[llvm-mca] Add tests for XOP and AVX512 instructions that implicitly clear the upper...

When the destination register of a XOP instruction is an XMM register, bits
[255:128] of the corresponding YMM register are cleared.

When the destination register of a EVEX encoded instruction is an XMM/YMM
register, the upper bits of the corresponding ZMM are cleared.
On processors that feature AVX512, a write to an XMM registers always clears the
upper portion of the corresponding ZMM register if the instruction is VEX or
EVEX encoded.

These new tests show some interesting cases which aren't correctly analyzed by
llvm-mca. The lack of knowledge related to the implicit update on the
super-registers is addressed by D48225.

llvm-svn: 334945

diff --git a/llvm/test/tools/llvm-mca/X86/Generic/avx512-super-registers-1.s b/llvm/test/tools/llvm-mca/X86/Generic/avx512-super-registers-1.s
new file mode 100644 (file)
index 0000000..52e6fc4
--- /dev/null
+++ b/llvm/test/tools/llvm-mca/X86/Generic/avx512-super-registers-1.s
@@ -0,0 +1,86 @@
+# NOTE: Assertions have been autogenerated by utils/update_mca_test_checks.py
+# RUN: llvm-mca -mtriple=x86_64-unknown-unknown -mcpu=x86-64 -timeline -timeline-max-iterations=2 < %s | FileCheck %s
+
+  vmulps  %zmm0, %zmm1, %zmm2
+  vaddps  %xmm1, %xmm1, %xmm2
+  vmulps  %ymm2, %ymm3, %ymm4
+  vaddps  %xmm4, %xmm5, %xmm6
+  vmulps  %xmm6, %xmm3, %xmm4
+  vaddps  %xmm4, %xmm5, %xmm0
+
+# CHECK:      Iterations:        100
+# CHECK-NEXT: Instructions:      600
+# CHECK-NEXT: Total Cycles:      2103
+# CHECK-NEXT: Dispatch Width:    4
+# CHECK-NEXT: IPC:               0.29
+# CHECK-NEXT: Block RThroughput: 3.0
+
+# CHECK:      Instruction Info:
+# CHECK-NEXT: [1]: #uOps
+# CHECK-NEXT: [2]: Latency
+# CHECK-NEXT: [3]: RThroughput
+# CHECK-NEXT: [4]: MayLoad
+# CHECK-NEXT: [5]: MayStore
+# CHECK-NEXT: [6]: HasSideEffects
+
+# CHECK:      [1]    [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  1      5     1.00                        vmulps %zmm0, %zmm1, %zmm2
+# CHECK-NEXT:  1      3     1.00                        vaddps %xmm1, %xmm1, %xmm2
+# CHECK-NEXT:  1      5     1.00                        vmulps %ymm2, %ymm3, %ymm4
+# CHECK-NEXT:  1      3     1.00                        vaddps %xmm4, %xmm5, %xmm6
+# CHECK-NEXT:  1      5     1.00                        vmulps %xmm6, %xmm3, %xmm4
+# CHECK-NEXT:  1      3     1.00                        vaddps %xmm4, %xmm5, %xmm0
+
+# CHECK:      Resources:
+# CHECK-NEXT: [0]   - SBDivider
+# CHECK-NEXT: [1]   - SBFPDivider
+# CHECK-NEXT: [2]   - SBPort0
+# CHECK-NEXT: [3]   - SBPort1
+# CHECK-NEXT: [4]   - SBPort4
+# CHECK-NEXT: [5]   - SBPort5
+# CHECK-NEXT: [6.0] - SBPort23
+# CHECK-NEXT: [6.1] - SBPort23
+
+# CHECK:      Resource pressure per iteration:
+# CHECK-NEXT: [0]    [1]    [2]    [3]    [4]    [5]    [6.0]  [6.1]
+# CHECK-NEXT:  -      -     3.00   3.00    -      -      -      -
+
+# CHECK:      Resource pressure by instruction:
+# CHECK-NEXT: [0]    [1]    [2]    [3]    [4]    [5]    [6.0]  [6.1]  Instructions:
+# CHECK-NEXT:  -      -     1.00    -      -      -      -      -     vmulps   %zmm0, %zmm1, %zmm2
+# CHECK-NEXT:  -      -      -     1.00    -      -      -      -     vaddps   %xmm1, %xmm1, %xmm2
+# CHECK-NEXT:  -      -     1.00    -      -      -      -      -     vmulps   %ymm2, %ymm3, %ymm4
