[llvm] AMDGPU: Add tests for atomicrmw handling of new metadata (PR #89248)
via llvm-commits
llvm-commits at lists.llvm.org
Thu Apr 18 08:21:10 PDT 2024
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-backend-amdgpu
Author: Matt Arsenault (arsenm)
<details>
<summary>Changes</summary>
Add baseline tests which should comprehensively test the new atomic metadata. Test codegen / expansion, and preservation in a few transforms.
New metadata defined in #<!-- -->85052
---
Patch is 1.49 MiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/89248.diff
16 Files Affected:
- (modified) llvm/test/CodeGen/AMDGPU/flat_atomics_i32_system.ll (+1744-417)
- (modified) llvm/test/CodeGen/AMDGPU/flat_atomics_i64_system.ll (+1875-393)
- (modified) llvm/test/CodeGen/AMDGPU/global_atomics_i32_system.ll (+1918-463)
- (modified) llvm/test/CodeGen/AMDGPU/global_atomics_i64_system.ll (+1961-367)
- (modified) llvm/test/CodeGen/AMDGPU/global_atomics_scan_fadd.ll (+741)
- (modified) llvm/test/CodeGen/AMDGPU/global_atomics_scan_fmax.ll (+672)
- (modified) llvm/test/CodeGen/AMDGPU/global_atomics_scan_fmin.ll (+671)
- (added) llvm/test/Transforms/AtomicExpand/AMDGPU/expand-atomic-f32-system.ll (+3717)
- (added) llvm/test/Transforms/AtomicExpand/AMDGPU/expand-atomic-f64-system.ll (+1685)
- (added) llvm/test/Transforms/AtomicExpand/AMDGPU/expand-atomic-i32-system.ll (+828)
- (added) llvm/test/Transforms/AtomicExpand/AMDGPU/expand-atomic-i64-system.ll (+828)
- (added) llvm/test/Transforms/AtomicExpand/AMDGPU/expand-atomic-v2bf16-system.ll (+859)
- (added) llvm/test/Transforms/AtomicExpand/AMDGPU/expand-atomic-v2f16-system.ll (+859)
- (modified) llvm/test/Transforms/AtomicExpand/AMDGPU/expand-atomicrmw-integer-ops-0-to-add-0.ll (+10)
- (modified) llvm/test/Transforms/InferAddressSpaces/AMDGPU/basic.ll (+10)
- (added) llvm/test/Transforms/Inline/AMDGPU/inline-atomicrmw-md-preserve.ll (+30)
``````````diff
diff --git a/llvm/test/CodeGen/AMDGPU/flat_atomics_i32_system.ll b/llvm/test/CodeGen/AMDGPU/flat_atomics_i32_system.ll
index 94956511c39dfb..961273468e75ff 100644
--- a/llvm/test/CodeGen/AMDGPU/flat_atomics_i32_system.ll
+++ b/llvm/test/CodeGen/AMDGPU/flat_atomics_i32_system.ll
@@ -287,6 +287,72 @@ define amdgpu_gfx i32 @flat_atomic_xchg_i32_ret_offset_scalar(ptr inreg %out, i3
ret i32 %result
}
+define void @flat_atomic_xchg_i32_noret_offset__amdgpu_no_remote_memory_access(ptr %out, i32 %in) {
+; GCN1-LABEL: flat_atomic_xchg_i32_noret_offset__amdgpu_no_remote_memory_access:
+; GCN1: ; %bb.0:
+; GCN1-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GCN1-NEXT: v_add_i32_e32 v0, vcc, 16, v0
+; GCN1-NEXT: v_addc_u32_e32 v1, vcc, 0, v1, vcc
+; GCN1-NEXT: flat_atomic_swap v[0:1], v2
+; GCN1-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
+; GCN1-NEXT: buffer_wbinvl1_vol
