llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT--> @llvm/pr-subscribers-backend-amdgpu Author: Pierre van Houtryve (Pierre-vh) <details> <summary>Changes</summary> --- Patch is 4.65 MiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/154709.diff 5 Files Affected: - (added) llvm/test/CodeGen/AMDGPU/memory-legalizer-private-agent.ll (+20976) - (added) llvm/test/CodeGen/AMDGPU/memory-legalizer-private-singlethread.ll (+21253) - (added) llvm/test/CodeGen/AMDGPU/memory-legalizer-private-system.ll (+19992) - (added) llvm/test/CodeGen/AMDGPU/memory-legalizer-private-wavefront.ll (+21253) - (added) llvm/test/CodeGen/AMDGPU/memory-legalizer-private-workgroup.ll (+21253) ``````````diff diff --git a/llvm/test/CodeGen/AMDGPU/memory-legalizer-private-agent.ll b/llvm/test/CodeGen/AMDGPU/memory-legalizer-private-agent.ll new file mode 100644 index 0000000000000..af5b529fc387e --- /dev/null +++ b/llvm/test/CodeGen/AMDGPU/memory-legalizer-private-agent.ll @@ -0,0 +1,20976 @@ +; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py +; RUN: llc -mtriple=amdgcn-amd-amdhsa -O0 -mcpu=gfx600 < %s | FileCheck --check-prefixes=GFX6 %s +; RUN: llc -mtriple=amdgcn-amd-amdhsa -O0 -mcpu=gfx700 < %s | FileCheck --check-prefixes=GFX7 %s +; RUN: llc -mtriple=amdgcn-amd-amdhsa -O0 -mcpu=gfx1010 < %s | FileCheck --check-prefixes=GFX10-WGP %s +; RUN: llc -mtriple=amdgcn-amd-amdhsa -O0 -mcpu=gfx1010 -mattr=+cumode < %s | FileCheck --check-prefixes=GFX10-CU %s +; RUN: llc -mtriple=amdgcn-amd-amdpal -O0 -mcpu=gfx700 -amdgcn-skip-cache-invalidations < %s | FileCheck --check-prefixes=SKIP-CACHE-INV %s +; RUN: llc -mtriple=amdgcn-amd-amdhsa -O0 -mcpu=gfx90a < %s | FileCheck -check-prefixes=GFX90A-NOTTGSPLIT %s +; RUN: llc -mtriple=amdgcn-amd-amdhsa -O0 -mcpu=gfx90a -mattr=+tgsplit < %s | FileCheck -check-prefixes=GFX90A-TGSPLIT %s +; RUN: llc -mtriple=amdgcn-amd-amdhsa -O0 -mcpu=gfx942 < %s | FileCheck -check-prefixes=GFX942-NOTTGSPLIT %s +; RUN: llc -mtriple=amdgcn-amd-amdhsa -O0 -mcpu=gfx942 -mattr=+tgsplit < %s | FileCheck -check-prefixes=GFX942-TGSPLIT %s +; RUN: llc -mtriple=amdgcn-amd-amdhsa -O0 -mcpu=gfx1100 < %s | FileCheck --check-prefixes=GFX11-WGP %s +; RUN: llc -mtriple=amdgcn-amd-amdhsa -O0 -mcpu=gfx1100 -mattr=+cumode < %s | FileCheck --check-prefixes=GFX11-CU %s +; RUN: llc -mtriple=amdgcn-amd-amdhsa -O0 -mcpu=gfx1200 < %s | FileCheck --check-prefixes=GFX12-WGP %s +; RUN: llc -mtriple=amdgcn-amd-amdhsa -O0 -mcpu=gfx1200 -mattr=+cumode < %s | FileCheck --check-prefixes=GFX12-CU %s +; RUN: llc -mtriple=amdgcn-amd-amdhsa -O0 -mcpu=gfx1250 < %s | FileCheck --check-prefixes=GFX1250 %s + +define amdgpu_kernel void @private_agent_unordered_load( +; GFX6-LABEL: private_agent_unordered_load: +; GFX6: ; %bb.0: ; %entry +; GFX6-NEXT: s_add_u32 s0, s0, s15 +; GFX6-NEXT: s_addc_u32 s1, s1, 0 +; GFX6-NEXT: s_load_dword s5, s[8:9], 0x0 +; GFX6-NEXT: s_load_dword s4, s[8:9], 0x1 +; GFX6-NEXT: s_waitcnt lgkmcnt(0) +; GFX6-NEXT: v_mov_b32_e32 v0, s5 +; GFX6-NEXT: buffer_load_dword v0, v0, s[0:3], 0 offen +; GFX6-NEXT: v_mov_b32_e32 v1, s4 +; GFX6-NEXT: s_waitcnt vmcnt(0) +; GFX6-NEXT: buffer_store_dword v0, v1, s[0:3], 0 offen +; GFX6-NEXT: s_endpgm +; +; GFX7-LABEL: private_agent_unordered_load: +; GFX7: ; %bb.0: ; %entry +; GFX7-NEXT: s_add_u32 s0, s0, s17 +; GFX7-NEXT: s_addc_u32 s1, s1, 0 +; GFX7-NEXT: s_load_dword s5, s[8:9], 0x0 +; GFX7-NEXT: s_load_dword s4, s[8:9], 0x1 +; GFX7-NEXT: s_waitcnt lgkmcnt(0) +; GFX7-NEXT: v_mov_b32_e32 v0, s5 +; GFX7-NEXT: buffer_load_dword v0, v0, s[0:3], 0 offen +; GFX7-NEXT: v_mov_b32_e32 v1, s4 +; GFX7-NEXT: s_waitcnt vmcnt(0) +; GFX7-NEXT: buffer_store_dword v0, v1, s[0:3], 0 offen +; GFX7-NEXT: s_endpgm +; +; GFX10-WGP-LABEL: private_agent_unordered_load: +; GFX10-WGP: ; %bb.0: ; %entry +; GFX10-WGP-NEXT: s_add_u32 s0, s0, s17 +; GFX10-WGP-NEXT: s_addc_u32 s1, s1, 0 +; GFX10-WGP-NEXT: s_load_dword s5, s[8:9], 0x0 +; GFX10-WGP-NEXT: s_load_dword s4, s[8:9], 0x4 +; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0) +; GFX10-WGP-NEXT: v_mov_b32_e32 v0, s5 +; GFX10-WGP-NEXT: buffer_load_dword v0, v0, s[0:3], 0 offen +; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s4 +; GFX10-WGP-NEXT: s_waitcnt vmcnt(0) +; GFX10-WGP-NEXT: buffer_store_dword v0, v1, s[0:3], 0 offen +; GFX10-WGP-NEXT: s_endpgm +; +; GFX10-CU-LABEL: private_agent_unordered_load: +; GFX10-CU: ; %bb.0: ; %entry +; GFX10-CU-NEXT: s_add_u32 s0, s0, s17 +; GFX10-CU-NEXT: s_addc_u32 s1, s1, 0 +; GFX10-CU-NEXT: s_load_dword s5, s[8:9], 0x0 +; GFX10-CU-NEXT: s_load_dword s4, s[8:9], 0x4 +; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0) +; GFX10-CU-NEXT: v_mov_b32_e32 v0, s5 +; GFX10-CU-NEXT: buffer_load_dword v0, v0, s[0:3], 0 offen +; GFX10-CU-NEXT: v_mov_b32_e32 v1, s4 +; GFX10-CU-NEXT: s_waitcnt vmcnt(0) +; GFX10-CU-NEXT: buffer_store_dword v0, v1, s[0:3], 0 offen +; GFX10-CU-NEXT: s_endpgm +; +; SKIP-CACHE-INV-LABEL: private_agent_unordered_load: +; SKIP-CACHE-INV: ; %bb.0: ; %entry +; SKIP-CACHE-INV-NEXT: s_getpc_b64 s[12:13] +; SKIP-CACHE-INV-NEXT: s_mov_b32 s12, s0 +; SKIP-CACHE-INV-NEXT: s_load_dwordx4 s[12:15], s[12:13], 0x0 +; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0) +; SKIP-CACHE-INV-NEXT: