: llc -mtriple=amdgcn-- -mcpu=gfx1010 -filetype=obj < %s | llvm-objdump -arch=amdgcn -mcpu=gfx1010 -disassemble - | FileCheck -check-prefixes=GCN,GCN-OBJ,GFX10NOEND,GFX10NOEND-OBJ %s
[AMDGPU] gfx1010 s_code_end generation Also add some missing metadata in the streamer. Differential Revision: https://reviews.llvm.org/D61531 llvm-svn: 359937
2019-05-04 05:26:39 +08:00
; GCN: a_kernel1:
AMDGPU/GFX10: Don't generate s_code_end padding in the asm-printer Summary: The purpose of the padding is to guard against stale code being fetched into the instruction cache by the lowest level prefetching. We're generating relocatable ELF here, and so the padding should arguably be added by the linker. This is in fact what Mesa does. This also fixes multi-part shaders for Mesa. Change-Id: I6bfede58f20e9f337762ccf39ef9e0e263e69e82 Reviewers: arsenm, rampitec, t-tye Subscribers: kzhuravl, jvesely, wdng, yaxunl, dstuttard, tpr, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D63427 llvm-svn: 363602
2019-06-18 03:28:43 +08:00
; GCN: s_endpgm
; GCN-ASM: [[END_LABEL1:\.Lfunc_end.*]]:
[AMDGPU] gfx1010 s_code_end generation Also add some missing metadata in the streamer. Differential Revision: https://reviews.llvm.org/D61531 llvm-svn: 359937
2019-05-04 05:26:39 +08:00
; GCN-ASM-NEXT: .size a_kernel1, [[END_LABEL1]]-a_kernel1
; GCN-OBJ-NEXT: s_nop 0
define amdgpu_kernel void @a_kernel1() {
ret void
}
; GCN: a_kernel2:
AMDGPU/GFX10: Don't generate s_code_end padding in the asm-printer Summary: The purpose of the padding is to guard against stale code being fetched into the instruction cache by the lowest level prefetching. We're generating relocatable ELF here, and so the padding should arguably be added by the linker. This is in fact what Mesa does. This also fixes multi-part shaders for Mesa. Change-Id: I6bfede58f20e9f337762ccf39ef9e0e263e69e82 Reviewers: arsenm, rampitec, t-tye Subscribers: kzhuravl, jvesely, wdng, yaxunl, dstuttard, tpr, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D63427 llvm-svn: 363602
2019-06-18 03:28:43 +08:00
; GCN: s_endpgm
; GCN-ASM: [[END_LABEL2:\.Lfunc_end.*]]:
[AMDGPU] gfx1010 s_code_end generation Also add some missing metadata in the streamer. Differential Revision: https://reviews.llvm.org/D61531 llvm-svn: 359937
2019-05-04 05:26:39 +08:00
; GCN-ASM-NEXT: .size a_kernel2, [[END_LABEL2]]-a_kernel2
AMDGPU/GFX10: Don't generate s_code_end padding in the asm-printer Summary: The purpose of the padding is to guard against stale code being fetched into the instruction cache by the lowest level prefetching. We're generating relocatable ELF here, and so the padding should arguably be added by the linker. This is in fact what Mesa does. This also fixes multi-part shaders for Mesa. Change-Id: I6bfede58f20e9f337762ccf39ef9e0e263e69e82 Reviewers: arsenm, rampitec, t-tye Subscribers: kzhuravl, jvesely, wdng, yaxunl, dstuttard, tpr, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D63427 llvm-svn: 363602
2019-06-18 03:28:43 +08:00
; GCN-OBJ: {{^$}}
[AMDGPU] gfx1010 s_code_end generation Also add some missing metadata in the streamer. Differential Revision: https://reviews.llvm.org/D61531 llvm-svn: 359937
2019-05-04 05:26:39 +08:00
define amdgpu_kernel void @a_kernel2() {
ret void
}
AMDGPU/GFX10: Don't generate s_code_end padding in the asm-printer Summary: The purpose of the padding is to guard against stale code being fetched into the instruction cache by the lowest level prefetching. We're generating relocatable ELF here, and so the padding should arguably be added by the linker. This is in fact what Mesa does. This also fixes multi-part shaders for Mesa. Change-Id: I6bfede58f20e9f337762ccf39ef9e0e263e69e82 Reviewers: arsenm, rampitec, t-tye Subscribers: kzhuravl, jvesely, wdng, yaxunl, dstuttard, tpr, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D63427 llvm-svn: 363602
2019-06-18 03:28:43 +08:00
; GCN-ASM: .globl a_function
[AMDGPU] gfx1010 s_code_end generation Also add some missing metadata in the streamer. Differential Revision: https://reviews.llvm.org/D61531 llvm-svn: 359937
2019-05-04 05:26:39 +08:00
; GCN-ASM-NEXT: .p2align 2
