[llvm] [AtomicExpand] Drop explicit datalayout from test (PR #137923)
via llvm-commits
llvm-commits at lists.llvm.org
Tue Apr 29 22:11:20 PDT 2025
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-backend-amdgpu
Author: Alexander Richardson (arichardson)
<details>
<summary>Changes</summary>
This results in different codegen for GCN and R600 but no further change.
---
Patch is 119.46 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/137923.diff
1 Files Affected:
- (modified) llvm/test/Transforms/AtomicExpand/AMDGPU/expand-atomic-i16.ll (+1104-557)
``````````diff
diff --git a/llvm/test/Transforms/AtomicExpand/AMDGPU/expand-atomic-i16.ll b/llvm/test/Transforms/AtomicExpand/AMDGPU/expand-atomic-i16.ll
index bb6596fb39b56..7d8c254251a48 100644
--- a/llvm/test/Transforms/AtomicExpand/AMDGPU/expand-atomic-i16.ll
+++ b/llvm/test/Transforms/AtomicExpand/AMDGPU/expand-atomic-i16.ll
@@ -3,33 +3,55 @@
; RUN: opt -mtriple=amdgcn-amd-amdhsa -S -passes=atomic-expand %s | FileCheck -check-prefixes=CHECK,GCN,GFX942 %s
; RUN: opt -mtriple=r600-mesa-mesa3d -S -passes=atomic-expand %s | FileCheck -check-prefixes=CHECK,R600 %s
-target datalayout = "e-p:64:64-p1:64:64-p2:32:32-p3:32:32-p4:64:64-p5:32:32-p6:32:32-p7:160:256:256:32-p8:128:128-i64:64-v16:16-v24:32-v32:32-v48:64-v96:128-v192:256-v256:256-v512:512-v1024:1024-v2048:2048-n32:64-S32-A5"
-
define i16 @test_atomicrmw_xchg_i16_global_agent(ptr addrspace(1) %ptr, i16 %value) {
-; CHECK-LABEL: @test_atomicrmw_xchg_i16_global_agent(
-; CHECK-NEXT: [[ALIGNEDADDR:%.*]] = call ptr addrspace(1) @llvm.ptrmask.p1.i64(ptr addrspace(1) [[PTR:%.*]], i64 -4)
-; CHECK-NEXT: [[TMP1:%.*]] = ptrtoint ptr addrspace(1) [[PTR]] to i64
-; CHECK-NEXT: [[PTRLSB:%.*]] = and i64 [[TMP1]], 3
-; CHECK-NEXT: [[TMP2:%.*]] = shl i64 [[PTRLSB]], 3
-; CHECK-NEXT: [[SHIFTAMT:%.*]] = trunc i64 [[TMP2]] to i32
-; CHECK-NEXT: [[MASK:%.*]] = shl i32 65535, [[SHIFTAMT]]
-; CHECK-NEXT: [[INV_MASK:%.*]] = xor i32 [[MASK]], -1
-; CHECK-NEXT: [[TMP3:%.*]] = zext i16 [[VALUE:%.*]] to i32
-; CHECK-NEXT: [[VALOPERAND_SHIFTED:%.*]] = shl i32 [[TMP3]], [[SHIFTAMT]]
-; CHECK-NEXT: [[TMP4:%.*]] = load i32, ptr addrspace(1) [[ALIGNEDADDR]], align 4
-; CHECK-NEXT: br label [[ATOMICRMW_START:%.*]]
-; CHECK: atomicrmw.start:
-; CHECK-NEXT: [[LOADED:%.*]] = phi i32 [ [[TMP4]], [[TMP0:%.*]] ], [ [[NEWLOADED:%.*]], [[ATOMICRMW_START]] ]
-; CHECK-NEXT: [[TMP5:%.*]] = and i32 [[LOADED]], [[INV_MASK]]
-; CHECK-NEXT: [[TMP6:%.*]] = or i32 [[TMP5]], [[VALOPERAND_SHIFTED]]
