[RegAlloc] Fix the terminal rule check for interfere with DstReg (#168661)

This maybe a bug which is introduced by commit
6749ae36b4a33769e7a77cf812d7cd0a908ae3b9, and has been present ever
since.
In this case, `OtherReg` always overlaps with `DstReg` cause they from
the `Copy` all.

1 files changed, 75 insertions, 75 deletions

diff --git a/llvm/test/CodeGen/NVPTX/atomics-b128.ll b/llvm/test/CodeGen/NVPTX/atomics-b128.ll
index 3057e91e8ebe..b2a3f94d11a1 100644
--- a/llvm/test/CodeGen/NVPTX/atomics-b128.ll
+++ b/llvm/test/CodeGen/NVPTX/atomics-b128.ll
@@ -756,24 +756,24 @@ define i128 @test_atomicrmw_and(ptr %ptr, i128 %val) {
 ; CHECK-NEXT:    ld.v2.b64 {%rd11, %rd12}, [%rd3];
 ; CHECK-NEXT:  $L__BB34_1: // %atomicrmw.start
 ; CHECK-NEXT:    // =>This Inner Loop Header: Depth=1
-; CHECK-NEXT:    mov.b64 %rd2, %rd12;
-; CHECK-NEXT:    mov.b64 %rd1, %rd11;
-; CHECK-NEXT:    and.b64 %rd6, %rd1, %rd4;
-; CHECK-NEXT:    and.b64 %rd7, %rd2, %rd5;
+; CHECK-NEXT:    and.b64 %rd6, %rd11, %rd4;
+; CHECK-NEXT:    and.b64 %rd7, %rd12, %rd5;
 ; CHECK-NEXT:    {
 ; CHECK-NEXT:    .reg .b128 cmp, swap, dst;
-; CHECK-NEXT:    mov.b128 cmp, {%rd1, %rd2};
+; CHECK-NEXT:    mov.b128 cmp, {%rd11, %rd12};
 ; CHECK-NEXT:    mov.b128 swap, {%rd6, %rd7};
 ; CHECK-NEXT:    atom.relaxed.sys.cas.b128 dst, [%rd3], cmp, swap;
-; CHECK-NEXT:    mov.b128 {%rd11, %rd12}, dst;
+; CHECK-NEXT:    mov.b128 {%rd1, %rd2}, dst;
 ; CHECK-NEXT:    }
-; CHECK-NEXT:    xor.b64 %rd8, %rd12, %rd2;
-; CHECK-NEXT:    xor.b64 %rd9, %rd11, %rd1;
+; CHECK-NEXT:    xor.b64 %rd8, %rd2, %rd12;
+; CHECK-NEXT:    xor.b64 %rd9, %rd1, %rd11;
 ; CHECK-NEXT:    or.b64 %rd10, %rd9, %rd8;
 ; CHECK-NEXT:    setp.ne.b64 %p1, %rd10, 0;
+; CHECK-NEXT:    mov.b64 %rd11, %rd1;
+; CHECK-NEXT:    mov.b64 %rd12, %rd2;
 ; CHECK-NEXT:    @%p1 bra $L__BB34_1;
 ; CHECK-NEXT:  // %bb.2: // %atomicrmw.end
-; CHECK-NEXT:    st.param.v2.b64 [func_retval0], {%rd11, %rd12};
+; CHECK-NEXT:    st.param.v2.b64 [func_retval0], {%rd1, %rd2};
 ; CHECK-NEXT:    ret;
   %ret = atomicrmw and ptr %ptr, i128 %val monotonic
   ret i128 %ret
@@ -791,24 +791,24 @@ define i128 @test_atomicrmw_or(ptr %ptr, i128 %val) {
