[NFC][X86][MCA] AMD Zen 3: improve MULX test coverage

Latency for MULX isn't right

3 files changed, 467 insertions, 0 deletions

diff --git a/llvm/test/tools/llvm-mca/X86/Znver3/mulx-lo-reg-use.s b/llvm/test/tools/llvm-mca/X86/Znver3/mulx-lo-reg-use.s
new file mode 100644
index 000000000000..0db28c9708df
--- /dev/null
+++ b/llvm/test/tools/llvm-mca/X86/Znver3/mulx-lo-reg-use.s
@@ -0,0 +1,154 @@
+# NOTE: Assertions have been autogenerated by utils/update_mca_test_checks.py
+# RUN: llvm-mca -mtriple=x86_64-unknown-unknown -mcpu=znver3 -timeline -iterations=2 < %s | FileCheck %s
+
+# LLVM-MCA-BEGIN
+mulxl %eax, %eax, %ecx
+# LLVM-MCA-END
+
+# LLVM-MCA-BEGIN
+mulxq %rax, %rax, %rcx
+# LLVM-MCA-END
+
+# CHECK:      [0] Code Region
+
+# CHECK:      Iterations:        2
+# CHECK-NEXT: Instructions:      2
+# CHECK-NEXT: Total Cycles:      11
+# CHECK-NEXT: Total uOps:        4
+
+# CHECK:      Dispatch Width:    6
+# CHECK-NEXT: uOps Per Cycle:    0.36
+# CHECK-NEXT: IPC:               0.18
+# CHECK-NEXT: Block RThroughput: 1.0
+
+# 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 (U)
+
+# CHECK:      [1]    [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  2      4     1.00                        mulxl	%eax, %eax, %ecx
+
+# CHECK:      Resources:
+# CHECK-NEXT: [0]   - Zn3AGU0
+# CHECK-NEXT: [1]   - Zn3AGU1
+# CHECK-NEXT: [2]   - Zn3AGU2
+# CHECK-NEXT: [3]   - Zn3ALU0
+# CHECK-NEXT: [4]   - Zn3ALU1
+# CHECK-NEXT: [5]   - Zn3ALU2
+# CHECK-NEXT: [6]   - Zn3ALU3
+# CHECK-NEXT: [7]   - Zn3BRU1
+# CHECK-NEXT: [8]   - Zn3FPP0
+# CHECK-NEXT: [9]   - Zn3FPP1
+# CHECK-NEXT: [10]  - Zn3FPP2
+# CHECK-NEXT: [11]  - Zn3FPP3
+# CHECK-NEXT: [12.0] - Zn3FPP45
+# CHECK-NEXT: [12.1] - Zn3FPP45
+# CHECK-NEXT: [13]  - Zn3FPSt
+# CHECK-NEXT: [14.0] - Zn3LSU
+# CHECK-NEXT: [14.1] - Zn3LSU
+# CHECK-NEXT: [14.2] - Zn3LSU
+# CHECK-NEXT: [15.0] - Zn3Load
+# CHECK-NEXT: [15.1] - Zn3Load
+# CHECK-NEXT: [15.2] - Zn3Load
+# CHECK-NEXT: [16.0] - Zn3Store
+# CHECK-NEXT: [16.1] - Zn3Store
+
+# CHECK:      Resource pressure per iteration:
+# CHECK-NEXT: [0]    [1]    [2]    [3]    [4]    [5]    [6]    [7]    [8]    [9]    [10]   [11]   [12.0] [12.1] [13]   [14.0] [14.1] [14.2] [15.0] [15.1] [15.2] [16.0] [16.1]
+# CHECK-NEXT:  -      -      -      -     1.00    -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -
+
+# CHECK:      Resource pressure by instruction:
+# CHECK-NEXT: [0]    [1]    [2]    [3]    [4]    [5]    [6]    [7]    [8]    [9]    [10]   [11]   [12.0] [12.1] [13]   [14.0] [14.1] [14.2] [15.0] [15.1] [15.2] [16.0] [16.1] Instructions:
+# CHECK-NEXT:  -      -      -      -     1.00    -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     mulxl	%eax, %eax, %ecx
+
+# CHECK:      Timeline view:
+# CHECK-NEXT:                     0
+# CHECK-NEXT: Index     0123456789
+
+# CHECK:      [0,0]     DeeeeER   .   mulxl	%eax, %eax, %ecx
+# CHECK-NEXT: [1,0]     D====eeeeER   mulxl	%eax, %eax, %ecx
+