-; CHECK-NEXT: [[TMP7:%.*]] = cmpxchg ptr addrspace(1) [[ALIGNEDADDR]], i32 [[LOADED]], i32 [[TMP6]] syncscope("agent") seq_cst seq_cst, align 4
-; CHECK-NEXT: [[SUCCESS:%.*]] = extractvalue { i32, i1 } [[TMP7]], 1
-; CHECK-NEXT: [[NEWLOADED]] = extractvalue { i32, i1 } [[TMP7]], 0
-; CHECK-NEXT: br i1 [[SUCCESS]], label [[ATOMICRMW_END:%.*]], label [[ATOMICRMW_START]]
-; CHECK: atomicrmw.end:
-; CHECK-NEXT: [[SHIFTED:%.*]] = lshr i32 [[NEWLOADED]], [[SHIFTAMT]]
-; CHECK-NEXT: [[EXTRACTED:%.*]] = trunc i32 [[SHIFTED]] to i16
-; CHECK-NEXT: ret i16 [[EXTRACTED]]
+; GCN-LABEL: @test_atomicrmw_xchg_i16_global_agent(
+; GCN-NEXT: [[ALIGNEDADDR:%.*]] = call ptr addrspace(1) @llvm.ptrmask.p1.i64(ptr addrspace(1) [[PTR:%.*]], i64 -4)
+; GCN-NEXT: [[TMP1:%.*]] = ptrtoint ptr addrspace(1) [[PTR]] to i64
+; GCN-NEXT: [[PTRLSB:%.*]] = and i64 [[TMP1]], 3
+; GCN-NEXT: [[TMP2:%.*]] = shl i64 [[PTRLSB]], 3
+; GCN-NEXT: [[SHIFTAMT:%.*]] = trunc i64 [[TMP2]] to i32
+; GCN-NEXT: [[MASK:%.*]] = shl i32 65535, [[SHIFTAMT]]
+; GCN-NEXT: [[INV_MASK:%.*]] = xor i32 [[MASK]], -1
+; GCN-NEXT: [[TMP3:%.*]] = zext i16 [[VALUE:%.*]] to i32
+; GCN-NEXT: [[VALOPERAND_SHIFTED:%.*]] = shl i32 [[TMP3]], [[SHIFTAMT]]
+; GCN-NEXT: [[TMP4:%.*]] = load i32, ptr addrspace(1) [[ALIGNEDADDR]], align 4
+; GCN-NEXT: br label [[ATOMICRMW_START:%.*]]
+; GCN: atomicrmw.start:
+; GCN-NEXT: [[LOADED:%.*]] = phi i32 [ [[TMP4]], [[TMP0:%.*]] ], [ [[NEWLOADED:%.*]], [[ATOMICRMW_START]] ]
+; GCN-NEXT: [[TMP5:%.*]] = and i32 [[LOADED]], [[INV_MASK]]
+; GCN-NEXT: [[TMP6:%.*]] = or i32 [[TMP5]], [[VALOPERAND_SHIFTED]]
+; GCN-NEXT: [[TMP7:%.*]] = cmpxchg ptr addrspace(1) [[ALIGNEDADDR]], i32 [[LOADED]], i32 [[TMP6]] syncscope("agent") seq_cst seq_cst, align 4
+; GCN-NEXT: [[SUCCESS:%.*]] = extractvalue { i32, i1 } [[TMP7]], 1
+; GCN-NEXT: [[NEWLOADED]] = extractvalue { i32, i1 } [[TMP7]], 0
+; GCN-NEXT: br i1 [[SUCCESS]], label [[ATOMICRMW_END:%.*]], label [[ATOMICRMW_START]]
+; GCN: atomicrmw.end:
+; GCN-NEXT: [[SHIFTED:%.*]] = lshr i32 [[NEWLOADED]], [[SHIFTAMT]]
+; GCN-NEXT: [[EXTRACTED:%.*]] = trunc i32 [[SHIFTED]] to i16
+; GCN-NEXT: ret i16 [[EXTRACTED]]
+;
+; R600-LABEL: @test_atomicrmw_xchg_i16_global_agent(
+; R600-NEXT: [[ALIGNEDADDR:%.*]] = call ptr addrspace(1) @llvm.ptrmask.p1.i32(ptr addrspace(1) [[PTR:%.*]], i32 -4)
+; R600-NEXT: [[TMP1:%.*]] = ptrtoint ptr addrspace(1) [[PTR]] to i32
+; R600-NEXT: [[PTRLSB:%.*]] = and i32 [[TMP1]], 3
+; R600-NEXT: [[TMP2:%.*]] = shl i32 [[PTRLSB]], 3
+; R600-NEXT: [[MASK:%.*]] = shl i32 65535, [[TMP2]]
+; R600-NEXT: [[INV_MASK:%.*]] = xor i32 [[MASK]], -1