 ; CHECK-NEXT:    ld.v2.b64 {%rd11, %rd12}, [%rd3];
 ; CHECK-NEXT:  $L__BB35_1: // %atomicrmw.start
 ; CHECK-NEXT:    // =>This Inner Loop Header: Depth=1
-; CHECK-NEXT:    mov.b64 %rd2, %rd12;
-; CHECK-NEXT:    mov.b64 %rd1, %rd11;
-; CHECK-NEXT:    or.b64 %rd6, %rd1, %rd4;
-; CHECK-NEXT:    or.b64 %rd7, %rd2, %rd5;
+; CHECK-NEXT:    or.b64 %rd6, %rd11, %rd4;
+; CHECK-NEXT:    or.b64 %rd7, %rd12, %rd5;
 ; CHECK-NEXT:    {
 ; CHECK-NEXT:    .reg .b128 cmp, swap, dst;
-; CHECK-NEXT:    mov.b128 cmp, {%rd1, %rd2};
+; CHECK-NEXT:    mov.b128 cmp, {%rd11, %rd12};
 ; CHECK-NEXT:    mov.b128 swap, {%rd6, %rd7};
 ; CHECK-NEXT:    atom.relaxed.sys.cas.b128 dst, [%rd3], cmp, swap;
-; CHECK-NEXT:    mov.b128 {%rd11, %rd12}, dst;
+; CHECK-NEXT:    mov.b128 {%rd1, %rd2}, dst;
 ; CHECK-NEXT:    }
-; CHECK-NEXT:    xor.b64 %rd8, %rd12, %rd2;
-; CHECK-NEXT:    xor.b64 %rd9, %rd11, %rd1;
+; CHECK-NEXT:    xor.b64 %rd8, %rd2, %rd12;
+; CHECK-NEXT:    xor.b64 %rd9, %rd1, %rd11;
 ; CHECK-NEXT:    or.b64 %rd10, %rd9, %rd8;
 ; CHECK-NEXT:    setp.ne.b64 %p1, %rd10, 0;
+; CHECK-NEXT:    mov.b64 %rd11, %rd1;
+; CHECK-NEXT:    mov.b64 %rd12, %rd2;
 ; CHECK-NEXT:    @%p1 bra $L__BB35_1;
 ; CHECK-NEXT:  // %bb.2: // %atomicrmw.end
-; CHECK-NEXT:    st.param.v2.b64 [func_retval0], {%rd11, %rd12};
+; CHECK-NEXT:    st.param.v2.b64 [func_retval0], {%rd1, %rd2};
 ; CHECK-NEXT:    ret;
   %ret = atomicrmw or ptr %ptr, i128 %val monotonic
   ret i128 %ret
@@ -826,24 +826,24 @@ define i128 @test_atomicrmw_xor(ptr %ptr, i128 %val) {
 ; CHECK-NEXT:    ld.v2.b64 {%rd11, %rd12}, [%rd3];
 ; CHECK-NEXT:  $L__BB36_1: // %atomicrmw.start
 ; CHECK-NEXT:    // =>This Inner Loop Header: Depth=1
-; CHECK-NEXT:    mov.b64 %rd2, %rd12;
-; CHECK-NEXT:    mov.b64 %rd1, %rd11;
-; CHECK-NEXT:    xor.b64 %rd6, %rd1, %rd4;
-; CHECK-NEXT:    xor.b64 %rd7, %rd2, %rd5;
+; CHECK-NEXT:    xor.b64 %rd6, %rd11, %rd4;
+; CHECK-NEXT:    xor.b64 %rd7, %rd12, %rd5;
 ; CHECK-NEXT:    {
 ; CHECK-NEXT:    .reg .b128 cmp, swap, dst;
-; CHECK-NEXT:    mov.b128 cmp, {%rd1, %rd2};
+; CHECK-NEXT:    mov.b128 cmp, {%rd11, %rd12};
