[RISCV] Add scheduling info for XSfvfnrclipxfqf instructions

llvm/lib/Target/RISCV/RISCVInstrInfoXSf.td

@@ -177,7 +177,8 @@ class CustomSiFiveVMACC<bits<6> funct6, RISCVVFormat opv, string opcodestr>
 }
 
 class CustomSiFiveVFNRCLIP<bits<6> funct6, RISCVVFormat opv, string opcodestr>
-    : VALUVF<funct6, opv, opcodestr> {
+    : VALUVF<funct6, opv, opcodestr>,
+      SchedBinaryMC<"WriteSF_VFNRClipV", "ReadSF_VFNRClipV", "ReadSF_VFNRClipF"> {
   let Inst{6-0} = OPC_CUSTOM_2.Value;
 }
 
@@ -403,7 +404,10 @@ multiclass VPseudoSiFiveVFNRCLIP<string Constraint = "@earlyclobber $rd"> {
                                                        MxListVF4[i].vrclass,
                                                        FPR32, MxListW[i],
                                                        Constraint, /*sew*/0,
-                                                       UsesVXRM=0>;
+                                                       UsesVXRM=0>,
+                             SchedBinary<"WriteSF_VFNRClipV", "ReadSF_VFNRClipV",
+                                         "ReadSF_VFNRClipF",
+                                         MxListW[i].MX>;
 }
 
 let Predicates = [HasVendorXSfvcp] in {

llvm/lib/Target/RISCV/RISCVSchedAndes45.td

@@ -331,6 +331,7 @@ defm : UnsupportedSchedQ;
 defm : UnsupportedSchedSFB;
 defm : UnsupportedSchedV;
 defm : UnsupportedSchedXsfvcp;
+defm : UnsupportedSchedXSfvfnrclipxfqf;
 defm : UnsupportedSchedZabha;
 defm : UnsupportedSchedZbkb;
 defm : UnsupportedSchedZbkx;

llvm/lib/Target/RISCV/RISCVSchedGenericOOO.td

@@ -498,4 +498,5 @@ defm : UnsupportedSchedZfaWithQ;
 defm : UnsupportedSchedZvk;
 defm : UnsupportedSchedSFB;
 defm : UnsupportedSchedXsfvcp;
+defm : UnsupportedSchedXSfvfnrclipxfqf;
 }

llvm/lib/Target/RISCV/RISCVSchedMIPSP8700.td

@@ -274,5 +274,6 @@ defm : UnsupportedSchedZfhmin;
 defm : UnsupportedSchedSFB;
 defm : UnsupportedSchedZabha;
 defm : UnsupportedSchedXsfvcp;
+defm : UnsupportedSchedXSfvfnrclipxfqf;
 defm : UnsupportedSchedZvk;
 }

llvm/lib/Target/RISCV/RISCVSchedRocket.td

@@ -263,5 +263,6 @@ defm : UnsupportedSchedZfa;
 defm : UnsupportedSchedZfhmin;
 defm : UnsupportedSchedSFB;
 defm : UnsupportedSchedXsfvcp;
+defm : UnsupportedSchedXSfvfnrclipxfqf;
 defm : UnsupportedSchedZvk;
 }

llvm/lib/Target/RISCV/RISCVSchedSiFive7.td

@@ -169,6 +169,20 @@ class SiFive7GetOrderedReductionCycles<string mx, int sew, int VLEN> {
   int c = !mul(6, VLUpperBound);
 }
 
+class SiFive7GetSiFiveVFNRClipCycles<string mx, int VLEN> {
+  int latency = !cond(
+    !eq(mx, "MF8"): 7,
+    !eq(mx, "MF4"): 8,
+    !eq(mx, "MF2"): 10,
+    !eq(mx, "M1"): 13,
+    !eq(mx, "M2"): 19,
+  );
+
+  defvar DLEN = !div(VLEN, 2);
+  int occupancy = SiFive7GetCyclesOnePerElement<mx, sew=!div(DLEN, 4),
+                                                VLEN=VLEN>.c;
+}
+
 class SiFive7FPLatencies {
   int BasicFP16ALU;
   int BasicFP32ALU;
@@ -1049,6 +1063,15 @@ multiclass SiFive7WriteResBase<int VLEN,
       }
     }
   }
+
+  foreach mx = !listremove(SchedMxListW, ["M4"]) in {
+    defvar Cycles = SiFive7GetSiFiveVFNRClipCycles<mx, VLEN>;
+    let Latency = Cycles.latency,
+        AcquireAtCycles = [0, 1],
+        ReleaseAtCycles = [1, !add(1, Cycles.occupancy)] in
+    defm : LMULWriteResMX<"WriteSF_VFNRClipV", [VCQ, VA1], mx,
+                          IsWorstCase=!eq(mx, "M2")>;
+  }
 }
 
