[MIPS] Fix the opcode of max.fmt and mina.fmt by Cyanoxygen · Pull Request #85609 · llvm/llvm-project

Cyanoxygen · 2024-03-18T07:35:45Z

The opcode of the mina.fmt and max.fmt is documented wrong, the
object code compiled from the same assembly with LLVM behaves
differently than one compiled with GCC and Binutils.
Modify the opcodes to match Binutils. The actual opcodes are as follows:

{5,3} | bits {2,0} of func
| ... | 100 | 101 | 110 | 111
-----+-----+-----+-----+-----+-----
010 | ... | min | mina | max | maxa

github-actions · 2024-03-18T07:36:02Z

Thank you for submitting a Pull Request (PR) to the LLVM Project!

This PR will be automatically labeled and the relevant teams will be
notified.

If you wish to, you can add reviewers by using the "Reviewers" section on this page.

If this is not working for you, it is probably because you do not have write
permissions for the repository. In which case you can instead tag reviewers by
name in a comment by using @ followed by their GitHub username.

If you have received no comments on your PR for a week, you can request a review
by "ping"ing the PR by adding a comment “Ping”. The common courtesy "ping" rate
is once a week. Please remember that you are asking for valuable time from other developers.

If you have further questions, they may be answered by the LLVM GitHub User Guide.

You can also ask questions in a comment on this PR, on the LLVM Discord or on the forums.

llvmbot · 2024-03-20T10:09:45Z

@llvm/pr-subscribers-mc

Author: Cinhi Young (Cyanoxygen)

Changes

TODO: Write MC tests and IR tests.

Fixes #85608.

Patch is 33.29 KiB, truncated to 20.00 KiB below, full version: https://github.com/llvm/llvm-project/pull/85609.diff

9 Files Affected:

(modified) llvm/lib/Target/Mips/Mips32r6InstrInfo.td (+20-4)
(modified) llvm/lib/Target/Mips/MipsISelLowering.cpp (+9)
(modified) llvm/test/CodeGen/Mips/msa/f16-llvm-ir.ll (+301-186)
(modified) llvm/test/MC/Disassembler/Mips/mips32r6/valid-mips32r6-el.txt (+4-4)
(modified) llvm/test/MC/Disassembler/Mips/mips32r6/valid-mips32r6.txt (+4-4)
(modified) llvm/test/MC/Disassembler/Mips/mips64r6/valid-mips64r6-el.txt (+4-4)
(modified) llvm/test/MC/Disassembler/Mips/mips64r6/valid-mips64r6.txt (+4-4)
(modified) llvm/test/MC/Mips/mips32r6/valid.s (+4-4)
(modified) llvm/test/MC/Mips/mips64r6/valid.s (+4-4)

diff --git a/llvm/lib/Target/Mips/Mips32r6InstrInfo.td b/llvm/lib/Target/Mips/Mips32r6InstrInfo.td
index 9c29acbd0d8a88..f609305bfee429 100644
--- a/llvm/lib/Target/Mips/Mips32r6InstrInfo.td
+++ b/llvm/lib/Target/Mips/Mips32r6InstrInfo.td
@@ -153,15 +153,15 @@ class SELNEZ_ENC : SPECIAL_3R_FM<0b00000, 0b110111>;
 
 class LWPC_ENC   : PCREL19_FM<OPCODE2_LWPC>;
 
-class MAX_S_ENC : COP1_3R_FM<0b011101, FIELD_FMT_S>;
-class MAX_D_ENC : COP1_3R_FM<0b011101, FIELD_FMT_D>;
+class MAX_S_ENC : COP1_3R_FM<0b011110, FIELD_FMT_S>;
+class MAX_D_ENC : COP1_3R_FM<0b011110, FIELD_FMT_D>;
 class MIN_S_ENC : COP1_3R_FM<0b011100, FIELD_FMT_S>;
 class MIN_D_ENC : COP1_3R_FM<0b011100, FIELD_FMT_D>;
 
 class MAXA_S_ENC : COP1_3R_FM<0b011111, FIELD_FMT_S>;
 class MAXA_D_ENC : COP1_3R_FM<0b011111, FIELD_FMT_D>;
-class MINA_S_ENC : COP1_3R_FM<0b011110, FIELD_FMT_S>;
-class MINA_D_ENC : COP1_3R_FM<0b011110, FIELD_FMT_D>;
+class MINA_S_ENC : COP1_3R_FM<0b011101, FIELD_FMT_S>;
+class MINA_D_ENC : COP1_3R_FM<0b011101, FIELD_FMT_D>;
 
 class SELEQZ_S_ENC : COP1_3R_FM<0b010100, FIELD_FMT_S>;
 class SELEQZ_D_ENC : COP1_3R_FM<0b010100, FIELD_FMT_D>;
@@ -1117,6 +1117,22 @@ def : MipsPat<(select i32:$cond, immz, i32:$f),
               ISA_MIPS32R6;
 }
 
