[llvm-mca][BtVer2] Add tests for dependency breaking instructions.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@337024 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/test/tools/llvm-mca/X86/BtVer2/dependency-breaking-cmp.s b/test/tools/llvm-mca/X86/BtVer2/dependency-breaking-cmp.s
new file mode 100644 (file)
index 0000000..bc5ceb5
--- /dev/null
+++ b/test/tools/llvm-mca/X86/BtVer2/dependency-breaking-cmp.s
@@ -0,0 +1,74 @@
+# NOTE: Assertions have been autogenerated by utils/update_mca_test_checks.py
+# RUN: llvm-mca -mtriple=x86_64-unknown-unknown -mcpu=btver2 -timeline -timeline-max-iterations=3 -iterations=1500 < %s | FileCheck %s
+
+# Perf stat reports an IPC of 1.97 for this block of code.
+
+# The CMP instruction doesn't depend on the value of EAX.  It can set the flags
+# without having to read the inputs.
+
+cmp %eax, %eax
+cmovae %ebx, %eax
+
+# CHECK:      Iterations:        1500
+# CHECK-NEXT: Instructions:      3000
+# CHECK-NEXT: Total Cycles:      3003
+# CHECK-NEXT: Dispatch Width:    2
+# CHECK-NEXT: IPC:               1.00
+# 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:  1      1     0.50                        cmpl   %eax, %eax
+# CHECK-NEXT:  1      1     0.50                        cmovael        %ebx, %eax
+
+# CHECK:      Resources:
+# CHECK-NEXT: [0]   - JALU0
+# CHECK-NEXT: [1]   - JALU1
+# CHECK-NEXT: [2]   - JDiv
+# CHECK-NEXT: [3]   - JFPA
+# CHECK-NEXT: [4]   - JFPM
+# CHECK-NEXT: [5]   - JFPU0
+# CHECK-NEXT: [6]   - JFPU1
+# CHECK-NEXT: [7]   - JLAGU
+# CHECK-NEXT: [8]   - JMul
+# CHECK-NEXT: [9]   - JSAGU
+# CHECK-NEXT: [10]  - JSTC
+# CHECK-NEXT: [11]  - JVALU0
+# CHECK-NEXT: [12]  - JVALU1
+# CHECK-NEXT: [13]  - JVIMUL
+
+# CHECK:      Resource pressure per iteration:
+# CHECK-NEXT: [0]    [1]    [2]    [3]    [4]    [5]    [6]    [7]    [8]    [9]    [10]   [11]   [12]   [13]
+# CHECK-NEXT: 1.00   1.00    -      -      -      -      -      -      -      -      -      -      -      -
+
+# CHECK:      Resource pressure by instruction:
+# CHECK-NEXT: [0]    [1]    [2]    [3]    [4]    [5]    [6]    [7]    [8]    [9]    [10]   [11]   [12]   [13]   Instructions:
+# CHECK-NEXT:  -     1.00    -      -      -      -      -      -      -      -      -      -      -      -     cmpl   %eax, %eax
+# CHECK-NEXT: 1.00    -      -      -      -      -      -      -      -      -      -      -      -      -     cmovael        %ebx, %eax
+
+# CHECK:      Timeline view:
+# CHECK-NEXT: Index     012345678
+
+# CHECK:      [0,0]     DeER .  .   cmpl       %eax, %eax
+# CHECK-NEXT: [0,1]     D=eER.  .   cmovael    %ebx, %eax
+# CHECK-NEXT: [1,0]     .D=eER  .   cmpl       %eax, %eax
+# CHECK-NEXT: [1,1]     .D==eER .   cmovael    %ebx, %eax
+# CHECK-NEXT: [2,0]     . D==eER.   cmpl       %eax, %eax
+# CHECK-NEXT: [2,1]     . D===eER   cmovael    %ebx, %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.     3     2.0    0.3    0.0       cmpl        %eax, %eax
+# CHECK-NEXT: 1.     3     3.0    0.0    0.0       cmovael     %ebx, %eax

diff --git a/test/tools/llvm-mca/X86/BtVer2/dependency-breaking-pcmpeq.s b/test/tools/llvm-mca/X86/BtVer2/dependency-breaking-pcmpeq.s
new file mode 100644 (file)
index 0000000..97bf501
--- /dev/null
+++ b/test/tools/llvm-mca/X86/BtVer2/dependency-breaking-pcmpeq.s
@@ -0,0 +1,90 @@
+# NOTE: Assertions have been autogenerated by utils/update_mca_test_checks.py
+# RUN: llvm-mca -mtriple=x86_64-unknown-unknown -mcpu=btver2 -timeline -timeline-max-iterations=3 -iterations=1500 < %s | FileCheck %s
+
+# perf stat reports an IPC of 2.00 for this block of code.
