AMDGPU: Start selecting buffer fat pointer atomicrmw fmin/fmax #95593

arsenm · 2024-06-14T19:35:54Z

No description provided.

arsenm · 2024-06-14T19:36:02Z

This stack of pull requests is managed by Graphite. Learn more about stacking.

Join @arsenm and the rest of your teammates on Graphite

llvmbot · 2024-06-14T19:37:58Z

@llvm/pr-subscribers-backend-amdgpu

Author: Matt Arsenault (arsenm)

Changes

Patch is 148.79 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/95593.diff

3 Files Affected:

(modified) llvm/lib/Target/AMDGPU/SIISelLowering.cpp (+2-1)
(modified) llvm/test/CodeGen/AMDGPU/buffer-fat-pointer-atomicrmw-fmax.ll (+141-1029)
(modified) llvm/test/CodeGen/AMDGPU/buffer-fat-pointer-atomicrmw-fmin.ll (+141-1029)

diff --git a/llvm/lib/Target/AMDGPU/SIISelLowering.cpp b/llvm/lib/Target/AMDGPU/SIISelLowering.cpp
index 78557e006170a..e03f262831eae 100644
--- a/llvm/lib/Target/AMDGPU/SIISelLowering.cpp
+++ b/llvm/lib/Target/AMDGPU/SIISelLowering.cpp
@@ -16049,7 +16049,8 @@ SITargetLowering::shouldExpandAtomicRMWInIR(AtomicRMWInst *RMW) const {
         return AtomicExpansionKind::None;
       if (Subtarget->hasAtomicFMinFMaxF64FlatInsts() && Ty->isDoubleTy())
         return AtomicExpansionKind::None;
-    } else if (AMDGPU::isExtendedGlobalAddrSpace(AS)) {
+    } else if (AMDGPU::isExtendedGlobalAddrSpace(AS) ||
+               AS == AMDGPUAS::BUFFER_FAT_POINTER) {
       if (Subtarget->hasAtomicFMinFMaxF32GlobalInsts() && Ty->isFloatTy())
         return AtomicExpansionKind::None;
       if (Subtarget->hasAtomicFMinFMaxF64GlobalInsts() && Ty->isDoubleTy())
diff --git a/llvm/test/CodeGen/AMDGPU/buffer-fat-pointer-atomicrmw-fmax.ll b/llvm/test/CodeGen/AMDGPU/buffer-fat-pointer-atomicrmw-fmax.ll
index fb068e35fc597..4b5cdd2ed32ef 100644
--- a/llvm/test/CodeGen/AMDGPU/buffer-fat-pointer-atomicrmw-fmax.ll
+++ b/llvm/test/CodeGen/AMDGPU/buffer-fat-pointer-atomicrmw-fmax.ll
@@ -21,32 +21,11 @@ define float @buffer_fat_ptr_agent_atomic_fmax_ret_f32__offset(ptr addrspace(7)
 ; GFX12-NEXT:    s_wait_samplecnt 0x0
 ; GFX12-NEXT:    s_wait_bvhcnt 0x0
 ; GFX12-NEXT:    s_wait_kmcnt 0x0
-; GFX12-NEXT:    v_dual_mov_b32 v1, v0 :: v_dual_mov_b32 v0, s4
-; GFX12-NEXT:    s_addk_co_i32 s4, 0x400
-; GFX12-NEXT:    s_delay_alu instid0(VALU_DEP_1) | instid1(SALU_CYCLE_1)
-; GFX12-NEXT:    v_dual_mov_b32 v3, s4 :: v_dual_max_num_f32 v2, v1, v1
-; GFX12-NEXT:    buffer_load_b32 v0, v0, s[0:3], null offen offset:1024
-; GFX12-NEXT:    s_mov_b32 s4, 0
-; GFX12-NEXT:  .LBB0_1: ; %atomicrmw.start
-; GFX12-NEXT:    ; =>This Inner Loop Header: Depth=1
-; GFX12-NEXT:    s_wait_loadcnt 0x0
-; GFX12-NEXT:    v_mov_b32_e32 v5, v0
+; GFX12-NEXT:    v_mov_b32_e32 v1, s4
 ; GFX12-NEXT:    s_wait_storecnt 0x0
-; GFX12-NEXT:    s_delay_alu instid0(VALU_DEP_1) | instskip(NEXT) | instid1(VALU_DEP_1)
-; GFX12-NEXT:    v_max_num_f32_e32 v0, v5, v5
-; GFX12-NEXT:    v_max_num_f32_e32 v4, v0, v2
-; GFX12-NEXT:    s_delay_alu instid0(VALU_DEP_1)
-; GFX12-NEXT:    v_dual_mov_b32 v0, v4 :: v_dual_mov_b32 v1, v5
-; GFX12-NEXT:    buffer_atomic_cmpswap_b32 v[0:1], v3, s[0:3], null offen th:TH_ATOMIC_RETURN
+; GFX12-NEXT:    buffer_atomic_max_num_f32 v0, v1, s[0:3], null offen offset:1024 th:TH_ATOMIC_RETURN
 ; GFX12-NEXT:    s_wait_loadcnt 0x0
 ; GFX12-NEXT:    global_inv scope:SCOPE_DEV
-; GFX12-NEXT:    v_cmp_eq_u32_e32 vcc_lo, v0, v5
-; GFX12-NEXT:    s_or_b32 s4, vcc_lo, s4
-; GFX12-NEXT:    s_delay_alu instid0(SALU_CYCLE_1)
-; GFX12-NEXT:    s_and_not1_b32 exec_lo, exec_lo, s4
-; GFX12-NEXT:    s_cbranch_execnz .LBB0_1
-; GFX12-NEXT:  ; %bb.2: ; %atomicrmw.end
-; GFX12-NEXT:    s_or_b32 exec_lo, exec_lo, s4
 ; GFX12-NEXT:    s_setpc_b64 s[30:31]
 ;
 ; GFX940-LABEL: buffer_fat_ptr_agent_atomic_fmax_ret_f32__offset:
@@ -81,64 +60,23 @@ define float @buffer_fat_ptr_agent_atomic_fmax_ret_f32__offset(ptr addrspace(7)
 ; GFX11-LABEL: buffer_fat_ptr_agent_atomic_fmax_ret_f32__offset:
 ; GFX11:       ; %bb.0:
 ; GFX11-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GFX11-NEXT:    v_dual_mov_b32 v1, v0 :: v_dual_mov_b32 v0, s4
-; GFX11-NEXT:    s_addk_i32 s4, 0x400
-; GFX11-NEXT:    s_delay_alu instid0(VALU_DEP_1) | instid1(SALU_CYCLE_1)
-; GFX11-NEXT:    v_dual_mov_b32 v3, s4 :: v_dual_max_f32 v2, v1, v1