; GCN-ASM-NEXT: .type a_function,@function
; GCN-NEXT: a_function:
; GCN: s_setpc_b64
; GCN-ASM-NEXT: [[END_LABEL3:\.Lfunc_end.*]]:
; GCN-ASM-NEXT: .size a_function, [[END_LABEL3]]-a_function
AMDGPU/GFX10: Don't generate s_code_end padding in the asm-printer Summary: The purpose of the padding is to guard against stale code being fetched into the instruction cache by the lowest level prefetching. We're generating relocatable ELF here, and so the padding should arguably be added by the linker. This is in fact what Mesa does. This also fixes multi-part shaders for Mesa. Change-Id: I6bfede58f20e9f337762ccf39ef9e0e263e69e82 Reviewers: arsenm, rampitec, t-tye Subscribers: kzhuravl, jvesely, wdng, yaxunl, dstuttard, tpr, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D63427 llvm-svn: 363602
2019-06-18 03:28:43 +08:00
; GFX10END-ASM: .p2alignl 6, 3214868480
[AMDGPU] Increase kernel padding To support prefetch mode 3 we need to pad current cacheline and fill 3 cachelines after. Current padding is only sufficient for mode 2. Differential Revision: https://reviews.llvm.org/D65236 llvm-svn: 366938
2019-07-25 03:40:13 +08:00
; GFX10END-ASM-NEXT: .fill 48, 4, 3214868480
AMDGPU/GFX10: Don't generate s_code_end padding in the asm-printer Summary: The purpose of the padding is to guard against stale code being fetched into the instruction cache by the lowest level prefetching. We're generating relocatable ELF here, and so the padding should arguably be added by the linker. This is in fact what Mesa does. This also fixes multi-part shaders for Mesa. Change-Id: I6bfede58f20e9f337762ccf39ef9e0e263e69e82 Reviewers: arsenm, rampitec, t-tye Subscribers: kzhuravl, jvesely, wdng, yaxunl, dstuttard, tpr, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D63427 llvm-svn: 363602
2019-06-18 03:28:43 +08:00
; GFX10NOEND-NOT: .fill
[AMDGPU] gfx1010 s_code_end generation Also add some missing metadata in the streamer. Differential Revision: https://reviews.llvm.org/D61531 llvm-svn: 359937
2019-05-04 05:26:39 +08:00
AMDGPU/GFX10: Don't generate s_code_end padding in the asm-printer Summary: The purpose of the padding is to guard against stale code being fetched into the instruction cache by the lowest level prefetching. We're generating relocatable ELF here, and so the padding should arguably be added by the linker. This is in fact what Mesa does. This also fixes multi-part shaders for Mesa. Change-Id: I6bfede58f20e9f337762ccf39ef9e0e263e69e82 Reviewers: arsenm, rampitec, t-tye Subscribers: kzhuravl, jvesely, wdng, yaxunl, dstuttard, tpr, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D63427 llvm-svn: 363602
2019-06-18 03:28:43 +08:00
; GFX10NOEND-OBJ-NOT: s_code_end
; GFX10END-OBJ-NEXT: s_code_end
[AMDGPU] gfx1010 s_code_end generation Also add some missing metadata in the streamer. Differential Revision: https://reviews.llvm.org/D61531 llvm-svn: 359937
2019-05-04 05:26:39 +08:00
AMDGPU/GFX10: Don't generate s_code_end padding in the asm-printer Summary: The purpose of the padding is to guard against stale code being fetched into the instruction cache by the lowest level prefetching. We're generating relocatable ELF here, and so the padding should arguably be added by the linker. This is in fact what Mesa does. This also fixes multi-part shaders for Mesa. Change-Id: I6bfede58f20e9f337762ccf39ef9e0e263e69e82 Reviewers: arsenm, rampitec, t-tye Subscribers: kzhuravl, jvesely, wdng, yaxunl, dstuttard, tpr, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D63427 llvm-svn: 363602
2019-06-18 03:28:43 +08:00
; GFX10END-OBJ: s_code_end // 000000000140:
[AMDGPU] Increase kernel padding To support prefetch mode 3 we need to pad current cacheline and fill 3 cachelines after. Current padding is only sufficient for mode 2. Differential Revision: https://reviews.llvm.org/D65236 llvm-svn: 366938
2019-07-25 03:40:13 +08:00
; GFX10END-OBJ-COUNT-47: s_code_end
[AMDGPU] gfx1010 s_code_end generation Also add some missing metadata in the streamer. Differential Revision: https://reviews.llvm.org/D61531 llvm-svn: 359937
2019-05-04 05:26:39 +08:00
define void @a_function() {
ret void
}