+
+# All of the vector packed compares from this test are dependency breaking
+# instructions. That means, there is no RAW dependency between any of the
+# instructions, and the code can be fully parallelized in hardware.
+
+vpcmpeqb %xmm0, %xmm0, %xmm1
+vpcmpeqw %xmm1, %xmm1, %xmm2
+vpcmpeqd %xmm2, %xmm2, %xmm3
+vpcmpeqq %xmm3, %xmm3, %xmm0
+
+# CHECK:      Iterations:        1500
+# CHECK-NEXT: Instructions:      6000
+# CHECK-NEXT: Total Cycles:      6003
+# CHECK-NEXT: Dispatch Width:    2
+# CHECK-NEXT: IPC:               1.00
+# 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:  1      1     0.50                        vpcmpeqb       %xmm0, %xmm0, %xmm1
+# CHECK-NEXT:  1      1     0.50                        vpcmpeqw       %xmm1, %xmm1, %xmm2
+# CHECK-NEXT:  1      1     0.50                        vpcmpeqd       %xmm2, %xmm2, %xmm3
+# CHECK-NEXT:  1      1     0.50                        vpcmpeqq       %xmm3, %xmm3, %xmm0
+
+# CHECK:      Resources:
+# CHECK-NEXT: [0]   - JALU0
+# CHECK-NEXT: [1]   - JALU1
+# CHECK-NEXT: [2]   - JDiv
+# CHECK-NEXT: [3]   - JFPA
+# CHECK-NEXT: [4]   - JFPM
+# CHECK-NEXT: [5]   - JFPU0
+# CHECK-NEXT: [6]   - JFPU1
+# CHECK-NEXT: [7]   - JLAGU
+# CHECK-NEXT: [8]   - JMul
+# CHECK-NEXT: [9]   - JSAGU
+# CHECK-NEXT: [10]  - JSTC
+# CHECK-NEXT: [11]  - JVALU0
+# CHECK-NEXT: [12]  - JVALU1
+# CHECK-NEXT: [13]  - JVIMUL
+
+# CHECK:      Resource pressure per iteration:
+# CHECK-NEXT: [0]    [1]    [2]    [3]    [4]    [5]    [6]    [7]    [8]    [9]    [10]   [11]   [12]   [13]
+# CHECK-NEXT:  -      -      -      -      -     2.00   2.00    -      -      -      -     2.00   2.00    -
+
+# CHECK:      Resource pressure by instruction:
+# CHECK-NEXT: [0]    [1]    [2]    [3]    [4]    [5]    [6]    [7]    [8]    [9]    [10]   [11]   [12]   [13]   Instructions:
+# CHECK-NEXT:  -      -      -      -      -      -     1.00    -      -      -      -      -     1.00    -     vpcmpeqb       %xmm0, %xmm0, %xmm1
+# CHECK-NEXT:  -      -      -      -      -     1.00    -      -      -      -      -     1.00    -      -     vpcmpeqw       %xmm1, %xmm1, %xmm2
+# CHECK-NEXT:  -      -      -      -      -      -     1.00    -      -      -      -      -     1.00    -     vpcmpeqd       %xmm2, %xmm2, %xmm3
+# CHECK-NEXT:  -      -      -      -      -     1.00    -      -      -      -      -     1.00    -      -     vpcmpeqq       %xmm3, %xmm3, %xmm0
+
+# CHECK:      Timeline view:
+# CHECK-NEXT:                     01234
+# CHECK-NEXT: Index     0123456789
+
+# CHECK:      [0,0]     DeER .    .   .   vpcmpeqb     %xmm0, %xmm0, %xmm1
+# CHECK-NEXT: [0,1]     D=eER.    .   .   vpcmpeqw     %xmm1, %xmm1, %xmm2
+# CHECK-NEXT: [0,2]     .D=eER    .   .   vpcmpeqd     %xmm2, %xmm2, %xmm3
+# CHECK-NEXT: [0,3]     .D==eER   .   .   vpcmpeqq     %xmm3, %xmm3, %xmm0