-; GFX11-NEXT:    buffer_load_b32 v0, v0, s[0:3], 0 offen offset:1024
-; GFX11-NEXT:    s_mov_b32 s4, 0
-; GFX11-NEXT:  .LBB0_1: ; %atomicrmw.start
-; GFX11-NEXT:    ; =>This Inner Loop Header: Depth=1
-; GFX11-NEXT:    s_waitcnt vmcnt(0)
-; GFX11-NEXT:    v_mov_b32_e32 v5, v0
+; GFX11-NEXT:    v_mov_b32_e32 v1, s4
 ; GFX11-NEXT:    s_waitcnt_vscnt null, 0x0
-; GFX11-NEXT:    s_delay_alu instid0(VALU_DEP_1) | instskip(NEXT) | instid1(VALU_DEP_1)
-; GFX11-NEXT:    v_max_f32_e32 v0, v5, v5
-; GFX11-NEXT:    v_max_f32_e32 v4, v0, v2
-; GFX11-NEXT:    s_delay_alu instid0(VALU_DEP_1)
-; GFX11-NEXT:    v_dual_mov_b32 v0, v4 :: v_dual_mov_b32 v1, v5
-; GFX11-NEXT:    buffer_atomic_cmpswap_b32 v[0:1], v3, s[0:3], 0 offen glc
+; GFX11-NEXT:    buffer_atomic_max_f32 v0, v1, s[0:3], 0 offen offset:1024 glc
 ; GFX11-NEXT:    s_waitcnt vmcnt(0)
 ; GFX11-NEXT:    buffer_gl1_inv
 ; GFX11-NEXT:    buffer_gl0_inv
-; GFX11-NEXT:    v_cmp_eq_u32_e32 vcc_lo, v0, v5
-; GFX11-NEXT:    s_or_b32 s4, vcc_lo, s4
-; GFX11-NEXT:    s_delay_alu instid0(SALU_CYCLE_1)
-; GFX11-NEXT:    s_and_not1_b32 exec_lo, exec_lo, s4
-; GFX11-NEXT:    s_cbranch_execnz .LBB0_1
-; GFX11-NEXT:  ; %bb.2: ; %atomicrmw.end
-; GFX11-NEXT:    s_or_b32 exec_lo, exec_lo, s4
 ; GFX11-NEXT:    s_setpc_b64 s[30:31]
 ;
 ; GFX10-LABEL: buffer_fat_ptr_agent_atomic_fmax_ret_f32__offset:
 ; GFX10:       ; %bb.0:
 ; GFX10-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GFX10-NEXT:    v_mov_b32_e32 v1, v0
-; GFX10-NEXT:    v_mov_b32_e32 v0, s8
-; GFX10-NEXT:    s_addk_i32 s8, 0x400
-; GFX10-NEXT:    v_mov_b32_e32 v3, s8
-; GFX10-NEXT:    v_max_f32_e32 v2, v1, v1
-; GFX10-NEXT:    buffer_load_dword v0, v0, s[4:7], 0 offen offset:1024
-; GFX10-NEXT:    s_mov_b32 s8, 0
-; GFX10-NEXT:  .LBB0_1: ; %atomicrmw.start
-; GFX10-NEXT:    ; =>This Inner Loop Header: Depth=1
-; GFX10-NEXT:    s_waitcnt vmcnt(0)
-; GFX10-NEXT:    v_mov_b32_e32 v5, v0
+; GFX10-NEXT:    v_mov_b32_e32 v1, s8
 ; GFX10-NEXT:    s_waitcnt_vscnt null, 0x0
-; GFX10-NEXT:    v_max_f32_e32 v0, v5, v5
-; GFX10-NEXT:    v_max_f32_e32 v4, v0, v2
-; GFX10-NEXT:    v_mov_b32_e32 v0, v4
-; GFX10-NEXT:    v_mov_b32_e32 v1, v5
-; GFX10-NEXT:    buffer_atomic_cmpswap v[0:1], v3, s[4:7], 0 offen glc
+; GFX10-NEXT:    buffer_atomic_fmax v0, v1, s[4:7], 0 offen offset:1024 glc
 ; GFX10-NEXT:    s_waitcnt vmcnt(0)
 ; GFX10-NEXT:    buffer_gl1_inv
 ; GFX10-NEXT:    buffer_gl0_inv
-; GFX10-NEXT:    v_cmp_eq_u32_e32 vcc_lo, v0, v5
-; GFX10-NEXT:    s_or_b32 s8, vcc_lo, s8
-; GFX10-NEXT:    s_andn2_b32 exec_lo, exec_lo, s8
-; GFX10-NEXT:    s_cbranch_execnz .LBB0_1
-; GFX10-NEXT:  ; %bb.2: ; %atomicrmw.end
-; GFX10-NEXT:    s_or_b32 exec_lo, exec_lo, s8
 ; GFX10-NEXT:    s_setpc_b64 s[30:31]
 ;
 ; GFX90A-LABEL: buffer_fat_ptr_agent_atomic_fmax_ret_f32__offset:
@@ -230,60 +168,19 @@ define float @buffer_fat_ptr_agent_atomic_fmax_ret_f32__offset(ptr addrspace(7)
 ; GFX7-LABEL: buffer_fat_ptr_agent_atomic_fmax_ret_f32__offset:
 ; GFX7:       ; %bb.0:
 ; GFX7-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GFX7-NEXT:    v_mov_b32_e32 v1, v0
-; GFX7-NEXT:    v_mov_b32_e32 v0, s8
-; GFX7-NEXT:    buffer_load_dword v0, v0, s[4:7], 0 offen offset:1024
-; GFX7-NEXT:    s_add_i32 s10, s8, 0x400
-; GFX7-NEXT:    s_mov_b64 s[8:9], 0
-; GFX7-NEXT:    v_mul_f32_e32 v2, 1.0, v1
-; GFX7-NEXT:    v_mov_b32_e32 v3, s10
-; GFX7-NEXT:  .LBB0_1: ; %atomicrmw.start
-; GFX7-NEXT:    ; =>This Inner Loop Header: Depth=1
-; GFX7-NEXT:    s_waitcnt vmcnt(0)
-; GFX7-NEXT:    v_mov_b32_e32 v5, v0
-; GFX7-NEXT:    v_mul_f32_e32 v0, 1.0, v5
-; GFX7-NEXT:    v_max_f32_e32 v4, v0, v2
-; GFX7-NEXT:    v_mov_b32_e32 v0, v4
-; GFX7-NEXT:    v_mov_b32_e32 v1, v5
-; GFX7-NEXT:    buffer_atomic_cmpswap v[0:1], v3, s[4:7], 0 offen glc
+; GFX7-NEXT:    v_mov_b32_e32 v1, s8
+; GFX7-NEXT:    buffer_atomic_fmax v0, v1, s[4:7], 0 offen offset:1024 glc
 ; GFX7-NEXT:    s_waitcnt vmcnt(0)
 ; GFX7-NEXT:    buffer_wbinvl1
-; GFX7-NEXT:    v_cmp_eq_u32_e32 vcc, v0, v5
-; GFX7-NEXT:    s_or_b64 s[8:9], vcc, s[8:9]
-; GFX7-NEXT:    s_andn2_b64 exec, exec, s[8:9]
-; GFX7-NEXT:    s_cbranch_execnz .LBB0_1
-; GFX7-NEXT:  ; %bb.2: ; %atomicrmw.end
-; GFX7-NEXT:    s_or_b64 exec, exec, s[8:9]
 ; GFX7-NEXT:    s_setpc_b64 s[30:31]
 ;