 ; CHECK-NEXT:    mov.b128 swap, {%rd6, %rd7};
 ; CHECK-NEXT:    atom.relaxed.sys.cas.b128 dst, [%rd3], cmp, swap;
-; CHECK-NEXT:    mov.b128 {%rd11, %rd12}, dst;
+; CHECK-NEXT:    mov.b128 {%rd1, %rd2}, dst;
 ; CHECK-NEXT:    }
-; CHECK-NEXT:    xor.b64 %rd8, %rd12, %rd2;
-; CHECK-NEXT:    xor.b64 %rd9, %rd11, %rd1;
+; CHECK-NEXT:    xor.b64 %rd8, %rd2, %rd12;
+; CHECK-NEXT:    xor.b64 %rd9, %rd1, %rd11;
 ; CHECK-NEXT:    or.b64 %rd10, %rd9, %rd8;
 ; CHECK-NEXT:    setp.ne.b64 %p1, %rd10, 0;
+; CHECK-NEXT:    mov.b64 %rd11, %rd1;
+; CHECK-NEXT:    mov.b64 %rd12, %rd2;
 ; CHECK-NEXT:    @%p1 bra $L__BB36_1;
 ; CHECK-NEXT:  // %bb.2: // %atomicrmw.end
-; CHECK-NEXT:    st.param.v2.b64 [func_retval0], {%rd11, %rd12};
+; CHECK-NEXT:    st.param.v2.b64 [func_retval0], {%rd1, %rd2};
 ; CHECK-NEXT:    ret;
   %ret = atomicrmw xor ptr %ptr, i128 %val monotonic
   ret i128 %ret
@@ -861,29 +861,29 @@ define i128 @test_atomicrmw_min(ptr %ptr, i128 %val) {
 ; CHECK-NEXT:    ld.v2.b64 {%rd11, %rd12}, [%rd3];
 ; CHECK-NEXT:  $L__BB37_1: // %atomicrmw.start
 ; CHECK-NEXT:    // =>This Inner Loop Header: Depth=1
-; CHECK-NEXT:    mov.b64 %rd2, %rd12;
-; CHECK-NEXT:    mov.b64 %rd1, %rd11;
-; CHECK-NEXT:    setp.lt.u64 %p1, %rd1, %rd4;
-; CHECK-NEXT:    setp.eq.b64 %p2, %rd2, %rd5;
+; CHECK-NEXT:    setp.lt.u64 %p1, %rd11, %rd4;
+; CHECK-NEXT:    setp.eq.b64 %p2, %rd12, %rd5;
 ; CHECK-NEXT:    and.pred %p3, %p2, %p1;
-; CHECK-NEXT:    setp.lt.s64 %p4, %rd2, %rd5;
+; CHECK-NEXT:    setp.lt.s64 %p4, %rd12, %rd5;
 ; CHECK-NEXT:    or.pred %p5, %p3, %p4;
-; CHECK-NEXT:    selp.b64 %rd6, %rd2, %rd5, %p5;
-; CHECK-NEXT:    selp.b64 %rd7, %rd1, %rd4, %p5;
+; CHECK-NEXT:    selp.b64 %rd6, %rd12, %rd5, %p5;
+; CHECK-NEXT:    selp.b64 %rd7, %rd11, %rd4, %p5;
 ; CHECK-NEXT:    {
 ; CHECK-NEXT:    .reg .b128 cmp, swap, dst;
-; CHECK-NEXT:    mov.b128 cmp, {%rd1, %rd2};
+; CHECK-NEXT:    mov.b128 cmp, {%rd11, %rd12};
 ; CHECK-NEXT:    mov.b128 swap, {%rd7, %rd6};
 ; CHECK-NEXT:    atom.relaxed.sys.cas.b128 dst, [%rd3], cmp, swap;
-; CHECK-NEXT:    mov.b128 {%rd11, %rd12}, dst;
+; CHECK-NEXT:    mov.b128 {%rd1, %rd2}, dst;
 ; CHECK-NEXT:    }