+# CHECK-NEXT:  -      -      -     1.00    -      -      -      -     vaddps   %xmm4, %xmm5, %xmm6
+# CHECK-NEXT:  -      -     1.00    -      -      -      -      -     vmulps   %xmm6, %xmm3, %xmm4
+# CHECK-NEXT:  -      -      -     1.00    -      -      -      -     vaddps   %xmm4, %xmm5, %xmm0
+
+# CHECK:      Timeline view:
+# CHECK-NEXT:                     0123456789          0123456789
+# CHECK-NEXT: Index     0123456789          0123456789          01234
+
+# CHECK:      [0,0]     DeeeeeER  .    .    .    .    .    .    .   .   vmulps %zmm0, %zmm1, %zmm2
+# CHECK-NEXT: [0,1]     DeeeE--R  .    .    .    .    .    .    .   .   vaddps %xmm1, %xmm1, %xmm2
+# CHECK-NEXT: [0,2]     D=====eeeeeER  .    .    .    .    .    .   .   vmulps %ymm2, %ymm3, %ymm4
+# CHECK-NEXT: [0,3]     D==========eeeER    .    .    .    .    .   .   vaddps %xmm4, %xmm5, %xmm6
+# CHECK-NEXT: [0,4]     .D============eeeeeER    .    .    .    .   .   vmulps %xmm6, %xmm3, %xmm4
+# CHECK-NEXT: [0,5]     .D=================eeeER .    .    .    .   .   vaddps %xmm4, %xmm5, %xmm0
+# CHECK-NEXT: [1,0]     .D====================eeeeeER .    .    .   .   vmulps %zmm0, %zmm1, %zmm2
+# CHECK-NEXT: [1,1]     .DeeeE----------------------R .    .    .   .   vaddps %xmm1, %xmm1, %xmm2
+# CHECK-NEXT: [1,2]     . D========================eeeeeER .    .   .   vmulps %ymm2, %ymm3, %ymm4
+# CHECK-NEXT: [1,3]     . D=============================eeeER   .   .   vaddps %xmm4, %xmm5, %xmm6
+# CHECK-NEXT: [1,4]     . D================================eeeeeER  .   vmulps %xmm6, %xmm3, %xmm4
+# CHECK-NEXT: [1,5]     . D=====================================eeeER   vaddps %xmm4, %xmm5, %xmm0
+
+# CHECK:      Average Wait times (based on the timeline view):
+# CHECK-NEXT: [0]: Executions
+# CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
+# CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
+# CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
+
+# CHECK:            [0]    [1]    [2]    [3]
+# CHECK-NEXT: 0.     2     11.0   0.5    0.0       vmulps      %zmm0, %zmm1, %zmm2
+# CHECK-NEXT: 1.     2     1.0    1.0    12.0      vaddps      %xmm1, %xmm1, %xmm2
+# CHECK-NEXT: 2.     2     15.5   0.0    0.0       vmulps      %ymm2, %ymm3, %ymm4
+# CHECK-NEXT: 3.     2     20.5   0.0    0.0       vaddps      %xmm4, %xmm5, %xmm6
+# CHECK-NEXT: 4.     2     23.0   0.0    0.0       vmulps      %xmm6, %xmm3, %xmm4
+# CHECK-NEXT: 5.     2     28.0   0.0    0.0       vaddps      %xmm4, %xmm5, %xmm0

diff --git a/llvm/test/tools/llvm-mca/X86/Generic/avx512-super-registers-2.s b/llvm/test/tools/llvm-mca/X86/Generic/avx512-super-registers-2.s
new file mode 100644 (file)
index 0000000..b63c1c8
--- /dev/null
+++ b/llvm/test/tools/llvm-mca/X86/Generic/avx512-super-registers-2.s
@@ -0,0 +1,86 @@
+# NOTE: Assertions have been autogenerated by utils/update_mca_test_checks.py
+# RUN: llvm-mca -mtriple=x86_64-unknown-unknown -mcpu=x86-64 -timeline -timeline-max-iterations=2 < %s | FileCheck %s
+
+  vmulps  %zmm0, %zmm1, %zmm2
+  vaddps  %ymm1, %ymm1, %ymm2
+  vmulps  %zmm2, %zmm3, %zmm4
+  vaddps  %xmm4, %xmm5, %xmm6
+  vmulps  %xmm6, %xmm3, %xmm4
+  vaddps  %xmm4, %xmm5, %xmm0
+
+# CHECK:      Iterations:        100
+# CHECK-NEXT: Instructions:      600