 ; GFX6-LABEL: buffer_fat_ptr_agent_atomic_fmax_ret_f32__offset:
 ; GFX6:       ; %bb.0:
 ; GFX6-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GFX6-NEXT:    v_mov_b32_e32 v1, v0
-; GFX6-NEXT:    v_mov_b32_e32 v0, s8
-; GFX6-NEXT:    buffer_load_dword v0, v0, s[4:7], 0 offen offset:1024
-; GFX6-NEXT:    s_add_i32 s10, s8, 0x400
-; GFX6-NEXT:    s_mov_b64 s[8:9], 0
-; GFX6-NEXT:    v_mul_f32_e32 v2, 1.0, v1
-; GFX6-NEXT:    v_mov_b32_e32 v3, s10
-; GFX6-NEXT:  .LBB0_1: ; %atomicrmw.start
-; GFX6-NEXT:    ; =>This Inner Loop Header: Depth=1
-; GFX6-NEXT:    s_waitcnt vmcnt(0)
-; GFX6-NEXT:    v_mov_b32_e32 v5, v0
-; GFX6-NEXT:    s_waitcnt expcnt(0)
-; GFX6-NEXT:    v_mul_f32_e32 v0, 1.0, v5
-; GFX6-NEXT:    v_max_f32_e32 v4, v0, v2
-; GFX6-NEXT:    v_mov_b32_e32 v0, v4
-; GFX6-NEXT:    v_mov_b32_e32 v1, v5
-; GFX6-NEXT:    buffer_atomic_cmpswap v[0:1], v3, s[4:7], 0 offen glc
+; GFX6-NEXT:    v_mov_b32_e32 v1, s8
+; GFX6-NEXT:    buffer_atomic_fmax v0, v1, s[4:7], 0 offen offset:1024 glc
 ; GFX6-NEXT:    s_waitcnt vmcnt(0)
 ; GFX6-NEXT:    buffer_wbinvl1
-; GFX6-NEXT:    v_cmp_eq_u32_e32 vcc, v0, v5
-; GFX6-NEXT:    s_or_b64 s[8:9], vcc, s[8:9]
-; GFX6-NEXT:    s_andn2_b64 exec, exec, s[8:9]
-; GFX6-NEXT:    s_cbranch_execnz .LBB0_1
-; GFX6-NEXT:  ; %bb.2: ; %atomicrmw.end
-; GFX6-NEXT:    s_or_b64 exec, exec, s[8:9]
 ; GFX6-NEXT:    s_waitcnt expcnt(0)
 ; GFX6-NEXT:    s_setpc_b64 s[30:31]
   %gep = getelementptr float, ptr addrspace(7) %ptr, i32 256
@@ -299,31 +196,11 @@ define void @buffer_fat_ptr_agent_atomic_fmax_noret_f32__offset(ptr addrspace(7)
 ; GFX12-NEXT:    s_wait_samplecnt 0x0
 ; GFX12-NEXT:    s_wait_bvhcnt 0x0
 ; GFX12-NEXT:    s_wait_kmcnt 0x0
-; GFX12-NEXT:    v_dual_mov_b32 v1, s4 :: v_dual_max_num_f32 v2, v0, v0
-; GFX12-NEXT:    s_addk_co_i32 s4, 0x400
-; GFX12-NEXT:    s_delay_alu instid0(SALU_CYCLE_1)
-; GFX12-NEXT:    v_mov_b32_e32 v3, s4
-; GFX12-NEXT:    buffer_load_b32 v1, v1, s[0:3], null offen offset:1024
-; GFX12-NEXT:    s_mov_b32 s4, 0
-; GFX12-NEXT:  .LBB1_1: ; %atomicrmw.start
-; GFX12-NEXT:    ; =>This Inner Loop Header: Depth=1
-; GFX12-NEXT:    s_wait_loadcnt 0x0
-; GFX12-NEXT:    v_max_num_f32_e32 v0, v1, v1
+; GFX12-NEXT:    v_mov_b32_e32 v1, s4
+; GFX12-NEXT:    s_wait_storecnt 0x0
+; GFX12-NEXT:    buffer_atomic_max_num_f32 v0, v1, s[0:3], null offen offset:1024
 ; GFX12-NEXT:    s_wait_storecnt 0x0
-; GFX12-NEXT:    s_delay_alu instid0(VALU_DEP_1) | instskip(NEXT) | instid1(VALU_DEP_1)
-; GFX12-NEXT:    v_max_num_f32_e32 v0, v0, v2
-; GFX12-NEXT:    v_dual_mov_b32 v5, v1 :: v_dual_mov_b32 v4, v0
-; GFX12-NEXT:    buffer_atomic_cmpswap_b32 v[4:5], v3, s[0:3], null offen th:TH_ATOMIC_RETURN
-; GFX12-NEXT:    s_wait_loadcnt 0x0
 ; GFX12-NEXT:    global_inv scope:SCOPE_DEV
-; GFX12-NEXT:    v_cmp_eq_u32_e32 vcc_lo, v4, v1
-; GFX12-NEXT:    v_mov_b32_e32 v1, v4
-; GFX12-NEXT:    s_or_b32 s4, vcc_lo, s4
-; GFX12-NEXT:    s_delay_alu instid0(SALU_CYCLE_1)
-; GFX12-NEXT:    s_and_not1_b32 exec_lo, exec_lo, s4
-; GFX12-NEXT:    s_cbranch_execnz .LBB1_1
-; GFX12-NEXT:  ; %bb.2: ; %atomicrmw.end
-; GFX12-NEXT:    s_or_b32 exec_lo, exec_lo, s4
 ; GFX12-NEXT:    s_setpc_b64 s[30:31]
 ;
 ; GFX940-LABEL: buffer_fat_ptr_agent_atomic_fmax_noret_f32__offset:
@@ -357,62 +234,23 @@ define void @buffer_fat_ptr_agent_atomic_fmax_noret_f32__offset(ptr addrspace(7)
 ; GFX11-LABEL: buffer_fat_ptr_agent_atomic_fmax_noret_f32__offset:
 ; GFX11:       ; %bb.0:
 ; GFX11-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GFX11-NEXT:    v_dual_mov_b32 v1, s4 :: v_dual_max_f32 v2, v0, v0
-; GFX11-NEXT:    s_addk_i32 s4, 0x400
-; GFX11-NEXT:    s_delay_alu instid0(SALU_CYCLE_1)
-; GFX11-NEXT:    v_mov_b32_e32 v3, s4
-; GFX11-NEXT:    buffer_load_b32 v1, v1, s[0:3], 0 offen offset:1024
-; GFX11-NEXT:    s_mov_b32 s4, 0
-; GFX11-NEXT:  .LBB1_1: ; %atomicrmw.start
-; GFX11-NEXT:    ; =>This Inner Loop Header: Depth=1
-; GFX11-NEXT:    s_waitcnt vmcnt(0)
-; GFX11-NEXT:    v_max_f32_e32 v0, v1, v1
+; GFX11-NEXT:    v_mov_b32_e32 v1, s4
+; GFX11-NEXT:    s_waitcnt_vscnt null, 0x0
+; GFX11-NEXT:    buffer_atomic_max_f32 v0, v1, s[0:3], 0 offen offset:1024
 ; GFX11-NEXT:    s_waitcnt_vscnt null, 0x0
-; GFX11-NEXT:    s_delay_alu instid0(VALU_DEP_1) | instskip(NEXT) | instid1(VALU_DEP_1)