+# 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     3.0    0.5    0.0       mulxl	%eax, %eax, %ecx
+
+# CHECK:      [1] Code Region
+
+# CHECK:      Iterations:        2
+# CHECK-NEXT: Instructions:      2
+# CHECK-NEXT: Total Cycles:      11
+# CHECK-NEXT: Total uOps:        4
+
+# CHECK:      Dispatch Width:    6
+# CHECK-NEXT: uOps Per Cycle:    0.36
+# CHECK-NEXT: IPC:               0.18
+# CHECK-NEXT: Block RThroughput: 1.0
+
+# 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 (U)
+
+# CHECK:      [1]    [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  2      4     1.00                        mulxq	%rax, %rax, %rcx
+
+# CHECK:      Resources:
+# CHECK-NEXT: [0]   - Zn3AGU0
+# CHECK-NEXT: [1]   - Zn3AGU1
+# CHECK-NEXT: [2]   - Zn3AGU2
+# CHECK-NEXT: [3]   - Zn3ALU0
+# CHECK-NEXT: [4]   - Zn3ALU1
+# CHECK-NEXT: [5]   - Zn3ALU2
+# CHECK-NEXT: [6]   - Zn3ALU3
+# CHECK-NEXT: [7]   - Zn3BRU1
+# CHECK-NEXT: [8]   - Zn3FPP0
+# CHECK-NEXT: [9]   - Zn3FPP1
+# CHECK-NEXT: [10]  - Zn3FPP2
+# CHECK-NEXT: [11]  - Zn3FPP3
+# CHECK-NEXT: [12.0] - Zn3FPP45
+# CHECK-NEXT: [12.1] - Zn3FPP45
+# CHECK-NEXT: [13]  - Zn3FPSt
+# CHECK-NEXT: [14.0] - Zn3LSU
+# CHECK-NEXT: [14.1] - Zn3LSU
+# CHECK-NEXT: [14.2] - Zn3LSU
+# CHECK-NEXT: [15.0] - Zn3Load
+# CHECK-NEXT: [15.1] - Zn3Load
+# CHECK-NEXT: [15.2] - Zn3Load
+# CHECK-NEXT: [16.0] - Zn3Store
+# CHECK-NEXT: [16.1] - Zn3Store
+
+# CHECK:      Resource pressure per iteration:
+# CHECK-NEXT: [0]    [1]    [2]    [3]    [4]    [5]    [6]    [7]    [8]    [9]    [10]   [11]   [12.0] [12.1] [13]   [14.0] [14.1] [14.2] [15.0] [15.1] [15.2] [16.0] [16.1]
+# CHECK-NEXT:  -      -      -      -     1.00    -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -
+
+# CHECK:      Resource pressure by instruction:
+# CHECK-NEXT: [0]    [1]    [2]    [3]    [4]    [5]    [6]    [7]    [8]    [9]    [10]   [11]   [12.0] [12.1] [13]   [14.0] [14.1] [14.2] [15.0] [15.1] [15.2] [16.0] [16.1] Instructions:
+# CHECK-NEXT:  -      -      -      -     1.00    -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     mulxq	%rax, %rax, %rcx
+
+# CHECK:      Timeline view:
+# CHECK-NEXT:                     0
+# CHECK-NEXT: Index     0123456789
+
+# CHECK:      [0,0]     DeeeeER   .   mulxq	%rax, %rax, %rcx
+# CHECK-NEXT: [1,0]     D====eeeeER   mulxq	%rax, %rax, %rcx
+
+# 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     3.0    0.5    0.0       mulxq	%rax, %rax, %rcx
diff --git a/llvm/test/tools/llvm-mca/X86/Znver3/mulx-read-advance.s b/llvm/test/tools/llvm-mca/X86/Znver3/mulx-read-advance.s
new file mode 100644
index 000000000000..d7858ecf8ee1
--- /dev/null
+++ b/llvm/test/tools/llvm-mca/X86/Znver3/mulx-read-advance.s
@@ -0,0 +1,156 @@
+# NOTE: Assertions have been autogenerated by utils/update_mca_test_checks.py
+# RUN: llvm-mca -mtriple=x86_64-unknown-unknown -mcpu=znver3 -timeline -iterations=2 < %s | FileCheck %s
+
+# PR51494: A read-advance on the implicit read of EDX/RDX was missing.
