Split fast-basictest.ll according to passes responsible for optimizations

- add logically missing test cases.
- add appropriate comments.
- add appropriate TODO's.

See initial motivation in https://reviews.llvm.org/D117302

Differential Revision: https://reviews.llvm.org/D118769

llvm/test/Transforms/InstCombine/fast-basictest.ll

@@ -0,0 +1,701 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+;
+; Test numbering remains continuous across:
+; - InstCombine/fast-basictest.ll
+; - PhaseOrdering/fast-basictest.ll
+; - PhaseOrdering/fast-reassociate-gvn.ll
+; - Reassociate/fast-basictest.ll
+;
+; RUN: opt < %s -instcombine -S | FileCheck %s
+
+; With reassociation, constant folding can eliminate the 12 and -12 constants.
+
+define float @test1(float %arg) {
+; CHECK-LABEL: @test1(
+; CHECK-NEXT:    [[TMP1:%.*]] = fneg fast float [[ARG:%.*]]
+; CHECK-NEXT:    ret float [[TMP1]]
+;
+  %t1 = fsub fast float -1.200000e+01, %arg
+  %t2 = fadd fast float %t1, 1.200000e+01
+  ret float %t2
+}
+
+; Check again using the minimal subset of FMF.
+; Both 'reassoc' and 'nsz' are required.
+define float @test1_minimal(float %arg) {
+; CHECK-LABEL: @test1_minimal(
+; CHECK-NEXT:    [[TMP1:%.*]] = fneg reassoc nsz float [[ARG:%.*]]
+; CHECK-NEXT:    ret float [[TMP1]]
+;
+  %t1 = fsub reassoc nsz float -1.200000e+01, %arg
+  %t2 = fadd reassoc nsz float %t1, 1.200000e+01
+  ret float %t2
+}
+
+; Verify the fold is not done with only 'reassoc' ('nsz' is required).
+define float @test1_reassoc(float %arg) {
+; CHECK-LABEL: @test1_reassoc(
+; CHECK-NEXT:    [[T1:%.*]] = fsub reassoc float -1.200000e+01, [[ARG:%.*]]
+; CHECK-NEXT:    [[T2:%.*]] = fadd reassoc float [[T1]], 1.200000e+01
+; CHECK-NEXT:    ret float [[T2]]
+;
+  %t1 = fsub reassoc float -1.200000e+01, %arg
+  %t2 = fadd reassoc float %t1, 1.200000e+01
+  ret float %t2
+}
+
+; ((a + (-3)) + b) + 3 -> a + b
+; That only works with both instcombine and reassociate passes enabled.
+; Check that instcombine is not enough.
+
+define float @test2(float %reg109, float %reg1111) {
+; CHECK-LABEL: @test2(
+; CHECK-NEXT:    [[REG115:%.*]] = fadd fast float [[REG109:%.*]], -3.000000e+01
+; CHECK-NEXT:    [[REG116:%.*]] = fadd fast float [[REG115]], [[REG1111:%.*]]
+; CHECK-NEXT:    [[REG117:%.*]] = fadd fast float [[REG116]], 3.000000e+01
+; CHECK-NEXT:    ret float [[REG117]]
+;
+  %reg115 = fadd fast float %reg109, -3.000000e+01
+  %reg116 = fadd fast float %reg115, %reg1111
+  %reg117 = fadd fast float %reg116, 3.000000e+01
+  ret float %reg117
+}
+
+define float @test2_no_FMF(float %reg109, float %reg1111) {
+; CHECK-LABEL: @test2_no_FMF(
+; CHECK-NEXT:    [[REG115:%.*]] = fadd float [[REG109:%.*]], -3.000000e+01
+; CHECK-NEXT:    [[REG116:%.*]] = fadd float [[REG115]], [[REG1111:%.*]]
+; CHECK-NEXT:    [[REG117:%.*]] = fadd float [[REG116]], 3.000000e+01
+; CHECK-NEXT:    ret float [[REG117]]
+;
+  %reg115 = fadd float %reg109, -3.000000e+01
+  %reg116 = fadd float %reg115, %reg1111
+  %reg117 = fadd float %reg116, 3.000000e+01
+  ret float %reg117
+}
+
+define float @test2_reassoc(float %reg109, float %reg1111) {
+; CHECK-LABEL: @test2_reassoc(
+; CHECK-NEXT:    [[REG115:%.*]] = fadd reassoc float [[REG109:%.*]], -3.000000e+01
+; CHECK-NEXT:    [[REG116:%.*]] = fadd reassoc float [[REG115]], [[REG1111:%.*]]
+; CHECK-NEXT:    [[REG117:%.*]] = fadd reassoc float [[REG116]], 3.000000e+01
+; CHECK-NEXT:    ret float [[REG117]]
+;
+  %reg115 = fadd reassoc float %reg109, -3.000000e+01
+  %reg116 = fadd reassoc float %reg115, %reg1111
+  %reg117 = fadd reassoc float %reg116, 3.000000e+01
+  ret float %reg117
+}
+
+; (-X)*Y + Z -> Z-X*Y
+
+define float @test7(float %X, float %Y, float %Z) {
+; CHECK-LABEL: @test7(
+; CHECK-NEXT:    [[TMP1:%.*]] = fmul fast float [[X:%.*]], [[Y:%.*]]
+; CHECK-NEXT:    [[C:%.*]] = fsub fast float [[Z:%.*]], [[TMP1]]
+; CHECK-NEXT:    ret float [[C]]
+;
+  %A = fsub fast float 0.0, %X
+  %B = fmul fast float %A, %Y
+  %C = fadd fast float %B, %Z
+  ret float %C
+}
+
+define float @test7_unary_fneg(float %X, float %Y, float %Z) {
+; CHECK-LABEL: @test7_unary_fneg(
+; CHECK-NEXT:    [[TMP1:%.*]] = fmul fast float [[X:%.*]], [[Y:%.*]]
+; CHECK-NEXT:    [[C:%.*]] = fsub fast float [[Z:%.*]], [[TMP1]]
+; CHECK-NEXT:    ret float [[C]]
+;
+  %A = fneg fast float %X
+  %B = fmul fast float %A, %Y
+  %C = fadd fast float %B, %Z
+  ret float %C
+}
+
+define float @test7_reassoc_nsz(float %X, float %Y, float %Z) {
+; CHECK-LABEL: @test7_reassoc_nsz(
+; CHECK-NEXT:    [[TMP1:%.*]] = fmul reassoc nsz float [[X:%.*]], [[Y:%.*]]
+; CHECK-NEXT:    [[C:%.*]] = fsub reassoc nsz float [[Z:%.*]], [[TMP1]]
+; CHECK-NEXT:    ret float [[C]]
+;
+  %A = fsub reassoc nsz float 0.0, %X
+  %B = fmul reassoc nsz float %A, %Y
+  %C = fadd reassoc nsz float %B, %Z
+  ret float %C
+}
+
+; Verify that fold is not done only with 'reassoc' ('nsz' is required)
+define float @test7_reassoc(float %X, float %Y, float %Z) {
+; CHECK-LABEL: @test7_reassoc(
+; CHECK-NEXT:    [[A:%.*]] = fsub reassoc float 0.000000e+00, [[X:%.*]]
+; CHECK-NEXT:    [[B:%.*]] = fmul reassoc float [[A]], [[Y:%.*]]
+; CHECK-NEXT:    [[C:%.*]] = fadd reassoc float [[B]], [[Z:%.*]]
+; CHECK-NEXT:    ret float [[C]]
+;
+  %A = fsub reassoc float 0.0, %X
+  %B = fmul reassoc float %A, %Y
+  %C = fadd reassoc float %B, %Z
+  ret float %C
+}
+
+define float @test8(float %X) {
+; CHECK-LABEL: @test8(
+; CHECK-NEXT:    [[TMP1:%.*]] = fmul fast float [[X:%.*]], 9.400000e+01
+; CHECK-NEXT:    ret float [[TMP1]]
+;
+  %Y = fmul fast float %X, 4.700000e+01
+  %Z = fadd fast float %Y, %Y
+  ret float %Z
+}
+
+; Check again with 'reassoc' and 'nsz' ('nsz' not technically required).
+define float @test8_reassoc_nsz(float %X) {
+; CHECK-LABEL: @test8_reassoc_nsz(
+; CHECK-NEXT:    [[TMP1:%.*]] = fmul reassoc nsz float [[X:%.*]], 9.400000e+01
+; CHECK-NEXT:    ret float [[TMP1]]
+;
+  %Y = fmul reassoc nsz float %X, 4.700000e+01
+  %Z = fadd reassoc nsz float %Y, %Y
+  ret float %Z
+}
+
+; TODO: This doesn't require 'nsz'.  It should fold to X * 94.0
+define float @test8_reassoc(float %X) {
+; CHECK-LABEL: @test8_reassoc(
+; CHECK-NEXT:    [[Y:%.*]] = fmul reassoc float [[X:%.*]], 4.700000e+01
+; CHECK-NEXT:    [[Z:%.*]] = fadd reassoc float [[Y]], [[Y]]
+; CHECK-NEXT:    ret float [[Z]]
+;
+  %Y = fmul reassoc float %X, 4.700000e+01
+  %Z = fadd reassoc float %Y, %Y
+  ret float %Z
+}
+
+; Side note: (x + x + x) and (3*x) each have only a single rounding.  So
+; transforming x+x+x to 3*x is always safe, even without any FMF.
+; To avoid that special-case, we have the addition of 'x' four times, here.
+
+define float @test9(float %X) {
+; CHECK-LABEL: @test9(
+; CHECK-NEXT:    [[TMP1:%.*]] = fmul fast float [[X:%.*]], 4.000000e+00
+; CHECK-NEXT:    ret float [[TMP1]]
+;
+  %Y = fadd fast float %X ,%X
+  %Z = fadd fast float %Y, %X
+  %W = fadd fast float %Z, %X
+  ret float %W
+}
+
+; Check again with 'reassoc' and 'nsz' ('nsz' not technically required).
+define float @test9_reassoc_nsz(float %X) {
+; CHECK-LABEL: @test9_reassoc_nsz(
+; CHECK-NEXT:    [[TMP1:%.*]] = fmul reassoc nsz float [[X:%.*]], 4.000000e+00
+; CHECK-NEXT:    ret float [[TMP1]]
+;
+  %Y = fadd reassoc nsz float %X ,%X
+  %Z = fadd reassoc nsz float %Y, %X
+  %W = fadd reassoc nsz float %Z, %X
+  ret float %W
+}
+
+; TODO: This doesn't require 'nsz'.  It should fold to 4 * x
+define float @test9_reassoc(float %X) {
+; CHECK-LABEL: @test9_reassoc(
+; CHECK-NEXT:    [[Y:%.*]] = fadd reassoc float [[X:%.*]], [[X]]
+; CHECK-NEXT:    [[Z:%.*]] = fadd reassoc float [[Y]], [[X]]
+; CHECK-NEXT:    [[W:%.*]] = fadd reassoc float [[Z]], [[X]]
+; CHECK-NEXT:    ret float [[W]]
+;
+  %Y = fadd reassoc float %X ,%X
+  %Z = fadd reassoc float %Y, %X
+  %W = fadd reassoc float %Z, %X
+  ret float %W
+}
+
+define float @test10(float %W) {
+; CHECK-LABEL: @test10(
+; CHECK-NEXT:    [[Z:%.*]] = fmul fast float [[W:%.*]], 3.810000e+02
+; CHECK-NEXT:    ret float [[Z]]
+;
+  %X = fmul fast float %W, 127.0
+  %Y = fadd fast float %X ,%X
+  %Z = fadd fast float %Y, %X
+  ret float %Z
+}
+
+; Check again using the minimal subset of FMF.
+; Check again with 'reassoc' and 'nsz' ('nsz' not technically required).
+define float @test10_reassoc_nsz(float %W) {
+; CHECK-LABEL: @test10_reassoc_nsz(
+; CHECK-NEXT:    [[Z:%.*]] = fmul reassoc nsz float [[W:%.*]], 3.810000e+02
+; CHECK-NEXT:    ret float [[Z]]
+;
+  %X = fmul reassoc nsz float %W, 127.0
+  %Y = fadd reassoc nsz float %X ,%X
+  %Z = fadd reassoc nsz float %Y, %X
+  ret float %Z
+}
+
+; TODO: This doesn't require 'nsz'.  It should fold to W*381.0.