+// llvm.fmin/fmax operations.
+let AdditionalPredicates = [NotInMicroMips] in {
+  def : MipsPat<(fmaxnum f32:$lhs, f32:$rhs),
+                (MAX_S   f32:$lhs, f32:$rhs)>,
+                ISA_MIPS32R6;
+  def : MipsPat<(fmaxnum f64:$lhs, f64:$rhs),
+                (MAX_D   f64:$lhs, f64:$rhs)>,
+                ISA_MIPS32R6;
+  def : MipsPat<(fminnum f32:$lhs, f32:$rhs),
+                (MIN_S   f32:$lhs, f32:$rhs)>,
+                ISA_MIPS32R6;
+  def : MipsPat<(fminnum f64:$lhs, f64:$rhs),
+                (MIN_D   f64:$lhs, f64:$rhs)>,
+                ISA_MIPS32R6;
+}
+
 // Pseudo instructions
 let isCall = 1, isTerminator = 1, isReturn = 1, isBarrier = 1, hasDelaySlot = 1,
     hasExtraSrcRegAllocReq = 1, isCTI = 1, Defs = [AT], hasPostISelHook = 1 in {
diff --git a/llvm/lib/Target/Mips/MipsISelLowering.cpp b/llvm/lib/Target/Mips/MipsISelLowering.cpp
index 0a0d40751fcf05..add2ec6fc64a2f 100644
--- a/llvm/lib/Target/Mips/MipsISelLowering.cpp
+++ b/llvm/lib/Target/Mips/MipsISelLowering.cpp
@@ -358,6 +358,15 @@ MipsTargetLowering::MipsTargetLowering(const MipsTargetMachine &TM,
   setOperationAction(ISD::FCOPYSIGN,          MVT::f64,   Custom);
   setOperationAction(ISD::FP_TO_SINT,         MVT::i32,   Custom);
 
+  // Lower fmin and fmax operations for MIPS R6.
+  // Instructions are defined but never used.
+  if (Subtarget.hasMips32r6()) {
+    setOperationAction(ISD::FMINNUM, MVT::f32, Legal);
+    setOperationAction(ISD::FMINNUM, MVT::f64, Legal);
+    setOperationAction(ISD::FMAXNUM, MVT::f32, Legal);
+    setOperationAction(ISD::FMAXNUM, MVT::f64, Legal);
+  }
+
   if (Subtarget.isGP64bit()) {
     setOperationAction(ISD::GlobalAddress,      MVT::i64,   Custom);
     setOperationAction(ISD::BlockAddress,       MVT::i64,   Custom);
diff --git a/llvm/test/CodeGen/Mips/msa/f16-llvm-ir.ll b/llvm/test/CodeGen/Mips/msa/f16-llvm-ir.ll
index 45c7ab980edd64..fe68bee408fc89 100644
--- a/llvm/test/CodeGen/Mips/msa/f16-llvm-ir.ll
+++ b/llvm/test/CodeGen/Mips/msa/f16-llvm-ir.ll
@@ -2365,101 +2365,159 @@ entry:
 declare float @llvm.minnum.f32(float %Val, float %b)
 