+
+# LLVM-MCA-BEGIN
+mulxl (%rdi), %eax, %edx
+# LLVM-MCA-END
+
+# LLVM-MCA-BEGIN
+mulxq (%rdi), %rax, %rdx
+# LLVM-MCA-END
+
+# CHECK:      [0] Code Region
+
+# CHECK:      Iterations:        2
+# CHECK-NEXT: Instructions:      2
+# CHECK-NEXT: Total Cycles:      15
+# CHECK-NEXT: Total uOps:        4
+
+# CHECK:      Dispatch Width:    6
+# CHECK-NEXT: uOps Per Cycle:    0.27
+# CHECK-NEXT: IPC:               0.13
+# CHECK-NEXT: Block RThroughput: 2.0
+
+# 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 (U)
+
+# CHECK:      [1]    [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  2      8     2.00    *                   mulxl	(%rdi), %eax, %edx
+
+# CHECK:      Resources:
+# CHECK-NEXT: [0]   - Zn3AGU0
+# CHECK-NEXT: [1]   - Zn3AGU1
+# CHECK-NEXT: [2]   - Zn3AGU2
+# CHECK-NEXT: [3]   - Zn3ALU0
+# CHECK-NEXT: [4]   - Zn3ALU1
+# CHECK-NEXT: [5]   - Zn3ALU2
+# CHECK-NEXT: [6]   - Zn3ALU3
+# CHECK-NEXT: [7]   - Zn3BRU1
+# CHECK-NEXT: [8]   - Zn3FPP0
+# CHECK-NEXT: [9]   - Zn3FPP1
+# CHECK-NEXT: [10]  - Zn3FPP2
+# CHECK-NEXT: [11]  - Zn3FPP3
+# CHECK-NEXT: [12.0] - Zn3FPP45
+# CHECK-NEXT: [12.1] - Zn3FPP45
+# CHECK-NEXT: [13]  - Zn3FPSt
+# CHECK-NEXT: [14.0] - Zn3LSU
+# CHECK-NEXT: [14.1] - Zn3LSU
+# CHECK-NEXT: [14.2] - Zn3LSU
+# CHECK-NEXT: [15.0] - Zn3Load
+# CHECK-NEXT: [15.1] - Zn3Load
+# CHECK-NEXT: [15.2] - Zn3Load
+# CHECK-NEXT: [16.0] - Zn3Store
+# CHECK-NEXT: [16.1] - Zn3Store
+
+# CHECK:      Resource pressure per iteration:
+# CHECK-NEXT: [0]    [1]    [2]    [3]    [4]    [5]    [6]    [7]    [8]    [9]    [10]   [11]   [12.0] [12.1] [13]   [14.0] [14.1] [14.2] [15.0] [15.1] [15.2] [16.0] [16.1]
+# CHECK-NEXT:  -     0.50   0.50    -     2.00    -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -     0.50   0.50    -      -
+
+# CHECK:      Resource pressure by instruction:
+# CHECK-NEXT: [0]    [1]    [2]    [3]    [4]    [5]    [6]    [7]    [8]    [9]    [10]   [11]   [12.0] [12.1] [13]   [14.0] [14.1] [14.2] [15.0] [15.1] [15.2] [16.0] [16.1] Instructions:
+# CHECK-NEXT:  -     0.50   0.50    -     2.00    -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -     0.50   0.50    -      -     mulxl	(%rdi), %eax, %edx
+
+# CHECK:      Timeline view:
+# CHECK-NEXT:                     01234
+# CHECK-NEXT: Index     0123456789
+
+# CHECK:      [0,0]     DeeeeeeeeER   .   mulxl	(%rdi), %eax, %edx
+# CHECK-NEXT: [1,0]     D====eeeeeeeeER   mulxl	(%rdi), %eax, %edx
+
+# 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     3.0    0.5    0.0       mulxl	(%rdi), %eax, %edx
+
+# CHECK:      [1] Code Region
+
+# CHECK:      Iterations:        2
+# CHECK-NEXT: Instructions:      2
+# CHECK-NEXT: Total Cycles:      15
+# CHECK-NEXT: Total uOps:        4
+
+# CHECK:      Dispatch Width:    6
+# CHECK-NEXT: uOps Per Cycle:    0.27