+define float @test10_reassoc(float %W) {
+; CHECK-LABEL: @test10_reassoc(
+; CHECK-NEXT:    [[X:%.*]] = fmul reassoc float [[W:%.*]], 1.270000e+02
+; CHECK-NEXT:    [[Y:%.*]] = fadd reassoc float [[X]], [[X]]
+; CHECK-NEXT:    [[Z:%.*]] = fadd reassoc float [[Y]], [[X]]
+; CHECK-NEXT:    ret float [[Z]]
+;
+  %X = fmul reassoc float %W, 127.0
+  %Y = fadd reassoc float %X ,%X
+  %Z = fadd reassoc float %Y, %X
+  ret float %Z
+}
+
+define float @test11(float %X) {
+; CHECK-LABEL: @test11(
+; CHECK-NEXT:    [[TMP1:%.*]] = fmul fast float [[X:%.*]], 3.000000e+00
+; CHECK-NEXT:    [[TMP2:%.*]] = fsub fast float 6.000000e+00, [[TMP1]]
+; CHECK-NEXT:    ret float [[TMP2]]
+;
+  %A = fsub fast float 1.000000e+00, %X
+  %B = fsub fast float 2.000000e+00, %X
+  %C = fsub fast float 3.000000e+00, %X
+  %Y = fadd fast float %A ,%B
+  %Z = fadd fast float %Y, %C
+  ret float %Z
+}
+
+; Check again with 'reassoc' and 'nsz' ('nsz' not technically required).
+define float @test11_reassoc_nsz(float %X) {
+; CHECK-LABEL: @test11_reassoc_nsz(
+; CHECK-NEXT:    [[TMP1:%.*]] = fmul reassoc nsz float [[X:%.*]], 3.000000e+00
+; CHECK-NEXT:    [[TMP2:%.*]] = fsub reassoc nsz float 6.000000e+00, [[TMP1]]
+; CHECK-NEXT:    ret float [[TMP2]]
+;
+  %A = fsub reassoc nsz float 1.000000e+00, %X
+  %B = fsub reassoc nsz float 2.000000e+00, %X
+  %C = fsub reassoc nsz float 3.000000e+00, %X
+  %Y = fadd reassoc nsz float %A ,%B
+  %Z = fadd reassoc nsz float %Y, %C
+  ret float %Z
+}
+
+; TODO: This doesn't require 'nsz'.  It should fold to (6.0 - 3.0*x)
+define float @test11_reassoc(float %X) {
+; CHECK-LABEL: @test11_reassoc(
+; CHECK-NEXT:    [[A:%.*]] = fsub reassoc float 1.000000e+00, [[X:%.*]]
+; CHECK-NEXT:    [[B:%.*]] = fsub reassoc float 2.000000e+00, [[X]]
+; CHECK-NEXT:    [[C:%.*]] = fsub reassoc float 3.000000e+00, [[X]]
+; CHECK-NEXT:    [[Y:%.*]] = fadd reassoc float [[A]], [[B]]
+; CHECK-NEXT:    [[Z:%.*]] = fadd reassoc float [[Y]], [[C]]
+; CHECK-NEXT:    ret float [[Z]]
+;
+  %A = fsub reassoc float 1.000000e+00, %X
+  %B = fsub reassoc float 2.000000e+00, %X
+  %C = fsub reassoc float 3.000000e+00, %X
+  %Y = fadd reassoc float %A ,%B
+  %Z = fadd reassoc float %Y, %C
+  ret float %Z
+}
+
+define float @test12(float %X1, float %X2, float %X3) {
+; CHECK-LABEL: @test12(
+; CHECK-NEXT:    [[TMP1:%.*]] = fsub fast float [[X3:%.*]], [[X2:%.*]]
+; CHECK-NEXT:    [[D:%.*]] = fmul fast float [[TMP1]], [[X1:%.*]]
+; CHECK-NEXT:    ret float [[D]]
+;
+  %A = fsub fast float 0.000000e+00, %X1
+  %B = fmul fast float %A, %X2   ; -X1*X2
+  %C = fmul fast float %X1, %X3  ; X1*X3
+  %D = fadd fast float %B, %C    ; -X1*X2 + X1*X3 -> X1*(X3-X2)
+  ret float %D
+}
+
+define float @test12_unary_fneg(float %X1, float %X2, float %X3) {
+; CHECK-LABEL: @test12_unary_fneg(
+; CHECK-NEXT:    [[TMP1:%.*]] = fsub fast float [[X3:%.*]], [[X2:%.*]]
+; CHECK-NEXT:    [[D:%.*]] = fmul fast float [[TMP1]], [[X1:%.*]]
+; CHECK-NEXT:    ret float [[D]]
+;
+  %A = fneg fast float %X1
+  %B = fmul fast float %A, %X2   ; -X1*X2
+  %C = fmul fast float %X1, %X3  ; X1*X3
+  %D = fadd fast float %B, %C    ; -X1*X2 + X1*X3 -> X1*(X3-X2)
+  ret float %D
+}
+
+define float @test12_reassoc_nsz(float %X1, float %X2, float %X3) {
+; CHECK-LABEL: @test12_reassoc_nsz(
+; CHECK-NEXT:    [[TMP1:%.*]] = fsub reassoc nsz float [[X3:%.*]], [[X2:%.*]]
+; CHECK-NEXT:    [[D:%.*]] = fmul reassoc nsz float [[TMP1]], [[X1:%.*]]
+; CHECK-NEXT:    ret float [[D]]
+;
+  %A = fsub reassoc nsz float 0.000000e+00, %X1
+  %B = fmul reassoc nsz float %A, %X2   ; -X1*X2
+  %C = fmul reassoc nsz float %X1, %X3  ; X1*X3
+  %D = fadd reassoc nsz float %B, %C    ; -X1*X2 + X1*X3 -> X1*(X3-X2)
+  ret float %D
+}
+
+; TODO: check if 'nsz' is technically required. Currently the optimization
+; is not done with only 'reassoc' without 'nsz'.
+define float @test12_reassoc(float %X1, float %X2, float %X3) {
+; CHECK-LABEL: @test12_reassoc(
+; CHECK-NEXT:    [[A:%.*]] = fsub reassoc float 0.000000e+00, [[X1:%.*]]
+; CHECK-NEXT:    [[B:%.*]] = fmul reassoc float [[A]], [[X2:%.*]]
+; CHECK-NEXT:    [[C:%.*]] = fmul reassoc float [[X1]], [[X3:%.*]]
+; CHECK-NEXT:    [[D:%.*]] = fadd reassoc float [[B]], [[C]]
+; CHECK-NEXT:    ret float [[D]]
+;
+  %A = fsub reassoc float 0.000000e+00, %X1
+  %B = fmul reassoc float %A, %X2   ; -X1*X2
+  %C = fmul reassoc float %X1, %X3  ; X1*X3
+  %D = fadd reassoc float %B, %C    ; -X1*X2 + X1*X3 -> X1*(X3-X2)
+  ret float %D
+}
+
+; (x1 * 47) + (x2 * -47) => (x1 - x2) * 47
+; That only works with both instcombine and reassociate passes enabled.
+; Check that instcombine is not enough.
+
+define float @test13(float %X1, float %X2) {
+; CHECK-LABEL: @test13(
+; CHECK-NEXT:    [[B:%.*]] = fmul fast float [[X1:%.*]], 4.700000e+01
+; CHECK-NEXT:    [[C:%.*]] = fmul fast float [[X2:%.*]], -4.700000e+01
+; CHECK-NEXT:    [[D:%.*]] = fadd fast float [[B]], [[C]]
+; CHECK-NEXT:    ret float [[D]]
+;
+  %B = fmul fast float %X1, 47.   ; X1*47
+  %C = fmul fast float %X2, -47.  ; X2*-47
+  %D = fadd fast float %B, %C     ; X1*47 + X2*-47 -> 47*(X1-X2)
+  ret float %D
+}
+
+define float @test13_reassoc_nsz(float %X1, float %X2) {
+; CHECK-LABEL: @test13_reassoc_nsz(
+; CHECK-NEXT:    [[B:%.*]] = fmul reassoc nsz float [[X1:%.*]], 4.700000e+01
+; CHECK-NEXT:    [[C:%.*]] = fmul reassoc nsz float [[X2:%.*]], -4.700000e+01
+; CHECK-NEXT:    [[D:%.*]] = fadd reassoc nsz float [[B]], [[C]]
+; CHECK-NEXT:    ret float [[D]]
+;
+  %B = fmul reassoc nsz float %X1, 47.   ; X1*47
+  %C = fmul reassoc nsz float %X2, -47.  ; X2*-47
+  %D = fadd reassoc nsz float %B, %C     ; X1*47 + X2*-47 -> 47*(X1-X2)
+  ret float %D
+}
+
+define float @test13_reassoc(float %X1, float %X2) {
+; CHECK-LABEL: @test13_reassoc(
+; CHECK-NEXT:    [[B:%.*]] = fmul reassoc float [[X1:%.*]], 4.700000e+01
+; CHECK-NEXT:    [[C:%.*]] = fmul reassoc float [[X2:%.*]], -4.700000e+01
+; CHECK-NEXT:    [[D:%.*]] = fadd reassoc float [[B]], [[C]]
+; CHECK-NEXT:    ret float [[D]]
+;
+  %B = fmul reassoc float %X1, 47.   ; X1*47
+  %C = fmul reassoc float %X2, -47.  ; X2*-47
+  %D = fadd reassoc float %B, %C     ; X1*47 + X2*-47 -> 47*(X1-X2)
+  ret float %D
+}
+
+define float @test14(float %arg) {
+; CHECK-LABEL: @test14(
+; CHECK-NEXT:    [[T2:%.*]] = fmul fast float [[ARG:%.*]], 1.440000e+02
+; CHECK-NEXT:    ret float [[T2]]
+;
+  %t1 = fmul fast float 1.200000e+01, %arg
+  %t2 = fmul fast float %t1, 1.200000e+01
+  ret float %t2
+}
+
+define float @test14_reassoc(float %arg) {
+; CHECK-LABEL: @test14_reassoc(
+; CHECK-NEXT:    [[T2:%.*]] = fmul reassoc float [[ARG:%.*]], 1.440000e+02
+; CHECK-NEXT:    ret float [[T2]]
+;
+  %t1 = fmul reassoc float 1.200000e+01, %arg
+  %t2 = fmul reassoc float %t1, 1.200000e+01
+  ret float %t2
+}
+
+; (b+(a+1234))+-a -> b+1234
+; That only works with both instcombine and reassociate passes enabled.
+; Check that instcombine is not enough.
+
+define float @test15(float %b, float %a) {
+; CHECK-LABEL: @test15(
+; CHECK-NEXT:    [[TMP1:%.*]] = fadd fast float [[A:%.*]], 1.234000e+03
+; CHECK-NEXT:    [[TMP2:%.*]] = fadd fast float [[TMP1]], [[B:%.*]]
+; CHECK-NEXT:    [[TMP3:%.*]] = fsub fast float [[TMP2]], [[A]]
+; CHECK-NEXT:    ret float [[TMP3]]
+;
+  %1 = fadd fast float %a, 1234.0
+  %2 = fadd fast float %b, %1
+  %3 = fsub fast float 0.0, %a
+  %4 = fadd fast float %2, %3
+  ret float %4
+}
+
+define float @test15_unary_fneg(float %b, float %a) {
+; CHECK-LABEL: @test15_unary_fneg(
+; CHECK-NEXT:    [[TMP1:%.*]] = fadd fast float [[A:%.*]], 1.234000e+03
+; CHECK-NEXT:    [[TMP2:%.*]] = fadd fast float [[TMP1]], [[B:%.*]]
+; CHECK-NEXT:    [[TMP3:%.*]] = fsub fast float [[TMP2]], [[A]]
+; CHECK-NEXT:    ret float [[TMP3]]
+;
+  %1 = fadd fast float %a, 1234.0
+  %2 = fadd fast float %b, %1
+  %3 = fneg fast float %a
+  %4 = fadd fast float %2, %3
+  ret float %4
+}
+
+define float @test15_reassoc_nsz(float %b, float %a) {
+; CHECK-LABEL: @test15_reassoc_nsz(
+; CHECK-NEXT:    [[TMP1:%.*]] = fadd reassoc nsz float [[A:%.*]], 1.234000e+03
+; CHECK-NEXT:    [[TMP2:%.*]] = fadd reassoc nsz float [[TMP1]], [[B:%.*]]
+; CHECK-NEXT:    [[TMP3:%.*]] = fsub reassoc nsz float [[TMP2]], [[A]]
+; CHECK-NEXT:    ret float [[TMP3]]
+;
+  %1 = fadd reassoc nsz float %a, 1234.0
+  %2 = fadd reassoc nsz float %b, %1
+  %3 = fsub reassoc nsz float 0.0, %a
+  %4 = fadd reassoc nsz float %2, %3
+  ret float %4
+}
+
+define float @test15_reassoc(float %b, float %a) {
+; CHECK-LABEL: @test15_reassoc(
+; CHECK-NEXT:    [[TMP1:%.*]] = fadd reassoc float [[A:%.*]], 1.234000e+03