 define void @fminnum(float %b) {
-; MIPS32-LABEL: fminnum:
-; MIPS32:       # %bb.0: # %entry
-; MIPS32-NEXT:    lui $2, %hi(_gp_disp)
-; MIPS32-NEXT:    addiu $2, $2, %lo(_gp_disp)
-; MIPS32-NEXT:    addiu $sp, $sp, -24
-; MIPS32-NEXT:    .cfi_def_cfa_offset 24
-; MIPS32-NEXT:    sw $ra, 20($sp) # 4-byte Folded Spill
-; MIPS32-NEXT:    sw $16, 16($sp) # 4-byte Folded Spill
-; MIPS32-NEXT:    .cfi_offset 31, -4
-; MIPS32-NEXT:    .cfi_offset 16, -8
-; MIPS32-NEXT:    addu $gp, $2, $25
-; MIPS32-NEXT:    mov.s $f14, $f12
-; MIPS32-NEXT:    lw $16, %got(g)($gp)
-; MIPS32-NEXT:    lh $1, 0($16)
-; MIPS32-NEXT:    fill.h $w0, $1
-; MIPS32-NEXT:    fexupr.w $w0, $w0
-; MIPS32-NEXT:    copy_s.w $1, $w0[0]
-; MIPS32-NEXT:    lw $25, %call16(fminf)($gp)
-; MIPS32-NEXT:    jalr $25
-; MIPS32-NEXT:    mtc1 $1, $f12
-; MIPS32-NEXT:    mfc1 $1, $f0
-; MIPS32-NEXT:    fill.w $w0, $1
-; MIPS32-NEXT:    fexdo.h $w0, $w0, $w0
-; MIPS32-NEXT:    copy_u.h $1, $w0[0]
-; MIPS32-NEXT:    sh $1, 0($16)
-; MIPS32-NEXT:    lw $16, 16($sp) # 4-byte Folded Reload
-; MIPS32-NEXT:    lw $ra, 20($sp) # 4-byte Folded Reload
-; MIPS32-NEXT:    jr $ra
-; MIPS32-NEXT:    addiu $sp, $sp, 24
+; MIPS32-O32-LABEL: fminnum:
+; MIPS32-O32:       # %bb.0: # %entry
+; MIPS32-O32-NEXT:    lui $2, %hi(_gp_disp)
+; MIPS32-O32-NEXT:    addiu $2, $2, %lo(_gp_disp)
+; MIPS32-O32-NEXT:    addiu $sp, $sp, -24
+; MIPS32-O32-NEXT:    .cfi_def_cfa_offset 24
+; MIPS32-O32-NEXT:    sw $ra, 20($sp) # 4-byte Folded Spill
+; MIPS32-O32-NEXT:    sw $16, 16($sp) # 4-byte Folded Spill
+; MIPS32-O32-NEXT:    .cfi_offset 31, -4
+; MIPS32-O32-NEXT:    .cfi_offset 16, -8
+; MIPS32-O32-NEXT:    addu $gp, $2, $25
+; MIPS32-O32-NEXT:    mov.s $f14, $f12
+; MIPS32-O32-NEXT:    lw $16, %got(g)($gp)
+; MIPS32-O32-NEXT:    lh $1, 0($16)
+; MIPS32-O32-NEXT:    fill.h $w0, $1
+; MIPS32-O32-NEXT:    fexupr.w $w0, $w0
+; MIPS32-O32-NEXT:    copy_s.w $1, $w0[0]
+; MIPS32-O32-NEXT:    lw $25, %call16(fminf)($gp)
+; MIPS32-O32-NEXT:    jalr $25
+; MIPS32-O32-NEXT:    mtc1 $1, $f12
+; MIPS32-O32-NEXT:    mfc1 $1, $f0
+; MIPS32-O32-NEXT:    fill.w $w0, $1
+; MIPS32-O32-NEXT:    fexdo.h $w0, $w0, $w0
+; MIPS32-O32-NEXT:    copy_u.h $1, $w0[0]
+; MIPS32-O32-NEXT:    sh $1, 0($16)
+; MIPS32-O32-NEXT:    lw $16, 16($sp) # 4-byte Folded Reload
+; MIPS32-O32-NEXT:    lw $ra, 20($sp) # 4-byte Folded Reload
+; MIPS32-O32-NEXT:    jr $ra
+; MIPS32-O32-NEXT:    addiu $sp, $sp, 24
 ;
-; MIPS64-N32-LABEL: fminnum:
-; MIPS64-N32:       # %bb.0: # %entry
-; MIPS64-N32-NEXT:    addiu $sp, $sp, -32
-; MIPS64-N32-NEXT:    .cfi_def_cfa_offset 32
-; MIPS64-N32-NEXT:    sd $ra, 24($sp) # 8-byte Folded Spill
-; MIPS64-N32-NEXT:    sd $gp, 16($sp) # 8-byte Folded Spill
-; MIPS64-N32-NEXT:    sd $16, 8($sp) # 8-byte Folded Spill
-; MIPS64-N32-NEXT:    .cfi_offset 31, -8
-; MIPS64-N32-NEXT:    .cfi_offset 28, -16
-; MIPS64-N32-NEXT:    .cfi_offset 16, -24
-; MIPS64-N32-NEXT:    lui $1, %hi(%neg(%gp_rel(fminnum)))
-; MIPS64-N32-NEXT:    addu $1, $1, $25
-; MIPS64-N32-NEXT:    addiu $gp, $1, %lo(%neg(%gp_rel(fminnum)))
-; MIPS64-N32-NEXT:    mov.s $f13, $f12
-; MIPS64-N32-NEXT:    lw $16, %got_disp(g)($gp)
-; MIPS64-N32-NEXT:    lh $1, 0($16)
-; MIPS64-N32-NEXT:    fill.h $w0, $1
-; MIPS64-N32-NEXT:    fexupr.w $w0, $w0
-; MIPS64-N32-NEXT:    copy_s.w $1, $w0[0]
-; MIPS64-N32-NEXT:    lw $25, %call16(fminf)($gp)
-; MIPS64-N32-NEXT:    jalr $25
-; MIPS64-N32-NEXT:    mtc1 $1, $f12
-; MIPS64-N32-NEXT:    mfc1 $1, $f0
-; MIPS64-N32-NEXT:    fill.w $w0, $1
-; MIPS64-N32-NEXT:    fexdo.h $w0, $w0, $w0
-; MIPS64-N32-NEXT:    copy_u.h $1, $w0[0]