+# CHECK-NEXT: IPC:               0.13
+# CHECK-NEXT: Block RThroughput: 2.0
+
+# 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 (U)
+
+# CHECK:      [1]    [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  2      8     2.00    *                   mulxq	(%rdi), %rax, %rdx
+
+# CHECK:      Resources:
+# CHECK-NEXT: [0]   - Zn3AGU0
+# CHECK-NEXT: [1]   - Zn3AGU1
+# CHECK-NEXT: [2]   - Zn3AGU2
+# CHECK-NEXT: [3]   - Zn3ALU0
+# CHECK-NEXT: [4]   - Zn3ALU1
+# CHECK-NEXT: [5]   - Zn3ALU2
+# CHECK-NEXT: [6]   - Zn3ALU3
+# CHECK-NEXT: [7]   - Zn3BRU1
+# CHECK-NEXT: [8]   - Zn3FPP0
+# CHECK-NEXT: [9]   - Zn3FPP1
+# CHECK-NEXT: [10]  - Zn3FPP2
+# CHECK-NEXT: [11]  - Zn3FPP3
+# CHECK-NEXT: [12.0] - Zn3FPP45
+# CHECK-NEXT: [12.1] - Zn3FPP45
+# CHECK-NEXT: [13]  - Zn3FPSt
+# CHECK-NEXT: [14.0] - Zn3LSU
+# CHECK-NEXT: [14.1] - Zn3LSU
+# CHECK-NEXT: [14.2] - Zn3LSU
+# CHECK-NEXT: [15.0] - Zn3Load
+# CHECK-NEXT: [15.1] - Zn3Load
+# CHECK-NEXT: [15.2] - Zn3Load
+# CHECK-NEXT: [16.0] - Zn3Store
+# CHECK-NEXT: [16.1] - Zn3Store
+
+# CHECK:      Resource pressure per iteration:
+# CHECK-NEXT: [0]    [1]    [2]    [3]    [4]    [5]    [6]    [7]    [8]    [9]    [10]   [11]   [12.0] [12.1] [13]   [14.0] [14.1] [14.2] [15.0] [15.1] [15.2] [16.0] [16.1]
+# CHECK-NEXT:  -     0.50   0.50    -     2.00    -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -     0.50   0.50    -      -
+
+# CHECK:      Resource pressure by instruction:
+# CHECK-NEXT: [0]    [1]    [2]    [3]    [4]    [5]    [6]    [7]    [8]    [9]    [10]   [11]   [12.0] [12.1] [13]   [14.0] [14.1] [14.2] [15.0] [15.1] [15.2] [16.0] [16.1] Instructions:
+# CHECK-NEXT:  -     0.50   0.50    -     2.00    -      -      -      -      -      -      -      -      -      -      -     0.50   0.50    -     0.50   0.50    -      -     mulxq	(%rdi), %rax, %rdx
+
+# CHECK:      Timeline view:
+# CHECK-NEXT:                     01234
+# CHECK-NEXT: Index     0123456789
+
+# CHECK:      [0,0]     DeeeeeeeeER   .   mulxq	(%rdi), %rax, %rdx
+# CHECK-NEXT: [1,0]     D====eeeeeeeeER   mulxq	(%rdi), %rax, %rdx
+
+# 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     3.0    0.5    0.0       mulxq	(%rdi), %rax, %rdx
diff --git a/llvm/test/tools/llvm-mca/X86/Znver3/mulx-same-regs.s b/llvm/test/tools/llvm-mca/X86/Znver3/mulx-same-regs.s
new file mode 100644
index 000000000000..bfe8be85086f
--- /dev/null
+++ b/llvm/test/tools/llvm-mca/X86/Znver3/mulx-same-regs.s
@@ -0,0 +1,157 @@
+# NOTE: Assertions have been autogenerated by utils/update_mca_test_checks.py
+# RUN: llvm-mca -mtriple=x86_64-unknown-unknown -mcpu=znver3 -timeline -iterations=2 < %s | FileCheck %s
+
+# PR51495: If the two destination registers are the same, the destination will
+# contain teh high half of the multiplication result.