-; GFX11-NEXT:    v_max_f32_e32 v0, v0, v2
-; GFX11-NEXT:    v_dual_mov_b32 v5, v1 :: v_dual_mov_b32 v4, v0
-; GFX11-NEXT:    buffer_atomic_cmpswap_b32 v[4:5], v3, s[0:3], 0 offen glc
-; GFX11-NEXT:    s_waitcnt vmcnt(0)
 ; GFX11-NEXT:    buffer_gl1_inv
 ; GFX11-NEXT:    buffer_gl0_inv
-; GFX11-NEXT:    v_cmp_eq_u32_e32 vcc_lo, v4, v1
-; GFX11-NEXT:    v_mov_b32_e32 v1, v4
-; GFX11-NEXT:    s_or_b32 s4, vcc_lo, s4
-; GFX11-NEXT:    s_delay_alu instid0(SALU_CYCLE_1)
-; GFX11-NEXT:    s_and_not1_b32 exec_lo, exec_lo, s4
-; GFX11-NEXT:    s_cbranch_execnz .LBB1_1
-; GFX11-NEXT:  ; %bb.2: ; %atomicrmw.end
-; GFX11-NEXT:    s_or_b32 exec_lo, exec_lo, s4
 ; GFX11-NEXT:    s_setpc_b64 s[30:31]
 ;
 ; GFX10-LABEL: buffer_fat_ptr_agent_atomic_fmax_noret_f32__offset:
 ; GFX10:       ; %bb.0:
 ; GFX10-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
 ; GFX10-NEXT:    v_mov_b32_e32 v1, s8
-; GFX10-NEXT:    s_addk_i32 s8, 0x400
-; GFX10-NEXT:    v_max_f32_e32 v2, v0, v0
-; GFX10-NEXT:    v_mov_b32_e32 v3, s8
-; GFX10-NEXT:    s_mov_b32 s8, 0
-; GFX10-NEXT:    buffer_load_dword v1, v1, s[4:7], 0 offen offset:1024
-; GFX10-NEXT:  .LBB1_1: ; %atomicrmw.start
-; GFX10-NEXT:    ; =>This Inner Loop Header: Depth=1
-; GFX10-NEXT:    s_waitcnt vmcnt(0)
-; GFX10-NEXT:    v_max_f32_e32 v0, v1, v1
 ; GFX10-NEXT:    s_waitcnt_vscnt null, 0x0
-; GFX10-NEXT:    v_max_f32_e32 v0, v0, v2
-; GFX10-NEXT:    v_mov_b32_e32 v5, v1
-; GFX10-NEXT:    v_mov_b32_e32 v4, v0
-; GFX10-NEXT:    buffer_atomic_cmpswap v[4:5], v3, s[4:7], 0 offen glc
-; GFX10-NEXT:    s_waitcnt vmcnt(0)
+; GFX10-NEXT:    buffer_atomic_fmax v0, v1, s[4:7], 0 offen offset:1024
+; GFX10-NEXT:    s_waitcnt_vscnt null, 0x0
 ; GFX10-NEXT:    buffer_gl1_inv
 ; GFX10-NEXT:    buffer_gl0_inv
-; GFX10-NEXT:    v_cmp_eq_u32_e32 vcc_lo, v4, v1
-; GFX10-NEXT:    v_mov_b32_e32 v1, v4
-; GFX10-NEXT:    s_or_b32 s8, vcc_lo, s8
-; GFX10-NEXT:    s_andn2_b32 exec_lo, exec_lo, s8
-; GFX10-NEXT:    s_cbranch_execnz .LBB1_1
-; GFX10-NEXT:  ; %bb.2: ; %atomicrmw.end
-; GFX10-NEXT:    s_or_b32 exec_lo, exec_lo, s8
 ; GFX10-NEXT:    s_setpc_b64 s[30:31]
 ;
 ; GFX90A-LABEL: buffer_fat_ptr_agent_atomic_fmax_noret_f32__offset:
@@ -502,57 +340,18 @@ define void @buffer_fat_ptr_agent_atomic_fmax_noret_f32__offset(ptr addrspace(7)
 ; GFX7:       ; %bb.0:
 ; GFX7-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
 ; GFX7-NEXT:    v_mov_b32_e32 v1, s8
-; GFX7-NEXT:    buffer_load_dword v1, v1, s[4:7], 0 offen offset:1024
-; GFX7-NEXT:    s_add_i32 s10, s8, 0x400
-; GFX7-NEXT:    s_mov_b64 s[8:9], 0
-; GFX7-NEXT:    v_mul_f32_e32 v2, 1.0, v0
-; GFX7-NEXT:    v_mov_b32_e32 v3, s10
-; GFX7-NEXT:  .LBB1_1: ; %atomicrmw.start
-; GFX7-NEXT:    ; =>This Inner Loop Header: Depth=1
-; GFX7-NEXT:    s_waitcnt vmcnt(0)
-; GFX7-NEXT:    v_mul_f32_e32 v0, 1.0, v1
-; GFX7-NEXT:    v_max_f32_e32 v0, v0, v2
-; GFX7-NEXT:    v_mov_b32_e32 v5, v1
-; GFX7-NEXT:    v_mov_b32_e32 v4, v0
-; GFX7-NEXT:    buffer_atomic_cmpswap v[4:5], v3, s[4:7], 0 offen glc
+; GFX7-NEXT:    buffer_atomic_fmax v0, v1, s[4:7], 0 offen offset:1024
 ; GFX7-NEXT:    s_waitcnt vmcnt(0)
 ; GFX7-NEXT:    buffer_wbinvl1
-; GFX7-NEXT:    v_cmp_eq_u32_e32 vcc, v4, v1
-; GFX7-NEXT:    s_or_b64 s[8:9], vcc, s[8:9]
-; GFX7-NEXT:    v_mov_b32_e32 v1, v4
-; GFX7-NEXT:    s_andn2_b64 exec, exec, s[8:9]
-; GFX7-NEXT:    s_cbranch_execnz .LBB1_1
-; GFX7-NEXT:  ; %bb.2: ; %atomicrmw.end
-; GFX7-NEXT:    s_or_b64 exec, exec, s[8:9]
 ; GFX7-NEXT:    s_setpc_b64 s[30:31]
 ;
 ; GFX6-LABEL: buffer_fat_ptr_agent_atomic_fmax_noret_f32__offset:
 ; GFX6:       ; %bb.0:
 ; GFX6-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
 ; GFX6-NEXT:    v_mov_b32_e32 v1, s8
-; GFX6-NEXT:    buffer_load_dword v1, v1, s[4:7], 0 offen offset:1024
-; GFX6-NEXT:    s_add_i32 s10, s8, 0x400
-; GFX6-NEXT:    s_mov_b64 s[8:9], 0
-; GFX6-NEXT:    v_mul_f32_e32 v2, 1.0, v0
-; GFX6-NEXT:    v_mov_b32_e32 v3, s10
-; GFX6-NEXT:  .LBB1_1: ; %atomicrmw.start
-; GFX6-NEXT:    ; =>This Inner Loop Header: Depth=1
-; GFX6-NEXT:    s_waitcnt vmcnt(0)
-; GFX6-NEXT:    v_mul_f32_e32 v0, 1.0, v1
-; GFX6-NEXT:    v_max_f32_e32 v0, v0, v2
-; GFX6-NEXT:    s_waitcnt expcnt(0)
-; GFX6-NEXT:    v_mov_b32_e32 v5, v1
-; GFX6-NEXT:    v_mov_b32_e32 v4, v0