-; MIPS64-N32-NEXT:    sh $1, 0($16)
-; MIPS64-N32-NEXT:    ld $16, 8($sp) # 8-byte Folded Reload
-; MIPS64-N32-NEXT:    ld $gp, 16($sp) # 8-byte Folded Reload
-; MIPS64-N32-NEXT:    ld $ra, 24($sp) # 8-byte Folded Reload
-; MIPS64-N32-NEXT:    jr $ra
-; MIPS64-N32-NEXT:    addiu $sp, $sp, 32
+; MIPS64R5-N32-LABEL: fminnum:
+; MIPS64R5-N32:       # %bb.0: # %entry
+; MIPS64R5-N32-NEXT:    addiu $sp, $sp, -32
+; MIPS64R5-N32-NEXT:    .cfi_def_cfa_offset 32
+; MIPS64R5-N32-NEXT:    sd $ra, 24($sp) # 8-byte Folded Spill
+; MIPS64R5-N32-NEXT:    sd $gp, 16($sp) # 8-byte Folded Spill
+; MIPS64R5-N32-NEXT:    sd $16, 8($sp) # 8-byte Folded Spill
+; MIPS64R5-N32-NEXT:    .cfi_offset 31, -8
+; MIPS64R5-N32-NEXT:    .cfi_offset 28, -16
+; MIPS64R5-N32-NEXT:    .cfi_offset 16, -24
+; MIPS64R5-N32-NEXT:    lui $1, %hi(%neg(%gp_rel(fminnum)))
+; MIPS64R5-N32-NEXT:    addu $1, $1, $25
+; MIPS64R5-N32-NEXT:    addiu $gp, $1, %lo(%neg(%gp_rel(fminnum)))
+; MIPS64R5-N32-NEXT:    mov.s $f13, $f12
+; MIPS64R5-N32-NEXT:    lw $16, %got_disp(g)($gp)
+; MIPS64R5-N32-NEXT:    lh $1, 0($16)
+; MIPS64R5-N32-NEXT:    fill.h $w0, $1
+; MIPS64R5-N32-NEXT:    fexupr.w $w0, $w0
+; MIPS64R5-N32-NEXT:    copy_s.w $1, $w0[0]
+; MIPS64R5-N32-NEXT:    lw $25, %call16(fminf)($gp)
+; MIPS64R5-N32-NEXT:    jalr $25
+; MIPS64R5-N32-NEXT:    mtc1 $1, $f12
+; MIPS64R5-N32-NEXT:    mfc1 $1, $f0
+; MIPS64R5-N32-NEXT:    fill.w $w0, $1
+; MIPS64R5-N32-NEXT:    fexdo.h $w0, $w0, $w0
+; MIPS64R5-N32-NEXT:    copy_u.h $1, $w0[0]
+; MIPS64R5-N32-NEXT:    sh $1, 0($16)
+; MIPS64R5-N32-NEXT:    ld $16, 8($sp) # 8-byte Folded Reload
+; MIPS64R5-N32-NEXT:    ld $gp, 16($sp) # 8-byte Folded Reload
+; MIPS64R5-N32-NEXT:    ld $ra, 24($sp) # 8-byte Folded Reload
+; MIPS64R5-N32-NEXT:    jr $ra
+; MIPS64R5-N32-NEXT:    addiu $sp, $sp, 32
+;
+; MIPS64R5-N64-LABEL: fminnum:
+; MIPS64R5-N64:       # %bb.0: # %entry
+; MIPS64R5-N64-NEXT:    daddiu $sp, $sp, -32
+; MIPS64R5-N64-NEXT:    .cfi_def_cfa_offset 32
+; MIPS64R5-N64-NEXT:    sd $ra, 24($sp) # 8-byte Folded Spill
+; MIPS64R5-N64-NEXT:    sd $gp, 16($sp) # 8-byte Folded Spill
+; MIPS64R5-N64-NEXT:    sd $16, 8($sp) # 8-byte Folded Spill
+; MIPS64R5-N64-NEXT:    .cfi_offset 31, -8
+; MIPS64R5-N64-NEXT:    .cfi_offset 28, -16
+; MIPS64R5-N64-NEXT:    .cfi_offset 16, -24
+; MIPS64R5-N64-NEXT:    lui $1, %hi(%neg(%gp_rel(fminnum)))
+; MIPS64R5-N64-NEXT:    daddu $1, $1, $25
+; MIPS64R5-N64-NEXT:    daddiu $gp, $1, %lo(%neg(%gp_rel(fminnum)))
+; MIPS64R5-N64-NEXT:    mov.s $f13, $f12
+; MIPS64R5-N64-NEXT:    ld $16, %got_disp(g)($gp)
+; MIPS64R5-N64-NEXT:    lh $1, 0($16)
+; MIPS64R5-N64-NEXT:    fill.h $w0, $1
+; MIPS64R5-N64-NEXT:    fexupr.w $w0, $w0
+; MIPS64R5-N64-NEXT:    copy_s.w $1, $w0[0]
+; MIPS64R5-N64-NEXT:    ld $25, %call16(fminf)($gp)
+; MIPS64R5-N64-NEXT:    jalr $25
+; MIPS64R5-N64-NEXT:    mtc1 $1, $f12
+; MIPS64R5-N64-NEXT:    mfc1 $1, $f0
+; MIPS64R5-N64-NEXT:    fill.w $w0, $1
+; MIPS64R5-N64-NEXT:    fexdo.h $w0, $w0, $w0
+; MIPS64R5-N64-NEXT:    copy_u.h $1, $w0[0]
+; MIPS64R5-N64-NEXT:    sh $1, 0($16)
+; MIPS64R5-N64-NEXT:    ld $16, 8($sp) # 8-byte Folded Reload
+; MIPS64R5-N64-NEXT:    ld $gp, 16($sp) # 8-byte Folded Reload
+; MIPS64R5-N64-NEXT:    ld $ra, 24($sp) # 8-byte Folded Reload
+; MIPS64R5-N64-NEXT:    jr $ra
+; MIPS64R5-N64-NEXT:    daddiu $sp, $sp, 32
+;
+; MIPSR6-O32-LABEL: fminnum:
+; MIPSR6-O32:       # %bb.0: # %entry
+; MIPSR6-O32-NEXT:    lui $2, %hi(_gp_disp)
+; MIPSR6-O32-NEXT:    addiu $2, $2, %lo(_gp_disp)
+; MIPSR6-O32-NEXT:    addu $1, $2, $25
+; MIPSR6-O32-NEXT:    lw $1, %got(g)($1)