+; GCN1-NEXT: s_setpc_b64 s[30:31]
+;
+; GCN2-LABEL: flat_atomic_xchg_i32_noret_offset__amdgpu_no_remote_memory_access:
+; GCN2: ; %bb.0:
+; GCN2-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GCN2-NEXT: v_add_u32_e32 v0, vcc, 16, v0
+; GCN2-NEXT: v_addc_u32_e32 v1, vcc, 0, v1, vcc
+; GCN2-NEXT: flat_atomic_swap v[0:1], v2
+; GCN2-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
+; GCN2-NEXT: buffer_wbinvl1_vol
+; GCN2-NEXT: s_setpc_b64 s[30:31]
+;
+; GCN3-LABEL: flat_atomic_xchg_i32_noret_offset__amdgpu_no_remote_memory_access:
+; GCN3: ; %bb.0:
+; GCN3-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GCN3-NEXT: flat_atomic_swap v[0:1], v2 offset:16
+; GCN3-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
+; GCN3-NEXT: buffer_wbinvl1_vol
+; GCN3-NEXT: s_setpc_b64 s[30:31]
+ %gep = getelementptr i32, ptr %out, i64 4
+ %tmp0 = atomicrmw xchg ptr %gep, i32 %in seq_cst, !amdgpu.no.remote.memory.access !0
+ ret void
+}
+
+define i32 @flat_atomic_xchg_i32_ret_offset__amdgpu_no_remote_memory_access(ptr %out, i32 %in) {
+; GCN1-LABEL: flat_atomic_xchg_i32_ret_offset__amdgpu_no_remote_memory_access:
+; GCN1: ; %bb.0:
+; GCN1-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GCN1-NEXT: v_add_i32_e32 v0, vcc, 16, v0
+; GCN1-NEXT: v_addc_u32_e32 v1, vcc, 0, v1, vcc
+; GCN1-NEXT: flat_atomic_swap v0, v[0:1], v2 glc
+; GCN1-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
+; GCN1-NEXT: buffer_wbinvl1_vol
+; GCN1-NEXT: s_setpc_b64 s[30:31]
+;
+; GCN2-LABEL: flat_atomic_xchg_i32_ret_offset__amdgpu_no_remote_memory_access:
+; GCN2: ; %bb.0:
+; GCN2-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GCN2-NEXT: v_add_u32_e32 v0, vcc, 16, v0
+; GCN2-NEXT: v_addc_u32_e32 v1, vcc, 0, v1, vcc
+; GCN2-NEXT: flat_atomic_swap v0, v[0:1], v2 glc
+; GCN2-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
+; GCN2-NEXT: buffer_wbinvl1_vol
+; GCN2-NEXT: s_setpc_b64 s[30:31]
+;
+; GCN3-LABEL: flat_atomic_xchg_i32_ret_offset__amdgpu_no_remote_memory_access:
+; GCN3: ; %bb.0:
+; GCN3-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GCN3-NEXT: flat_atomic_swap v0, v[0:1], v2 offset:16 glc
+; GCN3-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
+; GCN3-NEXT: buffer_wbinvl1_vol
+; GCN3-NEXT: s_setpc_b64 s[30:31]
+ %gep = getelementptr i32, ptr %out, i64 4
+ %result = atomicrmw xchg ptr %gep, i32 %in seq_cst, !amdgpu.no.remote.memory.access !0
+ ret i32 %result
+}
+
; ---------------------------------------------------------------------
; atomicrmw xchg f32
; ---------------------------------------------------------------------
@@ -571,6 +637,72 @@ define amdgpu_gfx float @flat_atomic_xchg_f32_ret_offset_scalar(ptr inreg %out,
ret float %result
}
+define void @flat_atomic_xchg_f32_noret_offset__amdgpu_no_remote_memory_access(ptr %out, float %in) {