-; GFX6-NEXT:    buffer_atomic_cmpswap v[4:5], v3, s[4:7], 0 offen glc
+; GFX6-NEXT:    buffer_atomic_fmax v0, v1, s[4:7], 0 offen offset:1024
 ; GFX6-NEXT:    s_waitcnt vmcnt(0)
 ; GFX6-NEXT:    buffer_wbinvl1
-; GFX6-NEXT:    v_cmp_eq_u32_e32 vcc, v4, v1
-; GFX6-NEXT:    s_or_b64 s[8:9], vcc, s[8:9]
-; GFX6-NEXT:    v_mov_b32_e32 v1, v4
-; GFX6-NEXT:    s_andn2_b64 exec, exec, s[8:9]
-; GFX6-NEXT:    s_cbranch_execnz .LBB1_1
-; GFX6-NEXT:  ; %bb.2: ; %atomicrmw.end
-; GFX6-NEXT:    s_or_b64 exec, exec, s[8:9]
 ; GFX6-NEXT:    s_waitcnt expcnt(0)
 ; GFX6-NEXT:    s_setpc_b64 s[30:31]
   %gep = getelementptr float, ptr addrspace(7) %ptr, i32 256
@@ -568,8 +367,8 @@ define float @buffer_fat_ptr_agent_atomic_fmax_ret_f32__offset__waterfall(ptr ad
 ; GFX12-NEXT:    s_wait_samplecnt 0x0
 ; GFX12-NEXT:    s_wait_bvhcnt 0x0
 ; GFX12-NEXT:    s_wait_kmcnt 0x0
-; GFX12-NEXT:    v_add_nc_u32_e32 v7, 0x400, v4
 ; GFX12-NEXT:    s_mov_b32 s1, exec_lo
+; GFX12-NEXT:    s_wait_storecnt 0x0
 ; GFX12-NEXT:  .LBB2_1: ; =>This Inner Loop Header: Depth=1
 ; GFX12-NEXT:    v_readfirstlane_b32 s4, v0
 ; GFX12-NEXT:    v_readfirstlane_b32 s5, v1
@@ -581,54 +380,17 @@ define float @buffer_fat_ptr_agent_atomic_fmax_ret_f32__offset__waterfall(ptr ad
 ; GFX12-NEXT:    s_delay_alu instid0(VALU_DEP_1) | instskip(NEXT) | instid1(SALU_CYCLE_1)
 ; GFX12-NEXT:    s_and_b32 s0, vcc_lo, s0
 ; GFX12-NEXT:    s_and_saveexec_b32 s0, s0
-; GFX12-NEXT:    buffer_load_b32 v6, v4, s[4:7], null offen offset:1024
+; GFX12-NEXT:    s_wait_loadcnt 0x0
+; GFX12-NEXT:    buffer_atomic_max_num_f32 v5, v4, s[4:7], null offen offset:1024 th:TH_ATOMIC_RETURN
+; GFX12-NEXT:    ; implicit-def: $vgpr0_vgpr1_vgpr2_vgpr3
 ; GFX12-NEXT:    ; implicit-def: $vgpr4
 ; GFX12-NEXT:    s_xor_b32 exec_lo, exec_lo, s0
 ; GFX12-NEXT:    s_cbranch_execnz .LBB2_1
 ; GFX12-NEXT:  ; %bb.2:
 ; GFX12-NEXT:    s_mov_b32 exec_lo, s1
-; GFX12-NEXT:    v_max_num_f32_e32 v8, v5, v5
-; GFX12-NEXT:    s_mov_b32 s1, 0
-; GFX12-NEXT:  .LBB2_3: ; %atomicrmw.start
-; GFX12-NEXT:    ; =>This Loop Header: Depth=1
-; GFX12-NEXT:    ; Child Loop BB2_4 Depth 2
 ; GFX12-NEXT:    s_wait_loadcnt 0x0
-; GFX12-NEXT:    v_max_num_f32_e32 v4, v6, v6
-; GFX12-NEXT:    s_mov_b32 s2, exec_lo
-; GFX12-NEXT:    s_wait_storecnt 0x0
-; GFX12-NEXT:    s_delay_alu instid0(VALU_DEP_1) | instskip(NEXT) | instid1(VALU_DEP_1)
-; GFX12-NEXT:    v_max_num_f32_e32 v5, v4, v8
-; GFX12-NEXT:    v_mov_b32_e32 v4, v5
-; GFX12-NEXT:    v_mov_b32_e32 v5, v6
-; GFX12-NEXT:  .LBB2_4: ; Parent Loop BB2_3 Depth=1
-; GFX12-NEXT:    ; => This Inner Loop Header: Depth=2
-; GFX12-NEXT:    v_readfirstlane_b32 s4, v0
-; GFX12-NEXT:    v_readfirstlane_b32 s5, v1
-; GFX12-NEXT:    v_readfirstlane_b32 s6, v2
-; GFX12-NEXT:    v_readfirstlane_b32 s7, v3
-; GFX12-NEXT:    s_delay_alu instid0(VALU_DEP_3) | instskip(NEXT) | instid1(VALU_DEP_2)
-; GFX12-NEXT:    v_cmp_eq_u64_e32 vcc_lo, s[4:5], v[0:1]
-; GFX12-NEXT:    v_cmp_eq_u64_e64 s0, s[6:7], v[2:3]
-; GFX12-NEXT:    s_delay_alu instid0(VALU_DEP_1) | instskip(NEXT) | instid1(SALU_CYCLE_1)
-; GFX12-NEXT:    s_and_b32 s0, vcc_lo, s0
-; GFX12-NEXT:    s_and_saveexec_b32 s0, s0
-; GFX12-NEXT:    s_wait_loadcnt 0x0
-; GFX12-NEXT:    buffer_atomic_cmpswap_b32 v[4:5], v7, s[4:7], null offen th:TH_ATOMIC_RETURN
-; GFX12-NEXT:    s_xor_b32 exec_lo, exec_lo, s0
-; GFX12-NEXT:    s_cbranch_execnz .LBB2_4
-; GFX12-NEXT:  ; %bb.5: ; in Loop: Header=BB2_3 Depth=1
-; GFX12-NEXT:    s_mov_b32 exec_lo, s2
-; GFX12-NEXT:    s_wait_loadcnt 0x0
-; GFX12-NEXT:    v_cmp_eq_u32_e32 vcc_lo, v4, v6
-; GFX12-NEXT:    v_mov_b32_e32 v6, v4
+; GFX12-NEXT:    v_mov_b32_e32 v0, v5
 ; GFX12-NEXT:    global_inv scope:SCOPE_DEV
-; GFX12-NEXT:    s_or_b32 s1, vcc_lo, s1
-; GFX12-NEXT:    s_delay_alu instid0(SALU_CYCLE_1)
-; GFX12-NEXT:    s_and_not1_b32 exec_lo, exec_lo, s1
-; GFX12-NEXT:    s_cbranch_execnz .LBB2_3
-; GFX12-NEXT:  ; %bb.6: ; %atomicrmw.end
-; GFX12-NEXT:    s_or_b32 exec_lo, exec_lo, s1
-; GFX12-NEXT:    v_mov_b32_e32 v0, v4
 ; GFX12-NEXT:    s_setpc_b64 s[30:31]
 ;
 ; GFX940-LABEL: buffer_fat_ptr_agent_atomic_fmax_ret_f32__offset__waterfall:
@@ -695,9 +457,8 @@ define float @buffer_fat_ptr_agent_atomic_fmax_ret_f32__offset__waterfall(ptr...
[truncated]