+# CHECK-NEXT: [1,0]     . D==eER  .   .   vpcmpeqb     %xmm0, %xmm0, %xmm1
+# CHECK-NEXT: [1,1]     . D===eER .   .   vpcmpeqw     %xmm1, %xmm1, %xmm2
+# CHECK-NEXT: [1,2]     .  D===eER.   .   vpcmpeqd     %xmm2, %xmm2, %xmm3
+# CHECK-NEXT: [1,3]     .  D====eER   .   vpcmpeqq     %xmm3, %xmm3, %xmm0
+# CHECK-NEXT: [2,0]     .   D====eER  .   vpcmpeqb     %xmm0, %xmm0, %xmm1
+# CHECK-NEXT: [2,1]     .   D=====eER .   vpcmpeqw     %xmm1, %xmm1, %xmm2
+# CHECK-NEXT: [2,2]     .    D=====eER.   vpcmpeqd     %xmm2, %xmm2, %xmm3
+# CHECK-NEXT: [2,3]     .    D======eER   vpcmpeqq     %xmm3, %xmm3, %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.     3     3.0    0.3    0.0       vpcmpeqb    %xmm0, %xmm0, %xmm1
+# CHECK-NEXT: 1.     3     4.0    0.0    0.0       vpcmpeqw    %xmm1, %xmm1, %xmm2
+# CHECK-NEXT: 2.     3     4.0    0.0    0.0       vpcmpeqd    %xmm2, %xmm2, %xmm3
+# CHECK-NEXT: 3.     3     5.0    0.0    0.0       vpcmpeqq    %xmm3, %xmm3, %xmm0

diff --git a/test/tools/llvm-mca/X86/BtVer2/dependency-breaking-pcmpgt.s b/test/tools/llvm-mca/X86/BtVer2/dependency-breaking-pcmpgt.s
new file mode 100644 (file)
index 0000000..9ab8d03
--- /dev/null
+++ b/test/tools/llvm-mca/X86/BtVer2/dependency-breaking-pcmpgt.s
@@ -0,0 +1,90 @@
+# NOTE: Assertions have been autogenerated by utils/update_mca_test_checks.py
+# RUN: llvm-mca -mtriple=x86_64-unknown-unknown -mcpu=btver2 -timeline -timeline-max-iterations=3 -iterations=1500 < %s | FileCheck %s
+
+# perf stat reports an IPC of 2.00 for this block of code.
+
+# All of the vector packed compares from this test are zero idioms.  These zero
+# idioms are all detected and removed by the register renamer.  That means, no
+# uOp is executed, and there is no RAW dependency for any of the packed
+# compares.
+
+vpcmpgtb %xmm0, %xmm0, %xmm1
+vpcmpgtw %xmm1, %xmm1, %xmm2
+vpcmpgtd %xmm2, %xmm2, %xmm3
+vpcmpgtq %xmm3, %xmm3, %xmm0
+
+# CHECK:      Iterations:        1500
+# CHECK-NEXT: Instructions:      6000
+# CHECK-NEXT: Total Cycles:      3001
+# CHECK-NEXT: Dispatch Width:    2
+# CHECK-NEXT: IPC:               2.00
+# 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:  1      0     0.50                        vpcmpgtb       %xmm0, %xmm0, %xmm1
+# CHECK-NEXT:  1      0     0.50                        vpcmpgtw       %xmm1, %xmm1, %xmm2
+# CHECK-NEXT:  1      0     0.50                        vpcmpgtd       %xmm2, %xmm2, %xmm3
+# CHECK-NEXT:  1      0     0.50                        vpcmpgtq       %xmm3, %xmm3, %xmm0
+
+# CHECK:      Resources:
+# CHECK-NEXT: [0]   - JALU0
+# CHECK-NEXT: [1]   - JALU1
+# CHECK-NEXT: [2]   - JDiv
+# CHECK-NEXT: [3]   - JFPA
+# CHECK-NEXT: [4]   - JFPM
+# CHECK-NEXT: [5]   - JFPU0
+# CHECK-NEXT: [6]   - JFPU1
+# CHECK-NEXT: [7]   - JLAGU