+; GCN1-LABEL: flat_atomic_xchg_f32_noret_offset__amdgpu_no_remote_memory_access:
+; GCN1: ; %bb.0:
+; GCN1-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GCN1-NEXT: v_add_i32_e32 v0, vcc, 16, v0
+; GCN1-NEXT: v_addc_u32_e32 v1, vcc, 0, v1, vcc
+; GCN1-NEXT: flat_atomic_swap v[0:1], v2
+; GCN1-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
+; GCN1-NEXT: buffer_wbinvl1_vol
+; GCN1-NEXT: s_setpc_b64 s[30:31]
+;
+; GCN2-LABEL: flat_atomic_xchg_f32_noret_offset__amdgpu_no_remote_memory_access:
+; GCN2: ; %bb.0:
+; GCN2-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GCN2-NEXT: v_add_u32_e32 v0, vcc, 16, v0
+; GCN2-NEXT: v_addc_u32_e32 v1, vcc, 0, v1, vcc
+; GCN2-NEXT: flat_atomic_swap v[0:1], v2
+; GCN2-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
+; GCN2-NEXT: buffer_wbinvl1_vol
+; GCN2-NEXT: s_setpc_b64 s[30:31]
+;
+; GCN3-LABEL: flat_atomic_xchg_f32_noret_offset__amdgpu_no_remote_memory_access:
+; GCN3: ; %bb.0:
+; GCN3-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GCN3-NEXT: flat_atomic_swap v[0:1], v2 offset:16
+; GCN3-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
+; GCN3-NEXT: buffer_wbinvl1_vol
+; GCN3-NEXT: s_setpc_b64 s[30:31]
+ %gep = getelementptr float, ptr %out, i64 4
+ %tmp0 = atomicrmw xchg ptr %gep, float %in seq_cst, !amdgpu.no.remote.memory.access !0
+ ret void
+}
+
+define float @flat_atomic_xchg_f32_ret_offset__amdgpu_no_remote_memory_access(ptr %out, float %in) {
+; GCN1-LABEL: flat_atomic_xchg_f32_ret_offset__amdgpu_no_remote_memory_access:
+; GCN1: ; %bb.0:
+; GCN1-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GCN1-NEXT: v_add_i32_e32 v0, vcc, 16, v0
+; GCN1-NEXT: v_addc_u32_e32 v1, vcc, 0, v1, vcc
+; GCN1-NEXT: flat_atomic_swap v0, v[0:1], v2 glc
+; GCN1-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
+; GCN1-NEXT: buffer_wbinvl1_vol
+; GCN1-NEXT: s_setpc_b64 s[30:31]
+;
+; GCN2-LABEL: flat_atomic_xchg_f32_ret_offset__amdgpu_no_remote_memory_access:
+; GCN2: ; %bb.0:
+; GCN2-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GCN2-NEXT: v_add_u32_e32 v0, vcc, 16, v0
+; GCN2-NEXT: v_addc_u32_e32 v1, vcc, 0, v1, vcc
+; GCN2-NEXT: flat_atomic_swap v0, v[0:1], v2 glc
+; GCN2-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
+; GCN2-NEXT: buffer_wbinvl1_vol
+; GCN2-NEXT: s_setpc_b64 s[30:31]
+;
+; GCN3-LABEL: flat_atomic_xchg_f32_ret_offset__amdgpu_no_remote_memory_access:
+; GCN3: ; %bb.0:
+; GCN3-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GCN3-NEXT: flat_atomic_swap v0, v[0:1], v2 offset:16 glc
+; GCN3-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
+; GCN3-NEXT: buffer_wbinvl1_vol
+; GCN3-NEXT: s_setpc_b64 s[30:31]
+ %gep = getelementptr float, ptr %out, i64 4