+# CHECK-NEXT: Total Cycles:      2103
+# CHECK-NEXT: Dispatch Width:    4
+# CHECK-NEXT: IPC:               0.29
+# CHECK-NEXT: Block RThroughput: 3.0
+
+# CHECK:      Instruction Info:
+# CHECK-NEXT: [1]: #uOps
+# CHECK-NEXT: [2]: Latency
+# CHECK-NEXT: [3]: RThroughput
+# CHECK-NEXT: [4]: MayLoad
+# CHECK-NEXT: [5]: MayStore
+# CHECK-NEXT: [6]: HasSideEffects
+
+# CHECK:      [1]    [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  1      5     1.00                        vmulps %zmm0, %zmm1, %zmm2
+# CHECK-NEXT:  1      3     1.00                        vaddps %ymm1, %ymm1, %ymm2
+# CHECK-NEXT:  1      5     1.00                        vmulps %zmm2, %zmm3, %zmm4
+# CHECK-NEXT:  1      3     1.00                        vaddps %xmm4, %xmm5, %xmm6
+# CHECK-NEXT:  1      5     1.00                        vmulps %xmm6, %xmm3, %xmm4
+# CHECK-NEXT:  1      3     1.00                        vaddps %xmm4, %xmm5, %xmm0
+
+# CHECK:      Resources:
+# CHECK-NEXT: [0]   - SBDivider
+# CHECK-NEXT: [1]   - SBFPDivider
+# CHECK-NEXT: [2]   - SBPort0
+# CHECK-NEXT: [3]   - SBPort1
+# CHECK-NEXT: [4]   - SBPort4
+# CHECK-NEXT: [5]   - SBPort5
+# CHECK-NEXT: [6.0] - SBPort23
+# CHECK-NEXT: [6.1] - SBPort23
+
+# CHECK:      Resource pressure per iteration:
+# CHECK-NEXT: [0]    [1]    [2]    [3]    [4]    [5]    [6.0]  [6.1]
+# CHECK-NEXT:  -      -     3.00   3.00    -      -      -      -
+
+# CHECK:      Resource pressure by instruction:
+# CHECK-NEXT: [0]    [1]    [2]    [3]    [4]    [5]    [6.0]  [6.1]  Instructions:
+# CHECK-NEXT:  -      -     1.00    -      -      -      -      -     vmulps   %zmm0, %zmm1, %zmm2
+# CHECK-NEXT:  -      -      -     1.00    -      -      -      -     vaddps   %ymm1, %ymm1, %ymm2
+# CHECK-NEXT:  -      -     1.00    -      -      -      -      -     vmulps   %zmm2, %zmm3, %zmm4
+# CHECK-NEXT:  -      -      -     1.00    -      -      -      -     vaddps   %xmm4, %xmm5, %xmm6
+# CHECK-NEXT:  -      -     1.00    -      -      -      -      -     vmulps   %xmm6, %xmm3, %xmm4
+# CHECK-NEXT:  -      -      -     1.00    -      -      -      -     vaddps   %xmm4, %xmm5, %xmm0
+
+# CHECK:      Timeline view:
+# CHECK-NEXT:                     0123456789          0123456789
+# CHECK-NEXT: Index     0123456789          0123456789          01234
+
+# CHECK:      [0,0]     DeeeeeER  .    .    .    .    .    .    .   .   vmulps %zmm0, %zmm1, %zmm2
+# CHECK-NEXT: [0,1]     DeeeE--R  .    .    .    .    .    .    .   .   vaddps %ymm1, %ymm1, %ymm2
+# CHECK-NEXT: [0,2]     D=====eeeeeER  .    .    .    .    .    .   .   vmulps %zmm2, %zmm3, %zmm4
+# CHECK-NEXT: [0,3]     D==========eeeER    .    .    .    .    .   .   vaddps %xmm4, %xmm5, %xmm6
+# CHECK-NEXT: [0,4]     .D============eeeeeER    .    .    .    .   .   vmulps %xmm6, %xmm3, %xmm4
+# CHECK-NEXT: [0,5]     .D=================eeeER .    .    .    .   .   vaddps %xmm4, %xmm5, %xmm0
+# CHECK-NEXT: [1,0]     .D====================eeeeeER .    .    .   .   vmulps %zmm0, %zmm1, %zmm2
+# CHECK-NEXT: [1,1]     .DeeeE----------------------R .    .    .   .   vaddps %ymm1, %ymm1, %ymm2
+# CHECK-NEXT: [1,2]     . D========================eeeeeER .    .   .   vmulps %zmm2, %zmm3, %zmm4
+# CHECK-NEXT: [1,3]     . D=============================eeeER   .   .   vaddps %xmm4, %xmm5, %xmm6
