| Issue |
172932
|
| Summary |
[AMDGPU] Long strings of loads cause VMCNT overflow
|
| Labels |
|
| Assignees |
|
| Reporter |
krzysz00
|
I have observed that (on gfx1100, but I suspect this may affect other chips), a sufficiently long sequence of loads will cause the backend (on or around current main - 0729a74e and 42042443 have this bug) to emit more than 63 loads without issuing a waitcnt to bring the number of loads down below the hardware limit.
Overflowing VMCNT (which on gfx11 and other architectures, like gfx9, is stored as 6 bits) appears to have undefined behavior. In practice, this has led to unstable numerical results in a ML workload's matrix-vector multiplication where stale values were read because a waitcnt was passed before a value returned ... sometimes.
The full compilation for `input.ll` (attached below) was done with
```sh
llc -O3 -mtriple=amdgcn-amd-mdhsa -mcpu=gfx1100 -mattr='+wavefrontsize32' input.ll
```
Then, I reduced the testcase down to the following input (looking at the debug logs from si-insert-waitcnts to gauge interestingness) which is also attached as `reduced.ll`
<details>
<summary>Reduced LLVM IR</summary>
```llvm
target datalayout = "e-m: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-p8:128:128:128:48-p9:192:256:256:32-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-G1-ni:7:8:9"
target triple = "amdgcn-amd-amdhsa"
define amdgpu_kernel void @"main$async_dispatch_28_matmul_like_Dx1024x14x14x512_f32"(ptr addrspace(1) %invariant.gep, ptr addrspace(1) %0, ptr addrspace(1) %1, ptr addrspace(1) %2, ptr addrspace(1) %3, ptr addrspace(1) %4, ptr addrspace(1) %5, ptr addrspace(1) %6, ptr addrspace(1) %7, ptr addrspace(1) %8, ptr addrspace(1) %9, ptr addrspace(1) %10, ptr addrspace(1) %11, ptr addrspace(1) %12, ptr addrspace(1) %13, ptr addrspace(1) %14, ptr addrspace(1) %15, ptr addrspace(1) %16, ptr addrspace(1) %17, ptr addrspace(1) %18, ptr addrspace(1) %19, ptr addrspace(1) %20, ptr addrspace(1) %21, ptr addrspace(1) %22, ptr addrspace(1) %23, ptr addrspace(1) %24, ptr addrspace(1) %25, ptr addrspace(1) %26, ptr addrspace(1) %27, ptr addrspace(1) %28, ptr addrspace(1) %29, ptr addrspace(1) %30, ptr addrspace(1) %31, ptr addrspace(1) %32, ptr addrspace(1) %33, ptr addrspace(1) %34, ptr addrspace(1) %35, ptr addrspace(1) %36, ptr addrspace(1) %37, ptr addrspace(1) %38, ptr addrspace(1) %39, ptr addrspace(1) %40, ptr addrspace(1) %41, ptr addrspace(1) %42, ptr addrspace(1) %43, ptr addrspace(1) %44, ptr addrspace(1) %45, ptr addrspace(1) %46, ptr addrspace(1) %47, ptr addrspace(1) %48, ptr addrspace(1) %49, ptr addrspace(7) %50) {
.lr.ph197:
br label %.lr.ph
.lr.ph: ; preds = %.lr.ph, %.lr.ph197
%51 = load float, ptr addrspace(1) %27, align 8
%52 = load float, ptr addrspace(1) inttoptr (i64 80 to ptr addrspace(1)), align 16
%53 = load float, ptr addrspace(1) inttoptr (i64 96 to ptr addrspace(1)), align 32
%54 = insertelement <14 x float> zeroinitializer, float %53, i64 0
%55 = load float, ptr addrspace(1) inttoptr (i64 88 to ptr addrspace(1)), align 8
%56 = insertelement <14 x float> %54, float %55, i64 1
%57 = load float, ptr addrspace(1) null, align 8
%58 = insertelement <14 x float> %56, float %57, i64 9
%59 = load float, ptr addrspace(1) %43, align 32
%60 = insertelement <14 x float> zeroinitializer, float %59, i64 0
%61 = load float, ptr addrspace(1) %44, align 8
%62 = insertelement <14 x float> %60, float %61, i64 1
%63 = load float, ptr addrspace(1) %45, align 16
%64 = insertelement <14 x float> %62, float %63, i64 2
%65 = load float, ptr addrspace(1) %46, align 8
%66 = insertelement <14 x float> %64, float %65, i64 3
%67 = getelementptr i8, ptr addrspace(1) %43, i64 32