+; MIPSR6-O32-NEXT:    lh $2, 0($1)
+; MIPSR6-O32-NEXT:    fill.h $w0, $2
+; MIPSR6-O32-NEXT:    fexupr.w $w0, $w0
+; MIPSR6-O32-NEXT:    copy_s.w $2, $w0[0]
+; MIPSR6-O32-NEXT:    mtc1 $2, $f0
+; MIPSR6-O32-NEXT:    min.s $f0, $f0, $f12
+; MIPSR6-O32-NEXT:    mfc1 $2, $f0
+; MIPSR6-O32-NEXT:    fill.w $w0, $2
+; MIPSR6-O32-NEXT:    fexdo.h $w0, $w0, $w0
+; MIPSR6-O32-NEXT:    copy_u.h $2, $w0[0]
+; MIPSR6-O32-NEXT:    jr $ra
+; MIPSR6-O32-NEXT:    sh $2, 0($1)
+;
+; MIPSR6-N32-LABEL: fminnum:
+; MIPSR6-N32:       # %bb.0: # %entry
+; MIPSR6-N32-NEXT:    lui $1, %hi(%neg(%gp_rel(fminnum)))
+; MIPSR6-N32-NEXT:    addu $1, $1, $25
+; MIPSR6-N32-NEXT:    addiu $1, $1, %lo(%neg(%gp_rel(fminnum)))
+; MIPSR6-N32-NEXT:    lw $1, %got_disp(g)($1)
+; MIPSR6-N32-NEXT:    lh $2, 0($1)
+; MIPSR6-N32-NEXT:    fill.h $w0, $2
+; MIPSR6-N32-NEXT:    fexupr.w $w0, $w0
+; MIPSR6-N32-NEXT:    copy_s.w $2, $w0[0]
+; MIPSR6-N32-NEXT:    mtc1 $2, $f0
+; MIPSR6-N32-NEXT:    min.s $f0, $f0, $f12
+; MIPSR6-N32-NEXT:    mfc1 $2, $f0
+; MIPSR6-N32-NEXT:    fill.w $w0, $2
+; MIPSR6-N32-NEXT:    fexdo.h $w0, $w0, $w0
+; MIPSR6-N32-NEXT:    copy_u.h $2, $w0[0]
+; MIPSR6-N32-NEXT:    jr $ra
+; MIPSR6-N32-NEXT:    sh $2, 0($1)
+;
+; MIPSR6-N64-LABEL: fminnum:
+; MIPSR6-N64:       # %bb.0: # %entry
+; MIPSR6-N64-NEXT:    lui $1, %hi(%neg(%gp_rel(fminnum)))
+; MIPSR6-N64-NEXT:    daddu $1, $1, $25
+; MIPSR6-N64-NEXT:    daddiu $1, $1, %lo(%neg(%gp_rel(fminnum)))
+; MIPSR6-N64-NEXT:    ld $1, %got_disp(g)($1)
+; MIPSR6-N64-NEXT:    lh $2, 0($1)
+; MIPSR6-N64-NEXT:    fill.h $w0, $2
+; MIPSR6-N64-NEXT:    fexupr.w $w0, $w0
+; MIPSR6-N64-NEXT:    copy_s.w $2, $w0[0]
+; MIPSR6-N64-NEXT:    mtc1 $2, $f0
+; MIPSR6-N64-NEXT:    min.s $f0, $f0, $f12
+; MIPSR6-N64-NEXT:    mfc1 $2, $f0
+; MIPSR6-N64-NEXT:    fill.w $w0, $2
+; MIPSR6-N64-NEXT:    fexdo.h $w0, $w0, $w0
+; MIPSR6-N64-NEXT:    copy_u.h $2, $w0[0]
+; MIPSR6-N64-NEXT:    jr $ra
+; MIPSR6-N64-NEXT:    sh $2, 0($1)
 ;
-; MIPS64-N64-LABEL: fminnum:
-; MIPS64-N64:       # %bb.0: # %entry
-; MIPS64-N64-NEXT:    daddiu $sp, $sp, -32
-; MIPS64-N64-NEXT:    .cfi_def_cfa_offset 32
-; MIPS64-N64-NEXT:    sd $ra, 24($sp) # 8-byte Folded Spill
-; MIPS64-N64-NEXT:    sd $gp, 16($sp) # 8-byte Folded Spill
-; MIPS64-N64-NEXT:    sd $16, 8($sp) # 8-byte Folded Spill
-; MIPS64-N64-NEXT:    .cfi_offset 31, -8
-; MIPS64-N64-NEXT:    .cfi_offset 28, -16
-; MIPS64-N64-NEXT:    .cfi_offset 16, -24
-; MIPS64-N64-NEXT:    lui $1, %hi(%neg(%gp_rel(fminnum)))
-; MIPS64-N64-NEXT:    daddu $1, $1, $25
-; MIPS64-N64-NEXT:    daddiu $gp, $1, %lo(%neg(%gp_rel(fminnum)))
-; MIPS64-N64-NEXT:    mov.s $f13, $f12
-; MIPS64-N64-NEXT:    ld $16, %got_disp(g)($gp)
-; MIPS64-N64-NEXT:    lh $1, 0($16)
-; MIPS64-N64-NEXT:    fill.h $w0, $1
-; MIPS64-N64-NEXT:    fexupr.w $w0, $w0
-; MIPS64-N64-NEXT:    copy_s.w $1, $w0[0]
-; MIPS64-N64-NEXT:    ld $25, %call16(fminf)($gp)
-; MIPS64-N64-NEXT:    jalr $25
-; MIPS64-N64-NEXT:    mtc1 $1, $f12
-; MIPS64-N64-NEXT:    mfc1 $1, $f0
-; MIPS64-N64-NEXT:    fill.w $w0, $1
-; MIPS64-N64-NEXT:    fexdo.h $w0, $w0, $w0
-; MIPS64-N64-NEXT:    copy_u.h $1, $w0[0]
-; MIPS64-N64-NEXT:    sh $1, 0($16)
-; MIPS64-N64-NEXT:    ld $16, 8($sp) # 8-byte Folded Reload
-; MIPS64-N64-NEXT:    ld $gp, 16($sp) # 8-byte Folded Reload
-; MIPS64-N64-NEXT:    ld $ra, 24($sp) # 8-byte Folded Reload
-; MIPS64-N64-NEXT:    jr $ra
-; MIPS64-N64-NEXT:    daddiu $sp, $sp, 32
 entry:
   %0 = load i16, ptr @g, align 2
   %1 = call float @llvm.convert.from.fp16.f32(i16 %0)
@@ -2477,101 +2535,158 @@ entry:
 declare float @llvm.maxnum.f32(float %Val, float %b)
 
