[X86][Btver2] Fix masked load schedule

JFPU01 resource usage should match JFPX

Match AMD Fam16h SOG + llvm-exegesis tests

llvm-svn: 343468

diff --git a/llvm/lib/Target/X86/X86ScheduleBtVer2.td b/llvm/lib/Target/X86/X86ScheduleBtVer2.td
index 9df0c77..6220ebe 100644 (file)
--- a/llvm/lib/Target/X86/X86ScheduleBtVer2.td
+++ b/llvm/lib/Target/X86/X86ScheduleBtVer2.td
@@ -290,8 +290,8 @@ defm : X86WriteRes<WriteFLDC,          [JFPU1, JSTC], 3, [1,1], 1>;
 defm : X86WriteRes<WriteFLoad,         [JLAGU, JFPU01, JFPX], 5, [1, 1, 1], 1>;
 defm : X86WriteRes<WriteFLoadX,        [JLAGU, JFPU01, JFPX], 5, [1, 1, 1], 1>;
 defm : X86WriteRes<WriteFLoadY,        [JLAGU, JFPU01, JFPX], 5, [1, 1, 1], 1>;
-defm : X86WriteRes<WriteFMaskedLoad,   [JLAGU, JFPU01, JFPX], 6, [1, 1, 2], 1>;
-defm : X86WriteRes<WriteFMaskedLoadY,  [JLAGU, JFPU01, JFPX], 6, [2, 2, 4], 2>;
+defm : X86WriteRes<WriteFMaskedLoad,   [JLAGU, JFPU01, JFPX], 6, [1, 2, 2], 1>;
+defm : X86WriteRes<WriteFMaskedLoadY,  [JLAGU, JFPU01, JFPX], 6, [2, 4, 4], 2>;
 
 defm : X86WriteRes<WriteFStore,        [JSAGU, JFPU1,  JSTC], 2, [1, 1, 1], 1>;
 defm : X86WriteRes<WriteFStoreX,       [JSAGU, JFPU1,  JSTC], 1, [1, 1, 1], 1>;
@@ -444,8 +444,8 @@ defm : X86WriteRes<WriteVecLoadX,         [JLAGU, JFPU01, JVALU], 5, [1, 1, 1],
 defm : X86WriteRes<WriteVecLoadY,         [JLAGU, JFPU01, JVALU], 5, [1, 1, 1], 1>;
 defm : X86WriteRes<WriteVecLoadNT,        [JLAGU, JFPU01, JVALU], 5, [1, 1, 1], 1>;
 defm : X86WriteRes<WriteVecLoadNTY,       [JLAGU, JFPU01, JVALU], 5, [1, 1, 1], 1>;
-defm : X86WriteRes<WriteVecMaskedLoad,    [JLAGU, JFPU01, JVALU], 6, [1, 1, 2], 1>;
-defm : X86WriteRes<WriteVecMaskedLoadY,   [JLAGU, JFPU01, JVALU], 6, [2, 2, 4], 2>;
+defm : X86WriteRes<WriteVecMaskedLoad,    [JLAGU, JFPU01, JVALU], 6, [1, 2, 2], 1>;
+defm : X86WriteRes<WriteVecMaskedLoadY,   [JLAGU, JFPU01, JVALU], 6, [2, 4, 4], 2>;
 
 defm : X86WriteRes<WriteVecStore,         [JSAGU, JFPU1,   JSTC], 2, [1, 1, 1], 1>;
 defm : X86WriteRes<WriteVecStoreX,        [JSAGU, JFPU1,   JSTC], 1, [1, 1, 1], 1>;

diff --git a/llvm/test/tools/llvm-mca/X86/BtVer2/resources-avx1.s b/llvm/test/tools/llvm-mca/X86/BtVer2/resources-avx1.s
index 149f2e4..0bdca96 100644 (file)
--- a/llvm/test/tools/llvm-mca/X86/BtVer2/resources-avx1.s
+++ b/llvm/test/tools/llvm-mca/X86/BtVer2/resources-avx1.s
@@ -1740,7 +1740,7 @@ vzeroupper
 