%68 = load float, ptr addrspace(1) %67, align 32
%69 = insertelement <14 x float> %66, float %68, i64 4
%70 = load float, ptr addrspace(1) %47, align 8
%71 = insertelement <14 x float> %69, float %70, i64 5
%72 = getelementptr i8, ptr addrspace(1) %43, i64 48
%73 = load float, ptr addrspace(1) %72, align 16
%74 = insertelement <14 x float> %71, float %73, i64 6
%75 = getelementptr i8, ptr addrspace(1) %43, i64 56
%76 = load float, ptr addrspace(1) %75, align 8
%77 = insertelement <14 x float> %74, float %76, i64 7
%78 = load float, ptr addrspace(1) %13, align 32
%79 = insertelement <14 x float> %77, float %78, i64 8
%80 = load float, ptr addrspace(1) %49, align 8
%81 = load float, ptr addrspace(1) %28, align 32
%82 = insertelement <14 x float> zeroinitializer, float %81, i64 0
%83 = load float, ptr addrspace(1) %29, align 8
%84 = insertelement <14 x float> %82, float %83, i64 1
%85 = load float, ptr addrspace(1) %30, align 16
%86 = insertelement <14 x float> %84, float %85, i64 2
%87 = load float, ptr addrspace(1) %31, align 8
%88 = insertelement <14 x float> %86, float %87, i64 3
%89 = load float, ptr addrspace(1) %32, align 32
%90 = insertelement <14 x float> %88, float %89, i64 4
%91 = load float, ptr addrspace(1) %33, align 8
%92 = insertelement <14 x float> %90, float %91, i64 5
%93 = load float, ptr addrspace(1) %34, align 16
%94 = insertelement <14 x float> %92, float %93, i64 6
%95 = load float, ptr addrspace(1) %35, align 8
%96 = insertelement <14 x float> %94, float %95, i64 7
%97 = load float, ptr addrspace(1) %36, align 32
%98 = insertelement <14 x float> %96, float %97, i64 8
%99 = load float, ptr addrspace(1) %37, align 8
%100 = insertelement <14 x float> %98, float %99, i64 9
%101 = load float, ptr addrspace(1) %38, align 16
%102 = insertelement <14 x float> %100, float %101, i64 10
%103 = load float, ptr addrspace(1) %39, align 8
%104 = insertelement <14 x float> %102, float %103, i64 11
%105 = load float, ptr addrspace(1) %40, align 32
%106 = insertelement <14 x float> %104, float %105, i64 12
%107 = load float, ptr addrspace(1) %41, align 8
%108 = insertelement <14 x float> %106, float %107, i64 13
%109 = load float, ptr addrspace(1) %14, align 32
%110 = insertelement <14 x float> zeroinitializer, float %109, i64 0
%111 = load float, ptr addrspace(1) %15, align 8
%112 = insertelement <14 x float> %110, float %111, i64 1
%113 = load float, ptr addrspace(1) %16, align 16
%114 = insertelement <14 x float> %112, float %113, i64 2
%115 = load float, ptr addrspace(1) %17, align 8
%116 = insertelement <14 x float> %114, float %115, i64 3
%117 = load float, ptr addrspace(1) %18, align 32
%118 = insertelement <14 x float> %116, float %117, i64 4
%119 = load float, ptr addrspace(1) %19, align 8
%120 = insertelement <14 x float> %118, float %119, i64 5
%121 = load float, ptr addrspace(1) %20, align 16
%122 = insertelement <14 x float> %120, float %121, i64 6
%123 = load float, ptr addrspace(1) %21, align 8
%124 = insertelement <14 x float> %122, float %123, i64 7
%125 = load float, ptr addrspace(1) %22, align 32
%126 = insertelement <14 x float> %124, float %125, i64 8
%127 = load float, ptr addrspace(1) %23, align 8
%128 = insertelement <14 x float> %126, float %127, i64 9
%129 = load float, ptr addrspace(1) %24, align 16
%130 = insertelement <14 x float> %128, float %129, i64 10
%131 = load float, ptr addrspace(1) %25, align 8
%132 = insertelement <14 x float> %130, float %131, i64 11
%133 = load float, ptr addrspace(1) %26, align 32
%134 = insertelement <14 x float> %132, float %133, i64 12
%135 = load float, ptr addrspace(1) %invariant.gep, align 32
%136 = insertelement <14 x float> zeroinitializer, float %135, i64 0
%137 = load float, ptr addrspace(1) %0, align 8