+; CHECK-NEXT:    [[TMP2:%.*]] = fadd reassoc float [[TMP1]], [[B:%.*]]
+; CHECK-NEXT:    [[TMP3:%.*]] = fsub reassoc float 0.000000e+00, [[A]]
+; CHECK-NEXT:    [[TMP4:%.*]] = fadd reassoc float [[TMP2]], [[TMP3]]
+; CHECK-NEXT:    ret float [[TMP4]]
+;
+  %1 = fadd reassoc float %a, 1234.0
+  %2 = fadd reassoc float %b, %1
+  %3 = fsub reassoc float 0.0, %a
+  %4 = fadd reassoc float %2, %3
+  ret float %4
+}
+
+; X*-(Y*Z) -> X*-1*Y*Z
+; That only works with both instcombine and reassociate passes enabled.
+; Check that instcombine is not enough.
+
+define float @test16(float %a, float %b, float %z) {
+; CHECK-LABEL: @test16(
+; CHECK-NEXT:    [[C:%.*]] = fneg fast float [[Z:%.*]]
+; CHECK-NEXT:    [[D:%.*]] = fmul fast float [[A:%.*]], [[B:%.*]]
+; CHECK-NEXT:    [[E:%.*]] = fmul fast float [[D]], [[C]]
+; CHECK-NEXT:    [[G:%.*]] = fmul fast float [[E]], -1.234500e+04
+; CHECK-NEXT:    ret float [[G]]
+;
+  %c = fsub fast float 0.000000e+00, %z
+  %d = fmul fast float %a, %b
+  %e = fmul fast float %c, %d
+  %f = fmul fast float %e, 1.234500e+04
+  %g = fsub fast float 0.000000e+00, %f
+  ret float %g
+}
+
+define float @test16_unary_fneg(float %a, float %b, float %z) {
+; CHECK-LABEL: @test16_unary_fneg(
+; CHECK-NEXT:    [[C:%.*]] = fneg fast float [[Z:%.*]]
+; CHECK-NEXT:    [[D:%.*]] = fmul fast float [[A:%.*]], [[B:%.*]]
+; CHECK-NEXT:    [[E:%.*]] = fmul fast float [[D]], [[C]]
+; CHECK-NEXT:    [[G:%.*]] = fmul fast float [[E]], -1.234500e+04
+; CHECK-NEXT:    ret float [[G]]
+;
+  %c = fneg fast float %z
+  %d = fmul fast float %a, %b
+  %e = fmul fast float %c, %d
+  %f = fmul fast float %e, 1.234500e+04
+  %g = fneg fast float %f
+  ret float %g
+}
+
+define float @test16_reassoc_nsz(float %a, float %b, float %z) {
+; CHECK-LABEL: @test16_reassoc_nsz(
+; CHECK-NEXT:    [[C:%.*]] = fneg reassoc nsz float [[Z:%.*]]
+; CHECK-NEXT:    [[D:%.*]] = fmul reassoc nsz float [[A:%.*]], [[B:%.*]]
+; CHECK-NEXT:    [[E:%.*]] = fmul reassoc nsz float [[D]], [[C]]
+; CHECK-NEXT:    [[G:%.*]] = fmul reassoc nsz float [[E]], -1.234500e+04
+; CHECK-NEXT:    ret float [[G]]
+;
+  %c = fsub reassoc nsz float 0.000000e+00, %z
+  %d = fmul reassoc nsz float %a, %b
+  %e = fmul reassoc nsz float %c, %d
+  %f = fmul reassoc nsz float %e, 1.234500e+04
+  %g = fsub reassoc nsz float 0.000000e+00, %f
+  ret float %g
+}
+
+define float @test16_reassoc(float %a, float %b, float %z) {
+; CHECK-LABEL: @test16_reassoc(
+; CHECK-NEXT:    [[C:%.*]] = fsub reassoc float 0.000000e+00, [[Z:%.*]]
+; CHECK-NEXT:    [[D:%.*]] = fmul reassoc float [[A:%.*]], [[B:%.*]]
+; CHECK-NEXT:    [[E:%.*]] = fmul reassoc float [[C]], [[D]]
+; CHECK-NEXT:    [[F:%.*]] = fmul reassoc float [[E]], 1.234500e+04
+; CHECK-NEXT:    [[G:%.*]] = fsub reassoc float 0.000000e+00, [[F]]
+; CHECK-NEXT:    ret float [[G]]
+;
+  %c = fsub reassoc float 0.000000e+00, %z
+  %d = fmul reassoc float %a, %b
+  %e = fmul reassoc float %c, %d
+  %f = fmul reassoc float %e, 1.234500e+04
+  %g = fsub reassoc float 0.000000e+00, %f
+  ret float %g
+}
+
+define float @test17(float %a, float %b, float %z) {
+; CHECK-LABEL: @test17(
+; CHECK-NEXT:    [[TMP1:%.*]] = fmul fast float [[Z:%.*]], 4.000000e+01
+; CHECK-NEXT:    [[F:%.*]] = fmul fast float [[TMP1]], [[A:%.*]]
+; CHECK-NEXT:    ret float [[F]]
+;
+  %d = fmul fast float %z, 4.000000e+01
+  %c = fsub fast float 0.000000e+00, %d
+  %e = fmul fast float %a, %c
+  %f = fsub fast float 0.000000e+00, %e
+  ret float %f
+}
+
+define float @test17_unary_fneg(float %a, float %b, float %z) {
+; CHECK-LABEL: @test17_unary_fneg(
+; CHECK-NEXT:    [[TMP1:%.*]] = fmul fast float [[Z:%.*]], 4.000000e+01
+; CHECK-NEXT:    [[F:%.*]] = fmul fast float [[TMP1]], [[A:%.*]]
+; CHECK-NEXT:    ret float [[F]]
+;
+  %d = fmul fast float %z, 4.000000e+01
+  %c = fneg fast float %d
+  %e = fmul fast float %a, %c
+  %f = fneg fast float %e
+  ret float %f
+}
+
+define float @test17_reassoc_nsz(float %a, float %b, float %z) {
+; CHECK-LABEL: @test17_reassoc_nsz(
+; CHECK-NEXT:    [[TMP1:%.*]] = fmul reassoc nsz float [[Z:%.*]], 4.000000e+01
+; CHECK-NEXT:    [[F:%.*]] = fmul reassoc nsz float [[TMP1]], [[A:%.*]]
+; CHECK-NEXT:    ret float [[F]]
+;
+  %d = fmul reassoc nsz float %z, 4.000000e+01
+  %c = fsub reassoc nsz float 0.000000e+00, %d
+  %e = fmul reassoc nsz float %a, %c
+  %f = fsub reassoc nsz float 0.000000e+00, %e
+  ret float %f
+}
+
+; Verify the fold is not done with only 'reassoc' ('nsz' is required).
+define float @test17_reassoc(float %a, float %b, float %z) {
+; CHECK-LABEL: @test17_reassoc(
+; CHECK-NEXT:    [[D:%.*]] = fmul reassoc float [[Z:%.*]], 4.000000e+01
+; CHECK-NEXT:    [[C:%.*]] = fsub reassoc float 0.000000e+00, [[D]]
+; CHECK-NEXT:    [[E:%.*]] = fmul reassoc float [[C]], [[A:%.*]]
+; CHECK-NEXT:    [[F:%.*]] = fsub reassoc float 0.000000e+00, [[E]]
+; CHECK-NEXT:    ret float [[F]]
+;
+  %d = fmul reassoc float %z, 4.000000e+01
+  %c = fsub reassoc float 0.000000e+00, %d
+  %e = fmul reassoc float %a, %c
+  %f = fsub reassoc float 0.000000e+00, %e
+  ret float %f
+}
+
+; fneg of fneg is an identity operation, so no FMF are needed to remove those instructions.
+
+define float @test17_unary_fneg_no_FMF(float %a, float %b, float %z) {
+; CHECK-LABEL: @test17_unary_fneg_no_FMF(
+; CHECK-NEXT:    [[TMP1:%.*]] = fmul float [[Z:%.*]], 4.000000e+01
+; CHECK-NEXT:    [[F:%.*]] = fmul float [[TMP1]], [[A:%.*]]
+; CHECK-NEXT:    ret float [[F]]
+;
+  %d = fmul float %z, 4.000000e+01
+  %c = fneg float %d
+  %e = fmul float %a, %c
+  %f = fneg float %e
+  ret float %f
+}
+
+define float @test17_reassoc_unary_fneg(float %a, float %b, float %z) {
+; CHECK-LABEL: @test17_reassoc_unary_fneg(
+; CHECK-NEXT:    [[TMP1:%.*]] = fmul reassoc float [[Z:%.*]], 4.000000e+01
+; CHECK-NEXT:    [[F:%.*]] = fmul reassoc float [[TMP1]], [[A:%.*]]
+; CHECK-NEXT:    ret float [[F]]
+;
+  %d = fmul reassoc float %z, 4.000000e+01
+  %c = fneg reassoc float %d
+  %e = fmul reassoc float %a, %c
+  %f = fneg reassoc float %e
+  ret float %f
+}
+
+; With sub reassociation, constant folding can eliminate the 12 and -12 constants.
+; That only works with both instcombine and reassociate passes enabled.
+; Check that instcombine is not enough.
+
+define float @test18(float %A, float %B) {
+; CHECK-LABEL: @test18(
+; CHECK-NEXT:    [[X:%.*]] = fadd fast float [[A:%.*]], -1.200000e+01
+; CHECK-NEXT:    [[Y:%.*]] = fsub fast float [[X]], [[B:%.*]]
+; CHECK-NEXT:    [[Z:%.*]] = fadd fast float [[Y]], 1.200000e+01
+; CHECK-NEXT:    ret float [[Z]]
+;
+  %X = fadd fast float -1.200000e+01, %A
+  %Y = fsub fast float %X, %B
+  %Z = fadd fast float %Y, 1.200000e+01
+  ret float %Z
+}
+
+define float @test18_reassoc(float %A, float %B) {
+; CHECK-LABEL: @test18_reassoc(
+; CHECK-NEXT:    [[X:%.*]] = fadd reassoc float [[A:%.*]], -1.200000e+01
+; CHECK-NEXT:    [[Y:%.*]] = fsub reassoc float [[X]], [[B:%.*]]
+; CHECK-NEXT:    [[Z:%.*]] = fadd reassoc float [[Y]], 1.200000e+01
+; CHECK-NEXT:    ret float [[Z]]
+;
+  %X = fadd reassoc float -1.200000e+01, %A
+  %Y = fsub reassoc float %X, %B
+  %Z = fadd reassoc float %Y, 1.200000e+01
+  ret float %Z
+}
+
+; With sub reassociation, constant folding can eliminate the uses of %a.
+
+define float @test19(float %a, float %b, float %c) nounwind  {
+; CHECK-LABEL: @test19(
+; CHECK-NEXT:    [[TMP1:%.*]] = fadd fast float [[B:%.*]], [[C:%.*]]
+; CHECK-NEXT:    [[T7:%.*]] = fneg fast float [[TMP1]]
+; CHECK-NEXT:    ret float [[T7]]
+;
+  %t3 = fsub fast float %a, %b
+  %t5 = fsub fast float %t3, %c
+  %t7 = fsub fast float %t5, %a
+  ret float %t7
+}
+
+define float @test19_reassoc_nsz(float %a, float %b, float %c) nounwind  {
+; CHECK-LABEL: @test19_reassoc_nsz(
+; CHECK-NEXT:    [[TMP1:%.*]] = fadd reassoc nsz float [[B:%.*]], [[C:%.*]]
+; CHECK-NEXT:    [[T7:%.*]] = fneg reassoc nsz float [[TMP1]]
+; CHECK-NEXT:    ret float [[T7]]
+;
+  %t3 = fsub reassoc nsz float %a, %b
+  %t5 = fsub reassoc nsz float %t3, %c
+  %t7 = fsub reassoc nsz float %t5, %a
+  ret float %t7
+}
+
+; Verify the fold is not done with only 'reassoc' ('nsz' is required).
+define float @test19_reassoc(float %a, float %b, float %c) nounwind  {
+; CHECK-LABEL: @test19_reassoc(
+; CHECK-NEXT:    [[T3:%.*]] = fsub reassoc float [[A:%.*]], [[B:%.*]]
+; CHECK-NEXT:    [[T5:%.*]] = fsub reassoc float [[T3]], [[C:%.*]]
+; CHECK-NEXT:    [[T7:%.*]] = fsub reassoc float [[T5]], [[A]]
+; CHECK-NEXT:    ret float [[T7]]
+;
+  %t3 = fsub reassoc float %a, %b
+  %t5 = fsub reassoc float %t3, %c
+  %t7 = fsub reassoc float %t5, %a
+  ret float %t7
+}