arsenm · 2024-06-23T08:06:32Z

Merge activity

Jun 23, 4:06 AM EDT: @arsenm started a stack merge that includes this pull request via Graphite.
Jun 23, 4:11 AM EDT: Graphite rebased this pull request as part of a merge.
Jun 23, 4:13 AM EDT: @arsenm merged this pull request with Graphite.

llvm-ci · 2024-06-23T08:47:59Z

LLVM Buildbot has detected a new failure on builder sanitizer-ppc64be-linux running on ppc64be-sanitizer while building llvm at step 2 "annotate".

Full details are available at: https://lab.llvm.org/buildbot/#/builders/109/builds/274

Here is the relevant piece of the build log for the reference:

Step 2 (annotate) failure: 'python ../sanitizer_buildbot/sanitizers/zorg/buildbot/builders/sanitizers/buildbot_selector.py' (failure)
...
PASS: ThreadSanitizer-powerpc64 :: write_in_reader_lock.cpp (284 of 2421)
PASS: ScudoStandalone-Unit :: ./ScudoUnitTest-powerpc64-Test/139/267 (285 of 2421)
PASS: ThreadSanitizer-powerpc64 :: global_race2.cpp (286 of 2421)
PASS: ThreadSanitizer-powerpc64 :: print_full_thread_history.cpp (287 of 2421)
XFAIL: SanitizerCommon-tsan-powerpc64-Linux :: Posix/sanitizer_set_report_fd_test.cpp (288 of 2421)
PASS: SanitizerCommon-msan-powerpc64-Linux :: Linux/new_delete_test.cpp (289 of 2421)
PASS: ThreadSanitizer-powerpc64 :: mop_with_offset2.cpp (290 of 2421)
PASS: ThreadSanitizer-powerpc64 :: suppressions_race2.cpp (291 of 2421)
PASS: ThreadSanitizer-powerpc64 :: mutex_held_wrong_context.cpp (292 of 2421)
PASS: SanitizerCommon-msan-powerpc64-Linux :: Posix/dedup_token_length_test.cpp (293 of 2421)
FAIL: ThreadSanitizer-powerpc64 :: signal_block.cpp (294 of 2421)
******************** TEST 'ThreadSanitizer-powerpc64 :: signal_block.cpp' FAILED ********************
Exit Code: 1

Command Output (stderr):
--
RUN: at line 1: /home/buildbots/llvm-external-buildbots/workers/ppc64be-sanitizer/sanitizer-ppc64be/build/build_debug/./bin/clang  -fsanitize=thread -Wall  -m64   -gline-tables-only -I/home/buildbots/llvm-external-buildbots/workers/ppc64be-sanitizer/sanitizer-ppc64be/build/llvm-project/compiler-rt/test/tsan/../ -O1 /home/buildbots/llvm-external-buildbots/workers/ppc64be-sanitizer/sanitizer-ppc64be/build/llvm-project/compiler-rt/test/tsan/signal_block.cpp -o /home/buildbots/llvm-external-buildbots/workers/ppc64be-sanitizer/sanitizer-ppc64be/build/build_debug/runtimes/runtimes-bins/compiler-rt/test/tsan/POWERPC64Config/Output/signal_block.cpp.tmp &&  /home/buildbots/llvm-external-buildbots/workers/ppc64be-sanitizer/sanitizer-ppc64be/build/build_debug/runtimes/runtimes-bins/compiler-rt/test/tsan/POWERPC64Config/Output/signal_block.cpp.tmp 2>&1 | FileCheck /home/buildbots/llvm-external-buildbots/workers/ppc64be-sanitizer/sanitizer-ppc64be/build/llvm-project/compiler-rt/test/tsan/signal_block.cpp
+ /home/buildbots/llvm-external-buildbots/workers/ppc64be-sanitizer/sanitizer-ppc64be/build/build_debug/./bin/clang -fsanitize=thread -Wall -m64 -gline-tables-only -I/home/buildbots/llvm-external-buildbots/workers/ppc64be-sanitizer/sanitizer-ppc64be/build/llvm-project/compiler-rt/test/tsan/../ -O1 /home/buildbots/llvm-external-buildbots/workers/ppc64be-sanitizer/sanitizer-ppc64be/build/llvm-project/compiler-rt/test/tsan/signal_block.cpp -o /home/buildbots/llvm-external-buildbots/workers/ppc64be-sanitizer/sanitizer-ppc64be/build/build_debug/runtimes/runtimes-bins/compiler-rt/test/tsan/POWERPC64Config/Output/signal_block.cpp.tmp
+ /home/buildbots/llvm-external-buildbots/workers/ppc64be-sanitizer/sanitizer-ppc64be/build/build_debug/runtimes/runtimes-bins/compiler-rt/test/tsan/POWERPC64Config/Output/signal_block.cpp.tmp
+ FileCheck /home/buildbots/llvm-external-buildbots/workers/ppc64be-sanitizer/sanitizer-ppc64be/build/llvm-project/compiler-rt/test/tsan/signal_block.cpp
/home/buildbots/llvm-external-buildbots/workers/ppc64be-sanitizer/sanitizer-ppc64be/build/llvm-project/compiler-rt/test/tsan/signal_block.cpp:59:15: error: CHECK-NOT: excluded string found in input
// CHECK-NOT: WARNING: ThreadSanitizer:
              ^
<stdin>:2:1: note: found here
WARNING: ThreadSanitizer: signal handler spoils errno (pid=133804)
^~~~~~~~~~~~~~~~~~~~~~~~~

Input file: <stdin>
Check file: /home/buildbots/llvm-external-buildbots/workers/ppc64be-sanitizer/sanitizer-ppc64be/build/llvm-project/compiler-rt/test/tsan/signal_block.cpp

-dump-input=help explains the following input dump.