+ %result = atomicrmw xchg ptr %gep, float %in seq_cst, !amdgpu.no.remote.memory.access !0
+ ret float %result
+}
+
; ---------------------------------------------------------------------
; atomicrmw add
; ---------------------------------------------------------------------
@@ -855,6 +987,72 @@ define amdgpu_gfx i32 @flat_atomic_add_i32_ret_offset_scalar(ptr inreg %out, i32
ret i32 %result
}
+define void @flat_atomic_add_i32_noret_offset__amdgpu_no_remote_memory_access(ptr %out, i32 %in) {
+; GCN1-LABEL: flat_atomic_add_i32_noret_offset__amdgpu_no_remote_memory_access:
+; GCN1: ; %bb.0:
+; GCN1-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GCN1-NEXT: v_add_i32_e32 v0, vcc, 16, v0
+; GCN1-NEXT: v_addc_u32_e32 v1, vcc, 0, v1, vcc
+; GCN1-NEXT: flat_atomic_add v[0:1], v2
+; GCN1-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
+; GCN1-NEXT: buffer_wbinvl1_vol
+; GCN1-NEXT: s_setpc_b64 s[30:31]
+;
+; GCN2-LABEL: flat_atomic_add_i32_noret_offset__amdgpu_no_remote_memory_access:
+; GCN2: ; %bb.0:
+; GCN2-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GCN2-NEXT: v_add_u32_e32 v0, vcc, 16, v0
+; GCN2-NEXT: v_addc_u32_e32 v1, vcc, 0, v1, vcc
+; GCN2-NEXT: flat_atomic_add v[0:1], v2
+; GCN2-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
+; GCN2-NEXT: buffer_wbinvl1_vol
+; GCN2-NEXT: s_setpc_b64 s[30:31]
+;
+; GCN3-LABEL: flat_atomic_add_i32_noret_offset__amdgpu_no_remote_memory_access:
+; GCN3: ; %bb.0:
+; GCN3-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GCN3-NEXT: flat_atomic_add v[0:1], v2 offset:16
+; GCN3-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
+; GCN3-NEXT: buffer_wbinvl1_vol
+; GCN3-NEXT: s_setpc_b64 s[30:31]
+ %gep = getelementptr i32, ptr %out, i64 4
+ %tmp0 = atomicrmw add ptr %gep, i32 %in seq_cst, !amdgpu.no.remote.memory.access !0
+ ret void
+}
+
+define i32 @flat_atomic_add_i32_ret_offset__amdgpu_no_remote_memory_access(ptr %out, i32 %in) {
+; GCN1-LABEL: flat_atomic_add_i32_ret_offset__amdgpu_no_remote_memory_access:
+; GCN1: ; %bb.0:
+; GCN1-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GCN1-NEXT: v_add_i32_e32 v0, vcc, 16, v0
+; GCN1-NEXT: v_addc_u32_e32 v1, vcc, 0, v1, vcc
+; GCN1-NEXT: flat_atomic_add v0, v[0:1], v2 glc
+; GCN1-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
+; GCN1-NEXT: buffer_wbinvl1_vol
+; GCN1-NEXT: s_setpc_b64 s[30:31]
+;
+; GCN2-LABEL: flat_atomic_add_i32_ret_offset__amdgpu_no_remote_memory_access:
+; GCN2: ; %bb.0:
+; GCN2-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GCN2-NEXT: v_add_u32_e32 v0, vcc, 16, v0
+; GCN2-NEXT: v_addc_u32_e32 v1, vcc, 0, v1, vcc
+; GCN2-NEXT: flat_atomic_add v0, v[0:1], v2 glc
+; GCN2-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
+; GCN2-NEXT: buffer_wbinvl1_vol
+; GCN2-NEXT: s_setpc_b64 s[30:31]
+;