llvm/test/Transforms/PhaseOrdering/fast-basictest.ll

@@ -0,0 +1,307 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+;
+; Test cases in this file are intended to be run with both reassociate and
+; instcombine passes enabled.
+;
+; Test numbering remains continuous across:
+; - InstCombine/fast-basictest.ll
+; - PhaseOrdering/fast-basictest.ll
+; - PhaseOrdering/fast-reassociate-gvn.ll
+; - Reassociate/fast-basictest.ll
+;
+; RUN: opt < %s -reassociate -instcombine -S | FileCheck %s --check-prefixes=CHECK,REASSOC_AND_IC --allow-unused-prefixes
+; RUN: opt < %s -O2 -S | FileCheck %s --check-prefixes=CHECK,O2 --allow-unused-prefixes
+
+; test2 ... test18 - both reassociate and instcombine passes
+; are required to perform a transform
+
+; ((a + (-3)) + b) + 3 -> a + b
+
+define float @test2(float %reg109, float %reg1111) {
+; CHECK-LABEL: @test2(
+; CHECK-NEXT:    [[REG117:%.*]] = fadd fast float [[REG109:%.*]], [[REG1111:%.*]]
+; CHECK-NEXT:    ret float [[REG117]]
+;
+  %reg115 = fadd fast float %reg109, -3.000000e+01
+  %reg116 = fadd fast float %reg115, %reg1111
+  %reg117 = fadd fast float %reg116, 3.000000e+01
+  ret float %reg117
+}
+
+; Verify that fold is not done without 'fast'
+define float @test2_no_FMF(float %reg109, float %reg1111) {
+; CHECK-LABEL: @test2_no_FMF(
+; CHECK-NEXT:    [[REG115:%.*]] = fadd float [[REG109:%.*]], -3.000000e+01
+; CHECK-NEXT:    [[REG116:%.*]] = fadd float [[REG115]], [[REG1111:%.*]]
+; CHECK-NEXT:    [[REG117:%.*]] = fadd float [[REG116]], 3.000000e+01
+; CHECK-NEXT:    ret float [[REG117]]
+;
+  %reg115 = fadd float %reg109, -3.000000e+01
+  %reg116 = fadd float %reg115, %reg1111
+  %reg117 = fadd float %reg116, 3.000000e+01
+  ret float %reg117
+}
+
+define float @test2_reassoc(float %reg109, float %reg1111) {
+; CHECK-LABEL: @test2_reassoc(
+; CHECK-NEXT:    [[REG115:%.*]] = fadd reassoc float [[REG109:%.*]], -3.000000e+01
+; CHECK-NEXT:    [[REG116:%.*]] = fadd reassoc float [[REG115]], [[REG1111:%.*]]
+; CHECK-NEXT:    [[REG117:%.*]] = fadd reassoc float [[REG116]], 3.000000e+01
+; CHECK-NEXT:    ret float [[REG117]]
+;
+  %reg115 = fadd reassoc float %reg109, -3.000000e+01
+  %reg116 = fadd reassoc float %reg115, %reg1111
+  %reg117 = fadd reassoc float %reg116, 3.000000e+01
+  ret float %reg117
+}
+
+; (x1 * 47) + (x2 * -47) => (x1 - x2) * 47
+
+define float @test13(float %X1, float %X2) {
+; CHECK-LABEL: @test13(
+; CHECK-NEXT:    [[TMP1:%.*]] = fsub fast float [[X1:%.*]], [[X2:%.*]]
+; CHECK-NEXT:    [[TMP2:%.*]] = fmul fast float [[TMP1]], 4.700000e+01
+; CHECK-NEXT:    ret float [[TMP2]]
+;
+  %B = fmul fast float %X1, 47.   ; X1*47
+  %C = fmul fast float %X2, -47.  ; X2*-47
+  %D = fadd fast float %B, %C     ; X1*47 + X2*-47 -> 47*(X1-X2)
+  ret float %D
+}
+
+; Check again with 'reassoc' and 'nsz' ('nsz' not technically required).
+define float @test13_reassoc_nsz(float %X1, float %X2) {
+; CHECK-LABEL: @test13_reassoc_nsz(
+; CHECK-NEXT:    [[TMP1:%.*]] = fsub reassoc nsz float [[X1:%.*]], [[X2:%.*]]
+; CHECK-NEXT:    [[TMP2:%.*]] = fmul reassoc nsz float [[TMP1]], 4.700000e+01
+; CHECK-NEXT:    ret float [[TMP2]]
+;
+  %B = fmul reassoc nsz float %X1, 47.   ; X1*47
+  %C = fmul reassoc nsz float %X2, -47.  ; X2*-47
+  %D = fadd reassoc nsz float %B, %C     ; X1*47 + X2*-47 -> 47*(X1-X2)
+  ret float %D
+}
+
+; TODO: This doesn't require 'nsz'.  It should fold to ((x1 - x2) * 47.0)
+define float @test13_reassoc(float %X1, float %X2) {
+; CHECK-LABEL: @test13_reassoc(
+; CHECK-NEXT:    [[B:%.*]] = fmul reassoc float [[X1:%.*]], 4.700000e+01
+; CHECK-NEXT:    [[C:%.*]] = fmul reassoc float [[X2:%.*]], 4.700000e+01
+; CHECK-NEXT:    [[TMP1:%.*]] = fsub reassoc float [[B]], [[C]]
+; CHECK-NEXT:    ret float [[TMP1]]
+;
+  %B = fmul reassoc float %X1, 47.   ; X1*47
+  %C = fmul reassoc float %X2, -47.  ; X2*-47
+  %D = fadd reassoc float %B, %C     ; X1*47 + X2*-47 -> 47*(X1-X2)
+  ret float %D
+}
+
+; (b+(a+1234))+-a -> b+1234
+
+define float @test15(float %b, float %a) {
+; CHECK-LABEL: @test15(
+; CHECK-NEXT:    [[TMP1:%.*]] = fadd fast float [[B:%.*]], 1.234000e+03
+; CHECK-NEXT:    ret float [[TMP1]]
+;
+  %1 = fadd fast float %a, 1234.0
+  %2 = fadd fast float %b, %1
+  %3 = fsub fast float 0.0, %a
+  %4 = fadd fast float %2, %3
+  ret float %4
+}
+
+define float @test15_unary_fneg(float %b, float %a) {
+; CHECK-LABEL: @test15_unary_fneg(
+; CHECK-NEXT:    [[TMP1:%.*]] = fadd fast float [[B:%.*]], 1.234000e+03
+; CHECK-NEXT:    ret float [[TMP1]]
+;
+  %1 = fadd fast float %a, 1234.0
+  %2 = fadd fast float %b, %1
+  %3 = fneg fast float %a
+  %4 = fadd fast float %2, %3
+  ret float %4
+}
+
+; TODO: check if it is possible to perform the optimization without 'fast'
+; with 'reassoc' and 'nsz' only.
+define float @test15_reassoc_nsz(float %b, float %a) {
+; CHECK-LABEL: @test15_reassoc_nsz(
+; CHECK-NEXT:    [[TMP1:%.*]] = fadd reassoc nsz float [[A:%.*]], 1.234000e+03
+; CHECK-NEXT:    [[TMP2:%.*]] = fadd reassoc nsz float [[TMP1]], [[B:%.*]]
+; CHECK-NEXT:    [[TMP3:%.*]] = fsub reassoc nsz float [[TMP2]], [[A]]
+; CHECK-NEXT:    ret float [[TMP3]]
+;
+  %1 = fadd reassoc nsz float %a, 1234.0
+  %2 = fadd reassoc nsz float %b, %1
+  %3 = fsub reassoc nsz float 0.0, %a
+  %4 = fadd reassoc nsz float %2, %3
+  ret float %4
+}
+
+define float @test15_reassoc(float %b, float %a) {
+; CHECK-LABEL: @test15_reassoc(
+; CHECK-NEXT:    [[TMP1:%.*]] = fadd reassoc float [[A:%.*]], 1.234000e+03
+; CHECK-NEXT:    [[TMP2:%.*]] = fadd reassoc float [[TMP1]], [[B:%.*]]
+; CHECK-NEXT:    [[TMP3:%.*]] = fsub reassoc float 0.000000e+00, [[A]]
+; CHECK-NEXT:    [[TMP4:%.*]] = fadd reassoc float [[TMP3]], [[TMP2]]
+; CHECK-NEXT:    ret float [[TMP4]]
+;
+  %1 = fadd reassoc float %a, 1234.0
+  %2 = fadd reassoc float %b, %1
+  %3 = fsub reassoc float 0.0, %a
+  %4 = fadd reassoc float %2, %3
+  ret float %4
+}
+
+; Test that we can turn things like X*-(Y*Z) -> X*-1*Y*Z.
+
+define float @test16(float %a, float %b, float %z) {
+; REASSOC_AND_IC-LABEL: @test16(
+; REASSOC_AND_IC-NEXT:    [[C:%.*]] = fmul fast float [[A:%.*]], 1.234500e+04
+; REASSOC_AND_IC-NEXT:    [[E:%.*]] = fmul fast float [[C]], [[B:%.*]]
+; REASSOC_AND_IC-NEXT:    [[F:%.*]] = fmul fast float [[E]], [[Z:%.*]]
+; REASSOC_AND_IC-NEXT:    ret float [[F]]
+;
+; O2-LABEL: @test16(
+; O2-NEXT:    [[D:%.*]] = fmul fast float [[A:%.*]], 1.234500e+04
+; O2-NEXT:    [[E:%.*]] = fmul fast float [[D]], [[B:%.*]]
+; O2-NEXT:    [[G:%.*]] = fmul fast float [[E]], [[Z:%.*]]
+; O2-NEXT:    ret float [[G]]
+;
+  %c = fsub fast float 0.000000e+00, %z
+  %d = fmul fast float %a, %b
+  %e = fmul fast float %c, %d
+  %f = fmul fast float %e, 1.234500e+04
+  %g = fsub fast float 0.000000e+00, %f
+  ret float %g
+}
+
+define float @test16_unary_fneg(float %a, float %b, float %z) {
+; REASSOC_AND_IC-LABEL: @test16_unary_fneg(
+; REASSOC_AND_IC-NEXT:    [[E:%.*]] = fmul fast float [[A:%.*]], 1.234500e+04
+; REASSOC_AND_IC-NEXT:    [[F:%.*]] = fmul fast float [[E]], [[B:%.*]]
+; REASSOC_AND_IC-NEXT:    [[G:%.*]] = fmul fast float [[F]], [[Z:%.*]]
+; REASSOC_AND_IC-NEXT:    ret float [[G]]
+;
+; O2-LABEL: @test16_unary_fneg(
+; O2-NEXT:    [[D:%.*]] = fmul fast float [[A:%.*]], 1.234500e+04
+; O2-NEXT:    [[E:%.*]] = fmul fast float [[D]], [[B:%.*]]
+; O2-NEXT:    [[G:%.*]] = fmul fast float [[E]], [[Z:%.*]]
+; O2-NEXT:    ret float [[G]]
+;
+  %c = fneg fast float %z
+  %d = fmul fast float %a, %b
+  %e = fmul fast float %c, %d
+  %f = fmul fast float %e, 1.234500e+04
+  %g = fneg fast float %f
+  ret float %g
+}
+
+; TODO: check if it is possible to perform the optimization without 'fast'
+; with 'reassoc' and 'nsz' only.
+define float @test16_reassoc_nsz(float %a, float %b, float %z) {
+; CHECK-LABEL: @test16_reassoc_nsz(
+; CHECK-NEXT:    [[C:%.*]] = fneg reassoc nsz float [[Z:%.*]]
+; CHECK-NEXT:    [[D:%.*]] = fmul reassoc nsz float [[A:%.*]], [[B:%.*]]
+; CHECK-NEXT:    [[E:%.*]] = fmul reassoc nsz float [[D]], [[C]]
+; CHECK-NEXT:    [[G:%.*]] = fmul reassoc nsz float [[E]], -1.234500e+04
+; CHECK-NEXT:    ret float [[G]]
+;
+  %c = fsub reassoc nsz float 0.000000e+00, %z
+  %d = fmul reassoc nsz float %a, %b
+  %e = fmul reassoc nsz float %c, %d
+  %f = fmul reassoc nsz float %e, 1.234500e+04
+  %g = fsub reassoc nsz float 0.000000e+00, %f
+  ret float %g
+}
+
+define float @test16_reassoc(float %a, float %b, float %z) {
+; CHECK-LABEL: @test16_reassoc(
+; CHECK-NEXT:    [[C:%.*]] = fsub reassoc float 0.000000e+00, [[Z:%.*]]
+; CHECK-NEXT:    [[D:%.*]] = fmul reassoc float [[A:%.*]], [[B:%.*]]
+; CHECK-NEXT:    [[E:%.*]] = fmul reassoc float [[D]], [[C]]
+; CHECK-NEXT:    [[F:%.*]] = fmul reassoc float [[E]], 1.234500e+04
+; CHECK-NEXT:    [[G:%.*]] = fsub reassoc float 0.000000e+00, [[F]]
+; CHECK-NEXT:    ret float [[G]]
+;
+  %c = fsub reassoc float 0.000000e+00, %z
+  %d = fmul reassoc float %a, %b
+  %e = fmul reassoc float %c, %d
+  %f = fmul reassoc float %e, 1.234500e+04
+  %g = fsub reassoc float 0.000000e+00, %f
+  ret float %g
+}
+
+; With sub reassociation, constant folding can eliminate the 12 and -12 constants.
+
+define float @test18(float %A, float %B) {
+; CHECK-LABEL: @test18(
+; CHECK-NEXT:    [[Z:%.*]] = fsub fast float [[A:%.*]], [[B:%.*]]
+; CHECK-NEXT:    ret float [[Z]]
+;
+  %X = fadd fast float -1.200000e+01, %A
+  %Y = fsub fast float %X, %B
+  %Z = fadd fast float %Y, 1.200000e+01
+  ret float %Z
+}
+
+define float @test18_reassoc(float %A, float %B) {
+; CHECK-LABEL: @test18_reassoc(
+; CHECK-NEXT:    [[X:%.*]] = fadd reassoc float [[A:%.*]], -1.200000e+01
+; CHECK-NEXT:    [[Y:%.*]] = fsub reassoc float [[X]], [[B:%.*]]
+; CHECK-NEXT:    [[Z:%.*]] = fadd reassoc float [[Y]], 1.200000e+01
+; CHECK-NEXT:    ret float [[Z]]
+;
+  %X = fadd reassoc float -1.200000e+01, %A
+  %Y = fsub reassoc float %X, %B
+  %Z = fadd reassoc float %Y, 1.200000e+01
+  ret float %Z
+}
+
+; test18 - check that the bug described in the revision does not appear:
+; https://reviews.llvm.org/D72521
+
+; With sub reassociation, constant folding can eliminate the uses of %a.
+
+define float @test19(float %a, float %b, float %c) nounwind  {
+; REASSOC_AND_IC-LABEL: @test19(
+; REASSOC_AND_IC-NEXT:    [[TMP1:%.*]] = fadd fast float [[B:%.*]], [[C:%.*]]
+; REASSOC_AND_IC-NEXT:    [[T7:%.*]] = fneg fast float [[TMP1]]
+; REASSOC_AND_IC-NEXT:    ret float [[T7]]
+;
+; O2-LABEL: @test19(
+; O2-NEXT:    [[TMP1:%.*]] = fadd fast float [[C:%.*]], [[B:%.*]]
+; O2-NEXT:    [[T7:%.*]] = fneg fast float [[TMP1]]
+; O2-NEXT:    ret float [[T7]]
+;
+  %t3 = fsub fast float %a, %b
+  %t5 = fsub fast float %t3, %c
+  %t7 = fsub fast float %t5, %a
+  ret float %t7
+}
+
+define float @test19_reassoc_nsz(float %a, float %b, float %c) nounwind  {
+; CHECK-LABEL: @test19_reassoc_nsz(
+; CHECK-NEXT:    [[TMP1:%.*]] = fadd reassoc nsz float [[B:%.*]], [[C:%.*]]
+; CHECK-NEXT:    [[T7:%.*]] = fneg reassoc nsz float [[TMP1]]
+; CHECK-NEXT:    ret float [[T7]]
+;
+  %t3 = fsub reassoc nsz float %a, %b
+  %t5 = fsub reassoc nsz float %t3, %c
+  %t7 = fsub reassoc nsz float %t5, %a
+  ret float %t7
+}
+
+; Verify the fold is not done with only 'reassoc' ('nsz' is required).
+define float @test19_reassoc(float %a, float %b, float %c) nounwind  {
+; CHECK-LABEL: @test19_reassoc(
+; CHECK-NEXT:    [[T3:%.*]] = fsub reassoc float [[A:%.*]], [[B:%.*]]
+; CHECK-NEXT:    [[T5:%.*]] = fsub reassoc float [[T3]], [[C:%.*]]
+; CHECK-NEXT:    [[T7:%.*]] = fsub reassoc float [[T5]], [[A]]
+; CHECK-NEXT:    ret float [[T7]]
+;
+  %t3 = fsub reassoc float %a, %b
+  %t5 = fsub reassoc float %t3, %c
+  %t7 = fsub reassoc float %t5, %a
+  ret float %t7
+}

