[llvm] r343346 - [llvm-mca] Add a test for zero-idiom VPERM2F128rr. NFC

[Andrea Di Biagio via llvm-commits]

Author: adibiagio
Date: Fri Sep 28 10:47:09 2018
New Revision: 343346

URL: http://llvm.org/viewvc/llvm-project?rev=343346&view=rev
Log:
[llvm-mca] Add a test for zero-idiom VPERM2F128rr. NFC

We don't correctly model the latency and resource usage information for
zero-idiom VPERM2F128rr on Jaguar.

This is demonstrated by the incorrect numbers in the resource pressure view, and
the timeline view.
A follow up patch will fix this problem.

Modified:
    llvm/trunk/test/tools/llvm-mca/X86/BtVer2/zero-idioms-avx-256.s

Modified: llvm/trunk/test/tools/llvm-mca/X86/BtVer2/zero-idioms-avx-256.s
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/tools/llvm-mca/X86/BtVer2/zero-idioms-avx-256.s?rev=343346&r1=343345&r2=343346&view=diff
==============================================================================
--- llvm/trunk/test/tools/llvm-mca/X86/BtVer2/zero-idioms-avx-256.s (original)
+++ llvm/trunk/test/tools/llvm-mca/X86/BtVer2/zero-idioms-avx-256.s Fri Sep 28 10:47:09 2018
@@ -31,6 +31,11 @@ vaddps %ymm0, %ymm1, %ymm2
 vandnps %ymm2, %ymm2, %ymm3
 # LLVM-MCA-END
 
+# LLVM-MCA-BEGIN ZERO-IDIOM-5
+vperm2f128 $136, %ymm0, %ymm0, %ymm1
+vaddps  %ymm1, %ymm1, %ymm0
+# LLVM-MCA-END
+
 # CHECK:      [0] Code Region - ZERO-IDIOM-1
 
 # CHECK:      Iterations:        100
@@ -320,3 +325,73 @@ vandnps %ymm2, %ymm2, %ymm3
 # CHECK:            [0]    [1]    [2]    [3]
 # CHECK-NEXT: 0.     3     1.0    1.0    0.0       vaddps	%ymm0, %ymm1, %ymm2
 # CHECK-NEXT: 1.     3     1.0    1.0    1.0       vandnps	%ymm2, %ymm2, %ymm3
+
+# CHECK:      [4] Code Region - ZERO-IDIOM-5
+
+# CHECK:      Iterations:        100
+# CHECK-NEXT: Instructions:      200
+# CHECK-NEXT: Total Cycles:      403
+# CHECK-NEXT: Total uOps:        400
+
+# CHECK:      Dispatch Width:    2
+# CHECK-NEXT: uOps Per Cycle:    0.99
+# CHECK-NEXT: IPC:               0.50
+# 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      1     1.00                        vperm2f128	$136, %ymm0, %ymm0, %ymm1
+# CHECK-NEXT:  2      3     2.00                        vaddps	%ymm1, %ymm1, %ymm0
+
+# 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:  -      -      -      -     2.00    -     2.00    -      -      -      -      -      -      -     vperm2f128	$136, %ymm0, %ymm0, %ymm1
+# CHECK-NEXT:  -      -      -     2.00    -     2.00    -      -      -      -      -      -      -      -     vaddps	%ymm1, %ymm1, %ymm0
+
+# CHECK:      Timeline view:
+# CHECK-NEXT:                     01234
+# CHECK-NEXT: Index     0123456789
+
+# CHECK:      [0,0]     DeER .    .   .   vperm2f128	$136, %ymm0, %ymm0, %ymm1
+# CHECK-NEXT: [0,1]     .DeeeER   .   .   vaddps	%ymm1, %ymm1, %ymm0
+# CHECK-NEXT: [1,0]     . D==eER  .   .   vperm2f128	$136, %ymm0, %ymm0, %ymm1
+# CHECK-NEXT: [1,1]     .  D==eeeER   .   vaddps	%ymm1, %ymm1, %ymm0
+# CHECK-NEXT: [2,0]     .   D====eER  .   vperm2f128	$136, %ymm0, %ymm0, %ymm1
+# CHECK-NEXT: [2,1]     .    D====eeeER   vaddps	%ymm1, %ymm1, %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.     3     3.0    0.3    0.0       vperm2f128	$136, %ymm0, %ymm0, %ymm1
+# CHECK-NEXT: 1.     3     3.0    0.0    0.0       vaddps	%ymm1, %ymm1, %ymm0