+; R600-NEXT: [[TMP3:%.*]] = zext i16 [[VALUE:%.*]] to i32
+; R600-NEXT: [[VALOPERAND_SHIFTED:%.*]] = shl i32 [[TMP3]], [[TMP2]]
+; R600-NEXT: [[TMP4:%.*]] = load i32, ptr addrspace(1) [[ALIGNEDADDR]], align 4
+; R600-NEXT: br label [[ATOMICRMW_START:%.*]]
+; R600: atomicrmw.start:
+; R600-NEXT: [[LOADED:%.*]] = phi i32 [ [[TMP4]], [[TMP0:%.*]] ], [ [[NEWLOADED:%.*]], [[ATOMICRMW_START]] ]
+; R600-NEXT: [[TMP5:%.*]] = and i32 [[LOADED]], [[INV_MASK]]
+; R600-NEXT: [[TMP6:%.*]] = or i32 [[TMP5]], [[VALOPERAND_SHIFTED]]
+; R600-NEXT: [[TMP7:%.*]] = cmpxchg ptr addrspace(1) [[ALIGNEDADDR]], i32 [[LOADED]], i32 [[TMP6]] syncscope("agent") seq_cst seq_cst, align 4
+; R600-NEXT: [[SUCCESS:%.*]] = extractvalue { i32, i1 } [[TMP7]], 1
+; R600-NEXT: [[NEWLOADED]] = extractvalue { i32, i1 } [[TMP7]], 0
+; R600-NEXT: br i1 [[SUCCESS]], label [[ATOMICRMW_END:%.*]], label [[ATOMICRMW_START]]
+; R600: atomicrmw.end:
+; R600-NEXT: [[SHIFTED:%.*]] = lshr i32 [[NEWLOADED]], [[TMP2]]
+; R600-NEXT: [[EXTRACTED:%.*]] = trunc i32 [[SHIFTED]] to i16
+; R600-NEXT: ret i16 [[EXTRACTED]]
;
%res = atomicrmw xchg ptr addrspace(1) %ptr, i16 %value syncscope("agent") seq_cst
ret i16 %res
@@ -57,32 +79,58 @@ define i16 @test_atomicrmw_xchg_i16_global_agent_align4(ptr addrspace(1) %ptr, i
}
define i16 @test_atomicrmw_add_i16_global_agent(ptr addrspace(1) %ptr, i16 %value) {
-; CHECK-LABEL: @test_atomicrmw_add_i16_global_agent(
-; CHECK-NEXT: [[ALIGNEDADDR:%.*]] = call ptr addrspace(1) @llvm.ptrmask.p1.i64(ptr addrspace(1) [[PTR:%.*]], i64 -4)
-; CHECK-NEXT: [[TMP1:%.*]] = ptrtoint ptr addrspace(1) [[PTR]] to i64
-; CHECK-NEXT: [[PTRLSB:%.*]] = and i64 [[TMP1]], 3
-; CHECK-NEXT: [[TMP2:%.*]] = shl i64 [[PTRLSB]], 3
-; CHECK-NEXT: [[SHIFTAMT:%.*]] = trunc i64 [[TMP2]] to i32
-; CHECK-NEXT: [[MASK:%.*]] = shl i32 65535, [[SHIFTAMT]]
-; CHECK-NEXT: [[INV_MASK:%.*]] = xor i32 [[MASK]], -1
-; CHECK-NEXT: [[TMP3:%.*]] = zext i16 [[VALUE:%.*]] to i32
-; CHECK-NEXT: [[VALOPERAND_SHIFTED:%.*]] = shl i32 [[TMP3]], [[SHIFTAMT]]
-; CHECK-NEXT: [[TMP4:%.*]] = load i32, ptr addrspace(1) [[ALIGNEDADDR]], align 4
-; CHECK-NEXT: br label [[ATOMICRMW_START:%.*]]
-; CHECK: atomicrmw.start:
-; CHECK-NEXT: [[LOADED:%.*]] = phi i32 [ [[TMP4]], [[TMP0:%.*]] ], [ [[NEWLOADED:%.*]], [[ATOMICRMW_START]] ]
-; CHECK-NEXT: [[NEW:%.*]] = add i32 [[LOADED]], [[VALOPERAND_SHIFTED]]
-; CHECK-NEXT: [[TMP5:%.*]] = and i32 [[NEW]], [[MASK]]
-; CHECK-NEXT: [[TMP6:%.*]] = and i32 [[LOADED]], [[INV_MASK]]
-; CHECK-NEXT: [[TMP7:%.*]] = or i32 [[TMP6]], [[TMP5]]