+; GCN3-LABEL: flat_atomic_add_i32_ret_offset__amdgpu_no_remote_memory_access:
+; GCN3: ; %bb.0:
+; GCN3-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GCN3-NEXT: flat_atomic_add v0, v[0:1], v2 offset:16 glc
+; GCN3-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
+; GCN3-NEXT: buffer_wbinvl1_vol
+; GCN3-NEXT: s_setpc_b64 s[30:31]
+ %gep = getelementptr i32, ptr %out, i64 4
+ %result = atomicrmw add ptr %gep, i32 %in seq_cst, !amdgpu.no.remote.memory.access !0
+ ret i32 %result
+}
+
; ---------------------------------------------------------------------
; atomicrmw sub
; ---------------------------------------------------------------------
@@ -1139,6 +1337,72 @@ define amdgpu_gfx i32 @flat_atomic_sub_i32_ret_offset_scalar(ptr inreg %out, i32
ret i32 %result
}
+define void @flat_atomic_sub_i32_noret_offset__amdgpu_no_remote_memory_access(ptr %out, i32 %in) {
+; GCN1-LABEL: flat_atomic_sub_i32_noret_offset__amdgpu_no_remote_memory_access:
+; GCN1: ; %bb.0:
+; GCN1-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GCN1-NEXT: v_add_i32_e32 v0, vcc, 16, v0
+; GCN1-NEXT: v_addc_u32_e32 v1, vcc, 0, v1, vcc
+; GCN1-NEXT: flat_atomic_sub v[0:1], v2
+; GCN1-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
+; GCN1-NEXT: buffer_wbinvl1_vol
+; GCN1-NEXT: s_setpc_b64 s[30:31]
+;
+; GCN2-LABEL: flat_atomic_sub_i32_noret_offset__amdgpu_no_remote_memory_access:
+; GCN2: ; %bb.0:
+; GCN2-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GCN2-NEXT: v_add_u32_e32 v0, vcc, 16, v0
+; GCN2-NEXT: v_addc_u32_e32 v1, vcc, 0, v1, vcc
+; GCN2-NEXT: flat_atomic_sub v[0:1], v2
+; GCN2-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
+; GCN2-NEXT: buffer_wbinvl1_vol
+; GCN2-NEXT: s_setpc_b64 s[30:31]
+;
+; GCN3-LABEL: flat_atomic_sub_i32_noret_offset__amdgpu_no_remote_memory_access:
+; GCN3: ; %bb.0:
+; GCN3-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GCN3-NEXT: flat_atomic_sub v[0:1], v2 offset:16
+; GCN3-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
+; GCN3-NEXT: buffer_wbinvl1_vol
+; GCN3-NEXT: s_setpc_b64 s[30:31]
+ %gep = getelementptr i32, ptr %out, i64 4
+ %tmp0 = atomicrmw sub ptr %gep, i32 %in seq_cst, !amdgpu.no.remote.memory.access !0
+ ret void
+}
+
+define i32 @flat_atomic_sub_i32_ret_offset__amdgpu_no_remote_memory_access(ptr %out, i32 %in) {
+; GCN1-LABEL: flat_atomic_sub_i32_ret_offset__amdgpu_no_remote_memory_access:
+; GCN1: ; %bb.0:
+; GCN1-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GCN1-NEXT: v_add_i32_e32 v0, vcc, 16, v0
+; GCN1-NEXT: v_addc_u32_e32 v1, vcc, 0, v1, vcc
+; GCN1-NEXT: flat_atomic_sub v0, v[0:1], v2 glc
+; GCN1-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
+; GCN1-NEXT: buffer_wbinvl1_vol
+; GCN1-NEXT: s_setpc_b64 s[30:31]
+;
+; GCN2-LABEL: flat_atomic_sub_i32_ret_offset__amdgpu_no_remote_memory_access:
+; GCN2: ; %bb.0:
+; GCN2-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GCN2-NEXT: v_add_u32_e32 v0, vcc, 16, v0
+; GCN2-NEXT: v_addc_u32_e32 v1, vcc, 0, v1, vcc
+; GCN2-NEXT: flat_atomic_sub v0, v[0:1], v2 glc
+; GCN2-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
+; GCN2-NEXT: buffer_wbinvl1_vol
+; GCN2-NEXT: s_setpc_b64 s[30:31]
+;
+; GCN3-LABEL: flat_atomic_sub_i32_ret_offset__amdgpu_no_remote_memory_access:
+; GCN3: ; %bb.0:
+; GCN3-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GCN3-NEXT: flat_atomic_sub v0, v[0:1], v2 offset:16 glc
+; GCN3-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
+; GCN3-NEXT: buffer_wbinvl1_vol
+; GCN3-NEXT: s_setpc_b64 s[30:31]
+ %gep = getelementptr i32, ptr %out, i64 4
+ %result = atomicrmw sub ptr %gep, i32 %in seq_cst, !amdgpu.no.remote.memory.access !0
+ ret i32 %result
+}
+
; ---------------------------------------------------------------------
; atomicrmw and
; ---------------------------------------------------------------------
@@ -1423,61 +1687,127 @@ define amdgpu_gfx i32 @flat_atomic_and_i32_ret_offset_scalar(ptr inreg %out, i32
ret i32 %result
}
-; ---------------------------------------------------------------------
-; atomicrmw nand
-; ---------------------------------------------------------------------
-
-define void @flat_atomic_nand_i32_noret(ptr %ptr, i32 %in) {
-; GCN1-LABEL: flat_atomic_nand_i32_noret:
+define void @flat_atomic_and_i32_noret_offset__amdgpu_no_remote_memory_access(ptr %out, i32 %in) {
+; GCN1-LABEL: flat_atomic_and_i32_noret_offset__amdgpu_no_remote_memory_access:
; GCN1: ; %bb.0:
; GCN1-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GCN1-NEXT: flat_load_dword v4, v[0:1]
-; GCN1-NEXT: s_mov_b64 s[4:5], 0
-; GCN1-NEXT: .LBB40_1: ; %atomicrmw.start
-; GCN1-NEXT: ; =>This Inner Loop Header: Depth=1
-; GCN1-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
-; GCN1-NEXT: v_and_b32_e32 v3, v4, v2
-; GCN1-NEXT: v_not_b32_e32 v3, v3
-; GCN1-NEXT: flat_atomic_cmpswap v3, v[0:1], v[3:4] glc
+; GCN1-NEXT: v_add_i32_e32 v0, vcc, 16, v0
+; GCN1-NEXT: v_addc_u32_e32 v1, vcc, 0, v1, vcc
+; GCN1-NEXT: flat_atomic_and v[0:1], v2
; GCN1-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
; GCN1-NEXT: buffer_wbinvl1_vol
-; GCN1-NEXT: v_cmp_eq_u32_e32 vcc, v3, v4
-; GCN1-NEXT: s_or_b64 s[4:5], vcc, s[4:5]
-; GCN1-NEXT: v_mov_b32_e32 v4, v3
-; GCN1-NEXT: s_andn2_b64 exec, exec, s[4:5]
-; GCN1-NEXT: s_cbranch_execnz .LBB40_1
-; GCN1-NEXT: ; %bb.2: ; %atomicrmw.end
-; GCN1-NEXT: s_or_b64 exec, exec, s[4:5]
; GCN1-NEXT: s_setpc_b64 s[30:31]
;
-; GCN2-LABEL: flat_atomic_nand_i32_noret:
+; GCN2-LABEL: flat_atomic_and_i32_noret_offset__amdgpu_no_remote_memory_access:
; GCN2: ; %bb.0:
; GCN2-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