+# CHECK-NEXT: [1,4]     . D================================eeeeeER  .   vmulps %xmm6, %xmm3, %xmm4
+# CHECK-NEXT: [1,5]     . D=====================================eeeER   vaddps %xmm4, %xmm5, %xmm0
+
+# CHECK:      Average Wait times (based on the timeline view):
+# CHECK-NEXT: [0]: Executions
+# CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
+# CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
+# CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
+
+# CHECK:            [0]    [1]    [2]    [3]
+# CHECK-NEXT: 0.     2     11.0   0.5    0.0       vmulps      %zmm0, %zmm1, %zmm2
+# CHECK-NEXT: 1.     2     1.0    1.0    12.0      vaddps      %ymm1, %ymm1, %ymm2
+# CHECK-NEXT: 2.     2     15.5   0.0    0.0       vmulps      %zmm2, %zmm3, %zmm4
+# CHECK-NEXT: 3.     2     20.5   0.0    0.0       vaddps      %xmm4, %xmm5, %xmm6
+# CHECK-NEXT: 4.     2     23.0   0.0    0.0       vmulps      %xmm6, %xmm3, %xmm4
+# CHECK-NEXT: 5.     2     28.0   0.0    0.0       vaddps      %xmm4, %xmm5, %xmm0

diff --git a/llvm/test/tools/llvm-mca/X86/Generic/avx512-super-registers-3.s b/llvm/test/tools/llvm-mca/X86/Generic/avx512-super-registers-3.s
new file mode 100644 (file)
index 0000000..9dde249
--- /dev/null
+++ b/llvm/test/tools/llvm-mca/X86/Generic/avx512-super-registers-3.s
@@ -0,0 +1,86 @@
+# NOTE: Assertions have been autogenerated by utils/update_mca_test_checks.py
+# RUN: llvm-mca -mtriple=x86_64-unknown-unknown -mcpu=x86-64 -timeline -timeline-max-iterations=2 < %s | FileCheck %s
+
+  vmulps  %zmm0, %zmm1, %zmm2
+  vaddps  %xmm16, %xmm17, %xmm2
+  vmulps  %ymm2, %ymm3, %ymm4
+  vaddps  %xmm4, %xmm18, %xmm6
+  vmulps  %xmm6, %xmm19, %xmm4
+  vaddps  %xmm4, %xmm20, %xmm0
+
+# CHECK:      Iterations:        100
+# CHECK-NEXT: Instructions:      600
+# CHECK-NEXT: Total Cycles:      2103
+# CHECK-NEXT: Dispatch Width:    4
+# CHECK-NEXT: IPC:               0.29
+# CHECK-NEXT: Block RThroughput: 3.0
+
+# CHECK:      Instruction Info:
+# CHECK-NEXT: [1]: #uOps
+# CHECK-NEXT: [2]: Latency
+# CHECK-NEXT: [3]: RThroughput
+# CHECK-NEXT: [4]: MayLoad
+# CHECK-NEXT: [5]: MayStore
+# CHECK-NEXT: [6]: HasSideEffects
+
+# CHECK:      [1]    [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  1      5     1.00                        vmulps %zmm0, %zmm1, %zmm2
+# CHECK-NEXT:  1      3     1.00                        vaddps %xmm16, %xmm17, %xmm2
+# CHECK-NEXT:  1      5     1.00                        vmulps %ymm2, %ymm3, %ymm4
+# CHECK-NEXT:  1      3     1.00                        vaddps %xmm4, %xmm18, %xmm6
+# CHECK-NEXT:  1      5     1.00                        vmulps %xmm6, %xmm19, %xmm4
+# CHECK-NEXT:  1      3     1.00                        vaddps %xmm4, %xmm20, %xmm0
+
+# CHECK:      Resources:
+# CHECK-NEXT: [0]   - SBDivider
+# CHECK-NEXT: [1]   - SBFPDivider
+# CHECK-NEXT: [2]   - SBPort0
+# CHECK-NEXT: [3]   - SBPort1
+# CHECK-NEXT: [4]   - SBPort4
+# CHECK-NEXT: [5]   - SBPort5
+# CHECK-NEXT: [6.0] - SBPort23
+# CHECK-NEXT: [6.1] - SBPort23
+
+# CHECK:      Resource pressure per iteration:
+# CHECK-NEXT: [0]    [1]    [2]    [3]    [4]    [5]    [6.0]  [6.1]
+# CHECK-NEXT:  -      -     3.00   3.00    -      -      -      -
+
+# CHECK:      Resource pressure by instruction:
+# CHECK-NEXT: [0]    [1]    [2]    [3]    [4]    [5]    [6.0]  [6.1]  Instructions:
+# CHECK-NEXT:  -      -     1.00    -      -      -      -      -     vmulps   %zmm0, %zmm1, %zmm2
+# CHECK-NEXT:  -      -      -     1.00    -      -      -      -     vaddps   %xmm16, %xmm17, %xmm2
+# CHECK-NEXT:  -      -     1.00    -      -      -      -      -     vmulps   %ymm2, %ymm3, %ymm4
+# CHECK-NEXT:  -      -      -     1.00    -      -      -      -     vaddps   %xmm4, %xmm18, %xmm6
+# CHECK-NEXT:  -      -     1.00    -      -      -      -      -     vmulps   %xmm6, %xmm19, %xmm4
+# CHECK-NEXT:  -      -      -     1.00    -      -      -      -     vaddps   %xmm4, %xmm20, %xmm0
+
+# CHECK:      Timeline view:
+# CHECK-NEXT:                     0123456789          0123456789
+# CHECK-NEXT: Index     0123456789          0123456789          01234
+
+# CHECK:      [0,0]     DeeeeeER  .    .    .    .    .    .    .   .   vmulps %zmm0, %zmm1, %zmm2
+# CHECK-NEXT: [0,1]     DeeeE--R  .    .    .    .    .    .    .   .   vaddps %xmm16, %xmm17, %xmm2
+# CHECK-NEXT: [0,2]     D=====eeeeeER  .    .    .    .    .    .   .   vmulps %ymm2, %ymm3, %ymm4
+# CHECK-NEXT: [0,3]     D==========eeeER    .    .    .    .    .   .   vaddps %xmm4, %xmm18, %xmm6
+# CHECK-NEXT: [0,4]     .D============eeeeeER    .    .    .    .   .   vmulps %xmm6, %xmm19, %xmm4
+# CHECK-NEXT: [0,5]     .D=================eeeER .    .    .    .   .   vaddps %xmm4, %xmm20, %xmm0
+# CHECK-NEXT: [1,0]     .D====================eeeeeER .    .    .   .   vmulps %zmm0, %zmm1, %zmm2
+# CHECK-NEXT: [1,1]     .DeeeE----------------------R .    .    .   .   vaddps %xmm16, %xmm17, %xmm2
+# CHECK-NEXT: [1,2]     . D========================eeeeeER .    .   .   vmulps %ymm2, %ymm3, %ymm4
+# CHECK-NEXT: [1,3]     . D=============================eeeER   .   .   vaddps %xmm4, %xmm18, %xmm6
+# CHECK-NEXT: [1,4]     . D================================eeeeeER  .   vmulps %xmm6, %xmm19, %xmm4
+# CHECK-NEXT: [1,5]     . D=====================================eeeER   vaddps %xmm4, %xmm20, %xmm0
+
+# CHECK:      Average Wait times (based on the timeline view):
+# CHECK-NEXT: [0]: Executions
+# CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
+# CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
+# CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
+
+# CHECK:            [0]    [1]    [2]    [3]
+# CHECK-NEXT: 0.     2     11.0   0.5    0.0       vmulps      %zmm0, %zmm1, %zmm2
+# CHECK-NEXT: 1.     2     1.0    1.0    12.0      vaddps      %xmm16, %xmm17, %xmm2
+# CHECK-NEXT: 2.     2     15.5   0.0    0.0       vmulps      %ymm2, %ymm3, %ymm4
+# CHECK-NEXT: 3.     2     20.5   0.0    0.0       vaddps      %xmm4, %xmm18, %xmm6
+# CHECK-NEXT: 4.     2     23.0   0.0    0.0       vmulps      %xmm6, %xmm19, %xmm4
+# CHECK-NEXT: 5.     2     28.0   0.0    0.0       vaddps      %xmm4, %xmm20, %xmm0

diff --git a/llvm/test/tools/llvm-mca/X86/Generic/xop-super-registers-1.s b/llvm/test/tools/llvm-mca/X86/Generic/xop-super-registers-1.s
new file mode 100644 (file)
index 0000000..94cf5fc
--- /dev/null
+++ b/llvm/test/tools/llvm-mca/X86/Generic/xop-super-registers-1.s
@@ -0,0 +1,86 @@
+# NOTE: Assertions have been autogenerated by utils/update_mca_test_checks.py
+# RUN: llvm-mca -mtriple=x86_64-unknown-unknown -mcpu=x86-64 -timeline -timeline-max-iterations=2 < %s | FileCheck %s
