Skip to content

[AMDGPU][SIPreEmitPeephole] pre-commit tests: mustRetainExeczBranch: use a cost model #109816

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Sep 25, 2024
Merged

[AMDGPU][SIPreEmitPeephole] pre-commit tests: mustRetainExeczBranch: use a cost model #109816

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
365 changes: 365 additions & 0 deletions llvm/test/CodeGen/AMDGPU/amdgpu-demote-scc-branches.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,365 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
; RUN: llc -mtriple=amdgcn -mcpu=gfx90a < %s | FileCheck -check-prefixes=GFX9 %s
; RUN: llc -mtriple=amdgcn -mcpu=gfx1010 < %s | FileCheck -check-prefixes=GFX10,GFX1010 %s
; RUN: llc -mtriple=amdgcn -mcpu=gfx1030 < %s | FileCheck -check-prefixes=GFX10,GFX1030 %s

define void @uniform_br_no_metadata(i32 noundef inreg %value, ptr addrspace(8) nocapture writeonly inreg %res, i32 noundef inreg %v_offset, i32 noundef inreg %0, i32 noundef inreg %flag) {
; GFX9-LABEL: uniform_br_no_metadata:
; GFX9: ; %bb.0: ; %entry
; GFX9-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX9-NEXT: s_cmp_lt_i32 s21, 1
; GFX9-NEXT: s_cbranch_scc1 .LBB0_2
; GFX9-NEXT: ; %bb.1: ; %if.then
; GFX9-NEXT: s_mov_b32 s11, s18
; GFX9-NEXT: s_mov_b32 s10, s17
; GFX9-NEXT: s_mov_b32 s9, s16
; GFX9-NEXT: s_mov_b32 s8, s7
; GFX9-NEXT: v_mov_b32_e32 v0, s6
; GFX9-NEXT: v_mov_b32_e32 v1, s19
; GFX9-NEXT: buffer_store_dword v0, v1, s[8:11], 0 offen
; GFX9-NEXT: .LBB0_2: ; %if.end
; GFX9-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX9-NEXT: s_setpc_b64 s[30:31]
;
; GFX10-LABEL: uniform_br_no_metadata:
; GFX10: ; %bb.0: ; %entry
; GFX10-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX10-NEXT: s_cmp_lt_i32 s21, 1
; GFX10-NEXT: s_cbranch_scc1 .LBB0_2
; GFX10-NEXT: ; %bb.1: ; %if.then
; GFX10-NEXT: v_mov_b32_e32 v0, s6
; GFX10-NEXT: v_mov_b32_e32 v1, s19
; GFX10-NEXT: s_mov_b32 s11, s18
; GFX10-NEXT: s_mov_b32 s10, s17
; GFX10-NEXT: s_mov_b32 s9, s16
; GFX10-NEXT: s_mov_b32 s8, s7
; GFX10-NEXT: buffer_store_dword v0, v1, s[8:11], 0 offen
; GFX10-NEXT: .LBB0_2: ; %if.end
; GFX10-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX10-NEXT: s_setpc_b64 s[30:31]
entry:
%cmp = icmp sgt i32 %flag, 0
br i1 %cmp, label %if.then, label %if.end

if.then:
tail call void @llvm.amdgcn.raw.ptr.buffer.store.i32(i32 %value, ptr addrspace(8) %res, i32 %v_offset, i32 0, i32 0)
br label %if.end