llvm/test/Transforms/PhaseOrdering/fast-reassociate-gvn.ll

@@ -0,0 +1,103 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+;
+; Test cases in this file are intended to be run with both reassociate and
+; gvn passes enabled.
+;
+; Test numbering remains continuous across:
+; - InstCombine/fast-basictest.ll
+; - PhaseOrdering/fast-basictest.ll
+; - PhaseOrdering/fast-reassociate-gvn.ll
+; - Reassociate/fast-basictest.ll
+;
+; RUN: opt < %s -reassociate -gvn -S | FileCheck %s --check-prefixes=CHECK,REASSOC_AND_GVN --allow-unused-prefixes
+; RUN: opt < %s -O2 -S | FileCheck %s --check-prefixes=CHECK,O2 --allow-unused-prefixes
+
+@fe = external global float
+@fa = external global float
+@fb = external global float
+@fc = external global float
+@ff = external global float
+
+; If two sums of the same operands in different order are counted with 'fast'
+; flag and then stored to global variables, we can reuse the same value twice.
+; Sums:
+; - test3: (a+b)+c and (a+c)+b
+; - test4: c+(a+b) and (c+a)+b
+; - test5: c+(b+a) and (c+a)+b
+; TODO: check if 'reassoc' flag is technically enough for this optimization
+; (currently the transformation is not done with 'reassoc' only).
+
+define void @test3() {
+; CHECK-LABEL: @test3(
+; CHECK-NEXT:    [[A:%.*]] = load float, float* @fa, align 4
+; CHECK-NEXT:    [[B:%.*]] = load float, float* @fb, align 4
+; CHECK-NEXT:    [[C:%.*]] = load float, float* @fc, align 4
+; CHECK-NEXT:    [[T1:%.*]] = fadd fast float [[B]], [[A]]
+; CHECK-NEXT:    [[T2:%.*]] = fadd fast float [[T1]], [[C]]
+; CHECK-NEXT:    store float [[T2]], float* @fe, align 4
+; CHECK-NEXT:    store float [[T2]], float* @ff, align 4
+; CHECK-NEXT:    ret void
+;
+  %A = load float, float* @fa
+  %B = load float, float* @fb
+  %C = load float, float* @fc
+  %t1 = fadd fast float %A, %B
+  %t2 = fadd fast float %t1, %C
+  %t3 = fadd fast float %A, %C
+  %t4 = fadd fast float %t3, %B
+  ; e = (a+b)+c;
+  store float %t2, float* @fe
+  ; f = (a+c)+b
+  store float %t4, float* @ff
+  ret void
+}
+
+define void @test4() {
+; CHECK-LABEL: @test4(
+; CHECK-NEXT:    [[A:%.*]] = load float, float* @fa, align 4
+; CHECK-NEXT:    [[B:%.*]] = load float, float* @fb, align 4
+; CHECK-NEXT:    [[C:%.*]] = load float, float* @fc, align 4
+; CHECK-NEXT:    [[T1:%.*]] = fadd fast float [[B]], [[A]]
+; CHECK-NEXT:    [[T2:%.*]] = fadd fast float [[T1]], [[C]]
+; CHECK-NEXT:    store float [[T2]], float* @fe, align 4
+; CHECK-NEXT:    store float [[T2]], float* @ff, align 4
+; CHECK-NEXT:    ret void
+;
+  %A = load float, float* @fa
+  %B = load float, float* @fb
+  %C = load float, float* @fc
+  %t1 = fadd fast float %A, %B
+  %t2 = fadd fast float %C, %t1
+  %t3 = fadd fast float %C, %A
+  %t4 = fadd fast float %t3, %B
+  ; e = c+(a+b)
+  store float %t2, float* @fe
+  ; f = (c+a)+b
+  store float %t4, float* @ff
+  ret void
+}
+
+define void @test5() {
+; CHECK-LABEL: @test5(
+; CHECK-NEXT:    [[A:%.*]] = load float, float* @fa, align 4
+; CHECK-NEXT:    [[B:%.*]] = load float, float* @fb, align 4
+; CHECK-NEXT:    [[C:%.*]] = load float, float* @fc, align 4
+; CHECK-NEXT:    [[T1:%.*]] = fadd fast float [[B]], [[A]]
+; CHECK-NEXT:    [[T2:%.*]] = fadd fast float [[T1]], [[C]]
+; CHECK-NEXT:    store float [[T2]], float* @fe, align 4
+; CHECK-NEXT:    store float [[T2]], float* @ff, align 4
+; CHECK-NEXT:    ret void
+;
+  %A = load float, float* @fa
+  %B = load float, float* @fb
+  %C = load float, float* @fc
+  %t1 = fadd fast float %B, %A
+  %t2 = fadd fast float %C, %t1
+  %t3 = fadd fast float %C, %A
+  %t4 = fadd fast float %t3, %B
+  ; e = c+(b+a)
+  store float %t2, float* @fe
+  ; f = (c+a)+b
+  store float %t4, float* @ff
+  ret void
+}

llvm/test/Transforms/Reassociate/fast-basictest.ll

@@ -1,43 +1,32 @@
 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
-; RUN: opt < %s -reassociate -gvn -instcombine -S | FileCheck %s
-
-; With reassociation, constant folding can eliminate the 12 and -12 constants.
-define float @test1(float %arg) {
-; CHECK-LABEL: @test1(
-; CHECK-NEXT:    [[ARG_NEG:%.*]] = fneg fast float [[ARG:%.*]]
-; CHECK-NEXT:    ret float [[ARG_NEG]]
 ;
-  %t1 = fsub fast float -1.200000e+01, %arg
+; Test numbering remains continuous across:
-  %t2 = fadd fast float %t1, 1.200000e+01
+; - InstCombine/fast-basictest.ll
-  ret float %t2
+; - PhaseOrdering/fast-basictest.ll
-}
+; - PhaseOrdering/fast-reassociate-gvn.ll
-
+; - Reassociate/fast-basictest.ll
-; Check again using the minimal subset of FMF.
-; Both 'reassoc' and 'nsz' are required.
-define float @test1_minimal(float %arg) {
-; CHECK-LABEL: @test1_minimal(
-; CHECK-NEXT:    [[TMP1:%.*]] = fneg reassoc nsz float [[ARG:%.*]]
-; CHECK-NEXT:    ret float [[TMP1]]
 ;
-  %t1 = fsub reassoc nsz float -1.200000e+01, %arg
+; RUN: opt < %s -reassociate -S | FileCheck %s
-  %t2 = fadd reassoc nsz float %t1, 1.200000e+01
-  ret float %t2
-}
 
-; Verify the fold is not done with only 'reassoc' ('nsz' is required).
+; ((a + (-3)) + b) + 3 -> a + b
-define float @test1_reassoc(float %arg) {
+; That only works with both instcombine and reassociate passes enabled.
-; CHECK-LABEL: @test1_reassoc(
+; Check that reassociate is not enough.
-; CHECK-NEXT:    [[T1:%.*]] = fsub reassoc float -1.200000e+01, [[ARG:%.*]]
-; CHECK-NEXT:    [[T2:%.*]] = fadd reassoc float [[T1]], 1.200000e+01
-; CHECK-NEXT:    ret float [[T2]]
-;
-  %t1 = fsub reassoc float -1.200000e+01, %arg
-  %t2 = fadd reassoc float %t1, 1.200000e+01
-  ret float %t2
-}
 
+; TODO: check if we can eliminate zero add.
 define float @test2(float %reg109, float %reg1111) {
 ; CHECK-LABEL: @test2(
+; CHECK-NEXT:    [[REG116:%.*]] = fadd fast float [[REG109:%.*]], 0.000000e+00
+; CHECK-NEXT:    [[REG117:%.*]] = fadd fast float [[REG116]], [[REG1111:%.*]]
+; CHECK-NEXT:    ret float [[REG117]]
+;
+  %reg115 = fadd fast float %reg109, -3.000000e+01
+  %reg116 = fadd fast float %reg115, %reg1111
+  %reg117 = fadd fast float %reg116, 3.000000e+01
+  ret float %reg117
+}
+
+define float @test2_no_FMF(float %reg109, float %reg1111) {
+; CHECK-LABEL: @test2_no_FMF(
 ; CHECK-NEXT:    [[REG115:%.*]] = fadd float [[REG109:%.*]], -3.000000e+01
 ; CHECK-NEXT:    [[REG116:%.*]] = fadd float [[REG115]], [[REG1111:%.*]]
 ; CHECK-NEXT:    [[REG117:%.*]] = fadd float [[REG116]], 3.000000e+01
@@ -49,19 +38,8 @@ define float @test2(float %reg109, float %reg1111) {
   ret float %reg117
 }
 
-define float @test3(float %reg109, float %reg1111) {
+define float @test2_reassoc(float %reg109, float %reg1111) {
-; CHECK-LABEL: @test3(
+; CHECK-LABEL: @test2_reassoc(
-; CHECK-NEXT:    [[REG117:%.*]] = fadd fast float [[REG109:%.*]], [[REG1111:%.*]]
-; CHECK-NEXT:    ret float [[REG117]]
-;
-  %reg115 = fadd fast float %reg109, -3.000000e+01
-  %reg116 = fadd fast float %reg115, %reg1111
-  %reg117 = fadd fast float %reg116, 3.000000e+01
-  ret float %reg117
-}
-
-define float @test3_reassoc(float %reg109, float %reg1111) {
-; CHECK-LABEL: @test3_reassoc(
 ; CHECK-NEXT:    [[REG115:%.*]] = fadd reassoc float [[REG109:%.*]], -3.000000e+01
 ; CHECK-NEXT:    [[REG116:%.*]] = fadd reassoc float [[REG115]], [[REG1111:%.*]]
 ; CHECK-NEXT:    [[REG117:%.*]] = fadd reassoc float [[REG116]], 3.000000e+01
@@ -79,15 +57,27 @@ define float @test3_reassoc(float %reg109, float %reg1111) {
 @fc = external global float
 @ff = external global float
 
-define void @test4() {
+; If two sums of the same operands in different order are counted with 'fast'
-; CHECK-LABEL: @test4(
+; flag and then stored to global variables, we can reuse the same value twice.
+; Sums:
+; - test3: (a+b)+c and (a+c)+b
+; - test4: c+(a+b) and (c+a)+b
+; - test5: c+(b+a) and (c+a)+b
+;
+; That only works with both gvn and reassociate passes enabled.
+; Check that reassociate is not enough.
+
+define void @test3() {
+; CHECK-LABEL: @test3(
 ; CHECK-NEXT:    [[A:%.*]] = load float, float* @fa, align 4
 ; CHECK-NEXT:    [[B:%.*]] = load float, float* @fb, align 4
 ; CHECK-NEXT:    [[C:%.*]] = load float, float* @fc, align 4
 ; CHECK-NEXT:    [[T1:%.*]] = fadd fast float [[B]], [[A]]
 ; CHECK-NEXT:    [[T2:%.*]] = fadd fast float [[T1]], [[C]]
+; CHECK-NEXT:    [[T3:%.*]] = fadd fast float [[B]], [[A]]
+; CHECK-NEXT:    [[T4:%.*]] = fadd fast float [[T3]], [[C]]
 ; CHECK-NEXT:    store float [[T2]], float* @fe, align 4
-; CHECK-NEXT:    store float [[T2]], float* @ff, align 4
+; CHECK-NEXT:    store float [[T4]], float* @ff, align 4
 ; CHECK-NEXT:    ret void
 ;
   %A = load float, float* @fa
@@ -95,7 +85,7 @@ define void @test4() {
   %C = load float, float* @fc
   %t1 = fadd fast float %A, %B
   %t2 = fadd fast float %t1, %C
-  %t3 = fadd fast float %C, %A
+  %t3 = fadd fast float %A, %C
   %t4 = fadd fast float %t3, %B
   ; e = (a+b)+c;
   store float %t2, float* @fe
@@ -104,6 +94,33 @@ define void @test4() {
   ret void
 }
 
+define void @test4() {
+; CHECK-LABEL: @test4(
+; CHECK-NEXT:    [[A:%.*]] = load float, float* @fa, align 4
+; CHECK-NEXT:    [[B:%.*]] = load float, float* @fb, align 4
+; CHECK-NEXT:    [[C:%.*]] = load float, float* @fc, align 4
+; CHECK-NEXT:    [[T1:%.*]] = fadd fast float [[B]], [[A]]
+; CHECK-NEXT:    [[T2:%.*]] = fadd fast float [[T1]], [[C]]
+; CHECK-NEXT:    [[T3:%.*]] = fadd fast float [[B]], [[A]]
+; CHECK-NEXT:    [[T4:%.*]] = fadd fast float [[T3]], [[C]]
+; CHECK-NEXT:    store float [[T2]], float* @fe, align 4
+; CHECK-NEXT:    store float [[T4]], float* @ff, align 4
+; CHECK-NEXT:    ret void
+;
+  %A = load float, float* @fa
+  %B = load float, float* @fb
+  %C = load float, float* @fc
+  %t1 = fadd fast float %A, %B
+  %t2 = fadd fast float %C, %t1
+  %t3 = fadd fast float %C, %A
+  %t4 = fadd fast float %t3, %B
+  ; e = c+(a+b)
+  store float %t2, float* @fe
+  ; f = (c+a)+b
+  store float %t4, float* @ff
+  ret void
+}
+
 define void @test5() {
 ; CHECK-LABEL: @test5(
 ; CHECK-NEXT:    [[A:%.*]] = load float, float* @fa, align 4
@@ -111,40 +128,17 @@ define void @test5() {
 ; CHECK-NEXT:    [[C:%.*]] = load float, float* @fc, align 4
 ; CHECK-NEXT:    [[T1:%.*]] = fadd fast float [[B]], [[A]]
 ; CHECK-NEXT:    [[T2:%.*]] = fadd fast float [[T1]], [[C]]
+; CHECK-NEXT:    [[T3:%.*]] = fadd fast float [[B]], [[A]]
+; CHECK-NEXT:    [[T4:%.*]] = fadd fast float [[T3]], [[C]]
 ; CHECK-NEXT:    store float [[T2]], float* @fe, align 4
-; CHECK-NEXT:    store float [[T2]], float* @ff, align 4
+; CHECK-NEXT:    store float [[T4]], float* @ff, align 4
-; CHECK-NEXT:    ret void
-;
-  %A = load float, float* @fa
-  %B = load float, float* @fb
-  %C = load float, float* @fc
-  %t1 = fadd fast float %A, %B
-  %t2 = fadd fast float %t1, %C
-  %t3 = fadd fast float %C, %A
-  %t4 = fadd fast float %t3, %B
-  ; e = c+(a+b)
-  store float %t2, float* @fe
-  ; f = (c+a)+b
-  store float %t4, float* @ff
-  ret void
-}
-
-define void @test6() {
-; CHECK-LABEL: @test6(
-; CHECK-NEXT:    [[A:%.*]] = load float, float* @fa, align 4
-; CHECK-NEXT:    [[B:%.*]] = load float, float* @fb, align 4
-; CHECK-NEXT:    [[C:%.*]] = load float, float* @fc, align 4
-; CHECK-NEXT:    [[T1:%.*]] = fadd fast float [[B]], [[A]]
-; CHECK-NEXT:    [[T2:%.*]] = fadd fast float [[T1]], [[C]]
-; CHECK-NEXT:    store float [[T2]], float* @fe, align 4
-; CHECK-NEXT:    store float [[T2]], float* @ff, align 4
 ; CHECK-NEXT:    ret void
 ;
   %A = load float, float* @fa
   %B = load float, float* @fb
   %C = load float, float* @fc
   %t1 = fadd fast float %B, %A
-  %t2 = fadd fast float %t1, %C
+  %t2 = fadd fast float %C, %t1
   %t3 = fadd fast float %C, %A
   %t4 = fadd fast float %t3, %B
   ; e = c+(b+a)
@@ -154,8 +148,8 @@ define void @test6() {
   ret void
 }
 