-; CHECK-NEXT: [[TMP8:%.*]] = cmpxchg ptr addrspace(1) [[ALIGNEDADDR]], i32 [[LOADED]], i32 [[TMP7]] syncscope("agent") seq_cst seq_cst, align 4
-; CHECK-NEXT: [[SUCCESS:%.*]] = extractvalue { i32, i1 } [[TMP8]], 1
-; CHECK-NEXT: [[NEWLOADED]] = extractvalue { i32, i1 } [[TMP8]], 0
-; CHECK-NEXT: br i1 [[SUCCESS]], label [[ATOMICRMW_END:%.*]], label [[ATOMICRMW_START]]
-; CHECK: atomicrmw.end:
-; CHECK-NEXT: [[SHIFTED:%.*]] = lshr i32 [[NEWLOADED]], [[SHIFTAMT]]
-; CHECK-NEXT: [[EXTRACTED:%.*]] = trunc i32 [[SHIFTED]] to i16
-; CHECK-NEXT: ret i16 [[EXTRACTED]]
+; GCN-LABEL: @test_atomicrmw_add_i16_global_agent(
+; GCN-NEXT: [[ALIGNEDADDR:%.*]] = call ptr addrspace(1) @llvm.ptrmask.p1.i64(ptr addrspace(1) [[PTR:%.*]], i64 -4)
+; GCN-NEXT: [[TMP1:%.*]] = ptrtoint ptr addrspace(1) [[PTR]] to i64
+; GCN-NEXT: [[PTRLSB:%.*]] = and i64 [[TMP1]], 3
+; GCN-NEXT: [[TMP2:%.*]] = shl i64 [[PTRLSB]], 3
+; GCN-NEXT: [[SHIFTAMT:%.*]] = trunc i64 [[TMP2]] to i32
+; GCN-NEXT: [[MASK:%.*]] = shl i32 65535, [[SHIFTAMT]]
+; GCN-NEXT: [[INV_MASK:%.*]] = xor i32 [[MASK]], -1
+; GCN-NEXT: [[TMP3:%.*]] = zext i16 [[VALUE:%.*]] to i32
+; GCN-NEXT: [[VALOPERAND_SHIFTED:%.*]] = shl i32 [[TMP3]], [[SHIFTAMT]]
+; GCN-NEXT: [[TMP4:%.*]] = load i32, ptr addrspace(1) [[ALIGNEDADDR]], align 4
+; GCN-NEXT: br label [[ATOMICRMW_START:%.*]]
+; GCN: atomicrmw.start:
+; GCN-NEXT: [[LOADED:%.*]] = phi i32 [ [[TMP4]], [[TMP0:%.*]] ], [ [[NEWLOADED:%.*]], [[ATOMICRMW_START]] ]
+; GCN-NEXT: [[NEW:%.*]] = add i32 [[LOADED]], [[VALOPERAND_SHIFTED]]
+; GCN-NEXT: [[TMP5:%.*]] = and i32 [[NEW]], [[MASK]]
+; GCN-NEXT: [[TMP6:%.*]] = and i32 [[LOADED]], [[INV_MASK]]
+; GCN-NEXT: [[TMP7:%.*]] = or i32 [[TMP6]], [[TMP5]]
+; GCN-NEXT: [[TMP8:%.*]] = cmpxchg ptr addrspace(1) [[ALIGNEDADDR]], i32 [[LOADED]], i32 [[TMP7]] syncscope("agent") seq_cst seq_cst, align 4
+; GCN-NEXT: [[SUCCESS:%.*]] = extractvalue { i32, i1 } [[TMP8]], 1
+; GCN-NEXT: [[NEWLOADED]] = extractvalue { i32, i1 } [[TMP8]], 0
+; GCN-NEXT: br i1 [[SUCCESS]], label [[ATOMICRMW_END:%.*]], label [[ATOMICRMW_START]]
+; GCN: atomicrmw.end:
+; GCN-NEXT: [[SHIFTED:%.*]] = lshr i32 [[NEWLOADED]], [[SHIFTAMT]]
+; GCN-NEXT: [[EXTRACTED:%.*]] = trunc i32 [[SHIFTED]] to i16
+; GCN-NEXT: ret i16 [[EXTRACTED]]
+;
+; R600-LABEL: @test_atomicrmw_add_i16_global_agent(
+; R600-NEXT: [[ALIGNEDADDR:%.*]] = call ptr addrspace(1) @llvm.ptrmask.p1.i32(ptr addrspace(1) [[PTR:%.*]], i32 -4)
+; R600-NEXT: [[TMP1:%.*]] = ptrtoint ptr addrspace(1) [[PTR]] to i32
+; R600-NEXT: [[PTRLSB:%.*]] = and i32 [[TMP1]], 3