if.end:
call void @llvm.amdgcn.s.waitcnt(i32 0)
ret void
}

define void @uniform_br_unprofitable(i32 noundef inreg %value, ptr addrspace(8) nocapture writeonly inreg %res, i32 noundef inreg %v_offset, i32 noundef inreg %0, i32 noundef inreg %flag) {
; GFX9-LABEL: uniform_br_unprofitable:
; GFX9: ; %bb.0: ; %entry
; GFX9-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX9-NEXT: s_cmp_lt_i32 s21, 1
; GFX9-NEXT: s_cbranch_scc1 .LBB1_2
; GFX9-NEXT: ; %bb.1: ; %if.then
; GFX9-NEXT: s_mov_b32 s11, s18
; GFX9-NEXT: s_mov_b32 s10, s17
; GFX9-NEXT: s_mov_b32 s9, s16
; GFX9-NEXT: s_mov_b32 s8, s7
; GFX9-NEXT: v_mov_b32_e32 v0, s6
; GFX9-NEXT: v_mov_b32_e32 v1, s19
; GFX9-NEXT: buffer_store_dword v0, v1, s[8:11], 0 offen
; GFX9-NEXT: .LBB1_2: ; %if.end
; GFX9-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX9-NEXT: s_setpc_b64 s[30:31]
;
; GFX10-LABEL: uniform_br_unprofitable:
; GFX10: ; %bb.0: ; %entry
; GFX10-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX10-NEXT: s_cmp_lt_i32 s21, 1
; GFX10-NEXT: s_cbranch_scc1 .LBB1_2
; GFX10-NEXT: ; %bb.1: ; %if.then
; GFX10-NEXT: v_mov_b32_e32 v0, s6
; GFX10-NEXT: v_mov_b32_e32 v1, s19
; GFX10-NEXT: s_mov_b32 s11, s18
; GFX10-NEXT: s_mov_b32 s10, s17
; GFX10-NEXT: s_mov_b32 s9, s16
; GFX10-NEXT: s_mov_b32 s8, s7
; GFX10-NEXT: buffer_store_dword v0, v1, s[8:11], 0 offen
; GFX10-NEXT: .LBB1_2: ; %if.end
; GFX10-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX10-NEXT: s_setpc_b64 s[30:31]
entry:
%cmp = icmp sgt i32 %flag, 0
br i1 %cmp, label %if.then, label %if.end, !prof !0

if.then:
tail call void @llvm.amdgcn.raw.ptr.buffer.store.i32(i32 %value, ptr addrspace(8) %res, i32 %v_offset, i32 0, i32 0)
br label %if.end

if.end:
call void @llvm.amdgcn.s.waitcnt(i32 0)
ret void
}

define void @uniform_br_profitable(i32 noundef inreg %value, ptr addrspace(8) nocapture writeonly inreg %res, i32 noundef inreg %v_offset, i32 noundef inreg %0, i32 noundef inreg %flag) {
; GFX9-LABEL: uniform_br_profitable:
; GFX9: ; %bb.0: ; %entry
; GFX9-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX9-NEXT: s_cmp_lt_i32 s21, 1
; GFX9-NEXT: s_cbranch_scc1 .LBB2_2
; GFX9-NEXT: ; %bb.1: ; %if.then
; GFX9-NEXT: s_mov_b32 s11, s18
; GFX9-NEXT: s_mov_b32 s10, s17
; GFX9-NEXT: s_mov_b32 s9, s16
; GFX9-NEXT: s_mov_b32 s8, s7
; GFX9-NEXT: v_mov_b32_e32 v0, s6
; GFX9-NEXT: v_mov_b32_e32 v1, s19
; GFX9-NEXT: buffer_store_dword v0, v1, s[8:11], 0 offen
; GFX9-NEXT: .LBB2_2: ; %if.end
; GFX9-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX9-NEXT: s_setpc_b64 s[30:31]
;
; GFX10-LABEL: uniform_br_profitable:
; GFX10: ; %bb.0: ; %entry
; GFX10-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX10-NEXT: s_cmp_lt_i32 s21, 1
; GFX10-NEXT: s_cbranch_scc1 .LBB2_2
; GFX10-NEXT: ; %bb.1: ; %if.then
; GFX10-NEXT: v_mov_b32_e32 v0, s6
; GFX10-NEXT: v_mov_b32_e32 v1, s19
; GFX10-NEXT: s_mov_b32 s11, s18
; GFX10-NEXT: s_mov_b32 s10, s17
; GFX10-NEXT: s_mov_b32 s9, s16
; GFX10-NEXT: s_mov_b32 s8, s7
; GFX10-NEXT: buffer_store_dword v0, v1, s[8:11], 0 offen
; GFX10-NEXT: .LBB2_2: ; %if.end
; GFX10-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX10-NEXT: s_setpc_b64 s[30:31]
entry:
%cmp = icmp sgt i32 %flag, 0
br i1 %cmp, label %if.then, label %if.end, !prof !1

if.then:
tail call void @llvm.amdgcn.raw.ptr.buffer.store.i32(i32 %value, ptr addrspace(8) %res, i32 %v_offset, i32 0, i32 0)
br label %if.end