+# CHECK-NEXT: [8]   - JMul
+# CHECK-NEXT: [9]   - JSAGU
+# CHECK-NEXT: [10]  - JSTC
+# CHECK-NEXT: [11]  - JVALU0
+# CHECK-NEXT: [12]  - JVALU1
+# CHECK-NEXT: [13]  - JVIMUL
+
+# CHECK:      Resource pressure per iteration:
+# CHECK-NEXT: [0]    [1]    [2]    [3]    [4]    [5]    [6]    [7]    [8]    [9]    [10]   [11]   [12]   [13]
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -
+
+# CHECK:      Resource pressure by instruction:
+# CHECK-NEXT: [0]    [1]    [2]    [3]    [4]    [5]    [6]    [7]    [8]    [9]    [10]   [11]   [12]   [13]   Instructions:
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     vpcmpgtb       %xmm0, %xmm0, %xmm1
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     vpcmpgtw       %xmm1, %xmm1, %xmm2
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     vpcmpgtd       %xmm2, %xmm2, %xmm3
+# CHECK-NEXT:  -      -      -      -      -      -      -      -      -      -      -      -      -      -     vpcmpgtq       %xmm3, %xmm3, %xmm0
+
+# CHECK:      Timeline view:
+# CHECK-NEXT: Index     0123456
+
+# CHECK:      [0,0]     DR   ..   vpcmpgtb     %xmm0, %xmm0, %xmm1
+# CHECK-NEXT: [0,1]     DR   ..   vpcmpgtw     %xmm1, %xmm1, %xmm2
+# CHECK-NEXT: [0,2]     .DR  ..   vpcmpgtd     %xmm2, %xmm2, %xmm3
+# CHECK-NEXT: [0,3]     .DR  ..   vpcmpgtq     %xmm3, %xmm3, %xmm0
+# CHECK-NEXT: [1,0]     . DR ..   vpcmpgtb     %xmm0, %xmm0, %xmm1
+# CHECK-NEXT: [1,1]     . DR ..   vpcmpgtw     %xmm1, %xmm1, %xmm2
+# CHECK-NEXT: [1,2]     .  DR..   vpcmpgtd     %xmm2, %xmm2, %xmm3
+# CHECK-NEXT: [1,3]     .  DR..   vpcmpgtq     %xmm3, %xmm3, %xmm0
+# CHECK-NEXT: [2,0]     .   DR.   vpcmpgtb     %xmm0, %xmm0, %xmm1
+# CHECK-NEXT: [2,1]     .   DR.   vpcmpgtw     %xmm1, %xmm1, %xmm2
+# CHECK-NEXT: [2,2]     .    DR   vpcmpgtd     %xmm2, %xmm2, %xmm3
+# CHECK-NEXT: [2,3]     .    DR   vpcmpgtq     %xmm3, %xmm3, %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.     3     0.0    0.0    0.0       vpcmpgtb    %xmm0, %xmm0, %xmm1
+# CHECK-NEXT: 1.     3     0.0    0.0    0.0       vpcmpgtw    %xmm1, %xmm1, %xmm2
+# CHECK-NEXT: 2.     3     0.0    0.0    0.0       vpcmpgtd    %xmm2, %xmm2, %xmm3
+# CHECK-NEXT: 3.     3     0.0    0.0    0.0       vpcmpgtq    %xmm3, %xmm3, %xmm0

diff --git a/test/tools/llvm-mca/X86/BtVer2/dependency-breaking-sbb-1.s b/test/tools/llvm-mca/X86/BtVer2/dependency-breaking-sbb-1.s
new file mode 100644 (file)
index 0000000..34cabda
--- /dev/null
+++ b/test/tools/llvm-mca/X86/BtVer2/dependency-breaking-sbb-1.s
@@ -0,0 +1,75 @@
+# NOTE: Assertions have been autogenerated by utils/update_mca_test_checks.py
+# RUN: llvm-mca -mtriple=x86_64-unknown-unknown -mcpu=btver2 -timeline -timeline-max-iterations=3 -iterations=1500 < %s | FileCheck %s
+
+# perf stat reports an IPC of 1.00 for this code block.