+; R600-NEXT: [[TMP2:%.*]] = shl i32 [[PTRLSB]], 3
+; R600-NEXT: [[MASK:%.*]] = shl i32 65535, [[TMP2]]
+; R600-NEXT: [[INV_MASK:%.*]] = xor i32 [[MASK]], -1
+; R600-NEXT: [[TMP3:%.*]] = zext i16 [[VALUE:%.*]] to i32
+; R600-NEXT: [[VALOPERAND_SHIFTED:%.*]] = shl i32 [[TMP3]], [[TMP2]]
+; R600-NEXT: [[TMP4:%.*]] = load i32, ptr addrspace(1) [[ALIGNEDADDR]], align 4
+; R600-NEXT: br label [[ATOMICRMW_START:%.*]]
+; R600: atomicrmw.start:
+; R600-NEXT: [[LOADED:%.*]] = phi i32 [ [[TMP4]], [[TMP0:%.*]] ], [ [[NEWLOADED:%.*]], [[ATOMICRMW_START]] ]
+; R600-NEXT: [[NEW:%.*]] = add i32 [[LOADED]], [[VALOPERAND_SHIFTED]]
+; R600-NEXT: [[TMP5:%.*]] = and i32 [[NEW]], [[MASK]]
+; R600-NEXT: [[TMP6:%.*]] = and i32 [[LOADED]], [[INV_MASK]]
+; R600-NEXT: [[TMP7:%.*]] = or i32 [[TMP6]], [[TMP5]]
+; R600-NEXT: [[TMP8:%.*]] = cmpxchg ptr addrspace(1) [[ALIGNEDADDR]], i32 [[LOADED]], i32 [[TMP7]] syncscope("agent") seq_cst seq_cst, align 4
+; R600-NEXT: [[SUCCESS:%.*]] = extractvalue { i32, i1 } [[TMP8]], 1
+; R600-NEXT: [[NEWLOADED]] = extractvalue { i32, i1 } [[TMP8]], 0
+; R600-NEXT: br i1 [[SUCCESS]], label [[ATOMICRMW_END:%.*]], label [[ATOMICRMW_START]]
+; R600: atomicrmw.end:
+; R600-NEXT: [[SHIFTED:%.*]] = lshr i32 [[NEWLOADED]], [[TMP2]]
+; R600-NEXT: [[EXTRACTED:%.*]] = trunc i32 [[SHIFTED]] to i16
+; R600-NEXT: ret i16 [[EXTRACTED]]
;
%res = atomicrmw add ptr addrspace(1) %ptr, i16 %value syncscope("agent") seq_cst
ret i16 %res
@@ -112,53 +160,94 @@ define i16 @test_atomicrmw_add_i16_global_agent_align4(ptr addrspace(1) %ptr, i1
}
define i16 @test_atomicrmw_sub_i16_global_agent(ptr addrspace(1) %ptr, i16 %value) {
-; CHECK-LABEL: @test_atomicrmw_sub_i16_global_agent(
-; CHECK-NEXT: [[ALIGNEDADDR:%.*]] = call ptr addrspace(1) @llvm.ptrmask.p1.i64(ptr addrspace(1) [[PTR:%.*]], i64 -4)
-; CHECK-NEXT: [[TMP1:%.*]] = ptrtoint ptr addrspace(1) [[PTR]] to i64
-; CHECK-NEXT: [[PTRLSB:%.*]] = and i64 [[TMP1]], 3
-; CHECK-NEXT: [[TMP2:%.*]] = shl i64 [[PTRLSB]], 3
-; CHECK-NEXT: [[SHIFTAMT:%.*]] = trunc i64 [[TMP2]] to i32
-; CHECK-NEXT: [[MASK:%.*]] = shl i32 65535, [[SHIFTAMT]]
-; CHECK-NEXT: [[INV_MASK:%.*]] = xor i32 [[MASK]], -1
-; CHECK-NEXT: [[TMP3:%.*]] = zext i16 [[VALUE:%.*]] to i32
-; CHECK-NEXT: [[VALOPERAND_SHIFTED:%.*]] = shl i32 [[TMP3]], [[SHIFTAMT]]
-; CHECK-NEXT: [[TMP4:%.*]] = load i32, ptr addrspace(1) [[ALIGNEDADDR]], align 4
-; CHECK-NEXT: br label [[ATOMICRMW_START:%.*]]
-; CHECK: atomicrmw.start:
-; CHECK-NEXT: [[LOADED:%.*]] = phi i32 [ [[TMP4]], [[TMP0:%.*]] ], [ [[NEWLOADED:%.*]], [[ATOMICRMW_START]] ]