 # CHECK:      Resource pressure per iteration:
 # CHECK-NEXT: [0]    [1]    [2]    [3]    [4]    [5]    [6]    [7]    [8]    [9]    [10]   [11]   [12]   [13]
-# CHECK-NEXT: 56.00   -      -     365.00 915.00 423.50 437.50 394.00  -     51.00  132.00 131.50 155.50 38.00
+# CHECK-NEXT: 56.00   -      -     365.00 915.00 426.50 440.50 394.00  -     51.00  132.00 131.50 155.50 38.00
 
 # CHECK:      Resource pressure by instruction:
 # CHECK-NEXT: [0]    [1]    [2]    [3]    [4]    [5]    [6]    [7]    [8]    [9]    [10]   [11]   [12]   [13]   Instructions:
@@ -1934,12 +1934,12 @@ vzeroupper
 # CHECK-NEXT:  -      -      -      -      -     0.50   0.50   1.00    -      -      -     0.50   0.50    -     vlddqu (%rax), %ymm2
 # CHECK-NEXT:  -      -      -      -      -      -      -     1.00    -      -      -      -      -      -     vldmxcsr       (%rax)
 # CHECK-NEXT:  -      -      -      -      -      -     1.00    -      -     1.00   1.00    -      -      -     vmaskmovdqu    %xmm0, %xmm1
-# CHECK-NEXT:  -      -      -     1.00   1.00   0.50   0.50   1.00    -      -      -      -      -      -     vmaskmovpd     (%rax), %xmm0, %xmm2
-# CHECK-NEXT:  -      -      -     2.00   2.00   1.00   1.00   2.00    -      -      -      -      -      -     vmaskmovpd     (%rax), %ymm0, %ymm2
+# CHECK-NEXT:  -      -      -     1.00   1.00   1.00   1.00   1.00    -      -      -      -      -      -     vmaskmovpd     (%rax), %xmm0, %xmm2
+# CHECK-NEXT:  -      -      -     2.00   2.00   2.00   2.00   2.00    -      -      -      -      -      -     vmaskmovpd     (%rax), %ymm0, %ymm2
 # CHECK-NEXT:  -      -      -     2.00   2.00   0.50   0.50    -      -     1.00    -      -      -      -     vmaskmovpd     %xmm0, %xmm1, (%rax)
 # CHECK-NEXT:  -      -      -     2.00   2.00   1.00   1.00    -      -     2.00    -      -      -      -     vmaskmovpd     %ymm0, %ymm1, (%rax)
-# CHECK-NEXT:  -      -      -     1.00   1.00   0.50   0.50   1.00    -      -      -      -      -      -     vmaskmovps     (%rax), %xmm0, %xmm2
-# CHECK-NEXT:  -      -      -     2.00   2.00   1.00   1.00   2.00    -      -      -      -      -      -     vmaskmovps     (%rax), %ymm0, %ymm2
+# CHECK-NEXT:  -      -      -     1.00   1.00   1.00   1.00   1.00    -      -      -      -      -      -     vmaskmovps     (%rax), %xmm0, %xmm2
+# CHECK-NEXT:  -      -      -     2.00   2.00   2.00   2.00   2.00    -      -      -      -      -      -     vmaskmovps     (%rax), %ymm0, %ymm2
 # CHECK-NEXT:  -      -      -     2.00   2.00   0.50   0.50    -      -     1.00    -      -      -      -     vmaskmovps     %xmm0, %xmm1, (%rax)
 # CHECK-NEXT:  -      -      -     2.00   2.00   1.00   1.00    -      -     2.00    -      -      -      -     vmaskmovps     %ymm0, %ymm1, (%rax)
 # CHECK-NEXT:  -      -      -     1.00    -     1.00    -      -      -      -      -      -      -      -     vmaxpd %xmm0, %xmm1, %xmm2