-; CHECK-NEXT:    xor.b64 %rd8, %rd12, %rd2;
-; CHECK-NEXT:    xor.b64 %rd9, %rd11, %rd1;
+; CHECK-NEXT:    xor.b64 %rd8, %rd2, %rd12;
+; CHECK-NEXT:    xor.b64 %rd9, %rd1, %rd11;
 ; CHECK-NEXT:    or.b64 %rd10, %rd9, %rd8;
 ; CHECK-NEXT:    setp.ne.b64 %p6, %rd10, 0;
+; CHECK-NEXT:    mov.b64 %rd11, %rd1;
+; CHECK-NEXT:    mov.b64 %rd12, %rd2;
 ; CHECK-NEXT:    @%p6 bra $L__BB37_1;
 ; CHECK-NEXT:  // %bb.2: // %atomicrmw.end
-; CHECK-NEXT:    st.param.v2.b64 [func_retval0], {%rd11, %rd12};
+; CHECK-NEXT:    st.param.v2.b64 [func_retval0], {%rd1, %rd2};
 ; CHECK-NEXT:    ret;
   %ret = atomicrmw min ptr %ptr, i128 %val monotonic
   ret i128 %ret
@@ -901,29 +901,29 @@ define i128 @test_atomicrmw_max(ptr %ptr, i128 %val) {
 ; CHECK-NEXT:    ld.v2.b64 {%rd11, %rd12}, [%rd3];
 ; CHECK-NEXT:  $L__BB38_1: // %atomicrmw.start
 ; CHECK-NEXT:    // =>This Inner Loop Header: Depth=1
-; CHECK-NEXT:    mov.b64 %rd2, %rd12;
-; CHECK-NEXT:    mov.b64 %rd1, %rd11;
-; CHECK-NEXT:    setp.gt.u64 %p1, %rd1, %rd4;
-; CHECK-NEXT:    setp.eq.b64 %p2, %rd2, %rd5;
+; CHECK-NEXT:    setp.gt.u64 %p1, %rd11, %rd4;
+; CHECK-NEXT:    setp.eq.b64 %p2, %rd12, %rd5;
 ; CHECK-NEXT:    and.pred %p3, %p2, %p1;
-; CHECK-NEXT:    setp.gt.s64 %p4, %rd2, %rd5;
+; CHECK-NEXT:    setp.gt.s64 %p4, %rd12, %rd5;
 ; CHECK-NEXT:    or.pred %p5, %p3, %p4;
-; CHECK-NEXT:    selp.b64 %rd6, %rd2, %rd5, %p5;
-; CHECK-NEXT:    selp.b64 %rd7, %rd1, %rd4, %p5;
+; CHECK-NEXT:    selp.b64 %rd6, %rd12, %rd5, %p5;
+; CHECK-NEXT:    selp.b64 %rd7, %rd11, %rd4, %p5;
 ; CHECK-NEXT:    {
 ; CHECK-NEXT:    .reg .b128 cmp, swap, dst;
-; CHECK-NEXT:    mov.b128 cmp, {%rd1, %rd2};
+; CHECK-NEXT:    mov.b128 cmp, {%rd11, %rd12};
 ; CHECK-NEXT:    mov.b128 swap, {%rd7, %rd6};
 ; CHECK-NEXT:    atom.relaxed.sys.cas.b128 dst, [%rd3], cmp, swap;
-; CHECK-NEXT:    mov.b128 {%rd11, %rd12}, dst;
+; CHECK-NEXT:    mov.b128 {%rd1, %rd2}, dst;
 ; CHECK-NEXT:    }
-; CHECK-NEXT:    xor.b64 %rd8, %rd12, %rd2;
-; CHECK-NEXT:    xor.b64 %rd9, %rd11, %rd1;
+; CHECK-NEXT:    xor.b64 %rd8, %rd2, %rd12;
+; CHECK-NEXT:    xor.b64 %rd9, %rd1, %rd11;
 ; CHECK-NEXT:    or.b64 %rd10, %rd9, %rd8;