-; CHECK-NEXT: [[NEW:%.*]] = sub i32 [[LOADED]], [[VALOPERAND_SHIFTED]]
-; CHECK-NEXT: [[TMP5:%.*]] = and i32 [[NEW]], [[MASK]]
-; CHECK-NEXT: [[TMP6:%.*]] = and i32 [[LOADED]], [[INV_MASK]]
-; CHECK-NEXT: [[TMP7:%.*]] = or i32 [[TMP6]], [[TMP5]]
-; CHECK-NEXT: [[TMP8:%.*]] = cmpxchg ptr addrspace(1) [[ALIGNEDADDR]], i32 [[LOADED]], i32 [[TMP7]] syncscope("agent") seq_cst seq_cst, align 4
-; CHECK-NEXT: [[SUCCESS:%.*]] = extractvalue { i32, i1 } [[TMP8]], 1
-; CHECK-NEXT: [[NEWLOADED]] = extractvalue { i32, i1 } [[TMP8]], 0
-; CHECK-NEXT: br i1 [[SUCCESS]], label [[ATOMICRMW_END:%.*]], label [[ATOMICRMW_START]]
-; CHECK: atomicrmw.end:
-; CHECK-NEXT: [[SHIFTED:%.*]] = lshr i32 [[NEWLOADED]], [[SHIFTAMT]]
-; CHECK-NEXT: [[EXTRACTED:%.*]] = trunc i32 [[SHIFTED]] to i16
-; CHECK-NEXT: ret i16 [[EXTRACTED]]
+; GCN-LABEL: @test_atomicrmw_sub_i16_global_agent(
+; GCN-NEXT: [[ALIGNEDADDR:%.*]] = call ptr addrspace(1) @llvm.ptrmask.p1.i64(ptr addrspace(1) [[PTR:%.*]], i64 -4)
+; GCN-NEXT: [[TMP1:%.*]] = ptrtoint ptr addrspace(1) [[PTR]] to i64
+; GCN-NEXT: [[PTRLSB:%.*]] = and i64 [[TMP1]], 3
+; GCN-NEXT: [[TMP2:%.*]] = shl i64 [[PTRLSB]], 3
+; GCN-NEXT: [[SHIFTAMT:%.*]] = trunc i64 [[TMP2]] to i32
+; GCN-NEXT: [[MASK:%.*]] = shl i32 65535, [[SHIFTAMT]]
+; GCN-NEXT: [[INV_MASK:%.*]] = xor i32 [[MASK]], -1
+; GCN-NEXT: [[TMP3:%.*]] = zext i16 [[VALUE:%.*]] to i32
+; GCN-NEXT: [[VALOPERAND_SHIFTED:%.*]] = shl i32 [[TMP3]], [[SHIFTAMT]]
+; GCN-NEXT: [[TMP4:%.*]] = load i32, ptr addrspace(1) [[ALIGNEDADDR]], align 4
+; GCN-NEXT: br label [[ATOMICRMW_START:%.*]]
+; GCN: atomicrmw.start:
+; GCN-NEXT: [[LOADED:%.*]] = phi i32 [ [[TMP4]], [[TMP0:%.*]] ], [ [[NEWLOADED:%.*]], [[ATOMICRMW_START]] ]
+; GCN-NEXT: [[NEW:%.*]] = sub i32 [[LOADED]], [[VALOPERAND_SHIFTED]]
+; GCN-NEXT: [[TMP5:%.*]] = and i32 [[NEW]], [[MASK]]
+; GCN-NEXT: [[TMP6:%.*]] = and i32 [[LOADED]], [[INV_MASK]]
+; GCN-NEXT: [[TMP7:%.*]] = or i32 [[TMP6]], [[TMP5]]
+; GCN-NEXT: [[TMP8:%.*]] = cmpxchg ptr addrspace(1) [[ALIGNEDADDR]], i32 [[LOADED]], i32 [[TMP7]] syncscope("agent") seq_cst seq_cst, align 4
+; GCN-NEXT: [[SUCCESS:%.*]] = extractvalue { i32, i1 } [[TMP8]], 1
+; GCN-NEXT: [[NEWLOADED]] = extractvalue { i32, i1 } [[TMP8]], 0
+; GCN-NEXT: br i1 [[SUCCESS]], label [[ATOMICRMW_END:%.*]], label [[ATOMICRMW_START]]
+; GCN: atomicrmw.end:
+; GCN-NEXT: [[SHIFTED:%.*]] = lshr i32 [[NEWLOADED]], [[SHIFTAMT]]
+; GCN-NEXT: [[EXTRACTED:%.*]] = trunc i32 [[SHIFTED]] to i16
+; GCN-NEXT: ret i16 [[EXTRACTED]]