-define float @test7(float %A, float %B, float %C) {
+define float @test6(float %A, float %B, float %C) {
-; CHECK-LABEL: @test7(
+; CHECK-LABEL: @test6(
 ; CHECK-NEXT:    [[REASS_ADD1:%.*]] = fadd fast float [[C:%.*]], [[B:%.*]]
 ; CHECK-NEXT:    [[REASS_MUL2:%.*]] = fmul fast float [[A:%.*]], [[A]]
 ; CHECK-NEXT:    [[REASS_MUL:%.*]] = fmul fast float [[REASS_MUL2]], [[REASS_ADD1]]
@@ -169,12 +163,12 @@ define float @test7(float %A, float %B, float %C) {
   ret float %r
 }
 
-define float @test7_reassoc(float %A, float %B, float %C) {
+define float @test6_reassoc(float %A, float %B, float %C) {
-; CHECK-LABEL: @test7_reassoc(
+; CHECK-LABEL: @test6_reassoc(
 ; CHECK-NEXT:    [[AA:%.*]] = fmul reassoc float [[A:%.*]], [[A]]
 ; CHECK-NEXT:    [[AAB:%.*]] = fmul reassoc float [[AA]], [[B:%.*]]
-; CHECK-NEXT:    [[TMP1:%.*]] = fmul reassoc float [[A]], [[A]]
+; CHECK-NEXT:    [[AC:%.*]] = fmul reassoc float [[A]], [[C:%.*]]
-; CHECK-NEXT:    [[AAC:%.*]] = fmul reassoc float [[TMP1]], [[C:%.*]]
+; CHECK-NEXT:    [[AAC:%.*]] = fmul reassoc float [[A]], [[AC]]
 ; CHECK-NEXT:    [[R:%.*]] = fadd reassoc float [[AAB]], [[AAC]]
 ; CHECK-NEXT:    ret float [[R]]
 ;
@@ -187,12 +181,16 @@ define float @test7_reassoc(float %A, float %B, float %C) {
 }
 
 ; (-X)*Y + Z -> Z-X*Y
+; TODO: check why IR transformation of test7 with 'fast' math flag
+; is worse than without it (and even without transformation)
 
-define float @test8(float %X, float %Y, float %Z) {
+define float @test7(float %X, float %Y, float %Z) {
-; CHECK-LABEL: @test8(
+; CHECK-LABEL: @test7(
+; CHECK-NEXT:    [[TMP1:%.*]] = fsub fast float 0.000000e+00, 0.000000e+00
 ; CHECK-NEXT:    [[A:%.*]] = fmul fast float [[Y:%.*]], [[X:%.*]]
-; CHECK-NEXT:    [[C:%.*]] = fsub fast float [[Z:%.*]], [[A]]
+; CHECK-NEXT:    [[B:%.*]] = fmul fast float [[A]], 1.000000e+00
-; CHECK-NEXT:    ret float [[C]]
+; CHECK-NEXT:    [[TMP2:%.*]] = fsub fast float [[Z:%.*]], [[B]]
+; CHECK-NEXT:    ret float [[TMP2]]
 ;
   %A = fsub fast float 0.0, %X
   %B = fmul fast float %A, %Y
@@ -200,11 +198,13 @@ define float @test8(float %X, float %Y, float %Z) {
   ret float %C
 }
 
-define float @test8_unary_fneg(float %X, float %Y, float %Z) {
+define float @test7_unary_fneg(float %X, float %Y, float %Z) {
-; CHECK-LABEL: @test8_unary_fneg(
+; CHECK-LABEL: @test7_unary_fneg(
-; CHECK-NEXT:    [[TMP1:%.*]] = fmul fast float [[X:%.*]], [[Y:%.*]]
+; CHECK-NEXT:    [[TMP1:%.*]] = fneg fast float 0.000000e+00
-; CHECK-NEXT:    [[C:%.*]] = fsub fast float [[Z:%.*]], [[TMP1]]
+; CHECK-NEXT:    [[A:%.*]] = fmul fast float [[Y:%.*]], [[X:%.*]]
-; CHECK-NEXT:    ret float [[C]]
+; CHECK-NEXT:    [[B:%.*]] = fmul fast float [[A]], 1.000000e+00
+; CHECK-NEXT:    [[TMP2:%.*]] = fsub fast float [[Z:%.*]], [[B]]
+; CHECK-NEXT:    ret float [[TMP2]]
 ;
   %A = fneg fast float %X
   %B = fmul fast float %A, %Y
@@ -212,8 +212,22 @@ define float @test8_unary_fneg(float %X, float %Y, float %Z) {
   ret float %C
 }
 
-define float @test8_reassoc(float %X, float %Y, float %Z) {
+define float @test7_reassoc_nsz(float %X, float %Y, float %Z) {
-; CHECK-LABEL: @test8_reassoc(
+; CHECK-LABEL: @test7_reassoc_nsz(
+; CHECK-NEXT:    [[A:%.*]] = fsub reassoc nsz float 0.000000e+00, [[X:%.*]]
+; CHECK-NEXT:    [[B:%.*]] = fmul reassoc nsz float [[A]], [[Y:%.*]]
+; CHECK-NEXT:    [[C:%.*]] = fadd reassoc nsz float [[B]], [[Z:%.*]]
+; CHECK-NEXT:    ret float [[C]]
+;
+  %A = fsub reassoc nsz float 0.0, %X
+  %B = fmul reassoc nsz float %A, %Y
+  %C = fadd reassoc nsz float %B, %Z
+  ret float %C
+}
+
+; Verify that fold is not done only with 'reassoc' ('nsz' is required)
+define float @test7_reassoc(float %X, float %Y, float %Z) {
+; CHECK-LABEL: @test7_reassoc(
 ; CHECK-NEXT:    [[A:%.*]] = fsub reassoc float 0.000000e+00, [[X:%.*]]
 ; CHECK-NEXT:    [[B:%.*]] = fmul reassoc float [[A]], [[Y:%.*]]
 ; CHECK-NEXT:    [[C:%.*]] = fadd reassoc float [[B]], [[Z:%.*]]
@@ -225,8 +239,8 @@ define float @test8_reassoc(float %X, float %Y, float %Z) {
   ret float %C
 }
 
-define float @test9(float %X) {
+define float @test8(float %X) {
-; CHECK-LABEL: @test9(
+; CHECK-LABEL: @test8(
 ; CHECK-NEXT:    [[FACTOR:%.*]] = fmul fast float [[X:%.*]], 9.400000e+01
 ; CHECK-NEXT:    ret float [[FACTOR]]
 ;
@@ -235,34 +249,11 @@ define float @test9(float %X) {
   ret float %Z
 }
 
-; Check again with 'reassoc' and 'nsz' ('nsz' not technically required).
-define float @test9_reassoc_nsz(float %X) {
-; CHECK-LABEL: @test9_reassoc_nsz(
-; CHECK-NEXT:    [[TMP1:%.*]] = fmul reassoc nsz float [[X:%.*]], 9.400000e+01
-; CHECK-NEXT:    ret float [[TMP1]]
-;
-  %Y = fmul reassoc nsz float %X, 4.700000e+01
-  %Z = fadd reassoc nsz float %Y, %Y
-  ret float %Z
-}
-
-; TODO: This doesn't require 'nsz'.  It should fold to X * 94.0
-define float @test9_reassoc(float %X) {
-; CHECK-LABEL: @test9_reassoc(
-; CHECK-NEXT:    [[Y:%.*]] = fmul reassoc float [[X:%.*]], 4.700000e+01
-; CHECK-NEXT:    [[Z:%.*]] = fadd reassoc float [[Y]], [[Y]]
-; CHECK-NEXT:    ret float [[Z]]
-;
-  %Y = fmul reassoc float %X, 4.700000e+01
-  %Z = fadd reassoc float %Y, %Y
-  ret float %Z
-}
-
 ; Side note: (x + x + x) and (3*x) each have only a single rounding.  So
 ; transforming x+x+x to 3*x is always safe, even without any FMF.
 ; To avoid that special-case, we have the addition of 'x' four times, here.
-define float @test10(float %X) {
+define float @test9(float %X) {
-; CHECK-LABEL: @test10(
+; CHECK-LABEL: @test9(
 ; CHECK-NEXT:    [[FACTOR:%.*]] = fmul fast float [[X:%.*]], 4.000000e+00
 ; CHECK-NEXT:    ret float [[FACTOR]]
 ;
@@ -272,34 +263,8 @@ define float @test10(float %X) {
   ret float %W
 }
 
-; Check again with 'reassoc' and 'nsz' ('nsz' not technically required).
+define float @test10(float %W) {
-define float @test10_reassoc_nsz(float %X) {
+; CHECK-LABEL: @test10(
-; CHECK-LABEL: @test10_reassoc_nsz(
-; CHECK-NEXT:    [[TMP1:%.*]] = fmul reassoc nsz float [[X:%.*]], 4.000000e+00
-; CHECK-NEXT:    ret float [[TMP1]]
-;
-  %Y = fadd reassoc nsz float %X ,%X
-  %Z = fadd reassoc nsz float %Y, %X
-  %W = fadd reassoc nsz float %Z, %X
-  ret float %W
-}
-
-; TODO: This doesn't require 'nsz'.  It should fold to 4 * x
-define float @test10_reassoc(float %X) {
-; CHECK-LABEL: @test10_reassoc(
-; CHECK-NEXT:    [[Y:%.*]] = fadd reassoc float [[X:%.*]], [[X]]
-; CHECK-NEXT:    [[Z:%.*]] = fadd reassoc float [[Y]], [[X]]
-; CHECK-NEXT:    [[W:%.*]] = fadd reassoc float [[Z]], [[X]]
-; CHECK-NEXT:    ret float [[W]]
-;
-  %Y = fadd reassoc float %X ,%X
-  %Z = fadd reassoc float %Y, %X
-  %W = fadd reassoc float %Z, %X
-  ret float %W
-}
-
-define float @test11(float %W) {
-; CHECK-LABEL: @test11(
 ; CHECK-NEXT:    [[FACTOR:%.*]] = fmul fast float [[W:%.*]], 3.810000e+02
 ; CHECK-NEXT:    ret float [[FACTOR]]
 ;
@@ -309,35 +274,9 @@ define float @test11(float %W) {
   ret float %Z
 }
 
-; Check again using the minimal subset of FMF.
+define float @test11(float %X) {
-; Check again with 'reassoc' and 'nsz' ('nsz' not technically required).
+; CHECK-LABEL: @test11(
-define float @test11_reassoc_nsz(float %W) {
+; CHECK-NEXT:    [[TMP1:%.*]] = fneg fast float 0.000000e+00
-; CHECK-LABEL: @test11_reassoc_nsz(
-; CHECK-NEXT:    [[Z:%.*]] = fmul reassoc nsz float [[W:%.*]], 3.810000e+02
-; CHECK-NEXT:    ret float [[Z]]
-;
-  %X = fmul reassoc nsz float %W, 127.0
-  %Y = fadd reassoc nsz float %X ,%X
-  %Z = fadd reassoc nsz float %Y, %X
-  ret float %Z
-}
-
-; TODO: This doesn't require 'nsz'.  It should fold to W*381.0.
-define float @test11_reassoc(float %W) {
-; CHECK-LABEL: @test11_reassoc(
-; CHECK-NEXT:    [[X:%.*]] = fmul reassoc float [[W:%.*]], 1.270000e+02
-; CHECK-NEXT:    [[Y:%.*]] = fadd reassoc float [[X]], [[X]]
-; CHECK-NEXT:    [[Z:%.*]] = fadd reassoc float [[X]], [[Y]]
-; CHECK-NEXT:    ret float [[Z]]
-;
-  %X = fmul reassoc float %W, 127.0
-  %Y = fadd reassoc float %X ,%X
-  %Z = fadd reassoc float %Y, %X
-  ret float %Z
-}
-
-define float @test12(float %X) {
-; CHECK-LABEL: @test12(
 ; CHECK-NEXT:    [[FACTOR:%.*]] = fmul fast float [[X:%.*]], -3.000000e+00
 ; CHECK-NEXT:    [[Z:%.*]] = fadd fast float [[FACTOR]], 6.000000e+00
 ; CHECK-NEXT:    ret float [[Z]]
@@ -350,44 +289,17 @@ define float @test12(float %X) {
   ret float %Z
 }
 