Input was:
<<<<<<
        1: ================== 
        2: WARNING: ThreadSanitizer: signal handler spoils errno (pid=133804) 
not:59     !~~~~~~~~~~~~~~~~~~~~~~~~                                           error: no match expected
        3:  Signal 10 handler invoked at: 
        4:  #0 _DYNAMIC <null> (signal_block.cpp.tmp+0x16fe00) 
        5:  #1 thread(void*) /home/buildbots/llvm-external-buildbots/workers/ppc64be-sanitizer/sanitizer-ppc64be/build/llvm-project/compiler-rt/test/tsan/signal_block.cpp:25:5 (signal_block.cpp.tmp+0x11ce0c) 
        6:  
        7: SUMMARY: ThreadSanitizer: signal handler spoils errno (/home/buildbots/llvm-external-buildbots/workers/ppc64be-sanitizer/sanitizer-ppc64be/build/build_debug/runtimes/runtimes-bins/compiler-rt/test/tsan/POWERPC64Config/Output/signal_block.cpp.tmp+0x16fe00) in _DYNAMIC 
        8: ================== 
        9: DONE 
       10: ThreadSanitizer: reported 1 warnings 
>>>>>>

--

Step 11 (test compiler-rt debug) failure: test compiler-rt debug (failure)
...
PASS: ThreadSanitizer-powerpc64 :: write_in_reader_lock.cpp (284 of 2421)
PASS: ScudoStandalone-Unit :: ./ScudoUnitTest-powerpc64-Test/139/267 (285 of 2421)
PASS: ThreadSanitizer-powerpc64 :: global_race2.cpp (286 of 2421)
PASS: ThreadSanitizer-powerpc64 :: print_full_thread_history.cpp (287 of 2421)
XFAIL: SanitizerCommon-tsan-powerpc64-Linux :: Posix/sanitizer_set_report_fd_test.cpp (288 of 2421)
PASS: SanitizerCommon-msan-powerpc64-Linux :: Linux/new_delete_test.cpp (289 of 2421)
PASS: ThreadSanitizer-powerpc64 :: mop_with_offset2.cpp (290 of 2421)
PASS: ThreadSanitizer-powerpc64 :: suppressions_race2.cpp (291 of 2421)
PASS: ThreadSanitizer-powerpc64 :: mutex_held_wrong_context.cpp (292 of 2421)
PASS: SanitizerCommon-msan-powerpc64-Linux :: Posix/dedup_token_length_test.cpp (293 of 2421)
FAIL: ThreadSanitizer-powerpc64 :: signal_block.cpp (294 of 2421)
******************** TEST 'ThreadSanitizer-powerpc64 :: signal_block.cpp' FAILED ********************
Exit Code: 1

Command Output (stderr):
--
RUN: at line 1: /home/buildbots/llvm-external-buildbots/workers/ppc64be-sanitizer/sanitizer-ppc64be/build/build_debug/./bin/clang  -fsanitize=thread -Wall  -m64   -gline-tables-only -I/home/buildbots/llvm-external-buildbots/workers/ppc64be-sanitizer/sanitizer-ppc64be/build/llvm-project/compiler-rt/test/tsan/../ -O1 /home/buildbots/llvm-external-buildbots/workers/ppc64be-sanitizer/sanitizer-ppc64be/build/llvm-project/compiler-rt/test/tsan/signal_block.cpp -o /home/buildbots/llvm-external-buildbots/workers/ppc64be-sanitizer/sanitizer-ppc64be/build/build_debug/runtimes/runtimes-bins/compiler-rt/test/tsan/POWERPC64Config/Output/signal_block.cpp.tmp &&  /home/buildbots/llvm-external-buildbots/workers/ppc64be-sanitizer/sanitizer-ppc64be/build/build_debug/runtimes/runtimes-bins/compiler-rt/test/tsan/POWERPC64Config/Output/signal_block.cpp.tmp 2>&1 | FileCheck /home/buildbots/llvm-external-buildbots/workers/ppc64be-sanitizer/sanitizer-ppc64be/build/llvm-project/compiler-rt/test/tsan/signal_block.cpp
+ /home/buildbots/llvm-external-buildbots/workers/ppc64be-sanitizer/sanitizer-ppc64be/build/build_debug/./bin/clang -fsanitize=thread -Wall -m64 -gline-tables-only -I/home/buildbots/llvm-external-buildbots/workers/ppc64be-sanitizer/sanitizer-ppc64be/build/llvm-project/compiler-rt/test/tsan/../ -O1 /home/buildbots/llvm-external-buildbots/workers/ppc64be-sanitizer/sanitizer-ppc64be/build/llvm-project/compiler-rt/test/tsan/signal_block.cpp -o /home/buildbots/llvm-external-buildbots/workers/ppc64be-sanitizer/sanitizer-ppc64be/build/build_debug/runtimes/runtimes-bins/compiler-rt/test/tsan/POWERPC64Config/Output/signal_block.cpp.tmp
+ /home/buildbots/llvm-external-buildbots/workers/ppc64be-sanitizer/sanitizer-ppc64be/build/build_debug/runtimes/runtimes-bins/compiler-rt/test/tsan/POWERPC64Config/Output/signal_block.cpp.tmp
+ FileCheck /home/buildbots/llvm-external-buildbots/workers/ppc64be-sanitizer/sanitizer-ppc64be/build/llvm-project/compiler-rt/test/tsan/signal_block.cpp
/home/buildbots/llvm-external-buildbots/workers/ppc64be-sanitizer/sanitizer-ppc64be/build/llvm-project/compiler-rt/test/tsan/signal_block.cpp:59:15: error: CHECK-NOT: excluded string found in input
// CHECK-NOT: WARNING: ThreadSanitizer:
              ^
<stdin>:2:1: note: found here
WARNING: ThreadSanitizer: signal handler spoils errno (pid=133804)
^~~~~~~~~~~~~~~~~~~~~~~~~

Input file: <stdin>
Check file: /home/buildbots/llvm-external-buildbots/workers/ppc64be-sanitizer/sanitizer-ppc64be/build/llvm-project/compiler-rt/test/tsan/signal_block.cpp

-dump-input=help explains the following input dump.