+;
+; R600-LABEL: @test_atomicrmw_sub_i16_global_agent(
+; R600-NEXT: [[ALIGNEDADDR:%.*]] = call ptr addrspace(1) @llvm.ptrmask.p1.i32(ptr addrspace(1) [[PTR:%.*]], i32 -4)
+; R600-NEXT: [[TMP1:%.*]] = ptrtoint ptr addrspace(1) [[PTR]] to i32
+; R600-NEXT: [[PTRLSB:%.*]] = and i32 [[TMP1]], 3
+; R600-NEXT: [[TMP2:%.*]] = shl i32 [[PTRLSB]], 3
+; R600-NEXT: [[MASK:%.*]] = shl i32 65535, [[TMP2]]
+; R600-NEXT: [[INV_MASK:%.*]] = xor i32 [[MASK]], -1
+; R600-NEXT: [[TMP3:%.*]] = zext i16 [[VALUE:%.*]] to i32
+; R600-NEXT: [[VALOPERAND_SHIFTED:%.*]] = shl i32 [[TMP3]], [[TMP2]]
+; R600-NEXT: [[TMP4:%.*]] = load i32, ptr addrspace(1) [[ALIGNEDADDR]], align 4
+; R600-NEXT: br label [[ATOMICRMW_START:%.*]]
+; R600: atomicrmw.start:
+; R600-NEXT: [[LOADED:%.*]] = phi i32 [ [[TMP4]], [[TMP0:%.*]] ], [ [[NEWLOADED:%.*]], [[ATOMICRMW_START]] ]
+; R600-NEXT: [[NEW:%.*]] = sub i32 [[LOADED]], [[VALOPERAND_SHIFTED]]
+; R600-NEXT: [[TMP5:%.*]] = and i32 [[NEW]], [[MASK]]
+; R600-NEXT: [[TMP6:%.*]] = and i32 [[LOADED]], [[INV_MASK]]
+; R600-NEXT: [[TMP7:%.*]] = or i32 [[TMP6]], [[TMP5]]
+; R600-NEXT: [[TMP8:%.*]] = cmpxchg ptr addrspace(1) [[ALIGNEDADDR]], i32 [[LOADED]], i32 [[TMP7]] syncscope("agent") seq_cst seq_cst, align 4
+; R600-NEXT: [[SUCCESS:%.*]] = extractvalue { i32, i1 } [[TMP8]], 1
+; R600-NEXT: [[NEWLOADED]] = extractvalue { i32, i1 } [[TMP8]], 0
+; R600-NEXT: br i1 [[SUCCESS]], label [[ATOMICRMW_END:%.*]], label [[ATOMICRMW_START]]
+; R600: atomicrmw.end:
+; R600-NEXT: [[SHIFTED:%.*]] = lshr i32 [[NEWLOADED]], [[TMP2]]
+; R600-NEXT: [[EXTRACTED:%.*]] = trunc i32 [[SHIFTED]] to i16
+; R600-NEXT: ret i16 [[EXTRACTED]]
;
%res = atomicrmw sub ptr addrspace(1) %ptr, i16 %value syncscope("agent") seq_cst
ret i16 %res
}
define i16 @test_atomicrmw_and_i16_global_agent(ptr addrspace(1) %ptr, i16 %value) {
-; CHECK-LABEL: @test_atomicrmw_and_i16_global_agent(
-; CHECK-NEXT: [[ALIGNEDADDR:%.*]] = call ptr addrspace(1) @llvm.ptrmask.p1.i64(ptr addrspace(1) [[PTR:%.*]], i64 -4)
-; CHECK-NEXT: [[TMP1:%.*]] = ptrtoint ptr addrspace(1) [[PTR]] to i64
-; CHECK-NEXT: [[PTRLSB:%.*]] = and i64 [[TMP1]], 3
-; CHECK-NEXT: [[TMP2:%.*]] = shl i64 [[PTRLSB]], 3
-; CHECK-NEXT: [[SHIFTAMT:%.*]] = trunc i64 [[TMP2]] to i32
-; CHECK-NEXT: [[MASK:%.*]] = shl i32 65535, [[SHIFTAMT]]
-; CHECK-NEXT: [[INV_MASK:%.*]] = xor i32 [[MASK]], -1
-; CHECK-NEXT: [[TMP3:%.*]] = zext i16 [[VALUE:%.*]] to i32
-; CHECK-NEXT: [[VALOPERAND_SHIFTED:%.*]] = shl i32 [[TMP3]], [[SHIFTAMT]]
-; CHECK-NEXT: [[ANDOPERAND:%.*]] = or i32 [[VALOPERAND_SHIFTED]], [[INV_MASK]]