if.end:
call void @llvm.amdgcn.s.waitcnt(i32 0)
ret void
}

define void @divergent_br_no_metadata(i32 noundef inreg %value, ptr addrspace(8) nocapture writeonly inreg %res, i32 noundef inreg %v_offset, i32 noundef inreg %0, i32 noundef %flag) {
; GFX9-LABEL: divergent_br_no_metadata:
; GFX9: ; %bb.0: ; %entry
; GFX9-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX9-NEXT: v_cmp_lt_i32_e32 vcc, 0, v0
; GFX9-NEXT: s_and_saveexec_b64 s[4:5], vcc
; GFX9-NEXT: s_cbranch_execz .LBB3_2
; GFX9-NEXT: ; %bb.1: ; %if.then
; GFX9-NEXT: s_mov_b32 s11, s18
; GFX9-NEXT: s_mov_b32 s10, s17
; GFX9-NEXT: s_mov_b32 s9, s16
; GFX9-NEXT: s_mov_b32 s8, s7
; GFX9-NEXT: v_mov_b32_e32 v0, s6
; GFX9-NEXT: v_mov_b32_e32 v1, s19
; GFX9-NEXT: buffer_store_dword v0, v1, s[8:11], 0 offen
; GFX9-NEXT: .LBB3_2: ; %if.end
; GFX9-NEXT: s_or_b64 exec, exec, s[4:5]
; GFX9-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX9-NEXT: s_setpc_b64 s[30:31]
;
; GFX1010-LABEL: divergent_br_no_metadata:
; GFX1010: ; %bb.0: ; %entry
; GFX1010-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX1010-NEXT: v_cmp_lt_i32_e32 vcc_lo, 0, v0
; GFX1010-NEXT: s_and_saveexec_b32 s4, vcc_lo
; GFX1010-NEXT: s_cbranch_execz .LBB3_2
; GFX1010-NEXT: ; %bb.1: ; %if.then
; GFX1010-NEXT: v_mov_b32_e32 v0, s6
; GFX1010-NEXT: v_mov_b32_e32 v1, s19
; GFX1010-NEXT: s_mov_b32 s11, s18
; GFX1010-NEXT: s_mov_b32 s10, s17
; GFX1010-NEXT: s_mov_b32 s9, s16
; GFX1010-NEXT: s_mov_b32 s8, s7
; GFX1010-NEXT: buffer_store_dword v0, v1, s[8:11], 0 offen
; GFX1010-NEXT: .LBB3_2: ; %if.end
; GFX1010-NEXT: s_waitcnt_depctr 0xffe3
; GFX1010-NEXT: s_or_b32 exec_lo, exec_lo, s4
; GFX1010-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX1010-NEXT: s_setpc_b64 s[30:31]
;
; GFX1030-LABEL: divergent_br_no_metadata:
; GFX1030: ; %bb.0: ; %entry
; GFX1030-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX1030-NEXT: s_mov_b32 s4, exec_lo
; GFX1030-NEXT: v_cmpx_lt_i32_e32 0, v0
; GFX1030-NEXT: s_cbranch_execz .LBB3_2
; GFX1030-NEXT: ; %bb.1: ; %if.then
; GFX1030-NEXT: v_mov_b32_e32 v0, s6
; GFX1030-NEXT: v_mov_b32_e32 v1, s19
; GFX1030-NEXT: s_mov_b32 s11, s18
; GFX1030-NEXT: s_mov_b32 s10, s17
; GFX1030-NEXT: s_mov_b32 s9, s16
; GFX1030-NEXT: s_mov_b32 s8, s7
; GFX1030-NEXT: buffer_store_dword v0, v1, s[8:11], 0 offen
; GFX1030-NEXT: .LBB3_2: ; %if.end
; GFX1030-NEXT: s_or_b32 exec_lo, exec_lo, s4
; GFX1030-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX1030-NEXT: s_setpc_b64 s[30:31]
entry:
%cmp = icmp sgt i32 %flag, 0
br i1 %cmp, label %if.then, label %if.end

if.then:
tail call void @llvm.amdgcn.raw.ptr.buffer.store.i32(i32 %value, ptr addrspace(8) %res, i32 %v_offset, i32 0, i32 0)
br label %if.end