 ; CHECK-NEXT:    setp.ne.b64 %p6, %rd10, 0;
+; CHECK-NEXT:    mov.b64 %rd11, %rd1;
+; CHECK-NEXT:    mov.b64 %rd12, %rd2;
 ; CHECK-NEXT:    @%p6 bra $L__BB38_1;
 ; CHECK-NEXT:  // %bb.2: // %atomicrmw.end
-; CHECK-NEXT:    st.param.v2.b64 [func_retval0], {%rd11, %rd12};
+; CHECK-NEXT:    st.param.v2.b64 [func_retval0], {%rd1, %rd2};
 ; CHECK-NEXT:    ret;
   %ret = atomicrmw max ptr %ptr, i128 %val monotonic
   ret i128 %ret
@@ -941,29 +941,29 @@ define i128 @test_atomicrmw_umin(ptr %ptr, i128 %val) {
 ; CHECK-NEXT:    ld.v2.b64 {%rd11, %rd12}, [%rd3];
 ; CHECK-NEXT:  $L__BB39_1: // %atomicrmw.start
 ; CHECK-NEXT:    // =>This Inner Loop Header: Depth=1
-; CHECK-NEXT:    mov.b64 %rd2, %rd12;
-; CHECK-NEXT:    mov.b64 %rd1, %rd11;
-; CHECK-NEXT:    setp.lt.u64 %p1, %rd1, %rd4;
-; CHECK-NEXT:    setp.eq.b64 %p2, %rd2, %rd5;
+; CHECK-NEXT:    setp.lt.u64 %p1, %rd11, %rd4;
+; CHECK-NEXT:    setp.eq.b64 %p2, %rd12, %rd5;
 ; CHECK-NEXT:    and.pred %p3, %p2, %p1;
-; CHECK-NEXT:    setp.lt.u64 %p4, %rd2, %rd5;
+; CHECK-NEXT:    setp.lt.u64 %p4, %rd12, %rd5;
 ; CHECK-NEXT:    or.pred %p5, %p3, %p4;
-; CHECK-NEXT:    selp.b64 %rd6, %rd2, %rd5, %p5;
-; CHECK-NEXT:    selp.b64 %rd7, %rd1, %rd4, %p5;
+; CHECK-NEXT:    selp.b64 %rd6, %rd12, %rd5, %p5;
+; CHECK-NEXT:    selp.b64 %rd7, %rd11, %rd4, %p5;
 ; CHECK-NEXT:    {
 ; CHECK-NEXT:    .reg .b128 cmp, swap, dst;
-; CHECK-NEXT:    mov.b128 cmp, {%rd1, %rd2};
+; CHECK-NEXT:    mov.b128 cmp, {%rd11, %rd12};
 ; CHECK-NEXT:    mov.b128 swap, {%rd7, %rd6};
 ; CHECK-NEXT:    atom.relaxed.sys.cas.b128 dst, [%rd3], cmp, swap;
-; CHECK-NEXT:    mov.b128 {%rd11, %rd12}, dst;
+; CHECK-NEXT:    mov.b128 {%rd1, %rd2}, dst;
 ; CHECK-NEXT:    }
-; CHECK-NEXT:    xor.b64 %rd8, %rd12, %rd2;
-; CHECK-NEXT:    xor.b64 %rd9, %rd11, %rd1;
+; CHECK-NEXT:    xor.b64 %rd8, %rd2, %rd12;
+; CHECK-NEXT:    xor.b64 %rd9, %rd1, %rd11;
 ; CHECK-NEXT:    or.b64 %rd10, %rd9, %rd8;
 ; CHECK-NEXT:    setp.ne.b64 %p6, %rd10, 0;
+; CHECK-NEXT:    mov.b64 %rd11, %rd1;
+; CHECK-NEXT:    mov.b64 %rd12, %rd2;
 ; CHECK-NEXT:    @%p6 bra $L__BB39_1;
 ; CHECK-NEXT:  // %bb.2: // %atomicrmw.end