+
+  vmulps  %ymm0, %ymm1, %ymm2
+  vfrczpd %xmm1, %xmm2
+  vmulps  %ymm2, %ymm3, %ymm4
+  vaddps  %ymm4, %ymm5, %ymm6
+  vmulps  %ymm6, %ymm3, %ymm4
+  vaddps  %ymm4, %ymm5, %ymm0
+
+# CHECK:      Iterations:        100
+# CHECK-NEXT: Instructions:      600
+# CHECK-NEXT: Total Cycles:      2103
+# CHECK-NEXT: Dispatch Width:    4
+# CHECK-NEXT: IPC:               0.29
+# CHECK-NEXT: Block RThroughput: 3.0
+
+# CHECK:      Instruction Info:
+# CHECK-NEXT: [1]: #uOps
+# CHECK-NEXT: [2]: Latency
+# CHECK-NEXT: [3]: RThroughput
+# CHECK-NEXT: [4]: MayLoad
+# CHECK-NEXT: [5]: MayStore
+# CHECK-NEXT: [6]: HasSideEffects
+
+# CHECK:      [1]    [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  1      5     1.00                        vmulps %ymm0, %ymm1, %ymm2
+# CHECK-NEXT:  1      3     1.00                        vfrczpd        %xmm1, %xmm2
+# CHECK-NEXT:  1      5     1.00                        vmulps %ymm2, %ymm3, %ymm4
+# CHECK-NEXT:  1      3     1.00                        vaddps %ymm4, %ymm5, %ymm6
+# CHECK-NEXT:  1      5     1.00                        vmulps %ymm6, %ymm3, %ymm4
+# CHECK-NEXT:  1      3     1.00                        vaddps %ymm4, %ymm5, %ymm0
+
+# CHECK:      Resources:
+# CHECK-NEXT: [0]   - SBDivider
+# CHECK-NEXT: [1]   - SBFPDivider
+# CHECK-NEXT: [2]   - SBPort0
+# CHECK-NEXT: [3]   - SBPort1
+# CHECK-NEXT: [4]   - SBPort4
+# CHECK-NEXT: [5]   - SBPort5
+# CHECK-NEXT: [6.0] - SBPort23
+# CHECK-NEXT: [6.1] - SBPort23
+
+# CHECK:      Resource pressure per iteration:
+# CHECK-NEXT: [0]    [1]    [2]    [3]    [4]    [5]    [6.0]  [6.1]
+# CHECK-NEXT:  -      -     3.00   3.00    -      -      -      -
+
+# CHECK:      Resource pressure by instruction:
+# CHECK-NEXT: [0]    [1]    [2]    [3]    [4]    [5]    [6.0]  [6.1]  Instructions:
+# CHECK-NEXT:  -      -     1.00    -      -      -      -      -     vmulps   %ymm0, %ymm1, %ymm2
+# CHECK-NEXT:  -      -      -     1.00    -      -      -      -     vfrczpd  %xmm1, %xmm2
+# CHECK-NEXT:  -      -     1.00    -      -      -      -      -     vmulps   %ymm2, %ymm3, %ymm4
+# CHECK-NEXT:  -      -      -     1.00    -      -      -      -     vaddps   %ymm4, %ymm5, %ymm6
+# CHECK-NEXT:  -      -     1.00    -      -      -      -      -     vmulps   %ymm6, %ymm3, %ymm4
+# CHECK-NEXT:  -      -      -     1.00    -      -      -      -     vaddps   %ymm4, %ymm5, %ymm0
+
+# CHECK:      Timeline view:
+# CHECK-NEXT:                     0123456789          0123456789
+# CHECK-NEXT: Index     0123456789          0123456789          01234
+
+# CHECK:      [0,0]     DeeeeeER  .    .    .    .    .    .    .   .   vmulps %ymm0, %ymm1, %ymm2
+# CHECK-NEXT: [0,1]     DeeeE--R  .    .    .    .    .    .    .   .   vfrczpd        %xmm1, %xmm2
+# CHECK-NEXT: [0,2]     D=====eeeeeER  .    .    .    .    .    .   .   vmulps %ymm2, %ymm3, %ymm4
+# CHECK-NEXT: [0,3]     D==========eeeER    .    .    .    .    .   .   vaddps %ymm4, %ymm5, %ymm6
+# CHECK-NEXT: [0,4]     .D============eeeeeER    .    .    .    .   .   vmulps %ymm6, %ymm3, %ymm4
+# CHECK-NEXT: [0,5]     .D=================eeeER .    .    .    .   .   vaddps %ymm4, %ymm5, %ymm0
+# CHECK-NEXT: [1,0]     .D====================eeeeeER .    .    .   .   vmulps %ymm0, %ymm1, %ymm2