+
+# Although both SBB are dependency breaking instructions, there is still an
+# implicit dependency on EFLAGS which limits the ILP. So, the hardware backend
+# can only execute one instruction per cycle.
+
+sbb %edx, %edx
+sbb %eax, %eax
+
+# CHECK:      Iterations:        1500
+# CHECK-NEXT: Instructions:      3000
+# CHECK-NEXT: Total Cycles:      3003
+# CHECK-NEXT: Dispatch Width:    2
+# CHECK-NEXT: IPC:               1.00
+# 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:  1      1     1.00                        sbbl   %edx, %edx
+# CHECK-NEXT:  1      1     1.00                        sbbl   %eax, %eax
+
+# CHECK:      Resources:
+# CHECK-NEXT: [0]   - JALU0
+# CHECK-NEXT: [1]   - JALU1
+# CHECK-NEXT: [2]   - JDiv
+# CHECK-NEXT: [3]   - JFPA
+# CHECK-NEXT: [4]   - JFPM
+# CHECK-NEXT: [5]   - JFPU0
+# CHECK-NEXT: [6]   - JFPU1
+# CHECK-NEXT: [7]   - JLAGU
+# CHECK-NEXT: [8]   - JMul
+# CHECK-NEXT: [9]   - JSAGU
+# CHECK-NEXT: [10]  - JSTC
+# CHECK-NEXT: [11]  - JVALU0
+# CHECK-NEXT: [12]  - JVALU1
+# CHECK-NEXT: [13]  - JVIMUL
+
+# CHECK:      Resource pressure per iteration:
+# CHECK-NEXT: [0]    [1]    [2]    [3]    [4]    [5]    [6]    [7]    [8]    [9]    [10]   [11]   [12]   [13]
+# CHECK-NEXT: 2.00   2.00    -      -      -      -      -      -      -      -      -      -      -      -
+
+# CHECK:      Resource pressure by instruction:
+# CHECK-NEXT: [0]    [1]    [2]    [3]    [4]    [5]    [6]    [7]    [8]    [9]    [10]   [11]   [12]   [13]   Instructions:
+# CHECK-NEXT:  -     2.00    -      -      -      -      -      -      -      -      -      -      -      -     sbbl   %edx, %edx
+# CHECK-NEXT: 2.00    -      -      -      -      -      -      -      -      -      -      -      -      -     sbbl   %eax, %eax
+
+# CHECK:      Timeline view:
+# CHECK-NEXT: Index     012345678
+
+# CHECK:      [0,0]     DeER .  .   sbbl       %edx, %edx
+# CHECK-NEXT: [0,1]     D=eER.  .   sbbl       %eax, %eax
+# CHECK-NEXT: [1,0]     .D=eER  .   sbbl       %edx, %edx
+# CHECK-NEXT: [1,1]     .D==eER .   sbbl       %eax, %eax
+# CHECK-NEXT: [2,0]     . D==eER.   sbbl       %edx, %edx
+# CHECK-NEXT: [2,1]     . D===eER   sbbl       %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.     3     2.0    0.3    0.0       sbbl        %edx, %edx
+# CHECK-NEXT: 1.     3     3.0    0.0    0.0       sbbl        %eax, %eax

diff --git a/test/tools/llvm-mca/X86/BtVer2/dependency-breaking-sbb-2.s b/test/tools/llvm-mca/X86/BtVer2/dependency-breaking-sbb-2.s
new file mode 100644 (file)
index 0000000..00b8895
--- /dev/null
+++ b/test/tools/llvm-mca/X86/BtVer2/dependency-breaking-sbb-2.s
@@ -0,0 +1,83 @@
+# NOTE: Assertions have been autogenerated by utils/update_mca_test_checks.py
+# RUN: llvm-mca -mtriple=x86_64-unknown-unknown -mcpu=btver2 -timeline -timeline-max-iterations=3 -iterations=1500 < %s | FileCheck %s
+
+# perf stat reports a throughput of 1.51 IPC for this block of code.
+
+# The SBB does not depend on the value of register EAX. That means, it doesn't
+# have to wait for the IMUL to write-back on EAX. However, it still depends on
+# the ADD for EFLAGS.