 //===----------------------------------------------------------------------===//
@@ -1326,6 +1349,10 @@ multiclass SiFive7ReadAdvance {
   def : ReadAdvance<ReadVMov4V, 0>;
   def : ReadAdvance<ReadVMov8V, 0>;
 
+  // XSfvfnrclipxfqf
+  defm : LMULReadAdvance<"ReadSF_VFNRClipV", 0>;
+  defm : LMULReadAdvance<"ReadSF_VFNRClipF", 0>;
+
   // Others
   def : ReadAdvance<ReadVMask, 0>;
   def : ReadAdvance<ReadVPassthru_WorstCase, 0>;

llvm/lib/Target/RISCV/RISCVSchedSiFiveP400.td

@@ -1239,4 +1239,5 @@ defm : UnsupportedSchedZbkx;
 defm : UnsupportedSchedSFB;
 defm : UnsupportedSchedZfa;
 defm : UnsupportedSchedXsfvcp;
+defm : UnsupportedSchedXSfvfnrclipxfqf;
 }

llvm/lib/Target/RISCV/RISCVSchedSiFiveP500.td

@@ -359,4 +359,5 @@ defm : UnsupportedSchedSFB;
 defm : UnsupportedSchedZfa;
 defm : UnsupportedSchedZvk;
 defm : UnsupportedSchedXsfvcp;
+defm : UnsupportedSchedXSfvfnrclipxfqf;
 }

llvm/lib/Target/RISCV/RISCVSchedSiFiveP600.td

@@ -1495,4 +1495,5 @@ defm : UnsupportedSchedZbkx;
 defm : UnsupportedSchedSFB;
 defm : UnsupportedSchedZfa;
 defm : UnsupportedSchedXsfvcp;
+defm : UnsupportedSchedXSfvfnrclipxfqf;
 }

llvm/lib/Target/RISCV/RISCVSchedSiFiveP800.td

@@ -1184,4 +1184,5 @@ defm : UnsupportedSchedZbkx;
 defm : UnsupportedSchedSFB;
 defm : UnsupportedSchedZfaWithQ;
 defm : UnsupportedSchedXsfvcp;
+defm : UnsupportedSchedXSfvfnrclipxfqf;
 }

llvm/lib/Target/RISCV/RISCVSchedSpacemitX60.td

@@ -346,6 +346,7 @@ def : ReadAdvance<ReadSingleBitImm, 0>;
 defm : UnsupportedSchedQ;
 defm : UnsupportedSchedV;
 defm : UnsupportedSchedXsfvcp;
+defm : UnsupportedSchedXSfvfnrclipxfqf;
 defm : UnsupportedSchedZabha;
 defm : UnsupportedSchedZbkb;
 defm : UnsupportedSchedZbkx;

llvm/lib/Target/RISCV/RISCVSchedSyntacoreSCR1.td

@@ -117,5 +117,6 @@ defm : UnsupportedSchedZbkb;
 defm : UnsupportedSchedZbkx;
 defm : UnsupportedSchedZfa;
 defm : UnsupportedSchedXsfvcp;
+defm : UnsupportedSchedXSfvfnrclipxfqf;
 defm : UnsupportedSchedZvk;
 }

llvm/lib/Target/RISCV/RISCVSchedSyntacoreSCR345.td

@@ -183,6 +183,7 @@ multiclass SCR_Unsupported :
   UnsupportedSchedSFB,
   UnsupportedSchedV,
   UnsupportedSchedXsfvcp,
+  UnsupportedSchedXSfvfnrclipxfqf,
   UnsupportedSchedZabha,
   UnsupportedSchedZba,
   UnsupportedSchedZbb,

llvm/lib/Target/RISCV/RISCVSchedSyntacoreSCR7.td

@@ -245,6 +245,7 @@ multiclass SCR7_Unsupported {
   defm : UnsupportedSchedSFB;
   defm : UnsupportedSchedV;
   defm : UnsupportedSchedXsfvcp;
+  defm : UnsupportedSchedXSfvfnrclipxfqf;
   defm : UnsupportedSchedZabha;
   defm : UnsupportedSchedZfa;
   defm : UnsupportedSchedZfhmin;