+# CHECK-NEXT: [1,1]     .DeeeE----------------------R .    .    .   .   vfrczpd        %xmm1, %xmm2
+# CHECK-NEXT: [1,2]     . D========================eeeeeER .    .   .   vmulps %ymm2, %ymm3, %ymm4
+# CHECK-NEXT: [1,3]     . D=============================eeeER   .   .   vaddps %ymm4, %ymm5, %ymm6
+# CHECK-NEXT: [1,4]     . D================================eeeeeER  .   vmulps %ymm6, %ymm3, %ymm4
+# CHECK-NEXT: [1,5]     . D=====================================eeeER   vaddps %ymm4, %ymm5, %ymm0
+
+# CHECK:      Average Wait times (based on the timeline view):
+# CHECK-NEXT: [0]: Executions
+# CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
+# CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
+# CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
+
+# CHECK:            [0]    [1]    [2]    [3]
+# CHECK-NEXT: 0.     2     11.0   0.5    0.0       vmulps      %ymm0, %ymm1, %ymm2
+# CHECK-NEXT: 1.     2     1.0    1.0    12.0      vfrczpd     %xmm1, %xmm2
+# CHECK-NEXT: 2.     2     15.5   0.0    0.0       vmulps      %ymm2, %ymm3, %ymm4
+# CHECK-NEXT: 3.     2     20.5   0.0    0.0       vaddps      %ymm4, %ymm5, %ymm6
+# CHECK-NEXT: 4.     2     23.0   0.0    0.0       vmulps      %ymm6, %ymm3, %ymm4
+# CHECK-NEXT: 5.     2     28.0   0.0    0.0       vaddps      %ymm4, %ymm5, %ymm0

diff --git a/llvm/test/tools/llvm-mca/X86/Generic/xop-super-registers-2.s b/llvm/test/tools/llvm-mca/X86/Generic/xop-super-registers-2.s
new file mode 100644 (file)
index 0000000..5d656b7
--- /dev/null
+++ b/llvm/test/tools/llvm-mca/X86/Generic/xop-super-registers-2.s
@@ -0,0 +1,86 @@
+# NOTE: Assertions have been autogenerated by utils/update_mca_test_checks.py
+# RUN: llvm-mca -mtriple=x86_64-unknown-unknown -mcpu=x86-64 -timeline -timeline-max-iterations=2 < %s | FileCheck %s
+
+  vmulps     %ymm0, %ymm1, %ymm2
+  vpermil2pd $16, %xmm3, %xmm5, %xmm1, %xmm2
+  vmulps     %ymm2, %ymm3, %ymm4
+  vaddps     %ymm4, %ymm5, %ymm6
+  vmulps     %ymm6, %ymm3, %ymm4
+  vaddps     %ymm4, %ymm5, %ymm0
+
+# CHECK:      Iterations:        100
+# CHECK-NEXT: Instructions:      600
+# CHECK-NEXT: Total Cycles:      2103
+# CHECK-NEXT: Dispatch Width:    4
+# CHECK-NEXT: IPC:               0.29
+# CHECK-NEXT: Block RThroughput: 3.0
+
+# CHECK:      Instruction Info:
+# CHECK-NEXT: [1]: #uOps
+# CHECK-NEXT: [2]: Latency
+# CHECK-NEXT: [3]: RThroughput
+# CHECK-NEXT: [4]: MayLoad
+# CHECK-NEXT: [5]: MayStore
+# CHECK-NEXT: [6]: HasSideEffects
+
+# CHECK:      [1]    [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  1      5     1.00                        vmulps %ymm0, %ymm1, %ymm2
+# CHECK-NEXT:  1      1     1.00                        vpermil2pd     $16, %xmm3, %xmm5, %xmm1, %xmm2
+# CHECK-NEXT:  1      5     1.00                        vmulps %ymm2, %ymm3, %ymm4
+# CHECK-NEXT:  1      3     1.00                        vaddps %ymm4, %ymm5, %ymm6
+# CHECK-NEXT:  1      5     1.00                        vmulps %ymm6, %ymm3, %ymm4
+# CHECK-NEXT:  1      3     1.00                        vaddps %ymm4, %ymm5, %ymm0
+
+# CHECK:      Resources:
+# CHECK-NEXT: [0]   - SBDivider
+# CHECK-NEXT: [1]   - SBFPDivider
+# CHECK-NEXT: [2]   - SBPort0
+# CHECK-NEXT: [3]   - SBPort1
+# CHECK-NEXT: [4]   - SBPort4
+# CHECK-NEXT: [5]   - SBPort5