Input was:
<<<<<<
        1: ================== 
        2: WARNING: ThreadSanitizer: signal handler spoils errno (pid=133804) 
not:59     !~~~~~~~~~~~~~~~~~~~~~~~~                                           error: no match expected
        3:  Signal 10 handler invoked at: 
        4:  #0 _DYNAMIC <null> (signal_block.cpp.tmp+0x16fe00) 
        5:  #1 thread(void*) /home/buildbots/llvm-external-buildbots/workers/ppc64be-sanitizer/sanitizer-ppc64be/build/llvm-project/compiler-rt/test/tsan/signal_block.cpp:25:5 (signal_block.cpp.tmp+0x11ce0c) 
        6:  
        7: SUMMARY: ThreadSanitizer: signal handler spoils errno (/home/buildbots/llvm-external-buildbots/workers/ppc64be-sanitizer/sanitizer-ppc64be/build/build_debug/runtimes/runtimes-bins/compiler-rt/test/tsan/POWERPC64Config/Output/signal_block.cpp.tmp+0x16fe00) in _DYNAMIC 
        8: ================== 
        9: DONE 
       10: ThreadSanitizer: reported 1 warnings 
>>>>>>

--

arsenm · 2024-06-23T08:59:02Z

LLVM Buildbot has detected a new failure on builder sanitizer-ppc64be-linux running on ppc64be-sanitizer while building llvm at step 2 "annotate".

Full details are available at: https://lab.llvm.org/buildbot/#/builders/109/builds/274

Not it

…95593)

This was referenced Jun 14, 2024

AMDGPU: Support local atomicrmw fmin/fmax for float/double #95590

Merged

AMDGPU: Create pseudo to real mapping for flat/buffer atomic fmin/fmax #95591

Merged

arsenm mentioned this pull request Jun 14, 2024

AMDGPU: Start selecting flat/global atomicrmw fmin/fmax. #95592

Merged

arsenm added the backend:AMDGPU label Jun 14, 2024 — with Graphite App

arsenm requested review from kosarev, mariusz-sikora-at-amd, piotrAMD, rampitec, rovka, shiltian, Sisyph and krzysz00 June 14, 2024 19:38

arsenm marked this pull request as ready for review June 14, 2024 19:38

krzysz00 approved these changes Jun 14, 2024

View reviewed changes

arsenm force-pushed the users/arsenm/amdgpu-select-flat-global-atomicrmw-fmin-fmax branch from 7396f87 to 5e389ee Compare June 17, 2024 17:56

arsenm force-pushed the users/arsenm/amdgpu-select-buffer-atomicrmw-fmin-fmax branch from f47b66a to 694f273 Compare June 17, 2024 17:56

arsenm force-pushed the users/arsenm/amdgpu-select-flat-global-atomicrmw-fmin-fmax branch from 5e389ee to f661aa1 Compare June 18, 2024 06:40

arsenm force-pushed the users/arsenm/amdgpu-select-buffer-atomicrmw-fmin-fmax branch from 694f273 to 12f8d7f Compare June 18, 2024 06:40

arsenm force-pushed the users/arsenm/amdgpu-select-flat-global-atomicrmw-fmin-fmax branch from f661aa1 to b85a15a Compare June 18, 2024 12:48

arsenm force-pushed the users/arsenm/amdgpu-select-buffer-atomicrmw-fmin-fmax branch from 12f8d7f to c2c6093 Compare June 18, 2024 12:48

arsenm force-pushed the users/arsenm/amdgpu-select-flat-global-atomicrmw-fmin-fmax branch from b85a15a to 230ddd2 Compare June 18, 2024 16:50

arsenm force-pushed the users/arsenm/amdgpu-select-buffer-atomicrmw-fmin-fmax branch from c2c6093 to 3eba246 Compare June 18, 2024 16:51

arsenm force-pushed the users/arsenm/amdgpu-select-flat-global-atomicrmw-fmin-fmax branch from 230ddd2 to 5853be5 Compare June 19, 2024 05:11

arsenm force-pushed the users/arsenm/amdgpu-select-buffer-atomicrmw-fmin-fmax branch from 3eba246 to 26bdea6 Compare June 19, 2024 05:12

arsenm force-pushed the users/arsenm/amdgpu-select-flat-global-atomicrmw-fmin-fmax branch from 5853be5 to 58b72f3 Compare June 21, 2024 18:44

arsenm force-pushed the users/arsenm/amdgpu-select-buffer-atomicrmw-fmin-fmax branch from 26bdea6 to 26d95dc Compare June 21, 2024 18:53

arsenm force-pushed the users/arsenm/amdgpu-select-flat-global-atomicrmw-fmin-fmax branch from 58b72f3 to d61d35a Compare June 21, 2024 21:53

arsenm force-pushed the users/arsenm/amdgpu-select-buffer-atomicrmw-fmin-fmax branch from 26d95dc to 1d2a548 Compare June 21, 2024 21:53

arsenm force-pushed the users/arsenm/amdgpu-select-flat-global-atomicrmw-fmin-fmax branch from d61d35a to ff38a3c Compare June 23, 2024 08:08

Base automatically changed from users/arsenm/amdgpu-select-flat-global-atomicrmw-fmin-fmax to main June 23, 2024 08:10

AMDGPU: Start selecting buffer fat pointer atomicrmw fmin/fmax

380b019

arsenm force-pushed the users/arsenm/amdgpu-select-buffer-atomicrmw-fmin-fmax branch from 1d2a548 to 380b019 Compare June 23, 2024 08:11

arsenm merged commit 414c741 into main Jun 23, 2024
4 of 7 checks passed

arsenm deleted the users/arsenm/amdgpu-select-buffer-atomicrmw-fmin-fmax branch June 23, 2024 08:13

AlexisPerry pushed a commit to llvm-project-tlp/llvm-project that referenced this pull request Jul 9, 2024

AMDGPU: Start selecting buffer fat pointer atomicrmw fmin/fmax (llvm#…

1ecdb47

…95593)

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

AMDGPU: Start selecting buffer fat pointer atomicrmw fmin/fmax #95593

AMDGPU: Start selecting buffer fat pointer atomicrmw fmin/fmax #95593

Uh oh!

arsenm commented Jun 14, 2024

Uh oh!

arsenm commented Jun 14, 2024 •

edited

Loading

Uh oh!

llvmbot commented Jun 14, 2024

Uh oh!

arsenm commented Jun 23, 2024 •

edited

Loading

Uh oh!

Uh oh!

llvm-ci commented Jun 23, 2024

Uh oh!

arsenm commented Jun 23, 2024

Uh oh!

Uh oh!

AMDGPU: Start selecting buffer fat pointer atomicrmw fmin/fmax #95593

AMDGPU: Start selecting buffer fat pointer atomicrmw fmin/fmax #95593

Uh oh!

Conversation

arsenm commented Jun 14, 2024

Uh oh!

arsenm commented Jun 14, 2024 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

llvmbot commented Jun 14, 2024

Uh oh!

arsenm commented Jun 23, 2024 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Merge activity

Uh oh!

Uh oh!

llvm-ci commented Jun 23, 2024

Uh oh!

arsenm commented Jun 23, 2024

Uh oh!

Uh oh!

arsenm commented Jun 14, 2024 •

edited

Loading

arsenm commented Jun 23, 2024 •

edited

Loading