 define void @fmaxnum(float %b) {
-; MIPS32-LABEL: fmaxnum:
-; MIPS32:       # %bb.0: # %entry
-; MIPS32-NEXT:    lui $2, %hi(_gp_disp)
-; MIPS32-NEXT:    addiu $2, $2, %lo(_gp_disp)
-; MIPS32-NEXT:    addiu $sp, $sp, -24
-; MIPS32-NEXT:    .cfi_def_cfa_offset 24
-; MIPS32-NEXT:    sw $ra, 20($sp) # 4-byte Folded Spill
-; MIPS32-NEXT:    sw $16, 16($sp) # 4-byte Folded Spill
-; MIPS32-NEXT:    .cfi_offset 31, -4
-; MIPS32-NEXT:    .cfi_offset 16, -8
-; MIPS32-NEXT:    addu $gp, $2, $25
-; MIPS32-NEXT:    mov.s $f14, $f12
-; MIPS32-NEXT:    lw $16, %got(g)($gp)
-; MIPS32-NEXT:    lh $1, 0($16)
-; MIPS32-NEXT:    fill.h $w0, $1
-; MIPS32-NEXT:    fexupr.w $w0, $w0
-; MIPS32-NEXT:    copy_s.w $1, $w0[0]
-; MIPS32-NEXT:    lw $25, %call16(fmaxf)($gp)
-; MIPS32-NEXT:    jalr $25
-; MIPS32-NEXT:    mtc1 $1, $f12
-; MIPS32-NEXT:    mfc1 $1, $f0
-; MIPS32-NEXT:    fill.w $w0, $1
-; MIPS32-NEXT:    fexdo.h $w0, $w0, $w0
-; MIPS32-NEXT:    copy_u.h $1, $w0[0]
-; MIPS32-NEXT:    sh $1, 0($16)
-; MIPS32-NEXT:    lw $16, 16($sp) # 4-byte Folded Reload
-; MIPS32-NEXT:    lw $ra, 20($sp) # 4-byte Folded Reload
-; MIPS32-NEXT:    jr $ra
-; MIPS32-NEXT:    addiu $sp, $sp, 24
+; MIPS32-O32-LABEL: fmaxnum:
+; MIPS32-O32:       # %bb.0: # %entry
+; MIPS32-O32-NEXT:    lui $2, %hi(_gp_disp)
+; MIPS32-O32-NEXT:    addiu $2, $2, %lo(_gp_disp)
+; MIPS32-O32-NEXT:    addiu $sp, $sp, -24
+; MIPS32-O32-NEXT:    .cfi_def_cfa_offset 24
+; MIPS32-O32-NEXT:    sw $ra, 20($sp) # 4-byte Folded Spill
+; MIPS32-O32-NEXT:    sw $16, 16($sp) # 4-byte Folded Spill
+; MIPS32-O32-NEXT:    .cfi_offset 31, -4
+; MIPS32-O32-NEXT:    .cfi_offset 16, -8
+; MIPS32-O32-NEXT:    addu $gp, $2, $25
+; MIPS32-O32-NEXT:    mov.s $f14, $f12
+; MIPS32-O32-NEXT:    lw $16, %got(g)($gp)
+; MIPS32-O32-NEXT:    lh $1, 0($16)
+; MIPS32-O32-NEXT:    fill.h $w0, $1
+; MIPS32-O32-NEXT:    fexupr.w $w0, $w0
+; MIPS32-O32-NEXT:    copy_s.w $1, $w0[0]
+; MIPS32-O32-NEXT:    lw $25, %call16(fmaxf)($gp)
+; MIPS32-O32-NEXT:    jalr $25
+; MIPS32-O32-NEXT:    mtc1 $1, $f12
+; MIPS32-O32-NEXT:    mfc1 $1, $f0
+; MIPS32-O32-NEXT:    fill.w $w0, $1
+; MIPS32-O32-NEXT:    fexdo.h $w0, $w0, $w0
+; MIPS32-O32-NEXT:    copy_u.h $1, $w0[0]
+; MIPS32-O32-NEXT:    sh $1, 0($16)
+; MIPS32-O32-NEXT:    lw $16, 16($sp) # 4-byte Folded Reload
+; MIPS32-O32-NEXT:    lw $ra, 20($sp) # 4-byte Folded Reload
+; MIPS32-O32-NEXT:    jr $ra
+; MIPS32-O32-NEXT:    addiu $sp, $sp, 24
 ;
-; MIPS64-N32-LABEL: fmaxnum:
-; MIPS64-N32:       # %bb.0: # %entry
-; MIPS64-N32-NEXT:    addiu $sp, $sp, -32
-; MIPS64-N32-NEXT:    .cfi_def_cfa_offset 32
-; MIPS64-N32-NEXT:    sd $ra, 24($sp) # 8-byte Folded Spill
-; MIPS64-N32-NEXT:    sd $gp, 16($sp) # 8-byte Folded Spill
-; MIPS64-N32-NEXT:    sd $16, 8($sp) # 8-byte Folded Spill
-; MIPS64-N32-NEXT:    .cfi_offset 31, -8
-; MIPS64-N32-NEXT:    .cfi_offset 28, -16
-; MIPS64-N32-NEXT:    .cfi_offset 16, -24
-; MIPS64-N32-NEXT:    lui $1, %hi(%neg(%gp_rel(fmaxnum)))
-; MIPS64-N32-NEXT:    addu $1, $1, $25
-; MIPS64-N32-NEXT:    addiu $gp, $1, %lo(%neg(%gp_rel(fmaxnum)))
-; MIPS64-N32-NEXT:    mov.s $f13, $f12
-; MIPS64-N32-NEXT:    lw $16, %got_disp(g)($gp)