+# CHECK-NEXT: [6.0] - SBPort23
+# CHECK-NEXT: [6.1] - SBPort23
+
+# CHECK:      Resource pressure per iteration:
+# CHECK-NEXT: [0]    [1]    [2]    [3]    [4]    [5]    [6.0]  [6.1]
+# CHECK-NEXT:  -      -     3.00   2.00    -     1.00    -      -
+
+# CHECK:      Resource pressure by instruction:
+# CHECK-NEXT: [0]    [1]    [2]    [3]    [4]    [5]    [6.0]  [6.1]  Instructions:
+# CHECK-NEXT:  -      -     1.00    -      -      -      -      -     vmulps   %ymm0, %ymm1, %ymm2
+# CHECK-NEXT:  -      -      -      -      -     1.00    -      -     vpermil2pd       $16, %xmm3, %xmm5, %xmm1, %xmm2
+# CHECK-NEXT:  -      -     1.00    -      -      -      -      -     vmulps   %ymm2, %ymm3, %ymm4
+# CHECK-NEXT:  -      -      -     1.00    -      -      -      -     vaddps   %ymm4, %ymm5, %ymm6
+# CHECK-NEXT:  -      -     1.00    -      -      -      -      -     vmulps   %ymm6, %ymm3, %ymm4
+# CHECK-NEXT:  -      -      -     1.00    -      -      -      -     vaddps   %ymm4, %ymm5, %ymm0
+
+# CHECK:      Timeline view:
+# CHECK-NEXT:                     0123456789          0123456789
+# CHECK-NEXT: Index     0123456789          0123456789          01234
+
+# CHECK:      [0,0]     DeeeeeER  .    .    .    .    .    .    .   .   vmulps %ymm0, %ymm1, %ymm2
+# CHECK-NEXT: [0,1]     DeE----R  .    .    .    .    .    .    .   .   vpermil2pd     $16, %xmm3, %xmm5, %xmm1, %xmm2
+# CHECK-NEXT: [0,2]     D=====eeeeeER  .    .    .    .    .    .   .   vmulps %ymm2, %ymm3, %ymm4
+# CHECK-NEXT: [0,3]     D==========eeeER    .    .    .    .    .   .   vaddps %ymm4, %ymm5, %ymm6
+# CHECK-NEXT: [0,4]     .D============eeeeeER    .    .    .    .   .   vmulps %ymm6, %ymm3, %ymm4
+# CHECK-NEXT: [0,5]     .D=================eeeER .    .    .    .   .   vaddps %ymm4, %ymm5, %ymm0
+# CHECK-NEXT: [1,0]     .D====================eeeeeER .    .    .   .   vmulps %ymm0, %ymm1, %ymm2
+# CHECK-NEXT: [1,1]     .DeE------------------------R .    .    .   .   vpermil2pd     $16, %xmm3, %xmm5, %xmm1, %xmm2
+# CHECK-NEXT: [1,2]     . D========================eeeeeER .    .   .   vmulps %ymm2, %ymm3, %ymm4
+# CHECK-NEXT: [1,3]     . D=============================eeeER   .   .   vaddps %ymm4, %ymm5, %ymm6
+# CHECK-NEXT: [1,4]     . D================================eeeeeER  .   vmulps %ymm6, %ymm3, %ymm4
+# CHECK-NEXT: [1,5]     . D=====================================eeeER   vaddps %ymm4, %ymm5, %ymm0
+
+# CHECK:      Average Wait times (based on the timeline view):
+# CHECK-NEXT: [0]: Executions
+# CHECK-NEXT: [1]: Average time spent waiting in a scheduler's queue
+# CHECK-NEXT: [2]: Average time spent waiting in a scheduler's queue while ready
+# CHECK-NEXT: [3]: Average time elapsed from WB until retire stage
+
+# CHECK:            [0]    [1]    [2]    [3]
+# CHECK-NEXT: 0.     2     11.0   0.5    0.0       vmulps      %ymm0, %ymm1, %ymm2
+# CHECK-NEXT: 1.     2     1.0    1.0    14.0      vpermil2pd  $16, %xmm3, %xmm5, %xmm1, %xmm2
+# CHECK-NEXT: 2.     2     15.5   0.0    0.0       vmulps      %ymm2, %ymm3, %ymm4
+# CHECK-NEXT: 3.     2     20.5   0.0    0.0       vaddps      %ymm4, %ymm5, %ymm6
+# CHECK-NEXT: 4.     2     23.0   0.0    0.0       vmulps      %ymm6, %ymm3, %ymm4
+# CHECK-NEXT: 5.     2     28.0   0.0    0.0       vaddps      %ymm4, %ymm5, %ymm0