-; CHECK-NEXT: [[TMP4:%.*]] = atomicrmw and ptr addrspace(1) [[ALIGNEDADDR]], i32 [[ANDOPERAND]] syncscope("agent") seq_cst, align 4
-; CHECK-NEXT: [[SHIFTED:%.*]] = lshr i32 [[TMP4]], [[SHIFTAMT]]
-; CHECK-NEXT: [[EXTRACTED:%.*]] = trunc i32 [[SHIFTED]] to i16
-; CHECK-NEXT: ret i16 [[EXTRACTED]]
+; GCN-LABEL: @test_atomicrmw_and_i16_global_agent(
+; GCN-NEXT: [[ALIGNEDADDR:%.*]] = call ptr addrspace(1) @llvm.ptrmask.p1.i64(ptr addrspace(1) [[PTR:%.*]], i64 -4)
+; GCN-NEXT: [[TMP1:%.*]] = ptrtoint ptr addrspace(1) [[PTR]] to i64
+; GCN-NEXT: [[PTRLSB:%.*]] = and i64 [[TMP1]], 3
+; GCN-NEXT: [[TMP2:%.*]] = shl i64 [[PTRLSB]], 3
+; GCN-NEXT: [[SHIFTAMT:%.*]] = trunc i64 [[TMP2]] to i32
+; GCN-NEXT: [[MASK:%.*]] = shl i32 65535, [[SHIFTAMT]]
+; GCN-NEXT: [[INV_MASK:%.*]] = xor i32 [[MASK]], -1
+; GCN-NEXT: [[TMP3:%.*]] = zext i16 [[VALUE:%.*]] to i32
+; GCN-NEXT: [[VALOPERAND_SHIFTED:%.*]] = shl i32 [[TMP3]], [[SHIFTAMT]]
+; GCN-NEXT: [[ANDOPERAND:%.*]] = or i32 [[VALOPERAND_SHIFTED]], [[INV_MASK]]
+; GCN-NEXT: [[TMP4:%.*]] = atomicrmw and ptr addrspace(1) [[ALIGNEDADDR]], i32 [[ANDOPERAND]] syncscope("agent") seq_cst, align 4
+; GCN-NEXT: [[SHIFTED:%.*]] = lshr i32 [[TMP4]], [[SHIFTAMT]]
+; GCN-NEXT: [[EXTRACTED:%.*]] = trunc i32 [[SHIFTED]] to i16
+; GCN-NEXT: ret i16 [[EXTRACTED]]
+;
+; R600-LABEL: @test_atomicrmw_and_i16_global_agent(
+; R600-NEXT: [[ALIGNEDADDR:%.*]] = call ptr addrspace(1) @llvm.ptrmask.p1.i32(ptr addrspace(1) [[PTR:%.*]], i32 -4)
+; R600-NEXT: [[TMP1:%.*]] = ptrtoint ptr addrspace(1) [[PTR]] to i32
+; R600-NEXT: [[PTRLSB:%.*]] = and i32 [[TMP1]], 3
+; R600-NEXT: [[TMP2:%.*]] = shl i32 [[PTRLSB]], 3
+; R600-NEXT: [[MASK:%.*]] = shl i32 65535, [[TMP2]]
+; R600-NEXT: [[INV_MASK:%.*]] = xor i32 [[MASK]], -1
+; R600-NEXT: [[TMP3:%.*]] = zext i16 [[VALUE:%.*]] to i32
+; R600-NEXT: [[VALOPERAND_SHIFTED:%.*]] = shl i32 [[TMP3]], [[TMP2]]
+; R600-NEXT: [[ANDOPERAND:%.*]] = or i32 [[VALOPERAND_SHIFTED]], [[INV_MASK]]
+; R600-NEXT: [[TMP4:%.*]] = atomicrmw and ptr addrspace(1) [[ALIGNEDADDR]], i32 [[ANDOPERAND]] syncscope("agent") seq_cst, align 4
+; R600-NEXT: [[SHIFTED:%.*]] = lshr i32 [[TMP4]], [[TMP2]]
+; R600-NEXT: [[EXTRACTED:%.*]] = trunc i32 [[SHIFTED]] to i16
+; R600-NEXT: ret i16 [[EXTRACTED]]
;
%res = atomicrmw and ptr addrspace(1) %ptr, i16 %value syncscope("agent") seq_cst
ret i16 %res
@@ -178,21 +267,36 @@ define ...
[truncated]
``````````
</details>
https://github.com/llvm/llvm-project/pull/137923
More information about the llvm-commits
mailing list