-; GCN2-NEXT: flat_load_dword v4, v[0:1]
-; GCN2-NEXT: s_mov_b64 s[4:5], 0
-; GCN2-NEXT: .LBB40_1: ; %atomicrmw.start
-; GCN2-NEXT: ; =>This Inner Loop Header: Depth=1
-; GCN2-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
-; GCN2-NEXT: v_and_b32_e32 v3, v4, v2
-; GCN2-NEXT: v_not_b32_e32 v3, v3
-; GCN2-NEXT: flat_atomic_cmpswap v3, v[0:1], v[3:4] glc
+; GCN2-NEXT: v_add_u32_e32 v0, vcc, 16, v0
+; GCN2-NEXT: v_addc_u32_e32 v1, vcc, 0, v1, vcc
+; GCN2-NEXT: flat_atomic_and v[0:1], v2
; GCN2-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
; GCN2-NEXT: buffer_wbinvl1_vol
-; GCN2-NEXT: v_cmp_eq_u32_e32 vcc, v3, v4
-; GCN2-NEXT: s_or_b64 s[4:5], vcc, s[4:5]
-; GCN2-NEXT: v_mov_b32_e32 v4, v3
-; GCN2-NEXT: s_andn2_b64 exec, exec, s[4:5]
-; GCN2-NEXT: s_cbranch_execnz .LBB40_1
-; GCN2-NEXT: ; %bb.2: ; %atomicrmw.end
-; GCN2-NEXT: s_or_b64 exec, exec, s[4:5]
; GCN2-NEXT: s_setpc_b64 s[30:31]
;
-; GCN3-LABEL: flat_atomic_nand_i32_noret:
+; GCN3-LABEL: flat_atomic_and_i32_noret_offset__amdgpu_no_remote_memory_access:
+; GCN3: ; %bb.0:
+; GCN3-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GCN3-NEXT: flat_atomic_and v[0:1], v2 offset:16
+; GCN3-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
+; GCN3-NEXT: buffer_wbinvl1_vol
+; GCN3-NEXT: s_setpc_b64 s[30:31]
+ %gep = getelementptr i32, ptr %out, i64 4
+ %tmp0 = atomicrmw and ptr %gep, i32 %in seq_cst, !amdgpu.no.remote.memory.access !0
+ ret void
+}
+
+define i32 @flat_atomic_and_i32_ret_offset__amdgpu_no_remote_memory_access(ptr %out, i32 %in) {
+; GCN1-LABEL: flat_atomic_and_i32_ret_offset__amdgpu_no_remote_memory_access:
+; GCN1: ; %bb.0:
+; GCN1-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GCN1-NEXT: v_add_i32_e32 v0, vcc, 16, v0
+; GCN1-NEXT: v_addc_u32_e32 v1, vcc, 0, v1, vcc
+; GCN1-NEXT: flat_atomic_and v0, v[0:1], v2 glc
+; GCN1-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
+; GCN1-NEXT: buffer_wbinvl1_vol
+; GCN1-NEXT: s_setpc_b64 s[30:31]
+;
+; GCN2-LABEL: flat_atomic_and_i32_ret_offset__amdgpu_no_remote_memory_access:
+; GCN2: ; %bb.0:
+; GCN2-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GCN2-NEXT: v_add_u32_e32 v0, vcc, 16, v0
+; GCN2-NEXT: v_addc_u32_e32 v1, vcc, 0, v1, vcc
+; GCN2-NEXT: flat_atomic_and v0, v[0:1], v2 glc
+; GCN2-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
+; GCN2-NEXT: buffer_wbinvl1_vol
+; GCN2-NEXT: s_setpc_b64 s[30:31]
+;
+; GCN3-LABEL: flat_atomic_and_i32_ret_offset__amdgpu_no_remote_memory_access:
+; GCN3: ; %bb.0:
+; GCN3-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GCN3-NEXT: flat_atomic_and v0, v[0:1], v2 offset:16 glc
+; GCN3-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
+; GCN3-NEXT: buffer_wbinvl1_vol
+; GCN3-NEXT: s_setpc_b64 s[30:31]
+ %gep = getelementptr i32, ptr %out, i64 4