llvm/lib/Target/RISCV/RISCVSchedTTAscalonD8.td

@@ -321,6 +321,7 @@ def : ReadAdvance<ReadSingleBitImm, 0>;
 defm : UnsupportedSchedQ;
 defm : UnsupportedSchedV;
 defm : UnsupportedSchedXsfvcp;
+defm : UnsupportedSchedXSfvfnrclipxfqf;
 defm : UnsupportedSchedZabha;
 defm : UnsupportedSchedZbc;
 defm : UnsupportedSchedZbkb;

llvm/lib/Target/RISCV/RISCVSchedXiangShanNanHu.td

@@ -313,5 +313,6 @@ defm : UnsupportedSchedZfhmin;
 defm : UnsupportedSchedSFB;
 defm : UnsupportedSchedZabha;
 defm : UnsupportedSchedXsfvcp;
+defm : UnsupportedSchedXSfvfnrclipxfqf;
 defm : UnsupportedSchedZvk;
 }

llvm/lib/Target/RISCV/RISCVScheduleXSf.td

@@ -57,3 +57,15 @@ foreach f = ["FPR16", "FPR32", "FPR64"] in {
 }
 }
 }
+
+defm "" : LMULSchedWritesImpl<"WriteSF_VFNRClipV", !listremove(SchedMxListW, ["M4"])>;
+defm "" : LMULSchedReadsImpl<"ReadSF_VFNRClipV",   !listremove(SchedMxListW, ["M4"])>;
+defm "" : LMULSchedReadsImpl<"ReadSF_VFNRClipF",   !listremove(SchedMxListW, ["M4"])>;
+
+multiclass UnsupportedSchedXSfvfnrclipxfqf {
+let Unsupported = true in {
+defm : LMULWriteRes<"WriteSF_VFNRClipV", []>;
+defm : LMULReadAdvance<"ReadSF_VFNRClipV", 0>;
+defm : LMULReadAdvance<"ReadSF_VFNRClipF", 0>;
+} // Unsupported = true
+}