if.end:
call void @llvm.amdgcn.s.waitcnt(i32 0)
ret void
}

define void @divergent_br_unprofitable(i32 noundef inreg %value, ptr addrspace(8) nocapture writeonly inreg %res, i32 noundef inreg %v_offset, i32 noundef inreg %0, i32 noundef %flag) {
; GFX9-LABEL: divergent_br_unprofitable:
; GFX9: ; %bb.0: ; %entry
; GFX9-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX9-NEXT: v_cmp_lt_i32_e32 vcc, 0, v0
; GFX9-NEXT: s_and_saveexec_b64 s[4:5], vcc
; GFX9-NEXT: s_cbranch_execz .LBB4_2
; GFX9-NEXT: ; %bb.1: ; %if.then
; GFX9-NEXT: s_mov_b32 s11, s18
; GFX9-NEXT: s_mov_b32 s10, s17
; GFX9-NEXT: s_mov_b32 s9, s16
; GFX9-NEXT: s_mov_b32 s8, s7
; GFX9-NEXT: v_mov_b32_e32 v0, s6
; GFX9-NEXT: v_mov_b32_e32 v1, s19
; GFX9-NEXT: buffer_store_dword v0, v1, s[8:11], 0 offen
; GFX9-NEXT: .LBB4_2: ; %if.end
; GFX9-NEXT: s_or_b64 exec, exec, s[4:5]
; GFX9-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX9-NEXT: s_setpc_b64 s[30:31]
;
; GFX1010-LABEL: divergent_br_unprofitable:
; GFX1010: ; %bb.0: ; %entry
; GFX1010-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX1010-NEXT: v_cmp_lt_i32_e32 vcc_lo, 0, v0
; GFX1010-NEXT: s_and_saveexec_b32 s4, vcc_lo
; GFX1010-NEXT: s_cbranch_execz .LBB4_2
; GFX1010-NEXT: ; %bb.1: ; %if.then
; GFX1010-NEXT: v_mov_b32_e32 v0, s6
; GFX1010-NEXT: v_mov_b32_e32 v1, s19
; GFX1010-NEXT: s_mov_b32 s11, s18
; GFX1010-NEXT: s_mov_b32 s10, s17
; GFX1010-NEXT: s_mov_b32 s9, s16
; GFX1010-NEXT: s_mov_b32 s8, s7
; GFX1010-NEXT: buffer_store_dword v0, v1, s[8:11], 0 offen
; GFX1010-NEXT: .LBB4_2: ; %if.end
; GFX1010-NEXT: s_waitcnt_depctr 0xffe3
; GFX1010-NEXT: s_or_b32 exec_lo, exec_lo, s4
; GFX1010-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX1010-NEXT: s_setpc_b64 s[30:31]
;
; GFX1030-LABEL: divergent_br_unprofitable:
; GFX1030: ; %bb.0: ; %entry
; GFX1030-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX1030-NEXT: s_mov_b32 s4, exec_lo
; GFX1030-NEXT: v_cmpx_lt_i32_e32 0, v0
; GFX1030-NEXT: s_cbranch_execz .LBB4_2
; GFX1030-NEXT: ; %bb.1: ; %if.then
; GFX1030-NEXT: v_mov_b32_e32 v0, s6
; GFX1030-NEXT: v_mov_b32_e32 v1, s19
; GFX1030-NEXT: s_mov_b32 s11, s18
; GFX1030-NEXT: s_mov_b32 s10, s17
; GFX1030-NEXT: s_mov_b32 s9, s16
; GFX1030-NEXT: s_mov_b32 s8, s7
; GFX1030-NEXT: buffer_store_dword v0, v1, s[8:11], 0 offen
; GFX1030-NEXT: .LBB4_2: ; %if.end
; GFX1030-NEXT: s_or_b32 exec_lo, exec_lo, s4
; GFX1030-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX1030-NEXT: s_setpc_b64 s[30:31]
entry:
%cmp = icmp sgt i32 %flag, 0
br i1 %cmp, label %if.then, label %if.end, !prof !0

if.then:
tail call void @llvm.amdgcn.raw.ptr.buffer.store.i32(i32 %value, ptr addrspace(8) %res, i32 %v_offset, i32 0, i32 0)
br label %if.end