+ %result = atomicrmw and ptr %gep, i32 %in seq_cst, !amdgpu.no.remote.memory.access !0
+ ret i32 %result
+}
+
+; ---------------------------------------------------------------------
+; atomicrmw nand
+; ---------------------------------------------------------------------
+
+define void @flat_atomic_nand_i32_noret(ptr %ptr, i32 %in) {
+; GCN1-LABEL: flat_atomic_nand_i32_noret:
+; GCN1: ; %bb.0:
+; GCN1-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GCN1-NEXT: flat_load_dword v4, v[0:1]
+; GCN1-NEXT: s_mov_b64 s[4:5], 0
+; GCN1-NEXT: .LBB50_1: ; %atomicrmw.start
+; GCN1-NEXT: ; =>This Inner Loop Header: Depth=1
+; GCN1-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
+; GCN1-NEXT: v_and_b32_e32 v3, v4, v2
+; GCN1-NEXT: v_not_b32_e32 v3, v3
+; GCN1-NEXT: flat_atomic_cmpswap v3, v[0:1], v[3:4] glc
+; GCN1-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
+; GCN1-NEXT: buffer_wbinvl1_vol
+; GCN1-NEXT: v_cmp_eq_u32_e32 vcc, v3, v4
+; GCN1-NEXT: s_or_b64 s[4:5], vcc, s[4:5]
+; GCN1-NEXT: v_mov_b32_e32 v4, v3
+; GCN1-NEXT: s_andn2_b64 exec, exec, s[4:5]
+; GCN1-NEXT: s_cbranch_execnz .LBB50_1
+; GCN1-NEXT: ; %bb.2: ; %atomicrmw.end
+; GCN1-NEXT: s_or_b64 exec, exec, s[4:5]
+; GCN1-NEXT: s_setpc_b64 s[30:31]
+;
+; GCN2-LABEL: flat_atomic_nand_i32_noret:
+; GCN2: ; %bb.0:
+; GCN2-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GCN2-NEXT: flat_load_dword v4, v[0:1]
+; GCN2-NEXT: s_mov_b64 s[4:5], 0
+; GCN2-NEXT: .LBB50_1: ; %atomicrmw.start
+; GCN2-NEXT: ; =>This Inner Loop Header: Depth=1
+; GCN2-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
+; GCN2-NEXT: v_and_b32_e32 v3, v4, v2
+; GCN2-NEXT: v_not_b32_e32 v3, v3
+; GCN2-NEXT: flat_atomic_cmpswap v3, v[0:1], v[3:4] glc
+; GCN2-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
+; GCN2-NEXT: buffer_wbinvl1_vol
+; GCN2-NEXT: v_cmp_eq_u32_e32 vcc, v3, v4
+; GCN2-NEXT: s_or_b64 s[4:5], vcc, s[4:5]
+; GCN2-NEXT: v_mov_b32_e32 v4, v3
+; GCN2-NEXT: s_andn2_b64 exec, exec, s[4:5]
+; GCN2-NEXT: s_cbranch_execnz .LBB50_1
+; GCN2-NEXT: ; %bb.2: ; %atomicrmw.end
+; GCN2-NEXT: s_or_b64 exec, exec, s[4:5]
+; GCN2-NEXT: s_setpc_b64 s[30:31]
+;
+; GCN3-LABEL: flat_atomic_nand_i32_noret:
; GCN3: ; %bb.0:
; GCN3-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GCN3-NEXT: flat_load_dword v4, v[0:1]
; GCN3-NEXT: s_mov_b64 s[4:5], 0
-; GCN3-NEXT: .LBB40_1: ; %atomicrmw.start
+; GCN3-NEXT: .LBB50_1: ; %atomicrmw.start
; GCN3-NEXT: ; =>This Inner Loop Header: Depth=1
; GCN3-NEXT: s_waitcnt vmcnt(0) lgkmcnt(0)
; GCN3-NEXT: v_and_b32_e32 v3, v4, v2
@@ -1489,7 +1819,7 @@ define void @flat_atomic_nand_i32_noret(ptr %ptr, i32 %in) {
; GCN3-NEXT...
[truncated]
``````````
</details>
https://github.com/llvm/llvm-project/pull/89248
More information about the llvm-commits
mailing list