s_add_u32 s12, s12, s11 +; SKIP-CACHE-INV-NEXT: s_addc_u32 s13, s13, 0 +; SKIP-CACHE-INV-NEXT: s_load_dword s1, s[4:5], 0x0 +; SKIP-CACHE-INV-NEXT: s_load_dword s0, s[4:5], 0x1 +; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0) +; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s1 +; SKIP-CACHE-INV-NEXT: buffer_load_dword v0, v0, s[12:15], 0 offen +; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v1, s0 +; SKIP-CACHE-INV-NEXT: s_waitcnt vmcnt(0) +; SKIP-CACHE-INV-NEXT: buffer_store_dword v0, v1, s[12:15], 0 offen +; SKIP-CACHE-INV-NEXT: s_endpgm +; +; GFX90A-NOTTGSPLIT-LABEL: private_agent_unordered_load: +; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry +; GFX90A-NOTTGSPLIT-NEXT: s_add_u32 s0, s0, s17 +; GFX90A-NOTTGSPLIT-NEXT: s_addc_u32 s1, s1, 0 +; GFX90A-NOTTGSPLIT-NEXT: s_load_dword s5, s[8:9], 0x0 +; GFX90A-NOTTGSPLIT-NEXT: s_load_dword s4, s[8:9], 0x4 +; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0) +; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v0, s5 +; GFX90A-NOTTGSPLIT-NEXT: buffer_load_dword v0, v0, s[0:3], 0 offen +; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v1, s4 +; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0) +; GFX90A-NOTTGSPLIT-NEXT: buffer_store_dword v0, v1, s[0:3], 0 offen +; GFX90A-NOTTGSPLIT-NEXT: s_endpgm +; +; GFX90A-TGSPLIT-LABEL: private_agent_unordered_load: +; GFX90A-TGSPLIT: ; %bb.0: ; %entry +; GFX90A-TGSPLIT-NEXT: s_add_u32 s0, s0, s17 +; GFX90A-TGSPLIT-NEXT: s_addc_u32 s1, s1, 0 +; GFX90A-TGSPLIT-NEXT: s_load_dword s5, s[8:9], 0x0 +; GFX90A-TGSPLIT-NEXT: s_load_dword s4, s[8:9], 0x4 +; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0) +; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v0, s5 +; GFX90A-TGSPLIT-NEXT: buffer_load_dword v0, v0, s[0:3], 0 offen +; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v1, s4 +; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0) +; GFX90A-TGSPLIT-NEXT: buffer_store_dword v0, v1, s[0:3], 0 offen +; GFX90A-TGSPLIT-NEXT: s_endpgm +; +; GFX942-NOTTGSPLIT-LABEL: private_agent_unordered_load: +; GFX942-NOTTGSPLIT: ; %bb.0: ; %entry +; GFX942-NOTTGSPLIT-NEXT: s_load_dword s1, s[4:5], 0x0 +; GFX942-NOTTGSPLIT-NEXT: s_load_dword s0, s[4:5], 0x4 +; GFX942-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0) +; GFX942-NOTTGSPLIT-NEXT: scratch_load_dword v0, off, s1 +; GFX942-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0) +; GFX942-NOTTGSPLIT-NEXT: scratch_store_dword off, v0, s0 +; GFX942-NOTTGSPLIT-NEXT: s_endpgm +; +; GFX942-TGSPLIT-LABEL: private_agent_unordered_load: +; GFX942-TGSPLIT: ; %bb.0: ; %entry +; GFX942-TGSPLIT-NEXT: s_load_dword s1, s[4:5], 0x0 +; GFX942-TGSPLIT-NEXT: s_load_dword s0, s[4:5], 0x4 +; GFX942-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0) +; GFX942-TGSPLIT-NEXT: scratch_load_dword v0, off, s1 +; GFX942-TGSPLIT-NEXT: s_waitcnt vmcnt(0) +; GFX942-TGSPLIT-NEXT: scratch_store_dword off, v0, s0 +; GFX942-TGSPLIT-NEXT: s_endpgm +; +; GFX11-WGP-LABEL: private_agent_unordered_load: +; GFX11-WGP: ; %bb.0: ; %entry +; GFX11-WGP-NEXT: s_load_b32 s1, s[4:5], 0x0 +; GFX11-WGP-NEXT: s_load_b32 s0, s[4:5], 0x4 +; GFX11-WGP-NEXT: s_waitcnt lgkmcnt(0) +; GFX11-WGP-NEXT: scratch_load_b32 v0, off, s1 +; GFX11-WGP-NEXT: s_waitcnt vmcnt(0) +; GFX11-WGP-NEXT: scratch_store_b32 off, v0, s0 +; GFX11-WGP-NEXT: s_endpgm +; +; GFX11-CU-LABEL: private_agent_unordered_load: +; GFX11-CU: ; %bb.0: ; %entry +; GFX11-CU-NEXT: s_load_b32 s1, s[4:5], 0x0 +; GFX11-CU-NEXT: s_load_b32 s0, s[4:5], 0x4 +; GFX11-CU-NEXT: s_waitcnt lgkmcnt(0) +; GFX11-CU-NEXT: scratch_load_b32 v0, off, s1 +; GFX11-CU-NEXT: s_waitcnt vmcnt(0) +; GFX11-CU-NEXT: scratch_store_b32 off, v0, s0 +; GFX11-CU-NEXT: s_endpgm +; +; GFX12-WGP-LABEL: private_agent_unordered_load: +; GFX12-WGP: ; %bb.0: ; %entry +; GFX12-WGP-NEXT: s_load_b32 s1, s[4:5], 0x0 +; GFX12-WGP-NEXT: s_load_b32 s0, s[4:5], 0x4 +; GFX12-WGP-NEXT: s_wait_kmcnt 0x0 +; GFX12-WGP-NEXT: scratch_load_b32 v0, off, s1 +; GFX12-WGP-NEXT: s_wait_loadcnt 0x0 +; GFX12-WGP-NEXT: scratch_store_b32 off, v0, s0 +; GFX12-WGP-NEXT: s_endpgm +; +; GFX12-CU-LABEL: private_agent_unordered_load: +; GFX12-CU: ; %bb.0: ; %entry +; GFX12-CU-NEXT: s_load_b32 s1, s[4:5], 0x0 +; GFX12-CU-NEXT: s_load_b32 s0, s[4:5], 0x4 +; GFX12-CU-NEXT: s_wait_kmcnt 0x0 +; GFX12-CU-NEXT: scratch_load_b32 v0, off, s1 +; GFX12-CU-NEXT: s_wait_loadcnt 0x0 +; GFX12-CU-NEXT: scratch_store_b32 off, v0, s0 +; GFX12-CU-NEXT: s_endpgm +; +; GFX1250-LABEL: private_agent_unordered_load: +; GFX1250: ; %bb.0: ; %entry +; GFX1250-NEXT: s_load_b32 s1, s[4:5], 0x0 +; GFX1250-NEXT: s_load_b32 s0, s[4:5], 0x4 +; GFX1250-NEXT: s_wait_kmcnt 0x0 +; GFX1250-NEXT: scratch_load_b32 v0, off, s1 +; GFX1250-NEXT: s_wait_loadcnt 0x0 +; GFX1250-NEXT: scratch_store_b32 off, v0, s0 scope:SCOPE_SE +; GFX1250-NEXT: s_endpgm + ptr addrspace(5) %in, ptr addrspace(5) %out) { +entry: + %val = load atomic i32, ptr addrspace(5) %in syncscope("agent") unordered, align 4 + store i32 %val, ptr addrspace(5) %out + ret void +} + +define amdgpu_kernel void @private_agent_monotonic_load( +; GFX6-LABEL: private_agent_monotonic_load: +; GFX6: ; %bb.0: ; %entry +; GFX6-NEXT: s_add_u32 