if.end:
call void @llvm.amdgcn.s.waitcnt(i32 0)
ret void
}

define void @divergent_br_profitable(i32 noundef inreg %value, ptr addrspace(8) nocapture writeonly inreg %res, i32 noundef inreg %v_offset, i32 noundef inreg %0, i32 noundef %flag) {
; GFX9-LABEL: divergent_br_profitable:
; GFX9: ; %bb.0: ; %entry
; GFX9-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX9-NEXT: v_cmp_lt_i32_e32 vcc, 0, v0
; GFX9-NEXT: s_and_saveexec_b64 s[4:5], vcc
; GFX9-NEXT: s_cbranch_execz .LBB5_2
; GFX9-NEXT: ; %bb.1: ; %if.then
; GFX9-NEXT: s_mov_b32 s11, s18
; GFX9-NEXT: s_mov_b32 s10, s17
; GFX9-NEXT: s_mov_b32 s9, s16
; GFX9-NEXT: s_mov_b32 s8, s7
; GFX9-NEXT: v_mov_b32_e32 v0, s6
; GFX9-NEXT: v_mov_b32_e32 v1, s19
; GFX9-NEXT: buffer_store_dword v0, v1, s[8:11], 0 offen
; GFX9-NEXT: .LBB5_2: ; %if.end
; GFX9-NEXT: s_or_b64 exec, exec, s[4:5]
; GFX9-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX9-NEXT: s_setpc_b64 s[30:31]
;
; GFX1010-LABEL: divergent_br_profitable:
; GFX1010: ; %bb.0: ; %entry
; GFX1010-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX1010-NEXT: v_cmp_lt_i32_e32 vcc_lo, 0, v0
; GFX1010-NEXT: s_and_saveexec_b32 s4, vcc_lo
; GFX1010-NEXT: s_cbranch_execz .LBB5_2
; GFX1010-NEXT: ; %bb.1: ; %if.then
; GFX1010-NEXT: v_mov_b32_e32 v0, s6
; GFX1010-NEXT: v_mov_b32_e32 v1, s19
; GFX1010-NEXT: s_mov_b32 s11, s18
; GFX1010-NEXT: s_mov_b32 s10, s17
; GFX1010-NEXT: s_mov_b32 s9, s16
; GFX1010-NEXT: s_mov_b32 s8, s7
; GFX1010-NEXT: buffer_store_dword v0, v1, s[8:11], 0 offen
; GFX1010-NEXT: .LBB5_2: ; %if.end
; GFX1010-NEXT: s_waitcnt_depctr 0xffe3
; GFX1010-NEXT: s_or_b32 exec_lo, exec_lo, s4
; GFX1010-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX1010-NEXT: s_setpc_b64 s[30:31]
;
; GFX1030-LABEL: divergent_br_profitable:
; GFX1030: ; %bb.0: ; %entry
; GFX1030-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX1030-NEXT: s_mov_b32 s4, exec_lo
; GFX1030-NEXT: v_cmpx_lt_i32_e32 0, v0
; GFX1030-NEXT: s_cbranch_execz .LBB5_2
; GFX1030-NEXT: ; %bb.1: ; %if.then
; GFX1030-NEXT: v_mov_b32_e32 v0, s6
; GFX1030-NEXT: v_mov_b32_e32 v1, s19
; GFX1030-NEXT: s_mov_b32 s11, s18
; GFX1030-NEXT: s_mov_b32 s10, s17
; GFX1030-NEXT: s_mov_b32 s9, s16
; GFX1030-NEXT: s_mov_b32 s8, s7
; GFX1030-NEXT: buffer_store_dword v0, v1, s[8:11], 0 offen
; GFX1030-NEXT: .LBB5_2: ; %if.end
; GFX1030-NEXT: s_or_b32 exec_lo, exec_lo, s4
; GFX1030-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GFX1030-NEXT: s_setpc_b64 s[30:31]
entry:
%cmp = icmp sgt i32 %flag, 0
br i1 %cmp, label %if.then, label %if.end, !prof !1

if.then:
tail call void @llvm.amdgcn.raw.ptr.buffer.store.i32(i32 %value, ptr addrspace(8) %res, i32 %v_offset, i32 0, i32 0)
br label %if.end

if.end:
call void @llvm.amdgcn.s.waitcnt(i32 0)
ret void
}

declare void @llvm.amdgcn.raw.ptr.buffer.store.i32(i32, ptr addrspace(8) nocapture writeonly, i32, i32, i32 immarg)
declare void @llvm.amdgcn.s.waitcnt(i32)
declare i32 @llvm.amdgcn.workitem.id.x()

!0 = !{!"branch_weights", i32 1000, i32 1000}
!1 = !{!"branch_weights", i32 2000, i32 1}
Loading