-; Check again with 'reassoc' and 'nsz' ('nsz' not technically required).
+; TODO: check why IR transformation of test12 with 'fast' math flag
-define float @test12_reassoc_nsz(float %X) {
+; is worse than without it (and even without transformation)
-; CHECK-LABEL: @test12_reassoc_nsz(
+
-; CHECK-NEXT:    [[TMP1:%.*]] = fmul reassoc nsz float [[X:%.*]], -3.000000e+00
+define float @test12(float %X1, float %X2, float %X3) {
-; CHECK-NEXT:    [[TMP2:%.*]] = fadd reassoc nsz float [[TMP1]], 6.000000e+00
+; CHECK-LABEL: @test12(
+; CHECK-NEXT:    [[TMP1:%.*]] = fsub fast float 0.000000e+00, 0.000000e+00
+; CHECK-NEXT:    [[A:%.*]] = fmul fast float [[X2:%.*]], [[X1:%.*]]
+; CHECK-NEXT:    [[B:%.*]] = fmul fast float [[A]], 1.000000e+00
+; CHECK-NEXT:    [[C:%.*]] = fmul fast float [[X3:%.*]], [[X1]]
+; CHECK-NEXT:    [[TMP2:%.*]] = fsub fast float [[C]], [[B]]
 ; CHECK-NEXT:    ret float [[TMP2]]
-;
-  %A = fsub reassoc nsz float 1.000000e+00, %X
-  %B = fsub reassoc nsz float 2.000000e+00, %X
-  %C = fsub reassoc nsz float 3.000000e+00, %X
-  %Y = fadd reassoc nsz float %A ,%B
-  %Z = fadd reassoc nsz float %Y, %C
-  ret float %Z
-}
-
-; TODO: This doesn't require 'nsz'.  It should fold to (6.0 - 3.0*x)
-define float @test12_reassoc(float %X) {
-; CHECK-LABEL: @test12_reassoc(
-; CHECK-NEXT:    [[A:%.*]] = fsub reassoc float 1.000000e+00, [[X:%.*]]
-; CHECK-NEXT:    [[B:%.*]] = fsub reassoc float 2.000000e+00, [[X]]
-; CHECK-NEXT:    [[C:%.*]] = fsub reassoc float 3.000000e+00, [[X]]
-; CHECK-NEXT:    [[Y:%.*]] = fadd reassoc float [[A]], [[B]]
-; CHECK-NEXT:    [[Z:%.*]] = fadd reassoc float [[C]], [[Y]]
-; CHECK-NEXT:    ret float [[Z]]
-;
-  %A = fsub reassoc float 1.000000e+00, %X
-  %B = fsub reassoc float 2.000000e+00, %X
-  %C = fsub reassoc float 3.000000e+00, %X
-  %Y = fadd reassoc float %A ,%B
-  %Z = fadd reassoc float %Y, %C
-  ret float %Z
-}
-
-define float @test13(float %X1, float %X2, float %X3) {
-; CHECK-LABEL: @test13(
-; CHECK-NEXT:    [[REASS_ADD:%.*]] = fsub fast float [[X3:%.*]], [[X2:%.*]]
-; CHECK-NEXT:    [[REASS_MUL:%.*]] = fmul fast float [[REASS_ADD]], [[X1:%.*]]
-; CHECK-NEXT:    ret float [[REASS_MUL]]
 ;
   %A = fsub fast float 0.000000e+00, %X1
   %B = fmul fast float %A, %X2   ; -X1*X2
@@ -396,11 +308,14 @@ define float @test13(float %X1, float %X2, float %X3) {
   ret float %D
 }
 
-define float @test13_unary_fneg(float %X1, float %X2, float %X3) {
+define float @test12_unary_fneg(float %X1, float %X2, float %X3) {
-; CHECK-LABEL: @test13_unary_fneg(
+; CHECK-LABEL: @test12_unary_fneg(
-; CHECK-NEXT:    [[TMP1:%.*]] = fsub fast float [[X3:%.*]], [[X2:%.*]]
+; CHECK-NEXT:    [[TMP1:%.*]] = fneg fast float 0.000000e+00
-; CHECK-NEXT:    [[D:%.*]] = fmul fast float [[TMP1]], [[X1:%.*]]
+; CHECK-NEXT:    [[A:%.*]] = fmul fast float [[X2:%.*]], [[X1:%.*]]
-; CHECK-NEXT:    ret float [[D]]
+; CHECK-NEXT:    [[B:%.*]] = fmul fast float [[A]], 1.000000e+00
+; CHECK-NEXT:    [[C:%.*]] = fmul fast float [[X3:%.*]], [[X1]]
+; CHECK-NEXT:    [[TMP2:%.*]] = fsub fast float [[C]], [[B]]
+; CHECK-NEXT:    ret float [[TMP2]]
 ;
   %A = fneg fast float %X1
   %B = fmul fast float %A, %X2   ; -X1*X2
@@ -409,8 +324,25 @@ define float @test13_unary_fneg(float %X1, float %X2, float %X3) {
   ret float %D
 }
 
-define float @test13_reassoc(float %X1, float %X2, float %X3) {
+define float @test12_reassoc_nsz(float %X1, float %X2, float %X3) {
-; CHECK-LABEL: @test13_reassoc(
+; CHECK-LABEL: @test12_reassoc_nsz(
+; CHECK-NEXT:    [[A:%.*]] = fsub reassoc nsz float 0.000000e+00, [[X1:%.*]]
+; CHECK-NEXT:    [[B:%.*]] = fmul reassoc nsz float [[A]], [[X2:%.*]]
+; CHECK-NEXT:    [[C:%.*]] = fmul reassoc nsz float [[X1]], [[X3:%.*]]
+; CHECK-NEXT:    [[D:%.*]] = fadd reassoc nsz float [[B]], [[C]]
+; CHECK-NEXT:    ret float [[D]]
+;
+  %A = fsub reassoc nsz float 0.000000e+00, %X1
+  %B = fmul reassoc nsz float %A, %X2   ; -X1*X2
+  %C = fmul reassoc nsz float %X1, %X3  ; X1*X3
+  %D = fadd reassoc nsz float %B, %C    ; -X1*X2 + X1*X3 -> X1*(X3-X2)
+  ret float %D
+}
+
+; TODO: check if 'nsz' is technically required. Currently the optimization
+; is not done with only 'reassoc' without 'nsz'.
+define float @test12_reassoc(float %X1, float %X2, float %X3) {
+; CHECK-LABEL: @test12_reassoc(
 ; CHECK-NEXT:    [[A:%.*]] = fsub reassoc float 0.000000e+00, [[X1:%.*]]
 ; CHECK-NEXT:    [[B:%.*]] = fmul reassoc float [[A]], [[X2:%.*]]
 ; CHECK-NEXT:    [[C:%.*]] = fmul reassoc float [[X1]], [[X3:%.*]]
@@ -424,48 +356,51 @@ define float @test13_reassoc(float %X1, float %X2, float %X3) {
   ret float %D
 }
 
-define float @test14(float %X1, float %X2) {
+; (x1 * 47) + (x2 * -47) => (x1 - x2) * 47
-; CHECK-LABEL: @test14(
+; That only works with both instcombine and reassociate passes enabled.
-; CHECK-NEXT:    [[TMP1:%.*]] = fsub fast float [[X1:%.*]], [[X2:%.*]]
+; Check that reassociate is not enough.
-; CHECK-NEXT:    [[D1:%.*]] = fmul fast float [[TMP1]], 4.700000e+01
+
-; CHECK-NEXT:    ret float [[D1]]
+define float @test13(float %X1, float %X2) {
+; CHECK-LABEL: @test13(
+; CHECK-NEXT:    [[B:%.*]] = fmul fast float [[X1:%.*]], 4.700000e+01
+; CHECK-NEXT:    [[C:%.*]] = fmul fast float [[X2:%.*]], 4.700000e+01
+; CHECK-NEXT:    [[TMP1:%.*]] = fsub fast float [[B]], [[C]]
+; CHECK-NEXT:    ret float [[TMP1]]
 ;
   %B = fmul fast float %X1, 47.   ; X1*47
   %C = fmul fast float %X2, -47.  ; X2*-47
-  %D = fadd fast float %B, %C    ; X1*47 + X2*-47 -> 47*(X1-X2)
+  %D = fadd fast float %B, %C     ; X1*47 + X2*-47 -> 47*(X1-X2)
   ret float %D
 }
 
-; (x1 * 47) + (x2 * -47) => (x1 - x2) * 47
+define float @test13_reassoc_nsz(float %X1, float %X2) {
-; Check again with 'reassoc' and 'nsz' ('nsz' not technically required).
+; CHECK-LABEL: @test13_reassoc_nsz(
-define float @test14_reassoc_nsz(float %X1, float %X2) {
+; CHECK-NEXT:    [[B:%.*]] = fmul reassoc nsz float [[X1:%.*]], 4.700000e+01
-; CHECK-LABEL: @test14_reassoc_nsz(
+; CHECK-NEXT:    [[C:%.*]] = fmul reassoc nsz float [[X2:%.*]], 4.700000e+01
-; CHECK-NEXT:    [[TMP1:%.*]] = fsub reassoc nsz float [[X1:%.*]], [[X2:%.*]]
+; CHECK-NEXT:    [[TMP1:%.*]] = fsub reassoc nsz float [[B]], [[C]]
-; CHECK-NEXT:    [[D1:%.*]] = fmul reassoc nsz float [[TMP1]], 4.700000e+01
+; CHECK-NEXT:    ret float [[TMP1]]
-; CHECK-NEXT:    ret float [[D1]]
 ;
   %B = fmul reassoc nsz float %X1, 47.   ; X1*47
   %C = fmul reassoc nsz float %X2, -47.  ; X2*-47
-  %D = fadd reassoc nsz float %B, %C    ; X1*47 + X2*-47 -> 47*(X1-X2)
+  %D = fadd reassoc nsz float %B, %C     ; X1*47 + X2*-47 -> 47*(X1-X2)
   ret float %D
 }
 
-; TODO: This doesn't require 'nsz'.  It should fold to ((x1 - x2) * 47.0)
+define float @test13_reassoc(float %X1, float %X2) {
-define float @test14_reassoc(float %X1, float %X2) {
+; CHECK-LABEL: @test13_reassoc(
-; CHECK-LABEL: @test14_reassoc(
 ; CHECK-NEXT:    [[B:%.*]] = fmul reassoc float [[X1:%.*]], 4.700000e+01
 ; CHECK-NEXT:    [[C:%.*]] = fmul reassoc float [[X2:%.*]], 4.700000e+01
-; CHECK-NEXT:    [[D1:%.*]] = fsub reassoc float [[B]], [[C]]
+; CHECK-NEXT:    [[TMP1:%.*]] = fsub reassoc float [[B]], [[C]]
-; CHECK-NEXT:    ret float [[D1]]
+; CHECK-NEXT:    ret float [[TMP1]]
 ;
   %B = fmul reassoc float %X1, 47.   ; X1*47
   %C = fmul reassoc float %X2, -47.  ; X2*-47
-  %D = fadd reassoc float %B, %C    ; X1*47 + X2*-47 -> 47*(X1-X2)
+  %D = fadd reassoc float %B, %C     ; X1*47 + X2*-47 -> 47*(X1-X2)
   ret float %D
 }
 
-define float @test15(float %arg) {
+define float @test14(float %arg) {
-; CHECK-LABEL: @test15(
+; CHECK-LABEL: @test14(
 ; CHECK-NEXT:    [[T2:%.*]] = fmul fast float [[ARG:%.*]], 1.440000e+02
 ; CHECK-NEXT:    ret float [[T2]]
 ;
@@ -474,9 +409,12 @@ define float @test15(float %arg) {
   ret float %t2
 }
 
-define float @test15_reassoc(float %arg) {
+; TODO: check if we can transform the code with 'reassoc' only.
-; CHECK-LABEL: @test15_reassoc(
+; The same IR is transformed to one fmul in instcombine pass.
-; CHECK-NEXT:    [[T2:%.*]] = fmul reassoc float [[ARG:%.*]], 1.440000e+02
+define float @test14_reassoc(float %arg) {
+; CHECK-LABEL: @test14_reassoc(
+; CHECK-NEXT:    [[T1:%.*]] = fmul reassoc float [[ARG:%.*]], 1.200000e+01
+; CHECK-NEXT:    [[T2:%.*]] = fmul reassoc float [[T1]], 1.200000e+01
 ; CHECK-NEXT:    ret float [[T2]]
 ;
   %t1 = fmul reassoc float 1.200000e+01, %arg
@@ -485,10 +423,15 @@ define float @test15_reassoc(float %arg) {
 }
 
 ; (b+(a+1234))+-a -> b+1234
-define float @test16(float %b, float %a) {
+; That only works with both instcombine and reassociate passes enabled.
-; CHECK-LABEL: @test16(
+; Check that reassociate is not enough.
-; CHECK-NEXT:    [[TMP1:%.*]] = fadd fast float [[B:%.*]], 1.234000e+03
+
-; CHECK-NEXT:    ret float [[TMP1]]
+; TODO: check if we can remove dead fsub.
+define float @test15(float %b, float %a) {
+; CHECK-LABEL: @test15(
+; CHECK-NEXT:    [[TMP1:%.*]] = fsub fast float 0.000000e+00, [[A:%.*]]
+; CHECK-NEXT:    [[TMP2:%.*]] = fadd fast float [[B:%.*]], 1.234000e+03
+; CHECK-NEXT:    ret float [[TMP2]]
 ;
   %1 = fadd fast float %a, 1234.0
   %2 = fadd fast float %b, %1
@@ -497,10 +440,12 @@ define float @test16(float %b, float %a) {
   ret float %4
 }
 