+
+# LLVM-MCA-BEGIN
+mulxl %eax, %eax, %eax
+# LLVM-MCA-END
+
+# LLVM-MCA-BEGIN
+mulxq %rax, %rax, %rax
+# LLVM-MCA-END
+
+# CHECK:      [0] Code Region
+
+# CHECK:      Iterations:        2
+# CHECK-NEXT: Instructions:      2
+# CHECK-NEXT: Total Cycles:      11
+# CHECK-NEXT: Total uOps:        4
+
+# CHECK:      Dispatch Width:    6
+# CHECK-NEXT: uOps Per Cycle:    0.36
+# CHECK-NEXT: IPC:               0.18
+# CHECK-NEXT: Block RThroughput: 1.0
+
+# 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 (U)
+
+# CHECK:      [1]    [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  2      4     1.00                        mulxl	%eax, %eax, %eax
+
+# CHECK:      Resources:
+# CHECK-NEXT: [0]   - Zn3AGU0
+# CHECK-NEXT: [1]   - Zn3AGU1
+# CHECK-NEXT: [2]   - Zn3AGU2
+# CHECK-NEXT: [3]   - Zn3ALU0
+# CHECK-NEXT: [4]   - Zn3ALU1
+# CHECK-NEXT: [5]   - Zn3ALU2
+# CHECK-NEXT: [6]   - Zn3ALU3
+# CHECK-NEXT: [7]   - Zn3BRU1
+# CHECK-NEXT: [8]   - Zn3FPP0
+# CHECK-NEXT: [9]   - Zn3FPP1
+# CHECK-NEXT: [10]  - Zn3FPP2
+# CHECK-NEXT: [11]  - Zn3FPP3
+# CHECK-NEXT: [12.0] - Zn3FPP45
+# CHECK-NEXT: [12.1] - Zn3FPP45
+# CHECK-NEXT: [13]  - Zn3FPSt
+# CHECK-NEXT: [14.0] - Zn3LSU
+# CHECK-NEXT: [14.1] - Zn3LSU
+# CHECK-NEXT: [14.2] - Zn3LSU
+# CHECK-NEXT: [15.0] - Zn3Load
+# CHECK-NEXT: [15.1] - Zn3Load
+# CHECK-NEXT: [15.2] - Zn3Load
+# CHECK-NEXT: [16.0] - Zn3Store
+# CHECK-NEXT: [16.1] - Zn3Store
+
+# CHECK:      Resource pressure per iteration:
+# CHECK-NEXT: [0]    [1]    [2]    [3]    [4]    [5]    [6]    [7]    [8]    [9]    [10]   [11]   [12.0] [12.1] [13]   [14.0] [14.1] [14.2] [15.0] [15.1] [15.2] [16.0] [16.1]
+# CHECK-NEXT:  -      -      -      -     1.00    -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -
+
+# CHECK:      Resource pressure by instruction:
+# CHECK-NEXT: [0]    [1]    [2]    [3]    [4]    [5]    [6]    [7]    [8]    [9]    [10]   [11]   [12.0] [12.1] [13]   [14.0] [14.1] [14.2] [15.0] [15.1] [15.2] [16.0] [16.1] Instructions:
+# CHECK-NEXT:  -      -      -      -     1.00    -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     mulxl	%eax, %eax, %eax
+
+# CHECK:      Timeline view:
+# CHECK-NEXT:                     0
+# CHECK-NEXT: Index     0123456789
+
+# CHECK:      [0,0]     DeeeeER   .   mulxl	%eax, %eax, %eax
+# CHECK-NEXT: [1,0]     D====eeeeER   mulxl	%eax, %eax, %eax
+
+# 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     3.0    0.5    0.0       mulxl	%eax, %eax, %eax