-; MIPS64-N32-NEXT:    lh $1, 0($16)
-; MIPS64-N32-NEXT:    fill.h $w0, $1
-; MIPS64-N32-NEXT:    fexupr.w $w0, $w0
-; MIPS64-N32-NEXT:    copy_s.w $1, $w0[0]
-; MIPS64-N32-NEXT:    lw $25, %call16(fmaxf)($gp)
-; MIPS64-N32-NEXT:    jalr $25
-; MIPS64-N32-NEXT:    mtc1 $1, $f12
-; MIPS64-N32-NEXT:    mfc1 $1, $f0
-; MIPS64-N32-NEXT:    fill.w $w0, $1
-; MIPS64-N32-NEXT:    fexdo.h $w0, $w0, $w0
-; MIPS64-N32-NEXT:    copy_u.h $1, $w0[0]
-; MIPS64-N32-NEXT:    sh $1, 0($16)
-; MIPS64-N32-NEXT:    ld $16, 8($sp) # 8-byte Folded Reload
-; MIPS64-N32-NEXT:    ld $gp, 16($sp) # 8-byte Folded Reload
-; MIPS64-N32-NEXT:    ld $ra, 24($sp) # 8-byte Folded Reload
-; MIPS64-N32-NEXT:    jr $ra
-; MIPS64-N32-NEXT:    addiu $sp, $sp, 32
+; MIPS64R5-N32-LABEL: fmaxnum:
+; MIPS64R5-N32:       # %bb.0: # %entry
+; MIPS64R5-N32-NEXT:    addiu $sp, $sp, -32
+; MIPS64R5-N32-NEXT:    .cfi_def_cfa_offset 32
+; MIPS64R5-N32-NEXT:    sd $ra, 24($sp) # 8-byte Folded Spill
+; MIPS64R5-N32-NEXT:    sd $gp, 16($sp) # 8-byte Folded Spill
+; MIPS64R5-N32-NEXT:    sd $16, 8($sp) # 8-byte Folded Spill
+; MIPS64R5-N32-NEXT:    .cfi_offset 31, -8
+; MIPS64R5-N32-NEXT:    .cfi_offset 28, -16
+; MIPS64R5-N32-NEXT:    .cfi_offset 16, -24
+; MIPS64R5-N32-NEXT:    lui $1, %hi(%neg(%gp_rel(fmaxnum)))
+; MIPS64R5-N32-NEXT:    addu $1, $1, $25
+; MIPS64R5-N32-NEXT:    addiu $gp, $1, %lo(%neg(%gp_rel(fmaxnum)))
+; MIPS64R5-N32-NEXT:    mov.s $f13, $f12
+; MIPS64R5-N32-NEXT:    lw $16, %got_disp(g)($gp)
+; MIPS64R5-N32-NEXT:    lh $1, 0($16)
+; MIPS64R5-N32-NEXT:    fill.h $w0, $1
+; MIPS64R5-N32-NEXT:    fexupr.w $w0, $w0
+; MIPS64R5-N32-NEXT:    copy_s.w $1, $w0[0]
+; MIPS64R5-N32-NEXT:    lw $25, %call16(fmaxf)($gp)
+; MIPS64R5-N32-NEXT:    jalr $25
+; MIPS64R5-N32-NEXT:    mtc1 $1, $f12
+; MIPS64R5-N32-NEXT:    mfc1 $1, $f0
+; MIPS64R5-N32-NEXT:    fill.w $w0, $1
+; MIPS64R5-N32-NEXT:    fexdo.h $w0, $w0, $w0
+; MIPS64R5-N32-NEXT:    copy_u.h $1, $w0[0]
+; MIPS64R5-N32-NEXT:    sh $1, 0($16)
+; MIPS64R5-N32-NEXT:    ld $16, 8($sp) # 8-byte Folded Reload
+; MIPS64R5-N32-NEXT:    ld $gp, 16($sp) # 8-byte Folded Reload
+; MIPS64R5-N32-NEXT:    ld $ra, 24($sp) # 8-byte Folded Reload
+; MIPS64R5-N32-NEXT:    jr $ra
+; MIPS64R5-N32-NEXT:    addiu $sp, $sp, 32
 ;
-; MIPS64-N64-LABEL: fmaxnum:
-; MIPS64-N64:       # %bb.0: # %entry
-; MIPS64-N64-NEXT:    daddiu $sp, $sp, -32
-; MIPS64-N64-NEXT:    .cfi_def_cfa_offset 32
-; MIPS64-N64-NEXT:    sd $ra, 24($sp) # 8-byte Folded Spill
-; MIPS64-N64-NEXT:    sd $gp, 16($sp) # 8-byte Folded Spill
-; MIPS64-N64-NEXT:    sd $16, 8($sp) # 8-byte Folded Spill
-; MIPS64-N64-NEXT:    .cfi_offset 31, -8
-; MIPS64-N64-NEXT:    .cfi_offset 28, -16
-; MIPS64-N64-NEXT:    .cfi_offset 16, -24
-; MIPS64-N64-NEXT:    lui $1, %hi(%neg(%gp_rel(fmaxnum)))
-; MIPS64-N64-NEXT:    daddu $1, $1, $25
-; MIPS64-N64-NEXT:    daddiu $gp, $1, %lo(%neg(%gp_rel(fmaxnum)))
-; MIPS64-N64-NEXT:    mov.s $f13, $f12
-; MIPS64-N64-NEXT:    ld $16, %got_disp(g)($gp)
-; MIPS64-N64-NEXT:    lh $1, 0($16)
-; MIPS64-N64-NEXT:    fill.h $w0, $1
-; MIPS64-N64-NEXT:    fexupr.w $w0, $w0
-; MIPS64-N64-NEXT:    copy_s.w $1, $w0[0]
-; MIPS64-N64-NEXT...
[truncated]