llvm/test/tools/llvm-mca/RISCV/SiFive7/xsfvfnrclip.s

@@ -0,0 +1,79 @@
+# NOTE: Assertions have been autogenerated by utils/update_mca_test_checks.py
+# RUN: llvm-mca -mtriple=riscv64 -mcpu=sifive-x280 -mattr='+xsfvfnrclipxfqf' -iterations=1 -instruction-tables=full %s | \
+# RUN:   FileCheck %s
+
+vsetvli a0, zero, e8, mf8, ta, ma
+sf.vfnrclip.xu.f.qf v4, v8, fa2
+
+vsetvli a0, zero, e8, mf4, ta, ma
+sf.vfnrclip.xu.f.qf v4, v8, fa2
+
+vsetvli a0, zero, e8, mf2, ta, ma
+sf.vfnrclip.xu.f.qf v4, v8, fa2
+
+vsetvli a0, zero, e8, m1, ta, ma
+sf.vfnrclip.xu.f.qf v4, v8, fa2
+
+vsetvli a0, zero, e8, m2, ta, ma
+sf.vfnrclip.xu.f.qf v4, v8, fa2
+
+# CHECK:      Resources:
+# CHECK-NEXT: [0]   - VLEN512SiFive7FDiv:1
+# CHECK-NEXT: [1]   - VLEN512SiFive7IDiv:1
+# CHECK-NEXT: [2]   - VLEN512SiFive7PipeA:1
+# CHECK-NEXT: [3]   - VLEN512SiFive7PipeAB:2 VLEN512SiFive7PipeA, VLEN512SiFive7PipeB
+# CHECK-NEXT: [4]   - VLEN512SiFive7PipeB:1
+# CHECK-NEXT: [5]   - VLEN512SiFive7VA:1
+# CHECK-NEXT: [6]   - VLEN512SiFive7VCQ:1
+# CHECK-NEXT: [7]   - VLEN512SiFive7VL:1
+# CHECK-NEXT: [8]   - VLEN512SiFive7VS:1
+
+# 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-NEXT: [7]: Bypass Latency
+# CHECK-NEXT: [8]: Resources (<Name> | <Name>[<ReleaseAtCycle>] | <Name>[<AcquireAtCycle>,<ReleaseAtCycle])
+# CHECK-NEXT: [9]: LLVM Opcode Name
+
+# CHECK:      [1]    [2]    [3]    [4]    [5]    [6]    [7]    [8]                                        [9]                        Instructions:
+# CHECK-NEXT:  1      3     1.00                  U      1     VLEN512SiFive7PipeA,VLEN512SiFive7PipeAB   VSETVLI                    vsetvli	a0, zero, e8, mf8, ta, ma
+# CHECK-NEXT:  1      7     1.00                         7     VLEN512SiFive7VA[1,2],VLEN512SiFive7VCQ    SF_VFNRCLIP_XU_F_QF        sf.vfnrclip.xu.f.qf	v4, v8, fa2
+# CHECK-NEXT:  1      3     1.00                  U      1     VLEN512SiFive7PipeA,VLEN512SiFive7PipeAB   VSETVLI                    vsetvli	a0, zero, e8, mf4, ta, ma
+# CHECK-NEXT:  1      8     2.00                         8     VLEN512SiFive7VA[1,3],VLEN512SiFive7VCQ    SF_VFNRCLIP_XU_F_QF        sf.vfnrclip.xu.f.qf	v4, v8, fa2
+# CHECK-NEXT:  1      3     1.00                  U      1     VLEN512SiFive7PipeA,VLEN512SiFive7PipeAB   VSETVLI                    vsetvli	a0, zero, e8, mf2, ta, ma
+# CHECK-NEXT:  1      10    4.00                         10    VLEN512SiFive7VA[1,5],VLEN512SiFive7VCQ    SF_VFNRCLIP_XU_F_QF        sf.vfnrclip.xu.f.qf	v4, v8, fa2
+# CHECK-NEXT:  1      3     1.00                  U      1     VLEN512SiFive7PipeA,VLEN512SiFive7PipeAB   VSETVLI                    vsetvli	a0, zero, e8, m1, ta, ma
+# CHECK-NEXT:  1      13    8.00                         13    VLEN512SiFive7VA[1,9],VLEN512SiFive7VCQ    SF_VFNRCLIP_XU_F_QF        sf.vfnrclip.xu.f.qf	v4, v8, fa2
+# CHECK-NEXT:  1      3     1.00                  U      1     VLEN512SiFive7PipeA,VLEN512SiFive7PipeAB   VSETVLI                    vsetvli	a0, zero, e8, m2, ta, ma
+# CHECK-NEXT:  1      19    16.00                        19    VLEN512SiFive7VA[1,17],VLEN512SiFive7VCQ   SF_VFNRCLIP_XU_F_QF        sf.vfnrclip.xu.f.qf	v4, v8, fa2
+
+# CHECK:      Resources:
+# CHECK-NEXT: [0]   - VLEN512SiFive7FDiv
+# CHECK-NEXT: [1]   - VLEN512SiFive7IDiv
+# CHECK-NEXT: [2]   - VLEN512SiFive7PipeA
+# CHECK-NEXT: [3]   - VLEN512SiFive7PipeB
+# CHECK-NEXT: [4]   - VLEN512SiFive7VA
+# CHECK-NEXT: [5]   - VLEN512SiFive7VCQ
+# CHECK-NEXT: [6]   - VLEN512SiFive7VL
+# CHECK-NEXT: [7]   - VLEN512SiFive7VS
+
+# CHECK:      Resource pressure per iteration:
+# CHECK-NEXT: [0]    [1]    [2]    [3]    [4]    [5]    [6]    [7]
+# CHECK-NEXT:  -      -     5.00    -     36.00  5.00    -      -
+
+# CHECK:      Resource pressure by instruction:
+# CHECK-NEXT: [0]    [1]    [2]    [3]    [4]    [5]    [6]    [7]    Instructions:
+# CHECK-NEXT:  -      -     1.00    -      -      -      -      -     vsetvli	a0, zero, e8, mf8, ta, ma
+# CHECK-NEXT:  -      -      -      -     2.00   1.00    -      -     sf.vfnrclip.xu.f.qf	v4, v8, fa2
+# CHECK-NEXT:  -      -     1.00    -      -      -      -      -     vsetvli	a0, zero, e8, mf4, ta, ma
+# CHECK-NEXT:  -      -      -      -     3.00   1.00    -      -     sf.vfnrclip.xu.f.qf	v4, v8, fa2
+# CHECK-NEXT:  -      -     1.00    -      -      -      -      -     vsetvli	a0, zero, e8, mf2, ta, ma
+# CHECK-NEXT:  -      -      -      -     5.00   1.00    -      -     sf.vfnrclip.xu.f.qf	v4, v8, fa2
+# CHECK-NEXT:  -      -     1.00    -      -      -      -      -     vsetvli	a0, zero, e8, m1, ta, ma
+# CHECK-NEXT:  -      -      -      -     9.00   1.00    -      -     sf.vfnrclip.xu.f.qf	v4, v8, fa2
+# CHECK-NEXT:  -      -     1.00    -      -      -      -      -     vsetvli	a0, zero, e8, m2, ta, ma
+# CHECK-NEXT:  -      -      -      -     17.00  1.00    -      -     sf.vfnrclip.xu.f.qf	v4, v8, fa2