+
+imul %edx, %eax
+add %edx, %edx
+sbb %eax, %eax
+
+# CHECK:      Iterations:        1500
+# CHECK-NEXT: Instructions:      4500
+# CHECK-NEXT: Total Cycles:      6745
+# CHECK-NEXT: Dispatch Width:    2
+# CHECK-NEXT: IPC:               0.67
+# 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      3     1.00                        imull  %edx, %eax
+# CHECK-NEXT:  1      1     0.50                        addl   %edx, %edx
+# CHECK-NEXT:  1      1     1.00                        sbbl   %eax, %eax
+
+# CHECK:      Resources:
+# CHECK-NEXT: [0]   - JALU0
+# CHECK-NEXT: [1]   - JALU1
+# CHECK-NEXT: [2]   - JDiv
+# CHECK-NEXT: [3]   - JFPA
+# CHECK-NEXT: [4]   - JFPM
+# CHECK-NEXT: [5]   - JFPU0
+# CHECK-NEXT: [6]   - JFPU1
+# CHECK-NEXT: [7]   - JLAGU
+# CHECK-NEXT: [8]   - JMul
+# CHECK-NEXT: [9]   - JSAGU
+# CHECK-NEXT: [10]  - JSTC
+# CHECK-NEXT: [11]  - JVALU0
+# CHECK-NEXT: [12]  - JVALU1
+# CHECK-NEXT: [13]  - JVIMUL
+
+# CHECK:      Resource pressure per iteration:
+# CHECK-NEXT: [0]    [1]    [2]    [3]    [4]    [5]    [6]    [7]    [8]    [9]    [10]   [11]   [12]   [13]
+# CHECK-NEXT: 2.01   1.99    -      -      -      -      -      -     1.00    -      -      -      -      -
+
+# CHECK:      Resource pressure by instruction:
+# CHECK-NEXT: [0]    [1]    [2]    [3]    [4]    [5]    [6]    [7]    [8]    [9]    [10]   [11]   [12]   [13]   Instructions:
+# CHECK-NEXT:  -     1.00    -      -      -      -      -      -     1.00    -      -      -      -      -     imull  %edx, %eax
+# CHECK-NEXT: 0.99   0.01    -      -      -      -      -      -      -      -      -      -      -      -     addl   %edx, %edx
+# CHECK-NEXT: 1.01   0.99    -      -      -      -      -      -      -      -      -      -      -      -     sbbl   %eax, %eax
+
+# CHECK:      Timeline view:
+# CHECK-NEXT:                     012345
+# CHECK-NEXT: Index     0123456789
+
+# CHECK:      [0,0]     DeeeER    .    .   imull       %edx, %eax
+# CHECK-NEXT: [0,1]     .DeE-R    .    .   addl        %edx, %edx
+# CHECK-NEXT: [0,2]     .D==eER   .    .   sbbl        %eax, %eax
+# CHECK-NEXT: [1,0]     . D===eeeER    .   imull       %edx, %eax
+# CHECK-NEXT: [1,1]     .  DeE----R    .   addl        %edx, %edx
+# CHECK-NEXT: [1,2]     .  D=====eER   .   sbbl        %eax, %eax
+# CHECK-NEXT: [2,0]     .   D=====eeeER.   imull       %edx, %eax
+# CHECK-NEXT: [2,1]     .    DeE------R.   addl        %edx, %edx
+# CHECK-NEXT: [2,2]     .    D=======eER   sbbl        %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.     3     3.7    0.7    0.0       imull       %edx, %eax
+# CHECK-NEXT: 1.     3     1.0    1.0    3.7       addl        %edx, %edx
+# CHECK-NEXT: 2.     3     5.7    0.0    0.0       sbbl        %eax, %eax

diff --git a/test/tools/llvm-mca/X86/BtVer2/one-idioms.s b/test/tools/llvm-mca/X86/BtVer2/one-idioms.s
index e524fe1..3beaf82 100644 (file)
--- a/test/tools/llvm-mca/X86/BtVer2/one-idioms.s
+++ b/test/tools/llvm-mca/X86/BtVer2/one-idioms.s
@@ -6,7 +6,6 @@
 
 pcmpeqb   %mm2, %mm2
 pcmpeqd   %mm2, %mm2
-# pcmpeqq %mm2, %mm2 # invalid operand for instruction
 pcmpeqw   %mm2, %mm2
 
 pcmpeqb   %xmm2, %xmm2