-define float @test16_unary_fneg(float %b, float %a) {
+; TODO: check if we can remove dead fneg.
-; CHECK-LABEL: @test16_unary_fneg(
+define float @test15_unary_fneg(float %b, float %a) {
-; CHECK-NEXT:    [[TMP1:%.*]] = fadd fast float [[B:%.*]], 1.234000e+03
+; CHECK-LABEL: @test15_unary_fneg(
-; CHECK-NEXT:    ret float [[TMP1]]
+; CHECK-NEXT:    [[TMP1:%.*]] = fneg fast float [[A:%.*]]
+; CHECK-NEXT:    [[TMP2:%.*]] = fadd fast float [[B:%.*]], 1.234000e+03
+; CHECK-NEXT:    ret float [[TMP2]]
 ;
   %1 = fadd fast float %a, 1234.0
   %2 = fadd fast float %b, %1
@@ -509,10 +454,25 @@ define float @test16_unary_fneg(float %b, float %a) {
   ret float %4
 }
 
-define float @test16_reassoc(float %b, float %a) {
+define float @test15_reassoc_nsz(float %b, float %a) {
-; CHECK-LABEL: @test16_reassoc(
+; CHECK-LABEL: @test15_reassoc_nsz(
+; CHECK-NEXT:    [[TMP1:%.*]] = fadd reassoc nsz float [[A:%.*]], 1.234000e+03
+; CHECK-NEXT:    [[TMP2:%.*]] = fadd reassoc nsz float [[B:%.*]], [[TMP1]]
+; CHECK-NEXT:    [[TMP3:%.*]] = fsub reassoc nsz float 0.000000e+00, [[A]]
+; CHECK-NEXT:    [[TMP4:%.*]] = fadd reassoc nsz float [[TMP3]], [[TMP2]]
+; CHECK-NEXT:    ret float [[TMP4]]
+;
+  %1 = fadd reassoc nsz float %a, 1234.0
+  %2 = fadd reassoc nsz float %b, %1
+  %3 = fsub reassoc nsz float 0.0, %a
+  %4 = fadd reassoc nsz float %2, %3
+  ret float %4
+}
+
+define float @test15_reassoc(float %b, float %a) {
+; CHECK-LABEL: @test15_reassoc(
 ; CHECK-NEXT:    [[TMP1:%.*]] = fadd reassoc float [[A:%.*]], 1.234000e+03
-; CHECK-NEXT:    [[TMP2:%.*]] = fadd reassoc float [[TMP1]], [[B:%.*]]
+; CHECK-NEXT:    [[TMP2:%.*]] = fadd reassoc float [[B:%.*]], [[TMP1]]
 ; CHECK-NEXT:    [[TMP3:%.*]] = fsub reassoc float 0.000000e+00, [[A]]
 ; CHECK-NEXT:    [[TMP4:%.*]] = fadd reassoc float [[TMP3]], [[TMP2]]
 ; CHECK-NEXT:    ret float [[TMP4]]
@@ -525,13 +485,17 @@ define float @test16_reassoc(float %b, float %a) {
 }
 
 ; Test that we can turn things like X*-(Y*Z) -> X*-1*Y*Z.
+; That only works with both instcombine and reassociate passes enabled.
+; Check that reassociate is not enough.
 
-define float @test17(float %a, float %b, float %z) {
+define float @test16(float %a, float %b, float %z) {
-; CHECK-LABEL: @test17(
+; CHECK-LABEL: @test16(
-; CHECK-NEXT:    [[E:%.*]] = fmul fast float [[A:%.*]], 1.234500e+04
+; CHECK-NEXT:    [[TMP1:%.*]] = fsub fast float 0.000000e+00, 0.000000e+00
-; CHECK-NEXT:    [[F:%.*]] = fmul fast float [[E]], [[B:%.*]]
+; CHECK-NEXT:    [[C:%.*]] = fmul fast float [[A:%.*]], 1.234500e+04
-; CHECK-NEXT:    [[G:%.*]] = fmul fast float [[F]], [[Z:%.*]]
+; CHECK-NEXT:    [[E:%.*]] = fmul fast float [[C]], [[B:%.*]]
-; CHECK-NEXT:    ret float [[G]]
+; CHECK-NEXT:    [[F:%.*]] = fmul fast float [[E]], [[Z:%.*]]
+; CHECK-NEXT:    [[TMP2:%.*]] = fadd fast float [[F]], 0.000000e+00
+; CHECK-NEXT:    ret float [[TMP2]]
 ;
   %c = fsub fast float 0.000000e+00, %z
   %d = fmul fast float %a, %b
@@ -541,12 +505,13 @@ define float @test17(float %a, float %b, float %z) {
   ret float %g
 }
 
-define float @test17_unary_fneg(float %a, float %b, float %z) {
+define float @test16_unary_fneg(float %a, float %b, float %z) {
-; CHECK-LABEL: @test17_unary_fneg(
+; CHECK-LABEL: @test16_unary_fneg(
-; CHECK-NEXT:    [[D:%.*]] = fmul fast float [[A:%.*]], 1.234500e+04
+; CHECK-NEXT:    [[TMP1:%.*]] = fneg fast float 0.000000e+00
-; CHECK-NEXT:    [[E:%.*]] = fmul fast float [[D]], [[B:%.*]]
+; CHECK-NEXT:    [[E:%.*]] = fmul fast float [[A:%.*]], 1.234500e+04
-; CHECK-NEXT:    [[TMP1:%.*]] = fmul fast float [[E]], [[Z:%.*]]
+; CHECK-NEXT:    [[F:%.*]] = fmul fast float [[E]], [[B:%.*]]
-; CHECK-NEXT:    ret float [[TMP1]]
+; CHECK-NEXT:    [[G:%.*]] = fmul fast float [[F]], [[Z:%.*]]
+; CHECK-NEXT:    ret float [[G]]
 ;
   %c = fneg fast float %z
   %d = fmul fast float %a, %b
@@ -556,8 +521,8 @@ define float @test17_unary_fneg(float %a, float %b, float %z) {
   ret float %g
 }
 
-define float @test17_reassoc(float %a, float %b, float %z) {
+define float @test16_reassoc(float %a, float %b, float %z) {
-; CHECK-LABEL: @test17_reassoc(
+; CHECK-LABEL: @test16_reassoc(
 ; CHECK-NEXT:    [[C:%.*]] = fsub reassoc float 0.000000e+00, [[Z:%.*]]
 ; CHECK-NEXT:    [[D:%.*]] = fmul reassoc float [[A:%.*]], [[B:%.*]]
 ; CHECK-NEXT:    [[E:%.*]] = fmul reassoc float [[D]], [[C]]
@@ -573,11 +538,17 @@ define float @test17_reassoc(float %a, float %b, float %z) {
   ret float %g
 }
 
-define float @test18(float %a, float %b, float %z) {
+; TODO: check if we can remove:
-; CHECK-LABEL: @test18(
+; - fsub fast 0, 0
-; CHECK-NEXT:    [[E:%.*]] = fmul fast float [[A:%.*]], 4.000000e+01
+; - fadd fast x, 0
-; CHECK-NEXT:    [[F:%.*]] = fmul fast float [[E]], [[Z:%.*]]
+; ... as 'fast' implies 'nsz'
-; CHECK-NEXT:    ret float [[F]]
+define float @test17(float %a, float %b, float %z) {
+; CHECK-LABEL: @test17(
+; CHECK-NEXT:    [[TMP1:%.*]] = fsub fast float 0.000000e+00, 0.000000e+00
+; CHECK-NEXT:    [[C:%.*]] = fmul fast float [[A:%.*]], 4.000000e+01
+; CHECK-NEXT:    [[E:%.*]] = fmul fast float [[C]], [[Z:%.*]]
+; CHECK-NEXT:    [[TMP2:%.*]] = fadd fast float [[E]], 0.000000e+00
+; CHECK-NEXT:    ret float [[TMP2]]
 ;
   %d = fmul fast float %z, 4.000000e+01
   %c = fsub fast float 0.000000e+00, %d
@@ -586,8 +557,10 @@ define float @test18(float %a, float %b, float %z) {
   ret float %f
 }
 
-define float @test18_unary_fneg(float %a, float %b, float %z) {
+; TODO: check if we can remove fneg fast 0 as 'fast' implies 'nsz'
-; CHECK-LABEL: @test18_unary_fneg(
+define float @test17_unary_fneg(float %a, float %b, float %z) {
+; CHECK-LABEL: @test17_unary_fneg(
+; CHECK-NEXT:    [[TMP1:%.*]] = fneg fast float 0.000000e+00
 ; CHECK-NEXT:    [[E:%.*]] = fmul fast float [[A:%.*]], 4.000000e+01
 ; CHECK-NEXT:    [[F:%.*]] = fmul fast float [[E]], [[Z:%.*]]
 ; CHECK-NEXT:    ret float [[F]]
@@ -599,53 +572,13 @@ define float @test18_unary_fneg(float %a, float %b, float %z) {
   ret float %f
 }
 
-define float @test18_reassoc(float %a, float %b, float %z) {
-; CHECK-LABEL: @test18_reassoc(
-; CHECK-NEXT:    [[D:%.*]] = fmul reassoc float [[Z:%.*]], 4.000000e+01
-; CHECK-NEXT:    [[C:%.*]] = fsub reassoc float 0.000000e+00, [[D]]
-; CHECK-NEXT:    [[E:%.*]] = fmul reassoc float [[C]], [[A:%.*]]
-; CHECK-NEXT:    [[F:%.*]] = fsub reassoc float 0.000000e+00, [[E]]
-; CHECK-NEXT:    ret float [[F]]
-;
-  %d = fmul reassoc float %z, 4.000000e+01
-  %c = fsub reassoc float 0.000000e+00, %d
-  %e = fmul reassoc float %a, %c
-  %f = fsub reassoc float 0.000000e+00, %e
-  ret float %f
-}
-
-; fneg of fneg is an identity operation, so no FMF are needed to remove those instructions.
-
-define float @test18_unary_fneg_no_FMF(float %a, float %b, float %z) {
-; CHECK-LABEL: @test18_unary_fneg_no_FMF(
-; CHECK-NEXT:    [[TMP1:%.*]] = fmul float [[Z:%.*]], 4.000000e+01
-; CHECK-NEXT:    [[F:%.*]] = fmul float [[TMP1]], [[A:%.*]]
-; CHECK-NEXT:    ret float [[F]]
-;
-  %d = fmul float %z, 4.000000e+01
-  %c = fneg float %d
-  %e = fmul float %a, %c
-  %f = fneg float %e
-  ret float %f
-}
-
-define float @test18_reassoc_unary_fneg(float %a, float %b, float %z) {
-; CHECK-LABEL: @test18_reassoc_unary_fneg(
-; CHECK-NEXT:    [[TMP1:%.*]] = fmul reassoc float [[Z:%.*]], 4.000000e+01
-; CHECK-NEXT:    [[F:%.*]] = fmul reassoc float [[TMP1]], [[A:%.*]]
-; CHECK-NEXT:    ret float [[F]]
-;
-  %d = fmul reassoc float %z, 4.000000e+01
-  %c = fneg reassoc float %d
-  %e = fmul reassoc float %a, %c
-  %f = fneg reassoc float %e
-  ret float %f
-}
-
 ; With sub reassociation, constant folding can eliminate the 12 and -12 constants.
-define float @test19(float %A, float %B) {
+; TODO: check if we can remove fadd fast x, 0 as 'fast' implies 'nsz'
-; CHECK-LABEL: @test19(
+define float @test18(float %A, float %B) {
-; CHECK-NEXT:    [[Z:%.*]] = fsub fast float [[A:%.*]], [[B:%.*]]
+; CHECK-LABEL: @test18(
+; CHECK-NEXT:    [[B_NEG:%.*]] = fneg fast float [[B:%.*]]
+; CHECK-NEXT:    [[Y:%.*]] = fadd fast float [[A:%.*]], 0.000000e+00
+; CHECK-NEXT:    [[Z:%.*]] = fadd fast float [[Y]], [[B_NEG]]
 ; CHECK-NEXT:    ret float [[Z]]
 ;
   %X = fadd fast float -1.200000e+01, %A
@@ -653,43 +586,3 @@ define float @test19(float %A, float %B) {
   %Z = fadd fast float %Y, 1.200000e+01
   ret float %Z
 }
-
-define float @test19_reassoc(float %A, float %B) {
-; CHECK-LABEL: @test19_reassoc(
-; CHECK-NEXT:    [[X:%.*]] = fadd reassoc float [[A:%.*]], -1.200000e+01
-; CHECK-NEXT:    [[Y:%.*]] = fsub reassoc float [[X]], [[B:%.*]]
-; CHECK-NEXT:    [[Z:%.*]] = fadd reassoc float [[Y]], 1.200000e+01
-; CHECK-NEXT:    ret float [[Z]]
-;
-  %X = fadd reassoc float -1.200000e+01, %A
-  %Y = fsub reassoc float %X, %B
-  %Z = fadd reassoc float %Y, 1.200000e+01
-  ret float %Z
-}
-
-; With sub reassociation, constant folding can eliminate the uses of %a.
-define float @test20(float %a, float %b, float %c) nounwind  {
-; CHECK-LABEL: @test20(
-; CHECK-NEXT:    [[TMP1:%.*]] = fadd fast float [[B:%.*]], [[C:%.*]]
-; CHECK-NEXT:    [[T7:%.*]] = fneg fast float [[TMP1]]
-; CHECK-NEXT:    ret float [[T7]]
-;
-  %t3 = fsub fast float %a, %b
-  %t5 = fsub fast float %t3, %c
-  %t7 = fsub fast float %t5, %a
-  ret float %t7
-}
-
-define float @test20_reassoc(float %a, float %b, float %c) nounwind  {
-; CHECK-LABEL: @test20_reassoc(
-; CHECK-NEXT:    [[T3:%.*]] = fsub reassoc float [[A:%.*]], [[B:%.*]]
-; CHECK-NEXT:    [[T5:%.*]] = fsub reassoc float [[T3]], [[C:%.*]]
-; CHECK-NEXT:    [[T7:%.*]] = fsub reassoc float [[T5]], [[A]]
-; CHECK-NEXT:    ret float [[T7]]
-;
-  %t3 = fsub reassoc float %a, %b
-  %t5 = fsub reassoc float %t3, %c
-  %t7 = fsub reassoc float %t5, %a
-  ret float %t7
-}
-