-; CHECK-NEXT:    st.param.v2.b64 [func_retval0], {%rd11, %rd12};
+; CHECK-NEXT:    st.param.v2.b64 [func_retval0], {%rd1, %rd2};
 ; CHECK-NEXT:    ret;
   %ret = atomicrmw umin ptr %ptr, i128 %val monotonic
   ret i128 %ret
@@ -981,29 +981,29 @@ define i128 @test_atomicrmw_umax(ptr %ptr, i128 %val) {
 ; CHECK-NEXT:    ld.v2.b64 {%rd11, %rd12}, [%rd3];
 ; CHECK-NEXT:  $L__BB40_1: // %atomicrmw.start
 ; CHECK-NEXT:    // =>This Inner Loop Header: Depth=1
-; CHECK-NEXT:    mov.b64 %rd2, %rd12;
-; CHECK-NEXT:    mov.b64 %rd1, %rd11;
-; CHECK-NEXT:    setp.gt.u64 %p1, %rd1, %rd4;
-; CHECK-NEXT:    setp.eq.b64 %p2, %rd2, %rd5;
+; CHECK-NEXT:    setp.gt.u64 %p1, %rd11, %rd4;
+; CHECK-NEXT:    setp.eq.b64 %p2, %rd12, %rd5;
 ; CHECK-NEXT:    and.pred %p3, %p2, %p1;
-; CHECK-NEXT:    setp.gt.u64 %p4, %rd2, %rd5;
+; CHECK-NEXT:    setp.gt.u64 %p4, %rd12, %rd5;
 ; CHECK-NEXT:    or.pred %p5, %p3, %p4;
-; CHECK-NEXT:    selp.b64 %rd6, %rd2, %rd5, %p5;
-; CHECK-NEXT:    selp.b64 %rd7, %rd1, %rd4, %p5;
+; CHECK-NEXT:    selp.b64 %rd6, %rd12, %rd5, %p5;
+; CHECK-NEXT:    selp.b64 %rd7, %rd11, %rd4, %p5;
 ; CHECK-NEXT:    {
 ; CHECK-NEXT:    .reg .b128 cmp, swap, dst;
-; CHECK-NEXT:    mov.b128 cmp, {%rd1, %rd2};
+; CHECK-NEXT:    mov.b128 cmp, {%rd11, %rd12};
 ; CHECK-NEXT:    mov.b128 swap, {%rd7, %rd6};
 ; CHECK-NEXT:    atom.relaxed.sys.cas.b128 dst, [%rd3], cmp, swap;
-; CHECK-NEXT:    mov.b128 {%rd11, %rd12}, dst;
+; CHECK-NEXT:    mov.b128 {%rd1, %rd2}, dst;
 ; CHECK-NEXT:    }
-; CHECK-NEXT:    xor.b64 %rd8, %rd12, %rd2;
-; CHECK-NEXT:    xor.b64 %rd9, %rd11, %rd1;
+; CHECK-NEXT:    xor.b64 %rd8, %rd2, %rd12;
+; CHECK-NEXT:    xor.b64 %rd9, %rd1, %rd11;
 ; CHECK-NEXT:    or.b64 %rd10, %rd9, %rd8;
 ; CHECK-NEXT:    setp.ne.b64 %p6, %rd10, 0;
+; CHECK-NEXT:    mov.b64 %rd11, %rd1;
+; CHECK-NEXT:    mov.b64 %rd12, %rd2;
 ; CHECK-NEXT:    @%p6 bra $L__BB40_1;
 ; CHECK-NEXT:  // %bb.2: // %atomicrmw.end
-; CHECK-NEXT:    st.param.v2.b64 [func_retval0], {%rd11, %rd12};
+; CHECK-NEXT:    st.param.v2.b64 [func_retval0], {%rd1, %rd2};
 ; CHECK-NEXT:    ret;
   %ret = atomicrmw umax ptr %ptr, i128 %val monotonic
   ret i128 %ret