Cyanoxygen · 2024-03-20T15:00:25Z

Don't know how this Clang test failed though 😄

wzssyqa · 2024-04-01T16:50:08Z

I think that we should split it to 2 commits.

wzssyqa · 2024-04-01T16:52:59Z

The first patch should only fix the encoding problem (including the test cases about it)
The 2nd patch should add the backend support.

- The opcode of the mina.fmt and max.fmt is documented wrong, the object code compiled from the same assembly with LLVM behaves differently than one compiled with GCC and Binutils. - Modify the opcodes to match Binutils. The actual opcodes are as follows: {5,3}| bits {2,0} of func | ... | 100 | 101 | 110 | 111 -----+-----+-----+-----+-----+----- 010 | ... | min | mina| max | maxa

Cyanoxygen · 2024-04-02T10:53:31Z

I think that we should split it to 2 commits.

Sure! But would it be better if we split this into two PRs? I've now removed unrelated changes from this branch.

github-actions · 2024-04-03T02:14:23Z

@Cyanoxygen Congratulations on having your first Pull Request (PR) merged into the LLVM Project!

Your changes will be combined with recent changes from other authors, then tested
by our build bots. If there is a problem with a build, you may receive a report in an email or a comment on this PR.

Please check whether problems have been caused by your change specifically, as
the builds can include changes from many authors. It is not uncommon for your
change to be included in a build that fails due to someone else's changes, or
infrastructure issues.

How to do this, and the rest of the post-merge process, is covered in detail here.

If your change does cause a problem, it may be reverted, or you can revert it yourself.
This is a normal part of LLVM development. You can fix your changes and open a new PR to merge them again.

If you don't get any reports, no action is required from you. Your changes are working as expected, well done!

- The opcode of the mina.fmt and max.fmt is documented wrong, the object code compiled from the same assembly with LLVM behaves differently than one compiled with GCC and Binutils. - Modify the opcodes to match Binutils. The actual opcodes are as follows: {5,3} | bits {2,0} of func | ... | 100 | 101 | 110 | 111 -----+-----+-----+-----+-----+----- 010 | ... | min | mina | max | maxa (cherry picked from commit 8b859c6)

Cyanoxygen force-pushed the mipsr6-minmax branch 2 times, most recently from 98bbbe9 to ff9b37e Compare March 20, 2024 10:08

Cyanoxygen marked this pull request as ready for review March 20, 2024 10:09

llvmbot added the llvm:mc Machine (object) code label Mar 20, 2024

wzssyqa self-requested a review April 1, 2024 16:53

Cyanoxygen force-pushed the mipsr6-minmax branch from ff9b37e to 50a2e6a Compare April 2, 2024 10:46

Cyanoxygen force-pushed the mipsr6-minmax branch from 50a2e6a to 828896f Compare April 2, 2024 10:50

Cyanoxygen force-pushed the mipsr6-minmax branch from 9b05b8d to 828896f Compare April 2, 2024 11:04

Cyanoxygen changed the title ~~[MIPS] Fix the opcode of max.fmt and mina.fmt and make them matchable by ISel~~ [MIPS] Fix the opcode of max.fmt and mina.fmt Apr 2, 2024

wzssyqa merged commit 8b859c6 into llvm:main Apr 3, 2024

brad0 mentioned this pull request Apr 11, 2024

Merge 8b859c6e4a8e9ab9969582267bbdc04ed6bfa535 into 18.1.x #88336

Closed

pointhex mentioned this pull request May 7, 2024

getStyleDiagHandler #91314

Closed

aemerson mentioned this pull request May 9, 2024

release/18.x: [AArc64][GlobalISel] Fix legalizer assert for G_INSERT_VECTOR_ELT - manual merge #91672

Merged

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

[MIPS] Fix the opcode of max.fmt and mina.fmt#85609

[MIPS] Fix the opcode of max.fmt and mina.fmt#85609
wzssyqa merged 1 commit intollvm:mainfrom
Cyanoxygen:mipsr6-minmax

Cyanoxygen commented Mar 18, 2024 •

edited by wzssyqa

Loading

Uh oh!

github-actions bot commented Mar 18, 2024

Uh oh!

llvmbot commented Mar 20, 2024

Uh oh!

Cyanoxygen commented Mar 20, 2024

Uh oh!

wzssyqa commented Apr 1, 2024

Uh oh!

wzssyqa commented Apr 1, 2024

Uh oh!

Cyanoxygen commented Apr 2, 2024

Uh oh!

github-actions bot commented Apr 3, 2024

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

Conversation

Cyanoxygen commented Mar 18, 2024 • edited by wzssyqa Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

github-actions bot commented Mar 18, 2024

Uh oh!

llvmbot commented Mar 20, 2024

Uh oh!

Cyanoxygen commented Mar 20, 2024

Uh oh!

wzssyqa commented Apr 1, 2024

Uh oh!

wzssyqa commented Apr 1, 2024

Uh oh!

Cyanoxygen commented Apr 2, 2024

Uh oh!

github-actions bot commented Apr 3, 2024

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

Cyanoxygen commented Mar 18, 2024 •

edited by wzssyqa

Loading