s0, s0, s15 +; GFX6-NEXT: s_addc_u32 s1, s1, 0 +; GFX6-NEXT: s_load_dword s5, s[8:9], 0x0 +; GFX6-NEXT: s_load_dword s4, s[8:9], 0x1 +; GFX6-NEXT: s_waitcnt lgkmcnt(0) +; GFX6-NEXT: v_mov_b32_e32 v0, s5 +; GFX6-NEXT: buffer_load_dword v0, v0, s[0:3], 0 offen +; GFX6-NEXT: v_mov_b32_e32 v1, s4 +; GFX6-NEXT: s_waitcnt vmcnt(0) +; GFX6-NEXT: buffer_store_dword v0, v1, s[0:3], 0 offen +; GFX6-NEXT: s_endpgm +; +; GFX7-LABEL: private_agent_monotonic_load: +; GFX7: ; %bb.0: ; %entry +; GFX7-NEXT: s_add_u32 s0, s0, s17 +; GFX7-NEXT: s_addc_u32 s1, s1, 0 +; GFX7-NEXT: s_load_dword s5, s[8:9], 0x0 +; GFX7-NEXT: s_load_dword s4, s[8:9], 0x1 +; GFX7-NEXT: s_waitcnt lgkmcnt(0) +; GFX7-NEXT: v_mov_b32_e32 v0, s5 +; GFX7-NEXT: buffer_load_dword v0, v0, s[0:3], 0 offen +; GFX7-NEXT: v_mov_b32_e32 v1, s4 +; GFX7-NEXT: s_waitcnt vmcnt(0) +; GFX7-NEXT: buffer_store_dword v0, v1, s[0:3], 0 offen +; GFX7-NEXT: s_endpgm +; +; GFX10-WGP-LABEL: private_agent_monotonic_load: +; GFX10-WGP: ; %bb.0: ; %entry +; GFX10-WGP-NEXT: s_add_u32 s0, s0, s17 +; GFX10-WGP-NEXT: s_addc_u32 s1, s1, 0 +; GFX10-WGP-NEXT: s_load_dword s5, s[8:9], 0x0 +; GFX10-WGP-NEXT: s_load_dword s4, s[8:9], 0x4 +; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0) +; GFX10-WGP-NEXT: v_mov_b32_e32 v0, s5 +; GFX10-WGP-NEXT: buffer_load_dword v0, v0, s[0:3], 0 offen +; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s4 +; GFX10-WGP-NEXT: s_waitcnt vmcnt(0) +; GFX10-WGP-NEXT: buffer_store_dword v0, v1, s[0:3], 0 offen +; GFX10-WGP-NEXT: s_endpgm +; +; GFX10-CU-LABEL: private_agent_monotonic_load: +; GFX10-CU: ; %bb.0: ; %entry +; GFX10-CU-NEXT: s_add_u32 s0, s0, s17 +; GFX10-CU-NEXT: s_addc_u32 s1, s1, 0 +; GFX10-CU-NEXT: s_load_dword s5, s[8:9], 0x0 +; GFX10-CU-NEXT: s_load_dword s4, s[8:9], 0x4 +; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0) +; GFX10-CU-NEXT: v_mov_b32_e32 v0, s5 +; GFX10-CU-NEXT: buffer_load_dword v0, v0, s[0:3], 0 offen +; GFX10-CU-NEXT: v_mov_b32_e32 v1, s4 +; GFX10-CU-NEXT: s_waitcnt vmcnt(0) +; GFX10-CU-NEXT: buffer_store_dword v0, v1, s[0:3], 0 offen +; GFX10-CU-NEXT: s_endpgm +; +; SKIP-CACHE-INV-LABEL: private_agent_monotonic_load: +; SKIP-CACHE-INV: ; %bb.0: ; %entry +; SKIP-CACHE-INV-NEXT: s_getpc_b64 s[12:13] +; SKIP-CACHE-INV-NEXT: s_mov_b32 s12, s0 +; SKIP-CACHE-INV-NEXT: s_load_dwordx4 s[12:15], s[12:13], 0x0 +; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0) +; SKIP-CACHE-INV-NEXT: s_add_u32 s12, s12, s11 +; SKIP-CACHE-INV-NEXT: s_addc_u32 s13, s13, 0 +; SKIP-CACHE-INV-NEXT: s_load_dword s1, s[4:5], 0x0 +; SKIP-CACHE-INV-NEXT: s_load_dword s0, s[4:5], 0x1 +; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0) +; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s1 +; SKIP-CACHE-INV-NEXT: buffer_load_dword v0, v0, s[12:15], 0 offen +; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v1, s0 +; SKIP-CACHE-INV-NEXT: s_waitcnt vmcnt(0) +; SKIP-CACHE-INV-NEXT: buffer_store_dword v0, v1, s[12:15], 0 offen +; SKIP-CACHE-INV-NEXT: s_endpgm +; +; GFX90A-NOTTGSPLIT-LABEL: private_agent_monotonic_load: +; GFX90A-NOTTGSPLIT: ; %bb.0: ; %entry +; GFX90A-NOTTGSPLIT-NEXT: s_add_u32 s0, s0, s17 +; GFX90A-NOTTGSPLIT-NEXT: s_addc_u32 s1, s1, 0 +; GFX90A-NOTTGSPLIT-NEXT: s_load_dword s5, s[8:9], 0x0 +; GFX90A-NOTTGSPLIT-NEXT: s_load_dword s4, s[8:9], 0x4 +; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0) +; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v0, s5 +; GFX90A-NOTTGSPLIT-NEXT: buffer_load_dword v0, v0, s[0:3], 0 offen +; GFX90A-NOTTGSPLIT-NEXT: v_mov_b32_e32 v1, s4 +; GFX90A-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0) +; GFX90A-NOTTGSPLIT-NEXT: buffer_store_dword v0, v1, s[0:3], 0 offen +; GFX90A-NOTTGSPLIT-NEXT: s_endpgm +; +; GFX90A-TGSPLIT-LABEL: private_agent_monotonic_load: +; GFX90A-TGSPLIT: ; %bb.0: ; %entry +; GFX90A-TGSPLIT-NEXT: s_add_u32 s0, s0, s17 +; GFX90A-TGSPLIT-NEXT: s_addc_u32 s1, s1, 0 +; GFX90A-TGSPLIT-NEXT: s_load_dword s5, s[8:9], 0x0 +; GFX90A-TGSPLIT-NEXT: s_load_dword s4, s[8:9], 0x4 +; GFX90A-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0) +; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v0, s5 +; GFX90A-TGSPLIT-NEXT: buffer_load_dword v0, v0, s[0:3], 0 offen +; GFX90A-TGSPLIT-NEXT: v_mov_b32_e32 v1, s4 +; GFX90A-TGSPLIT-NEXT: s_waitcnt vmcnt(0) +; GFX90A-TGSPLIT-NEXT: buffer_store_dword v0, v1, s[0:3], 0 offen +; GFX90A-TGSPLIT-NEXT: s_endpgm +; +; GFX942-NOTTGSPLIT-LABEL: private_agent_monotonic_load: +; GFX942-NOTTGSPLIT: ; %bb.0: ; %entry +; GFX942-NOTTGSPLIT-NEXT: s_load_dword s1, s[4:5], 0x0 +; GFX942-NOTTGSPLIT-NEXT: s_load_dword s0, s[4:5], 0x4 +; GFX942-NOTTGSPLIT-NEXT: s_waitcnt lgkmcnt(0) +; GFX942-NOTTGSPLIT-NEXT: scratch_load_dword v0, off, s1 +; GFX942-NOTTGSPLIT-NEXT: s_waitcnt vmcnt(0) +; GFX942-NOTTGSPLIT-NEXT: scratch_store_dword off, v0, s0 +; GFX942-NOTTGSPLIT-NEXT: s_endpgm +; +; GFX942-TGSPLIT-LABEL: private_agent_monotonic_load: +; GFX942-TGSPLIT: ; %bb.0: ; %entry +; GFX942-TGSPLIT-NEXT: s_load_dword s1, s[4:5], 0x0 +; GFX942-TGSPLIT-NEXT: s_load_dword s0, s[4:5], 0x4 +; GFX942-TGSPLIT-NEXT: s_waitcnt lgkmcnt(0) +; GFX942-TGSPLIT-NEXT: scratch_load_dword v0, off, s1 +; GFX942-TGSPLIT-NEXT: s_waitcnt