+
+# CHECK:      [1] Code Region
+
+# CHECK:      Iterations:        2
+# CHECK-NEXT: Instructions:      2
+# CHECK-NEXT: Total Cycles:      11
+# CHECK-NEXT: Total uOps:        4
+
+# CHECK:      Dispatch Width:    6
+# CHECK-NEXT: uOps Per Cycle:    0.36
+# CHECK-NEXT: IPC:               0.18
+# CHECK-NEXT: Block RThroughput: 1.0
+
+# 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 (U)
+
+# CHECK:      [1]    [2]    [3]    [4]    [5]    [6]    Instructions:
+# CHECK-NEXT:  2      4     1.00                        mulxq	%rax, %rax, %rax
+
+# CHECK:      Resources:
+# CHECK-NEXT: [0]   - Zn3AGU0
+# CHECK-NEXT: [1]   - Zn3AGU1
+# CHECK-NEXT: [2]   - Zn3AGU2
+# CHECK-NEXT: [3]   - Zn3ALU0
+# CHECK-NEXT: [4]   - Zn3ALU1
+# CHECK-NEXT: [5]   - Zn3ALU2
+# CHECK-NEXT: [6]   - Zn3ALU3
+# CHECK-NEXT: [7]   - Zn3BRU1
+# CHECK-NEXT: [8]   - Zn3FPP0
+# CHECK-NEXT: [9]   - Zn3FPP1
+# CHECK-NEXT: [10]  - Zn3FPP2
+# CHECK-NEXT: [11]  - Zn3FPP3
+# CHECK-NEXT: [12.0] - Zn3FPP45
+# CHECK-NEXT: [12.1] - Zn3FPP45
+# CHECK-NEXT: [13]  - Zn3FPSt
+# CHECK-NEXT: [14.0] - Zn3LSU
+# CHECK-NEXT: [14.1] - Zn3LSU
+# CHECK-NEXT: [14.2] - Zn3LSU
+# CHECK-NEXT: [15.0] - Zn3Load
+# CHECK-NEXT: [15.1] - Zn3Load
+# CHECK-NEXT: [15.2] - Zn3Load
+# CHECK-NEXT: [16.0] - Zn3Store
+# CHECK-NEXT: [16.1] - Zn3Store
+
+# CHECK:      Resource pressure per iteration:
+# CHECK-NEXT: [0]    [1]    [2]    [3]    [4]    [5]    [6]    [7]    [8]    [9]    [10]   [11]   [12.0] [12.1] [13]   [14.0] [14.1] [14.2] [15.0] [15.1] [15.2] [16.0] [16.1]
+# CHECK-NEXT:  -      -      -      -     1.00    -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -
+
+# CHECK:      Resource pressure by instruction:
+# CHECK-NEXT: [0]    [1]    [2]    [3]    [4]    [5]    [6]    [7]    [8]    [9]    [10]   [11]   [12.0] [12.1] [13]   [14.0] [14.1] [14.2] [15.0] [15.1] [15.2] [16.0] [16.1] Instructions:
+# CHECK-NEXT:  -      -      -      -     1.00    -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -      -     mulxq	%rax, %rax, %rax
+
+# CHECK:      Timeline view:
+# CHECK-NEXT:                     0
+# CHECK-NEXT: Index     0123456789
+
+# CHECK:      [0,0]     DeeeeER   .   mulxq	%rax, %rax, %rax
+# CHECK-NEXT: [1,0]     D====eeeeER   mulxq	%rax, %rax, %rax
+
+# 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     3.0    0.5    0.0       mulxq	%rax, %rax, %rax