%138 = insertelement <14 x float> %136, float %137, i64 1
%139 = load float, ptr addrspace(1) %1, align 16
%140 = insertelement <14 x float> %138, float %139, i64 2
%141 = load float, ptr addrspace(1) %2, align 8
%142 = insertelement <14 x float> %140, float %141, i64 3
%143 = load float, ptr addrspace(1) %3, align 32
%144 = insertelement <14 x float> %142, float %143, i64 4
%145 = load float, ptr addrspace(1) %4, align 8
%146 = insertelement <14 x float> %144, float %145, i64 5
%147 = load float, ptr addrspace(1) %5, align 16
%148 = insertelement <14 x float> %146, float %147, i64 6
%149 = load float, ptr addrspace(1) %6, align 8
%150 = insertelement <14 x float> %148, float %149, i64 7
%151 = load float, ptr addrspace(1) %7, align 32
%152 = insertelement <14 x float> %150, float %151, i64 8
%153 = load float, ptr addrspace(1) %8, align 8
%154 = load <32 x float>, ptr addrspace(7) %50, align 4
%155 = shufflevector <32 x float> %154, <32 x float> zeroinitializer, <14 x i32> <i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7>
%156 = shufflevector <32 x float> %154, <32 x float> zeroinitializer, <14 x i32> <i32 11, i32 11, i32 11, i32 11, i32 11, i32 11, i32 11, i32 11, i32 11, i32 11, i32 11, i32 11, i32 11, i32 11>
%157 = shufflevector <32 x float> %154, <32 x float> zeroinitializer, <14 x i32> <i32 13, i32 13, i32 13, i32 13, i32 13, i32 13, i32 13, i32 13, i32 13, i32 13, i32 13, i32 13, i32 13, i32 13>
%158 = tail call <14 x float> @llvm.fma.v14f32(<14 x float> %156, <14 x float> zeroinitializer, <14 x float> %157)
%159 = insertelement <14 x float> %79, float %80, i64 9
%160 = load float, ptr addrspace(1) %42, align 16
%161 = insertelement <14 x float> %159, float %160, i64 10
%162 = load float, ptr addrspace(1) %48, align 8
%163 = insertelement <14 x float> %161, float %162, i64 11
%164 = getelementptr i8, ptr addrspace(1) %43, i64 96
%165 = load float, ptr addrspace(1) %164, align 32
%166 = insertelement <14 x float> %163, float %165, i64 12
%167 = getelementptr i8, ptr addrspace(1) %43, i64 104
%168 = load float, ptr addrspace(1) %167, align 8
%169 = insertelement <14 x float> %166, float %168, i64 13
%170 = shufflevector <32 x float> %154, <32 x float> zeroinitializer, <14 x i32> <i32 3, i32 3, i32 3, i32 3, i32 3, i32 3, i32 3, i32 3, i32 3, i32 3, i32 3, i32 3, i32 3, i32 3>
%171 = insertelement <14 x float> %58, float %52, i64 10
%172 = tail call <14 x float> @llvm.fma.v14f32(<14 x float> %155, <14 x float> zeroinitializer, <14 x float> %158)
%173 = tail call <14 x float> @llvm.fma.v14f32(<14 x float> %171, <14 x float> zeroinitializer, <14 x float> %172)
%174 = tail call <14 x float> @llvm.fma.v14f32(<14 x float> %169, <14 x float> %170, <14 x float> %173)
%175 = insertelement <14 x float> %152, float %153, i64 9
%176 = load float, ptr addrspace(1) %9, align 16
%177 = insertelement <14 x float> %175, float %176, i64 10
%178 = load float, ptr addrspace(1) %10, align 8
%179 = insertelement <14 x float> %177, float %178, i64 11
%180 = load float, ptr addrspace(1) %11, align 32
%181 = insertelement <14 x float> %179, float %180, i64 12
%182 = load float, ptr addrspace(1) %12, align 8
%183 = insertelement <14 x float> %181, float %182, i64 13
%184 = insertelement <14 x float> %134, float %51, i64 13
%185 = tail call <14 x float> @llvm.fma.v14f32(<14 x float> %108, <14 x float> zeroinitializer, <14 x float> %174)
%186 = tail call <14 x float> @llvm.fma.v14f32(<14 x float> %184, <14 x float> zeroinitializer, <14 x float> %185)
%187 = tail call <14 x float> @llvm.fma.v14f32(<14 x float> %183, <14 x float> zeroinitializer, <14 x float> %186)
store <14 x float> %187, ptr addrspace(1) null, align 8
br label %.lr.ph