vmcnt(0) +; GFX942-TGSPLIT-NEXT: scratch_store_dword off, v0, s0 +; GFX942-TGSPLIT-NEXT: s_endpgm +; +; GFX11-WGP-LABEL: private_agent_monotonic_load: +; GFX11-WGP: ; %bb.0: ; %entry +; GFX11-WGP-NEXT: s_load_b32 s1, s[4:5], 0x0 +; GFX11-WGP-NEXT: s_load_b32 s0, s[4:5], 0x4 +; GFX11-WGP-NEXT: s_waitcnt lgkmcnt(0) +; GFX11-WGP-NEXT: scratch_load_b32 v0, off, s1 +; GFX11-WGP-NEXT: s_waitcnt vmcnt(0) +; GFX11-WGP-NEXT: scratch_store_b32 off, v0, s0 +; GFX11-WGP-NEXT: s_endpgm +; +; GFX11-CU-LABEL: private_agent_monotonic_load: +; GFX11-CU: ; %bb.0: ; %entry +; GFX11-CU-NEXT: s_load_b32 s1, s[4:5], 0x0 +; GFX11-CU-NEXT: s_load_b32 s0, s[4:5], 0x4 +; GFX11-CU-NEXT: s_waitcnt lgkmcnt(0) +; GFX11-CU-NEXT: scratch_load_b32 v0, off, s1 +; GFX11-CU-NEXT: s_waitcnt vmcnt(0) +; GFX11-CU-NEXT: scratch_store_b32 off, v0, s0 +; GFX11-CU-NEXT: s_endpgm +; +; GFX12-WGP-LABEL: private_agent_monotonic_load: +; GFX12-WGP: ; %bb.0: ; %entry +; GFX12-WGP-NEXT: s_load_b32 s1, s[4:5], 0x0 +; GFX12-WGP-NEXT: s_load_b32 s0, s[4:5], 0x4 +; GFX12-WGP-NEXT: s_wait_kmcnt 0x0 +; GFX12-WGP-NEXT: scratch_load_b32 v0, off, s1 +; GFX12-WGP-NEXT: s_wait_loadcnt 0x0 +; GFX12-WGP-NEXT: scratch_store_b32 off, v0, s0 +; GFX12-WGP-NEXT: s_endpgm +; +; GFX12-CU-LABEL: private_agent_monotonic_load: +; GFX12-CU: ; %bb.0: ; %entry +; GFX12-CU-NEXT: s_load_b32 s1, s[4:5], 0x0 +; GFX12-CU-NEXT: s_load_b32 s0, s[4:5], 0x4 +; GFX12-CU-NEXT: s_wait_kmcnt 0x0 +; GFX12-CU-NEXT: scratch_load_b32 v0, off, s1 +; GFX12-CU-NEXT: s_wait_loadcnt 0x0 +; GFX12-CU-NEXT: scratch_store_b32 off, v0, s0 +; GFX12-CU-NEXT: s_endpgm +; +; GFX1250-LABEL: private_agent_monotonic_load: +; GFX1250: ; %bb.0: ; %entry +; GFX1250-NEXT: s_load_b32 s1, s[4:5], 0x0 +; GFX1250-NEXT: s_load_b32 s0, s[4:5], 0x4 +; GFX1250-NEXT: s_wait_kmcnt 0x0 +; GFX1250-NEXT: scratch_load_b32 v0, off, s1 +; GFX1250-NEXT: s_wait_loadcnt 0x0 +; GFX1250-NEXT: scratch_store_b32 off, v0, s0 scope:SCOPE_SE +; GFX1250-NEXT: s_endpgm + ptr addrspace(5) %in, ptr addrspace(5) %out) { +entry: + %val = load atomic i32, ptr addrspace(5) %in syncscope("agent") monotonic, align 4 + store i32 %val, ptr addrspace(5) %out + ret void +} + +define amdgpu_kernel void @private_agent_acquire_load( +; GFX6-LABEL: private_agent_acquire_load: +; GFX6: ; %bb.0: ; %entry +; GFX6-NEXT: s_add_u32 s0, s0, s15 +; GFX6-NEXT: s_addc_u32 s1, s1, 0 +; GFX6-NEXT: s_load_dword s5, s[8:9], 0x0 +; GFX6-NEXT: s_load_dword s4, s[8:9], 0x1 +; GFX6-NEXT: s_waitcnt lgkmcnt(0) +; GFX6-NEXT: v_mov_b32_e32 v0, s5 +; GFX6-NEXT: buffer_load_dword v0, v0, s[0:3], 0 offen +; GFX6-NEXT: v_mov_b32_e32 v1, s4 +; GFX6-NEXT: s_waitcnt vmcnt(0) +; GFX6-NEXT: buffer_store_dword v0, v1, s[0:3], 0 offen +; GFX6-NEXT: s_endpgm +; +; GFX7-LABEL: private_agent_acquire_load: +; GFX7: ; %bb.0: ; %entry +; GFX7-NEXT: s_add_u32 s0, s0, s17 +; GFX7-NEXT: s_addc_u32 s1, s1, 0 +; GFX7-NEXT: s_load_dword s5, s[8:9], 0x0 +; GFX7-NEXT: s_load_dword s4, s[8:9], 0x1 +; GFX7-NEXT: s_waitcnt lgkmcnt(0) +; GFX7-NEXT: v_mov_b32_e32 v0, s5 +; GFX7-NEXT: buffer_load_dword v0, v0, s[0:3], 0 offen +; GFX7-NEXT: v_mov_b32_e32 v1, s4 +; GFX7-NEXT: s_waitcnt vmcnt(0) +; GFX7-NEXT: buffer_store_dword v0, v1, s[0:3], 0 offen +; GFX7-NEXT: s_endpgm +; +; GFX10-WGP-LABEL: private_agent_acquire_load: +; GFX10-WGP: ; %bb.0: ; %entry +; GFX10-WGP-NEXT: s_add_u32 s0, s0, s17 +; GFX10-WGP-NEXT: s_addc_u32 s1, s1, 0 +; GFX10-WGP-NEXT: s_load_dword s5, s[8:9], 0x0 +; GFX10-WGP-NEXT: s_load_dword s4, s[8:9], 0x4 +; GFX10-WGP-NEXT: s_waitcnt lgkmcnt(0) +; GFX10-WGP-NEXT: v_mov_b32_e32 v0, s5 +; GFX10-WGP-NEXT: buffer_load_dword v0, v0, s[0:3], 0 offen +; GFX10-WGP-NEXT: v_mov_b32_e32 v1, s4 +; GFX10-WGP-NEXT: s_waitcnt vmcnt(0) +; GFX10-WGP-NEXT: buffer_store_dword v0, v1, s[0:3], 0 offen +; GFX10-WGP-NEXT: s_endpgm +; +; GFX10-CU-LABEL: private_agent_acquire_load: +; GFX10-CU: ; %bb.0: ; %entry +; GFX10-CU-NEXT: s_add_u32 s0, s0, s17 +; GFX10-CU-NEXT: s_addc_u32 s1, s1, 0 +; GFX10-CU-NEXT: s_load_dword s5, s[8:9], 0x0 +; GFX10-CU-NEXT: s_load_dword s4, s[8:9], 0x4 +; GFX10-CU-NEXT: s_waitcnt lgkmcnt(0) +; GFX10-CU-NEXT: v_mov_b32_e32 v0, s5 +; GFX10-CU-NEXT: buffer_load_dword v0, v0, s[0:3], 0 offen +; GFX10-CU-NEXT: v_mov_b32_e32 v1, s4 +; GFX10-CU-NEXT: s_waitcnt vmcnt(0) +; GFX10-CU-NEXT: buffer_store_dword v0, v1, s[0:3], 0 offen +; GFX10-CU-NEXT: s_endpgm +; +; SKIP-CACHE-INV-LABEL: private_agent_acquire_load: +; SKIP-CACHE-INV: ; %bb.0: ; %entry +; SKIP-CACHE-INV-NEXT: s_getpc_b64 s[12:13] +; SKIP-CACHE-INV-NEXT: s_mov_b32 s12, s0 +; SKIP-CACHE-INV-NEXT: s_load_dwordx4 s[12:15], s[12:13], 0x0 +; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0) +; SKIP-CACHE-INV-NEXT: s_add_u32 s12, s12, s11 +; SKIP-CACHE-INV-NEXT: s_addc_u32 s13, s13, 0 +; SKIP-CACHE-INV-NEXT: s_load_dword s1, s[4:5], 0x0 +; SKIP-CACHE-INV-NEXT: s_load_dword s0, s[4:5], 0x1 +; SKIP-CACHE-INV-NEXT: s_waitcnt lgkmcnt(0) +; SKIP-CACHE-INV-NEXT: v_mov_b32_e32 v0, s1 +; SKIP-CACHE-I... [truncated] `````````` </details> https://github.com/llvm/llvm-project/pull/154709 _______________________________________________ llvm-branch-commits mailing list llvm-branch-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-branch-commits