llvm/test/tools/llvm-mca/RISCV/SiFiveX390/xsfvfnrclip.s

@@ -0,0 +1,82 @@
+# NOTE: Assertions have been autogenerated by utils/update_mca_test_checks.py
+# RUN: llvm-mca -mtriple=riscv64 -mcpu=sifive-x390 -mattr='+xsfvfnrclipxfqf' -iterations=1 -instruction-tables=full %s | \
+# RUN:   FileCheck %s
+
+vsetvli a0, zero, e8, mf8, ta, ma
+sf.vfnrclip.xu.f.qf v4, v8, fa2
+
+vsetvli a0, zero, e8, mf4, ta, ma
+sf.vfnrclip.xu.f.qf v4, v8, fa2
+
+vsetvli a0, zero, e8, mf2, ta, ma
+sf.vfnrclip.xu.f.qf v4, v8, fa2
+
+vsetvli a0, zero, e8, m1, ta, ma
+sf.vfnrclip.xu.f.qf v4, v8, fa2
+
+vsetvli a0, zero, e8, m2, ta, ma
+sf.vfnrclip.xu.f.qf v4, v8, fa2
+
+# CHECK:      Resources:
+# CHECK-NEXT: [0]   - VLEN1024X300SiFive7FDiv:1
+# CHECK-NEXT: [1]   - VLEN1024X300SiFive7IDiv:1
+# CHECK-NEXT: [2]   - VLEN1024X300SiFive7PipeA:1
+# CHECK-NEXT: [3]   - VLEN1024X300SiFive7PipeAB:2 VLEN1024X300SiFive7PipeA, VLEN1024X300SiFive7PipeB
+# CHECK-NEXT: [4]   - VLEN1024X300SiFive7PipeB:1
+# CHECK-NEXT: [5]   - VLEN1024X300SiFive7VA1:1
+# CHECK-NEXT: [6]   - VLEN1024X300SiFive7VA1OrVA2:2 VLEN1024X300SiFive7VA1, VLEN1024X300SiFive7VA2
+# CHECK-NEXT: [7]   - VLEN1024X300SiFive7VA2:1
+# CHECK-NEXT: [8]   - VLEN1024X300SiFive7VCQ:1
+# CHECK-NEXT: [9]   - VLEN1024X300SiFive7VL:1
+# CHECK-NEXT: [10]  - VLEN1024X300SiFive7VS:1
+
+# 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-NEXT: [7]: Bypass Latency
+# CHECK-NEXT: [8]: Resources (<Name> | <Name>[<ReleaseAtCycle>] | <Name>[<AcquireAtCycle>,<ReleaseAtCycle])
+# CHECK-NEXT: [9]: LLVM Opcode Name
+
+# CHECK:      [1]    [2]    [3]    [4]    [5]    [6]    [7]    [8]                                        [9]                        Instructions:
+# CHECK-NEXT:  1      3     1.00                  U      1     VLEN1024X300SiFive7PipeA,VLEN1024X300SiFive7PipeAB VSETVLI            vsetvli	a0, zero, e8, mf8, ta, ma
+# CHECK-NEXT:  1      7     1.00                         7     VLEN1024X300SiFive7VA1[1,2],VLEN1024X300SiFive7VA1OrVA2[1,2],VLEN1024X300SiFive7VCQ SF_VFNRCLIP_XU_F_QF sf.vfnrclip.xu.f.qf	v4, v8, fa2
+# CHECK-NEXT:  1      3     1.00                  U      1     VLEN1024X300SiFive7PipeA,VLEN1024X300SiFive7PipeAB VSETVLI            vsetvli	a0, zero, e8, mf4, ta, ma
+# CHECK-NEXT:  1      8     2.00                         8     VLEN1024X300SiFive7VA1[1,3],VLEN1024X300SiFive7VA1OrVA2[1,3],VLEN1024X300SiFive7VCQ SF_VFNRCLIP_XU_F_QF sf.vfnrclip.xu.f.qf	v4, v8, fa2
+# CHECK-NEXT:  1      3     1.00                  U      1     VLEN1024X300SiFive7PipeA,VLEN1024X300SiFive7PipeAB VSETVLI            vsetvli	a0, zero, e8, mf2, ta, ma
+# CHECK-NEXT:  1      10    4.00                         10    VLEN1024X300SiFive7VA1[1,5],VLEN1024X300SiFive7VA1OrVA2[1,5],VLEN1024X300SiFive7VCQ SF_VFNRCLIP_XU_F_QF sf.vfnrclip.xu.f.qf	v4, v8, fa2