}
; Function Attrs: nocallback nocreateundeforpoison nofree nosync nounwind speculatable willreturn memory(none)
declare <14 x float> @llvm.fma.v14f32(<14 x float>, <14 x float>, <14 x float>) #0
; uselistorder directives
uselistorder ptr @llvm.fma.v14f32, { 6, 5, 4, 3, 2, 1, 0 }
attributes #0 = { nocallback nocreateundeforpoison nofree nosync nounwind speculatable willreturn memory(none) }
```
</details>
When this is compiled with
```sh
llc -o reduced.s -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1100 reduced.ll
```
the resulting assembly - in relevant part - is as follows
<details>
<summary>Excerpt of generated assembly</summary>
```asm
s_clause 0x3
buffer_load_b128 v[19:22], v15, s[100:103], 0 offen offset:32
buffer_load_b128 v[27:30], v15, s[100:103], 0 offen
buffer_load_b128 v[18:21], v15, s[100:103], 0 offen offset:48
buffer_load_b128 v[23:26], v15, s[100:103], 0 offen offset:16
global_load_b32 v16, v[0:1], off
global_load_b32 v17, v[6:7], off
global_load_b32 v20, v[4:5], off
global_load_b32 v23, v[2:3], off
s_waitcnt lgkmcnt(0)
global_load_b32 v24, v14, s[8:9] offset:32
v_readlane_b32 s100, v82, 4
v_readlane_b32 s101, v82, 5
v_readlane_b32 s102, v82, 6
v_readlane_b32 s103, v82, 7
s_clause 0x1f
global_load_b32 v25, v14, s[100:101]
global_load_b32 v27, v14, s[8:9] offset:48
global_load_b32 v28, v14, s[8:9] offset:56
global_load_b32 v29, v14, s[12:13]
global_load_b32 v31, v14, s[14:15]
global_load_b32 v32, v14, s[102:103]
global_load_b32 v33, v14, s[8:9] offset:96
global_load_b32 v34, v14, s[8:9] offset:104
global_load_b32 v35, v14, s[48:49]
global_load_b32 v36, v14, s[6:7]
global_load_b32 v37, v14, s[34:35]
global_load_b32 v38, v14, s[8:9]
global_load_b32 v39, v14, s[10:11]
global_load_b32 v40, v14, s[0:1]
global_load_b32 v41, v14, s[98:99]
global_load_b32 v42, v14, s[96:97]
global_load_b32 v43, v14, s[94:95]
global_load_b32 v44, v14, s[4:5]
global_load_b32 v45, v14, s[2:3]
global_load_b32 v46, v14, s[84:85]
global_load_b32 v47, v14, s[82:83]
global_load_b32 v48, v14, s[80:81]
global_load_b32 v49, v14, s[86:87]
global_load_b32 v50, v14, s[88:89]
global_load_b32 v51, v14, s[90:91]
global_load_b32 v52, v14, s[92:93]
global_load_b32 v53, v14, s[78:79]
global_load_b32 v54, v14, s[58:59]
global_load_b32 v55, v14, s[60:61]
global_load_b32 v56, v14, s[62:63]
global_load_b32 v57, v14, s[64:65]
global_load_b32 v58, v14, s[50:51]
s_clause 0x16
global_load_b32 v59, v14, s[52:53]
global_load_b32 v60, v14, s[54:55]
global_load_b32 v61, v14, s[56:57]
global_load_b32 v62, v14, s[74:75]
global_load_b32 v63, v14, s[72:73]
global_load_b32 v64, v14, s[70:71]
global_load_b32 v65, v14, s[68:69]
global_load_b32 v66, v14, s[76:77]
global_load_b32 v67, v14, s[66:67]
global_load_b32 v68, v14, s[42:43]
global_load_b32 v69, v14, s[40:41]
global_load_b32 v70, v14, s[38:39]
global_load_b32 v71, v14, s[46:47]
global_load_b32 v72, v14, s[22:23]
global_load_b32 v73, v14, s[20:21]
global_load_b32 v74, v14, s[18:19]
global_load_b32 v75, v14, s[30:31]
global_load_b32 v76, v14, s[28:29]
global_load_b32 v77, v14, s[26:27]
global_load_b32 v78, v14, s[24:25]
global_load_b32 v79, v14, s[16:17]
global_load_b32 v80, v14, s[44:45]
global_load_b32 v81, v14, s[36:37]
s_waitcnt vmcnt(61)
v_fmac_f32_e32 v19, 0, v22
s_waitcnt vmcnt(60)
```
</details>
Observe that if we add up the clause lengths (noting the instruction's argument is length - 1) we get 32 + 17 + 4 = 59 loads, and then if we include the 5 unclaused `global_load`s after the `buffer_load`s, we get **64** t<truncated>Please see the issue for the entire body.
![]()
_______________________________________________
llvm-bugs mailing list
[email protected]
https://lists.llvm.org/cgi-bin/mailman/listinfo/llvm-bugs