+# CHECK-NEXT:  1      3     1.00                  U      1     VLEN1024X300SiFive7PipeA,VLEN1024X300SiFive7PipeAB VSETVLI            vsetvli	a0, zero, e8, m1, ta, ma
+# CHECK-NEXT:  1      13    8.00                         13    VLEN1024X300SiFive7VA1[1,9],VLEN1024X300SiFive7VA1OrVA2[1,9],VLEN1024X300SiFive7VCQ SF_VFNRCLIP_XU_F_QF sf.vfnrclip.xu.f.qf	v4, v8, fa2
+# CHECK-NEXT:  1      3     1.00                  U      1     VLEN1024X300SiFive7PipeA,VLEN1024X300SiFive7PipeAB VSETVLI            vsetvli	a0, zero, e8, m2, ta, ma
+# CHECK-NEXT:  1      19    16.00                        19    VLEN1024X300SiFive7VA1[1,17],VLEN1024X300SiFive7VA1OrVA2[1,17],VLEN1024X300SiFive7VCQ SF_VFNRCLIP_XU_F_QF sf.vfnrclip.xu.f.qf	v4, v8, fa2
+
+# CHECK:      Resources:
+# CHECK-NEXT: [0]   - VLEN1024X300SiFive7FDiv
+# CHECK-NEXT: [1]   - VLEN1024X300SiFive7IDiv
+# CHECK-NEXT: [2]   - VLEN1024X300SiFive7PipeA
+# CHECK-NEXT: [3]   - VLEN1024X300SiFive7PipeB
+# CHECK-NEXT: [4]   - VLEN1024X300SiFive7VA1
+# CHECK-NEXT: [5]   - VLEN1024X300SiFive7VA2
+# CHECK-NEXT: [6]   - VLEN1024X300SiFive7VCQ
+# CHECK-NEXT: [7]   - VLEN1024X300SiFive7VL
+# CHECK-NEXT: [8]   - VLEN1024X300SiFive7VS
+
+# CHECK:      Resource pressure per iteration:
+# CHECK-NEXT: [0]    [1]    [2]    [3]    [4]    [5]    [6]    [7]    [8]
+# CHECK-NEXT:  -      -     5.00    -     36.00   -     5.00    -      -
+
+# CHECK:      Resource pressure by instruction:
+# CHECK-NEXT: [0]    [1]    [2]    [3]    [4]    [5]    [6]    [7]    [8]    Instructions:
+# CHECK-NEXT:  -      -     1.00    -      -      -      -      -      -     vsetvli	a0, zero, e8, mf8, ta, ma
+# CHECK-NEXT:  -      -      -      -     2.00    -     1.00    -      -     sf.vfnrclip.xu.f.qf	v4, v8, fa2
+# CHECK-NEXT:  -      -     1.00    -      -      -      -      -      -     vsetvli	a0, zero, e8, mf4, ta, ma
+# CHECK-NEXT:  -      -      -      -     3.00    -     1.00    -      -     sf.vfnrclip.xu.f.qf	v4, v8, fa2
+# CHECK-NEXT:  -      -     1.00    -      -      -      -      -      -     vsetvli	a0, zero, e8, mf2, ta, ma
+# CHECK-NEXT:  -      -      -      -     5.00    -     1.00    -      -     sf.vfnrclip.xu.f.qf	v4, v8, fa2
+# CHECK-NEXT:  -      -     1.00    -      -      -      -      -      -     vsetvli	a0, zero, e8, m1, ta, ma
+# CHECK-NEXT:  -      -      -      -     9.00    -     1.00    -      -     sf.vfnrclip.xu.f.qf	v4, v8, fa2
+# CHECK-NEXT:  -      -     1.00    -      -      -      -      -      -     vsetvli	a0, zero, e8, m2, ta, ma
+# CHECK-NEXT:  -      -      -      -     17.00   -     1.00    -      -     sf.vfnrclip.xu.f.qf	v4, v8, fa2